System Logs

logs/dev_detailed.log
Timestamp Level Source Processor Process ID Message Args
2026-09-22 13:33:16,457 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/gql processor=gql status=running tokens=0 cost=0 models=[] thread=Thread-2515 (process_request_thread)
2026-09-22 13:33:16,456 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/gql processor=gql thread=Thread-2515 (process_request_thread) running_jobs=[]
2026-09-22 13:33:16,352 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/graphql processor=graphql status=running tokens=0 cost=0 models=[] thread=Thread-2513 (process_request_thread)
2026-09-22 13:33:16,351 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/graphql processor=graphql thread=Thread-2513 (process_request_thread) running_jobs=[]
2026-09-22 12:53:14,694 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] worker_end job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f job_type=video status=running tokens=2 cost=0 models=['gpt-transcribe'] running=1/3 thread=Thread-2474 (_run_worker)
2026-09-22 12:53:11,043 DEBUG video_processor.py:process:1145 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Temporäre Videodatei gelöscht: cache/video/temp/video/c5677ddd-f6ea-42f0-9267-49aa7427b838/upload_c23280f7-0489-49c8-8fde-c8ec89afec6e.mp4
2026-09-22 12:53:10,979 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_end job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org status_code=200 duration_ms=342 thread=Thread-2474 (_run_worker)
2026-09-22 12:53:10,636 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_start job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org timeout=10 thread=Thread-2474 (_run_worker) running_jobs=['job-89f77bd5-0219-4d35-aad1-e8414d806c9f']
2026-09-22 12:53:10,635 INFO transcription_utils.py:transcribe_segment:1836 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Transkription erfolgreich 
{"segment_id": 1, "duration_ms": 9350.567817687988, "tokens": 1, "text_length": 2649}
2026-09-22 12:53:10,635 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f 1 LLM-Requests hinzugefügt
2026-09-22 12:53:09,631 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_end job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org status_code=200 duration_ms=335 thread=Thread-2474 (_run_worker)
2026-09-22 12:53:09,295 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_start job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org timeout=10 thread=Thread-2474 (_run_worker) running_jobs=['job-89f77bd5-0219-4d35-aad1-e8414d806c9f']
2026-09-22 12:53:09,295 INFO transcription_utils.py:transcribe_segment:1836 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Transkription erfolgreich 
{"segment_id": 0, "duration_ms": 8351.842164993286, "tokens": 1, "text_length": 2558}
2026-09-22 12:53:09,294 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f 1 LLM-Requests hinzugefügt
2026-09-22 12:53:01,613 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_end job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org status_code=200 duration_ms=328 thread=Thread-2474 (_run_worker)
2026-09-22 12:53:01,284 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_start job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org timeout=10 thread=Thread-2474 (_run_worker) running_jobs=['job-89f77bd5-0219-4d35-aad1-e8414d806c9f']
2026-09-22 12:53:01,284 INFO transcription_utils.py:transcribe_segment:1603 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Starte Transkription von Segment 
{"segment_id": 1, "segment_title": null, "file_path": "cache/audio/temp/4cf1c57713d30c5fc191d92ca58d27e7/chapter_0/segment_1.mp3"}
2026-09-22 12:53:01,281 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_end job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org status_code=200 duration_ms=338 thread=Thread-2474 (_run_worker)
2026-09-22 12:53:00,943 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_start job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org timeout=10 thread=Thread-2474 (_run_worker) running_jobs=['job-89f77bd5-0219-4d35-aad1-e8414d806c9f']
2026-09-22 12:53:00,942 INFO transcription_utils.py:transcribe_segment:1603 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Starte Transkription von Segment 
{"segment_id": 0, "segment_title": null, "file_path": "cache/audio/temp/4cf1c57713d30c5fc191d92ca58d27e7/chapter_0/segment_0.mp3"}
2026-09-22 12:53:00,940 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_end job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org status_code=200 duration_ms=308 thread=Thread-2474 (_run_worker)
2026-09-22 12:53:00,631 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_start job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org timeout=10 thread=Thread-2474 (_run_worker) running_jobs=['job-89f77bd5-0219-4d35-aad1-e8414d806c9f']
2026-09-22 12:53:00,630 INFO transcription_utils.py:transcribe_segments:1989 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f TRANSKRIPTION-DEBUG: Starte parallele Transkription von 1 Segmenten/Kapiteln
2026-09-22 12:53:00,623 DEBUG audio_processor.py:get_audio_segments:570 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Kapitel 1 Teil 2/2 erstellt 
{"duration_sec": 173.408, "segment_path": "cache/audio/temp/4cf1c57713d30c5fc191d92ca58d27e7/chapter_0/segment_1.mp3"}
2026-09-22 12:52:59,885 DEBUG audio_processor.py:get_audio_segments:570 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Kapitel 1 Teil 1/2 erstellt 
{"duration_sec": 173.408, "segment_path": "cache/audio/temp/4cf1c57713d30c5fc191d92ca58d27e7/chapter_0/segment_0.mp3"}
2026-09-22 12:52:59,154 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_end job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org status_code=200 duration_ms=286 thread=Thread-2474 (_run_worker)
2026-09-22 12:52:58,868 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_start job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org timeout=10 thread=Thread-2474 (_run_worker) running_jobs=['job-89f77bd5-0219-4d35-aad1-e8414d806c9f']
2026-09-22 12:52:58,867 INFO audio_processor.py:get_audio_segments:532 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Kapitel 1 zu lang, teile es auf 
{"duration_minutes": 5.780266666666667, "max_duration_minutes": 5.0}
2026-09-22 12:52:58,006 DEBUG audio_processor.py:_create_cache_key:691 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Cache-Schlüssel erstellt: 95d0660dd62a3830685145695ed76212|lang=de
2026-09-22 12:52:58,004 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_end job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org status_code=200 duration_ms=325 thread=Thread-2474 (_run_worker)
2026-09-22 12:52:57,679 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_start job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org timeout=10 thread=Thread-2474 (_run_worker) running_jobs=['job-89f77bd5-0219-4d35-aad1-e8414d806c9f']
2026-09-22 12:52:57,678 INFO video_processor.py:process:1044 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Starte Audio-Verarbeitung
2026-09-22 12:52:53,813 DEBUG video_processor.py:_create_cache_key:617 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Cache-Schlüssel erstellt: 46bd4af70130258b06f5084ab8dec3af|lang=de
2026-09-22 12:52:53,308 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_end job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org status_code=200 duration_ms=293 thread=Thread-2474 (_run_worker)
2026-09-22 12:52:53,014 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_start job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org timeout=10 thread=Thread-2474 (_run_worker) running_jobs=['job-89f77bd5-0219-4d35-aad1-e8414d806c9f']
2026-09-22 12:52:53,014 INFO video_processor.py:__init__:209 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f yt-dlp ENV-Variablen geladen 
{"YTDLP_COOKIES_FROM_BROWSER": null, "YTDLP_COOKIES_FILE": null, "VIMEO_USERNAME": false, "VIMEO_PASSWORD": false, "YTDLP_NETRC": false, "YTDLP_CA_BUNDLE": null, "SSL_CERT_FILE": null, "REQUESTS_CA_BUNDLE": null, "PYTHONHTTPSVERIFY": null, "ca_bundle_resolved": null, "ca_bundle_exists": false}
2026-09-22 12:52:53,012 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_end job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org status_code=200 duration_ms=290 thread=Thread-2474 (_run_worker)
2026-09-22 12:52:52,722 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] webhook_post_start job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f host=knowledgescout.bcommonslab.org timeout=10 thread=Thread-2474 (_run_worker) running_jobs=['job-89f77bd5-0219-4d35-aad1-e8414d806c9f']
2026-09-22 12:52:52,722 INFO audio_processor.py:__init__:242 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Gesamte Initialisierungszeit: 368.77 ms
2026-09-22 12:52:52,670 DEBUG transformer_processor.py:__init__:199 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Transformer Init Timings 
{"total_init_ms": 176.85, "super_init_ms": 102.98, "config_load_ms": 20.97, "client_init_ms": 1.07, "transcriber_init_ms": 51.4}
2026-09-22 12:52:52,670 DEBUG transformer_processor.py:__init__:179 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-22 12:52:52,300 DEBUG transformer_processor.py:__init__:199 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Transformer Init Timings 
{"total_init_ms": 200.71, "super_init_ms": 104.42, "config_load_ms": 20.41, "client_init_ms": 0.03, "transcriber_init_ms": 75.51}
2026-09-22 12:52:52,300 DEBUG transformer_processor.py:__init__:179 TransformerProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-22 12:52:52,099 DEBUG video_processor.py:__init__:123 VideoProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f VideoProcessor initialisiert mit Konfiguration 
{"max_duration": 3600, "temp_dir": "cache/video/temp", "cache_dir": "cache/video"}
2026-09-22 12:52:51,968 DEBUG base_processor.py:init_logger:386 VideoProcessor job-89f77bd5-0219-4d35-aad1-e8414d806c9f Logger initialisiert
2026-09-22 12:52:51,474 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] worker_start job_id=job-89f77bd5-0219-4d35-aad1-e8414d806c9f job_type=video running=1/3 thread=Thread-2474 (_run_worker)
2026-09-22 12:52:49,957 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_202_discard path=/api/video/process thread=Thread-2473 (process_request_thread) had_tracker=True
2026-09-22 12:52:48,806 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/video/process processor=video thread=Thread-2473 (process_request_thread) running_jobs=[]
2026-09-21 15:14:28,725 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=373 cost=0 models=['voyage-3-large'] thread=Thread-2140 (process_request_thread)
2026-09-21 15:14:28,720 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor e8266e15-4b5a-4c6d-96c6-9938b2204a57 Embedding (client) abgeschlossen 
{"extra": {"document_id": "17f5dabf-38ad-4702-bf02-9a6244832f12", "chunks": 1, "duration_seconds": 0.2849094867706299}}
2026-09-21 15:14:28,719 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor e8266e15-4b5a-4c6d-96c6-9938b2204a57 1 LLM-Requests hinzugefügt
2026-09-21 15:14:28,435 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor e8266e15-4b5a-4c6d-96c6-9938b2204a57 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:28,435 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor e8266e15-4b5a-4c6d-96c6-9938b2204a57 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:14:28,435 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor e8266e15-4b5a-4c6d-96c6-9938b2204a57 Starte Chunking (client) 
{"extra": {"document_id": "17f5dabf-38ad-4702-bf02-9a6244832f12"}}
2026-09-21 15:14:28,435 INFO rag_processor.py:__init__:127 RAGProcessor e8266e15-4b5a-4c6d-96c6-9938b2204a57 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:28,324 DEBUG base_processor.py:init_logger:386 RAGProcessor e8266e15-4b5a-4c6d-96c6-9938b2204a57 Logger initialisiert
2026-09-21 15:14:28,323 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2140 (process_request_thread) running_jobs=[]
2026-09-21 15:14:28,206 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=2402 cost=0 models=['voyage-3-large'] thread=Thread-2139 (process_request_thread)
2026-09-21 15:14:28,164 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 3164916f-24d7-4bd3-8907-db84ea91376e Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi93aXNzZW5zbGFuZGthcnRlLm1k", "chunks": 11, "duration_seconds": 1.364786148071289}}
2026-09-21 15:14:28,163 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 3164916f-24d7-4bd3-8907-db84ea91376e 1 LLM-Requests hinzugefügt
2026-09-21 15:14:26,799 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 3164916f-24d7-4bd3-8907-db84ea91376e Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 11, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:26,799 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 3164916f-24d7-4bd3-8907-db84ea91376e Chunking abgeschlossen (client): 11 Chunks erstellt
2026-09-21 15:14:26,799 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 3164916f-24d7-4bd3-8907-db84ea91376e Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi93aXNzZW5zbGFuZGthcnRlLm1k"}}
2026-09-21 15:14:26,799 INFO rag_processor.py:__init__:127 RAGProcessor 3164916f-24d7-4bd3-8907-db84ea91376e RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:26,661 DEBUG base_processor.py:init_logger:386 RAGProcessor 3164916f-24d7-4bd3-8907-db84ea91376e Logger initialisiert
2026-09-21 15:14:26,659 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2139 (process_request_thread) running_jobs=[]
2026-09-21 15:14:25,369 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=247 cost=0 models=['voyage-3-large'] thread=Thread-2138 (process_request_thread)
2026-09-21 15:14:25,365 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 8ebd981a-77b2-4a75-a02e-6a4de4660c12 Embedding (client) abgeschlossen 
{"extra": {"document_id": "280b81bd-f998-4a21-909a-a08dc288c7e3", "chunks": 1, "duration_seconds": 0.268481969833374}}
2026-09-21 15:14:25,365 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 8ebd981a-77b2-4a75-a02e-6a4de4660c12 1 LLM-Requests hinzugefügt
2026-09-21 15:14:25,097 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 8ebd981a-77b2-4a75-a02e-6a4de4660c12 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:25,097 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 8ebd981a-77b2-4a75-a02e-6a4de4660c12 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:14:25,097 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 8ebd981a-77b2-4a75-a02e-6a4de4660c12 Starte Chunking (client) 
{"extra": {"document_id": "280b81bd-f998-4a21-909a-a08dc288c7e3"}}
2026-09-21 15:14:25,096 INFO rag_processor.py:__init__:127 RAGProcessor 8ebd981a-77b2-4a75-a02e-6a4de4660c12 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:24,991 DEBUG base_processor.py:init_logger:386 RAGProcessor 8ebd981a-77b2-4a75-a02e-6a4de4660c12 Logger initialisiert
2026-09-21 15:14:24,991 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2138 (process_request_thread) running_jobs=[]
2026-09-21 15:14:24,885 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=2196 cost=0 models=['voyage-3-large'] thread=Thread-2137 (process_request_thread)
2026-09-21 15:14:24,850 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 7256752a-cb76-4d08-878d-cae94fdddf4f Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9wcm9qZWt0cGxhbnVuZ19taXRfbXVzdGVyc3ByYWNoZWthcnRlbi5tZA==", "chunks": 10, "duration_seconds": 1.3731577396392822}}
2026-09-21 15:14:24,849 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 7256752a-cb76-4d08-878d-cae94fdddf4f 1 LLM-Requests hinzugefügt
2026-09-21 15:14:24,452 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=7928 cost=0.007375 models=['google/gemini-2.5-flash'] thread=Thread-2132 (process_request_thread)
2026-09-21 15:14:24,449 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 889f0f1d-6bf1-4c73-9615-694a4f233192 Template-Transformation abgeschlossen 
{"duration_ms": 8937.564611434937, "model": "google/gemini-2.5-flash"}
2026-09-21 15:14:24,443 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 889f0f1d-6bf1-4c73-9615-694a4f233192 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151424_template_transform.json", "tokens": 7928}
2026-09-21 15:14:24,441 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 889f0f1d-6bf1-4c73-9615-694a4f233192 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 7928, "duration": 8937.564611434937, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:14:24,440 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 889f0f1d-6bf1-4c73-9615-694a4f233192 1 LLM-Requests hinzugefügt
2026-09-21 15:14:23,477 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 7256752a-cb76-4d08-878d-cae94fdddf4f Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 10, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:23,477 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 7256752a-cb76-4d08-878d-cae94fdddf4f Chunking abgeschlossen (client): 10 Chunks erstellt
2026-09-21 15:14:23,477 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 7256752a-cb76-4d08-878d-cae94fdddf4f Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9wcm9qZWt0cGxhbnVuZ19taXRfbXVzdGVyc3ByYWNoZWthcnRlbi5tZA=="}}
2026-09-21 15:14:23,476 INFO rag_processor.py:__init__:127 RAGProcessor 7256752a-cb76-4d08-878d-cae94fdddf4f RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:23,328 DEBUG base_processor.py:init_logger:386 RAGProcessor 7256752a-cb76-4d08-878d-cae94fdddf4f Logger initialisiert
2026-09-21 15:14:23,326 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2137 (process_request_thread) running_jobs=[]
2026-09-21 15:14:22,852 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=344 cost=0 models=['voyage-3-large'] thread=Thread-2136 (process_request_thread)
2026-09-21 15:14:22,844 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 7d5feb49-141e-4898-8521-d18c1a01949e Embedding (client) abgeschlossen 
{"extra": {"document_id": "ad7b2b3b-a60a-45da-9fa3-d8602e2450c0", "chunks": 1, "duration_seconds": 0.26262545585632324}}
2026-09-21 15:14:22,843 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 7d5feb49-141e-4898-8521-d18c1a01949e 1 LLM-Requests hinzugefügt
2026-09-21 15:14:22,581 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 7d5feb49-141e-4898-8521-d18c1a01949e Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:22,581 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 7d5feb49-141e-4898-8521-d18c1a01949e Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:14:22,581 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 7d5feb49-141e-4898-8521-d18c1a01949e Starte Chunking (client) 
{"extra": {"document_id": "ad7b2b3b-a60a-45da-9fa3-d8602e2450c0"}}
2026-09-21 15:14:22,580 INFO rag_processor.py:__init__:127 RAGProcessor 7d5feb49-141e-4898-8521-d18c1a01949e RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:22,466 DEBUG base_processor.py:init_logger:386 RAGProcessor 7d5feb49-141e-4898-8521-d18c1a01949e Logger initialisiert
2026-09-21 15:14:22,465 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2136 (process_request_thread) running_jobs=[]
2026-09-21 15:14:22,358 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=2037 cost=0 models=['voyage-3-large'] thread=Thread-2134 (process_request_thread)
2026-09-21 15:14:22,327 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor abf2da7f-76cd-4c26-a5f7-8072200a9ad6 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9waGFzZW5tb2RlbGwgbWl0ZWluYW5kZXIgaW4gYmV3ZWd1bmcubWQ=", "chunks": 9, "duration_seconds": 0.9708375930786133}}
2026-09-21 15:14:22,326 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor abf2da7f-76cd-4c26-a5f7-8072200a9ad6 1 LLM-Requests hinzugefügt
2026-09-21 15:14:21,732 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=288 cost=0 models=['voyage-3-large'] thread=Thread-2135 (process_request_thread)
2026-09-21 15:14:21,729 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 08ccbe82-cdc8-4159-8dab-c02008ad22b3 Embedding (client) abgeschlossen 
{"extra": {"document_id": "a78ae96a-462d-45be-b4b6-c1d5c3d6e5c6", "chunks": 1, "duration_seconds": 0.24563241004943848}}
2026-09-21 15:14:21,728 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 08ccbe82-cdc8-4159-8dab-c02008ad22b3 1 LLM-Requests hinzugefügt
2026-09-21 15:14:21,483 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 08ccbe82-cdc8-4159-8dab-c02008ad22b3 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:21,483 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 08ccbe82-cdc8-4159-8dab-c02008ad22b3 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:14:21,483 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 08ccbe82-cdc8-4159-8dab-c02008ad22b3 Starte Chunking (client) 
{"extra": {"document_id": "a78ae96a-462d-45be-b4b6-c1d5c3d6e5c6"}}
2026-09-21 15:14:21,483 INFO rag_processor.py:__init__:127 RAGProcessor 08ccbe82-cdc8-4159-8dab-c02008ad22b3 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:21,370 DEBUG base_processor.py:init_logger:386 RAGProcessor 08ccbe82-cdc8-4159-8dab-c02008ad22b3 Logger initialisiert
2026-09-21 15:14:21,370 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2135 (process_request_thread) running_jobs=[]
2026-09-21 15:14:21,356 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor abf2da7f-76cd-4c26-a5f7-8072200a9ad6 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 9, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:21,356 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor abf2da7f-76cd-4c26-a5f7-8072200a9ad6 Chunking abgeschlossen (client): 9 Chunks erstellt
2026-09-21 15:14:21,356 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor abf2da7f-76cd-4c26-a5f7-8072200a9ad6 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9waGFzZW5tb2RlbGwgbWl0ZWluYW5kZXIgaW4gYmV3ZWd1bmcubWQ="}}
2026-09-21 15:14:21,355 INFO rag_processor.py:__init__:127 RAGProcessor abf2da7f-76cd-4c26-a5f7-8072200a9ad6 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:21,246 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=1868 cost=0 models=['voyage-3-large'] thread=Thread-2133 (process_request_thread)
2026-09-21 15:14:21,199 DEBUG base_processor.py:init_logger:386 RAGProcessor abf2da7f-76cd-4c26-a5f7-8072200a9ad6 Logger initialisiert
2026-09-21 15:14:21,197 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2134 (process_request_thread) running_jobs=[]
2026-09-21 15:14:21,196 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor bbb3e72c-0a35-49ba-96ec-eee701bd339f Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9ncm9zc2dydXBwZW52ZXJmYWhyZW4ubWQ=", "chunks": 8, "duration_seconds": 0.8666739463806152}}
2026-09-21 15:14:21,194 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor bbb3e72c-0a35-49ba-96ec-eee701bd339f 1 LLM-Requests hinzugefügt
2026-09-21 15:14:21,062 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=7849 cost=0.007175 models=['google/gemini-2.5-flash'] thread=Thread-2129 (process_request_thread)
2026-09-21 15:14:21,060 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 501969dd-1b5e-4864-af13-3a20a73b4380 Template-Transformation abgeschlossen 
{"duration_ms": 9705.768823623657, "model": "google/gemini-2.5-flash"}
2026-09-21 15:14:21,057 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 501969dd-1b5e-4864-af13-3a20a73b4380 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151421_template_transform.json", "tokens": 7849}
2026-09-21 15:14:21,055 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 501969dd-1b5e-4864-af13-3a20a73b4380 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 7849, "duration": 9705.768823623657, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:14:21,055 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 501969dd-1b5e-4864-af13-3a20a73b4380 1 LLM-Requests hinzugefügt
2026-09-21 15:14:20,329 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor bbb3e72c-0a35-49ba-96ec-eee701bd339f Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 8, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:20,329 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor bbb3e72c-0a35-49ba-96ec-eee701bd339f Chunking abgeschlossen (client): 8 Chunks erstellt
2026-09-21 15:14:20,329 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor bbb3e72c-0a35-49ba-96ec-eee701bd339f Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9ncm9zc2dydXBwZW52ZXJmYWhyZW4ubWQ="}}
2026-09-21 15:14:20,328 INFO rag_processor.py:__init__:127 RAGProcessor bbb3e72c-0a35-49ba-96ec-eee701bd339f RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:20,206 DEBUG base_processor.py:init_logger:386 RAGProcessor bbb3e72c-0a35-49ba-96ec-eee701bd339f Logger initialisiert
2026-09-21 15:14:20,205 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2133 (process_request_thread) running_jobs=[]
2026-09-21 15:14:18,917 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=7440 cost=0.006843 models=['google/gemini-2.5-flash'] thread=Thread-2126 (process_request_thread)
2026-09-21 15:14:18,916 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 684ebb4f-4ea8-41a7-85aa-ca2e4c280a03 Template-Transformation abgeschlossen 
{"duration_ms": 9517.145156860352, "model": "google/gemini-2.5-flash"}
2026-09-21 15:14:18,914 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 684ebb4f-4ea8-41a7-85aa-ca2e4c280a03 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151418_template_transform.json", "tokens": 7440}
2026-09-21 15:14:18,913 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 684ebb4f-4ea8-41a7-85aa-ca2e4c280a03 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 7440, "duration": 9517.145156860352, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:14:18,912 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 684ebb4f-4ea8-41a7-85aa-ca2e4c280a03 1 LLM-Requests hinzugefügt
2026-09-21 15:14:18,012 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=7301 cost=0.006417 models=['google/gemini-2.5-flash'] thread=Thread-2123 (process_request_thread)
2026-09-21 15:14:18,011 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 18355252-8e0c-4a3e-9419-f5fdf8067224 Template-Transformation abgeschlossen 
{"duration_ms": 10635.86950302124, "model": "google/gemini-2.5-flash"}
2026-09-21 15:14:18,009 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 18355252-8e0c-4a3e-9419-f5fdf8067224 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151418_template_transform.json", "tokens": 7301}
2026-09-21 15:14:18,008 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 18355252-8e0c-4a3e-9419-f5fdf8067224 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 7301, "duration": 10635.86950302124, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:14:18,008 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 18355252-8e0c-4a3e-9419-f5fdf8067224 1 LLM-Requests hinzugefügt
2026-09-21 15:14:15,502 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 889f0f1d-6bf1-4c73-9615-694a4f233192 Sende Anfrage an LLM Provider
2026-09-21 15:14:15,501 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 889f0f1d-6bf1-4c73-9615-694a4f233192 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 7687, "estimated_text_tokens": 2760, "estimated_system_tokens": 1812, "estimated_template_tokens": 2040, "total_estimated_tokens": 6612}
2026-09-21 15:14:15,500 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 889f0f1d-6bf1-4c73-9615-694a4f233192 Verwende direkt übergebenes Template-Inhalt (Länge: 11350)
2026-09-21 15:14:15,500 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 889f0f1d-6bf1-4c73-9615-694a4f233192 Starte Template-Transformation:
2026-09-21 15:14:15,500 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 889f0f1d-6bf1-4c73-9615-694a4f233192 Transformer Init Timings 
{"total_init_ms": 195.58, "super_init_ms": 113.43, "config_load_ms": 20.0, "client_init_ms": 0.01, "transcriber_init_ms": 61.8}
2026-09-21 15:14:15,499 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 889f0f1d-6bf1-4c73-9615-694a4f233192 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:14:15,304 DEBUG base_processor.py:init_logger:386 TransformerProcessor 889f0f1d-6bf1-4c73-9615-694a4f233192 Logger initialisiert
2026-09-21 15:14:15,303 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2132 (process_request_thread) running_jobs=[]
2026-09-21 15:14:13,124 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=377 cost=0 models=['voyage-3-large'] thread=Thread-2131 (process_request_thread)
2026-09-21 15:14:13,119 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor b60d60ed-1316-4ba1-93ea-02c7247246aa Embedding (client) abgeschlossen 
{"extra": {"document_id": "8d326bfa-6665-4600-b289-e8e1b74b9b1c", "chunks": 1, "duration_seconds": 0.2687845230102539}}
2026-09-21 15:14:13,119 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor b60d60ed-1316-4ba1-93ea-02c7247246aa 1 LLM-Requests hinzugefügt
2026-09-21 15:14:12,851 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor b60d60ed-1316-4ba1-93ea-02c7247246aa Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:12,851 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor b60d60ed-1316-4ba1-93ea-02c7247246aa Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:14:12,850 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor b60d60ed-1316-4ba1-93ea-02c7247246aa Starte Chunking (client) 
{"extra": {"document_id": "8d326bfa-6665-4600-b289-e8e1b74b9b1c"}}
2026-09-21 15:14:12,850 INFO rag_processor.py:__init__:127 RAGProcessor b60d60ed-1316-4ba1-93ea-02c7247246aa RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:12,735 DEBUG base_processor.py:init_logger:386 RAGProcessor b60d60ed-1316-4ba1-93ea-02c7247246aa Logger initialisiert
2026-09-21 15:14:12,734 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2131 (process_request_thread) running_jobs=[]
2026-09-21 15:14:12,652 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=1755 cost=0 models=['voyage-3-large'] thread=Thread-2130 (process_request_thread)
2026-09-21 15:14:12,634 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 95815ea4-c538-4bee-b3b8-a0b265241e01 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9nb3JkaXNjaGVyX2tub3Rlbi5tZA==", "chunks": 7, "duration_seconds": 1.0375573635101318}}
2026-09-21 15:14:12,634 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 95815ea4-c538-4bee-b3b8-a0b265241e01 1 LLM-Requests hinzugefügt
2026-09-21 15:14:11,597 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 95815ea4-c538-4bee-b3b8-a0b265241e01 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 7, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:11,597 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 95815ea4-c538-4bee-b3b8-a0b265241e01 Chunking abgeschlossen (client): 7 Chunks erstellt
2026-09-21 15:14:11,597 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 95815ea4-c538-4bee-b3b8-a0b265241e01 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9nb3JkaXNjaGVyX2tub3Rlbi5tZA=="}}
2026-09-21 15:14:11,596 INFO rag_processor.py:__init__:127 RAGProcessor 95815ea4-c538-4bee-b3b8-a0b265241e01 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:11,470 DEBUG base_processor.py:init_logger:386 RAGProcessor 95815ea4-c538-4bee-b3b8-a0b265241e01 Logger initialisiert
2026-09-21 15:14:11,469 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2130 (process_request_thread) running_jobs=[]
2026-09-21 15:14:11,349 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 501969dd-1b5e-4864-af13-3a20a73b4380 Sende Anfrage an LLM Provider
2026-09-21 15:14:11,348 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 501969dd-1b5e-4864-af13-3a20a73b4380 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 8006, "estimated_text_tokens": 2966, "estimated_system_tokens": 1812, "estimated_template_tokens": 2040, "total_estimated_tokens": 6818}
2026-09-21 15:14:11,347 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 501969dd-1b5e-4864-af13-3a20a73b4380 Verwende direkt übergebenes Template-Inhalt (Länge: 11350)
2026-09-21 15:14:11,347 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 501969dd-1b5e-4864-af13-3a20a73b4380 Starte Template-Transformation:
2026-09-21 15:14:11,346 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 501969dd-1b5e-4864-af13-3a20a73b4380 Transformer Init Timings 
{"total_init_ms": 192.79, "super_init_ms": 109.91, "config_load_ms": 20.54, "client_init_ms": 0.03, "transcriber_init_ms": 62.0}
2026-09-21 15:14:11,346 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 501969dd-1b5e-4864-af13-3a20a73b4380 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:14:11,154 DEBUG base_processor.py:init_logger:386 TransformerProcessor 501969dd-1b5e-4864-af13-3a20a73b4380 Logger initialisiert
2026-09-21 15:14:11,153 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2129 (process_request_thread) running_jobs=[]
2026-09-21 15:14:10,035 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=245 cost=0 models=['voyage-3-large'] thread=Thread-2128 (process_request_thread)
2026-09-21 15:14:10,032 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 614ae587-3b2a-45aa-b090-b01c5e1acb24 Embedding (client) abgeschlossen 
{"extra": {"document_id": "2d5ff8a5-5c8f-4581-b52c-af3d0aa5d3db", "chunks": 1, "duration_seconds": 0.24590349197387695}}
2026-09-21 15:14:10,032 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 614ae587-3b2a-45aa-b090-b01c5e1acb24 1 LLM-Requests hinzugefügt
2026-09-21 15:14:09,848 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=346 cost=0 models=['voyage-3-large'] thread=Thread-2127 (process_request_thread)
2026-09-21 15:14:09,845 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 62bd0bde-2e35-45ec-8b1e-c9d11991419b Embedding (client) abgeschlossen 
{"extra": {"document_id": "414b0f18-e1b9-4596-b893-9b41c5c68d54", "chunks": 1, "duration_seconds": 0.2735612392425537}}
2026-09-21 15:14:09,844 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 62bd0bde-2e35-45ec-8b1e-c9d11991419b 1 LLM-Requests hinzugefügt
2026-09-21 15:14:09,787 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 614ae587-3b2a-45aa-b090-b01c5e1acb24 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:09,786 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 614ae587-3b2a-45aa-b090-b01c5e1acb24 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:14:09,786 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 614ae587-3b2a-45aa-b090-b01c5e1acb24 Starte Chunking (client) 
{"extra": {"document_id": "2d5ff8a5-5c8f-4581-b52c-af3d0aa5d3db"}}
2026-09-21 15:14:09,786 INFO rag_processor.py:__init__:127 RAGProcessor 614ae587-3b2a-45aa-b090-b01c5e1acb24 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:09,667 DEBUG base_processor.py:init_logger:386 RAGProcessor 614ae587-3b2a-45aa-b090-b01c5e1acb24 Logger initialisiert
2026-09-21 15:14:09,666 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2128 (process_request_thread) running_jobs=[]
2026-09-21 15:14:09,594 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=1913 cost=0 models=['voyage-3-large'] thread=Thread-2125 (process_request_thread)
2026-09-21 15:14:09,576 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 8b2fe8af-2abe-425c-a362-622a073fbaa2 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9nZW1laW5zYW1lcl9iZXJhdHVuZ3NwZmFkLm1k", "chunks": 8, "duration_seconds": 1.0844566822052002}}
2026-09-21 15:14:09,575 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 8b2fe8af-2abe-425c-a362-622a073fbaa2 1 LLM-Requests hinzugefügt
2026-09-21 15:14:09,572 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 62bd0bde-2e35-45ec-8b1e-c9d11991419b Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:09,571 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 62bd0bde-2e35-45ec-8b1e-c9d11991419b Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:14:09,571 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 62bd0bde-2e35-45ec-8b1e-c9d11991419b Starte Chunking (client) 
{"extra": {"document_id": "414b0f18-e1b9-4596-b893-9b41c5c68d54"}}
2026-09-21 15:14:09,571 INFO rag_processor.py:__init__:127 RAGProcessor 62bd0bde-2e35-45ec-8b1e-c9d11991419b RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:09,457 DEBUG base_processor.py:init_logger:386 RAGProcessor 62bd0bde-2e35-45ec-8b1e-c9d11991419b Logger initialisiert
2026-09-21 15:14:09,456 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2127 (process_request_thread) running_jobs=[]
2026-09-21 15:14:09,402 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=7108 cost=0.006477 models=['google/gemini-2.5-flash'] thread=Thread-2117 (process_request_thread)
2026-09-21 15:14:09,401 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 6f83eaa0-ec91-4e91-960a-a547807136db Template-Transformation abgeschlossen 
{"duration_ms": 7895.95103263855, "model": "google/gemini-2.5-flash"}
2026-09-21 15:14:09,399 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 6f83eaa0-ec91-4e91-960a-a547807136db LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151409_template_transform.json", "tokens": 7108}
2026-09-21 15:14:09,398 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 6f83eaa0-ec91-4e91-960a-a547807136db LLM Request erstellt 
{"purpose": "template_transform", "tokens": 7108, "duration": 7895.95103263855, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:14:09,397 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 6f83eaa0-ec91-4e91-960a-a547807136db 1 LLM-Requests hinzugefügt
2026-09-21 15:14:09,395 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 684ebb4f-4ea8-41a7-85aa-ca2e4c280a03 Sende Anfrage an LLM Provider
2026-09-21 15:14:09,394 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 684ebb4f-4ea8-41a7-85aa-ca2e4c280a03 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 6404, "estimated_text_tokens": 2384, "estimated_system_tokens": 1812, "estimated_template_tokens": 2058, "total_estimated_tokens": 6254}
2026-09-21 15:14:09,393 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 684ebb4f-4ea8-41a7-85aa-ca2e4c280a03 Verwende direkt übergebenes Template-Inhalt (Länge: 11350)
2026-09-21 15:14:09,392 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 684ebb4f-4ea8-41a7-85aa-ca2e4c280a03 Starte Template-Transformation:
2026-09-21 15:14:09,392 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 684ebb4f-4ea8-41a7-85aa-ca2e4c280a03 Transformer Init Timings 
{"total_init_ms": 220.88, "super_init_ms": 115.63, "config_load_ms": 23.96, "client_init_ms": 0.02, "transcriber_init_ms": 80.99}
2026-09-21 15:14:09,392 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 684ebb4f-4ea8-41a7-85aa-ca2e4c280a03 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:14:09,363 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=2165 cost=0 models=['voyage-3-large'] thread=Thread-2124 (process_request_thread)
2026-09-21 15:14:09,344 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 3abac333-b9b6-4a2f-9fbb-d876a0e62ff9 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9mbHVzc2RpYWdyYW1tX21pdF9tdXN0ZXJrYXJ0ZW4ubWQ=", "chunks": 10, "duration_seconds": 1.2327024936676025}}
2026-09-21 15:14:09,343 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 3abac333-b9b6-4a2f-9fbb-d876a0e62ff9 1 LLM-Requests hinzugefügt
2026-09-21 15:14:09,172 DEBUG base_processor.py:init_logger:386 TransformerProcessor 684ebb4f-4ea8-41a7-85aa-ca2e4c280a03 Logger initialisiert
2026-09-21 15:14:09,170 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2126 (process_request_thread) running_jobs=[]
2026-09-21 15:14:08,492 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 8b2fe8af-2abe-425c-a362-622a073fbaa2 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 8, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:08,491 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 8b2fe8af-2abe-425c-a362-622a073fbaa2 Chunking abgeschlossen (client): 8 Chunks erstellt
2026-09-21 15:14:08,491 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 8b2fe8af-2abe-425c-a362-622a073fbaa2 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9nZW1laW5zYW1lcl9iZXJhdHVuZ3NwZmFkLm1k"}}
2026-09-21 15:14:08,491 INFO rag_processor.py:__init__:127 RAGProcessor 8b2fe8af-2abe-425c-a362-622a073fbaa2 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:08,378 DEBUG base_processor.py:init_logger:386 RAGProcessor 8b2fe8af-2abe-425c-a362-622a073fbaa2 Logger initialisiert
2026-09-21 15:14:08,377 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2125 (process_request_thread) running_jobs=[]
2026-09-21 15:14:08,112 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 3abac333-b9b6-4a2f-9fbb-d876a0e62ff9 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 10, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:08,112 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 3abac333-b9b6-4a2f-9fbb-d876a0e62ff9 Chunking abgeschlossen (client): 10 Chunks erstellt
2026-09-21 15:14:08,111 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 3abac333-b9b6-4a2f-9fbb-d876a0e62ff9 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9mbHVzc2RpYWdyYW1tX21pdF9tdXN0ZXJrYXJ0ZW4ubWQ="}}
2026-09-21 15:14:08,111 INFO rag_processor.py:__init__:127 RAGProcessor 3abac333-b9b6-4a2f-9fbb-d876a0e62ff9 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:07,982 DEBUG base_processor.py:init_logger:386 RAGProcessor 3abac333-b9b6-4a2f-9fbb-d876a0e62ff9 Logger initialisiert
2026-09-21 15:14:07,981 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2124 (process_request_thread) running_jobs=[]
2026-09-21 15:14:07,371 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 18355252-8e0c-4a3e-9419-f5fdf8067224 Sende Anfrage an LLM Provider
2026-09-21 15:14:07,371 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 18355252-8e0c-4a3e-9419-f5fdf8067224 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 6489, "estimated_text_tokens": 2184, "estimated_system_tokens": 1812, "estimated_template_tokens": 2040, "total_estimated_tokens": 6036}
2026-09-21 15:14:07,367 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 18355252-8e0c-4a3e-9419-f5fdf8067224 Verwende direkt übergebenes Template-Inhalt (Länge: 11350)
2026-09-21 15:14:07,367 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 18355252-8e0c-4a3e-9419-f5fdf8067224 Starte Template-Transformation:
2026-09-21 15:14:07,367 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 18355252-8e0c-4a3e-9419-f5fdf8067224 Transformer Init Timings 
{"total_init_ms": 230.7, "super_init_ms": 133.3, "config_load_ms": 20.69, "client_init_ms": 0.02, "transcriber_init_ms": 76.09}
2026-09-21 15:14:07,366 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 18355252-8e0c-4a3e-9419-f5fdf8067224 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:14:07,136 DEBUG base_processor.py:init_logger:386 TransformerProcessor 18355252-8e0c-4a3e-9419-f5fdf8067224 Logger initialisiert
2026-09-21 15:14:07,134 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2123 (process_request_thread) running_jobs=[]
2026-09-21 15:14:06,940 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=217 cost=0 models=['voyage-3-large'] thread=Thread-2122 (process_request_thread)
2026-09-21 15:14:06,936 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 1fd2f21b-7cc8-4132-af2d-0831fe10c3f8 Embedding (client) abgeschlossen 
{"extra": {"document_id": "db5d1029-35c4-49ff-8770-61cf84492e83", "chunks": 1, "duration_seconds": 0.2515292167663574}}
2026-09-21 15:14:06,936 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 1fd2f21b-7cc8-4132-af2d-0831fe10c3f8 1 LLM-Requests hinzugefügt
2026-09-21 15:14:06,685 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 1fd2f21b-7cc8-4132-af2d-0831fe10c3f8 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:06,685 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 1fd2f21b-7cc8-4132-af2d-0831fe10c3f8 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:14:06,685 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 1fd2f21b-7cc8-4132-af2d-0831fe10c3f8 Starte Chunking (client) 
{"extra": {"document_id": "db5d1029-35c4-49ff-8770-61cf84492e83"}}
2026-09-21 15:14:06,684 INFO rag_processor.py:__init__:127 RAGProcessor 1fd2f21b-7cc8-4132-af2d-0831fe10c3f8 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:06,574 DEBUG base_processor.py:init_logger:386 RAGProcessor 1fd2f21b-7cc8-4132-af2d-0831fe10c3f8 Logger initialisiert
2026-09-21 15:14:06,573 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2122 (process_request_thread) running_jobs=[]
2026-09-21 15:14:06,500 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=1809 cost=0 models=['voyage-3-large'] thread=Thread-2121 (process_request_thread)
2026-09-21 15:14:06,484 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor ae75318f-a193-49a1-b9f9-bfdcdca66adf Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9jb21tb25pbmdfdmlzaW9uY2FyZC5tZA==", "chunks": 8, "duration_seconds": 0.8958892822265625}}
2026-09-21 15:14:06,484 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor ae75318f-a193-49a1-b9f9-bfdcdca66adf 1 LLM-Requests hinzugefügt
2026-09-21 15:14:06,208 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=7447 cost=0.006425 models=['google/gemini-2.5-flash'] thread=Thread-2115 (process_request_thread)
2026-09-21 15:14:06,207 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 1199611a-10be-4c9a-b659-712fd639c552 Template-Transformation abgeschlossen 
{"duration_ms": 8706.092834472656, "model": "google/gemini-2.5-flash"}
2026-09-21 15:14:06,205 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 1199611a-10be-4c9a-b659-712fd639c552 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151406_template_transform.json", "tokens": 7447}
2026-09-21 15:14:06,204 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 1199611a-10be-4c9a-b659-712fd639c552 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 7447, "duration": 8706.092834472656, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:14:06,204 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 1199611a-10be-4c9a-b659-712fd639c552 1 LLM-Requests hinzugefügt
2026-09-21 15:14:05,770 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=7914 cost=0.007227 models=['google/gemini-2.5-flash'] thread=Thread-2113 (process_request_thread)
2026-09-21 15:14:05,769 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor c319a76d-88ed-45fa-9b83-9b57c78b71c5 Template-Transformation abgeschlossen 
{"duration_ms": 10260.525465011597, "model": "google/gemini-2.5-flash"}
2026-09-21 15:14:05,768 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor c319a76d-88ed-45fa-9b83-9b57c78b71c5 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151405_template_transform.json", "tokens": 7914}
2026-09-21 15:14:05,767 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor c319a76d-88ed-45fa-9b83-9b57c78b71c5 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 7914, "duration": 10260.525465011597, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:14:05,767 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor c319a76d-88ed-45fa-9b83-9b57c78b71c5 1 LLM-Requests hinzugefügt
2026-09-21 15:14:05,589 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor ae75318f-a193-49a1-b9f9-bfdcdca66adf Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 8, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:05,589 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor ae75318f-a193-49a1-b9f9-bfdcdca66adf Chunking abgeschlossen (client): 8 Chunks erstellt
2026-09-21 15:14:05,588 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor ae75318f-a193-49a1-b9f9-bfdcdca66adf Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9jb21tb25pbmdfdmlzaW9uY2FyZC5tZA=="}}
2026-09-21 15:14:05,588 INFO rag_processor.py:__init__:127 RAGProcessor ae75318f-a193-49a1-b9f9-bfdcdca66adf RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:05,472 DEBUG base_processor.py:init_logger:386 RAGProcessor ae75318f-a193-49a1-b9f9-bfdcdca66adf Logger initialisiert
2026-09-21 15:14:05,470 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2121 (process_request_thread) running_jobs=[]
2026-09-21 15:14:05,129 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=265 cost=0 models=['voyage-3-large'] thread=Thread-2120 (process_request_thread)
2026-09-21 15:14:05,126 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor de75ee18-0ebe-421e-8416-fce1c30cef26 Embedding (client) abgeschlossen 
{"extra": {"document_id": "86937f80-f489-4b6f-92e6-deebbd2796bb", "chunks": 1, "duration_seconds": 0.2701413631439209}}
2026-09-21 15:14:05,125 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor de75ee18-0ebe-421e-8416-fce1c30cef26 1 LLM-Requests hinzugefügt
2026-09-21 15:14:04,856 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor de75ee18-0ebe-421e-8416-fce1c30cef26 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:04,856 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor de75ee18-0ebe-421e-8416-fce1c30cef26 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:14:04,856 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor de75ee18-0ebe-421e-8416-fce1c30cef26 Starte Chunking (client) 
{"extra": {"document_id": "86937f80-f489-4b6f-92e6-deebbd2796bb"}}
2026-09-21 15:14:04,855 INFO rag_processor.py:__init__:127 RAGProcessor de75ee18-0ebe-421e-8416-fce1c30cef26 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:04,724 DEBUG base_processor.py:init_logger:386 RAGProcessor de75ee18-0ebe-421e-8416-fce1c30cef26 Logger initialisiert
2026-09-21 15:14:04,723 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2120 (process_request_thread) running_jobs=[]
2026-09-21 15:14:04,609 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=2194 cost=0 models=['voyage-3-large'] thread=Thread-2119 (process_request_thread)
2026-09-21 15:14:04,587 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor fe966b12-b5fc-4f50-90f3-04c03770f8ce Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9jb21tb25pbmdfbGFuZGthcnRlLm1k", "chunks": 10, "duration_seconds": 1.3329792022705078}}
2026-09-21 15:14:04,587 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor fe966b12-b5fc-4f50-90f3-04c03770f8ce 1 LLM-Requests hinzugefügt
2026-09-21 15:14:03,308 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=7316 cost=0.006516 models=['google/gemini-2.5-flash'] thread=Thread-2111 (process_request_thread)
2026-09-21 15:14:03,307 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 8bcb5dc3-6f82-40a8-8196-b3361ba4e496 Template-Transformation abgeschlossen 
{"duration_ms": 9746.703624725342, "model": "google/gemini-2.5-flash"}
2026-09-21 15:14:03,304 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 8bcb5dc3-6f82-40a8-8196-b3361ba4e496 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151403_template_transform.json", "tokens": 7316}
2026-09-21 15:14:03,303 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 8bcb5dc3-6f82-40a8-8196-b3361ba4e496 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 7316, "duration": 9746.703624725342, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:14:03,303 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 8bcb5dc3-6f82-40a8-8196-b3361ba4e496 1 LLM-Requests hinzugefügt
2026-09-21 15:14:03,255 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor fe966b12-b5fc-4f50-90f3-04c03770f8ce Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 10, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:03,255 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor fe966b12-b5fc-4f50-90f3-04c03770f8ce Chunking abgeschlossen (client): 10 Chunks erstellt
2026-09-21 15:14:03,254 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor fe966b12-b5fc-4f50-90f3-04c03770f8ce Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9jb21tb25pbmdfbGFuZGthcnRlLm1k"}}
2026-09-21 15:14:03,254 INFO rag_processor.py:__init__:127 RAGProcessor fe966b12-b5fc-4f50-90f3-04c03770f8ce RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:03,123 DEBUG base_processor.py:init_logger:386 RAGProcessor fe966b12-b5fc-4f50-90f3-04c03770f8ce Logger initialisiert
2026-09-21 15:14:03,122 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2119 (process_request_thread) running_jobs=[]
2026-09-21 15:14:01,760 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=239 cost=0 models=['voyage-3-large'] thread=Thread-2118 (process_request_thread)
2026-09-21 15:14:01,757 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 2bb076ab-4bca-46eb-ac6b-7b5a91eb7f9d Embedding (client) abgeschlossen 
{"extra": {"document_id": "19d199b5-36c9-4555-b6a0-1f9c094480ff", "chunks": 1, "duration_seconds": 0.24358439445495605}}
2026-09-21 15:14:01,757 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 2bb076ab-4bca-46eb-ac6b-7b5a91eb7f9d 1 LLM-Requests hinzugefügt
2026-09-21 15:14:01,514 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 2bb076ab-4bca-46eb-ac6b-7b5a91eb7f9d Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:01,514 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 2bb076ab-4bca-46eb-ac6b-7b5a91eb7f9d Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:14:01,514 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 2bb076ab-4bca-46eb-ac6b-7b5a91eb7f9d Starte Chunking (client) 
{"extra": {"document_id": "19d199b5-36c9-4555-b6a0-1f9c094480ff"}}
2026-09-21 15:14:01,513 INFO rag_processor.py:__init__:127 RAGProcessor 2bb076ab-4bca-46eb-ac6b-7b5a91eb7f9d RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:01,501 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 6f83eaa0-ec91-4e91-960a-a547807136db Sende Anfrage an LLM Provider
2026-09-21 15:14:01,496 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 6f83eaa0-ec91-4e91-960a-a547807136db Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 5739, "estimated_text_tokens": 2204, "estimated_system_tokens": 1812, "estimated_template_tokens": 2040, "total_estimated_tokens": 6056}
2026-09-21 15:14:01,483 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 6f83eaa0-ec91-4e91-960a-a547807136db Verwende direkt übergebenes Template-Inhalt (Länge: 11350)
2026-09-21 15:14:01,483 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 6f83eaa0-ec91-4e91-960a-a547807136db Starte Template-Transformation:
2026-09-21 15:14:01,477 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 6f83eaa0-ec91-4e91-960a-a547807136db Transformer Init Timings 
{"total_init_ms": 296.62, "super_init_ms": 143.07, "config_load_ms": 32.92, "client_init_ms": 0.01, "transcriber_init_ms": 120.23}
2026-09-21 15:14:01,477 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 6f83eaa0-ec91-4e91-960a-a547807136db Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:14:01,325 DEBUG base_processor.py:init_logger:386 RAGProcessor 2bb076ab-4bca-46eb-ac6b-7b5a91eb7f9d Logger initialisiert
2026-09-21 15:14:01,324 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2118 (process_request_thread) running_jobs=[]
2026-09-21 15:14:01,181 DEBUG base_processor.py:init_logger:386 TransformerProcessor 6f83eaa0-ec91-4e91-960a-a547807136db Logger initialisiert
2026-09-21 15:14:01,179 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2117 (process_request_thread) running_jobs=[]
2026-09-21 15:14:01,177 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=1528 cost=0 models=['voyage-3-large'] thread=Thread-2116 (process_request_thread)
2026-09-21 15:14:01,162 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor cf174af3-eeea-498f-b932-1afe5a26c400 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9jb21tb25pbmdfa29tcGFzcy5tZA==", "chunks": 6, "duration_seconds": 0.7795555591583252}}
2026-09-21 15:14:01,161 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor cf174af3-eeea-498f-b932-1afe5a26c400 1 LLM-Requests hinzugefügt
2026-09-21 15:14:01,072 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=7606 cost=0.006974 models=['google/gemini-2.5-flash'] thread=Thread-2108 (process_request_thread)
2026-09-21 15:14:01,071 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 7304b175-eb6a-4142-8363-eb27710f2b7c Template-Transformation abgeschlossen 
{"duration_ms": 9656.25286102295, "model": "google/gemini-2.5-flash"}
2026-09-21 15:14:01,069 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 7304b175-eb6a-4142-8363-eb27710f2b7c LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151401_template_transform.json", "tokens": 7606}
2026-09-21 15:14:01,068 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 7304b175-eb6a-4142-8363-eb27710f2b7c LLM Request erstellt 
{"purpose": "template_transform", "tokens": 7606, "duration": 9656.25286102295, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:14:01,068 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 7304b175-eb6a-4142-8363-eb27710f2b7c 1 LLM-Requests hinzugefügt
2026-09-21 15:14:00,383 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor cf174af3-eeea-498f-b932-1afe5a26c400 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 6, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:14:00,382 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor cf174af3-eeea-498f-b932-1afe5a26c400 Chunking abgeschlossen (client): 6 Chunks erstellt
2026-09-21 15:14:00,382 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor cf174af3-eeea-498f-b932-1afe5a26c400 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tZXRob2Rlbi9jb21tb25pbmdfa29tcGFzcy5tZA=="}}
2026-09-21 15:14:00,382 INFO rag_processor.py:__init__:127 RAGProcessor cf174af3-eeea-498f-b932-1afe5a26c400 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:14:00,251 DEBUG base_processor.py:init_logger:386 RAGProcessor cf174af3-eeea-498f-b932-1afe5a26c400 Logger initialisiert
2026-09-21 15:14:00,249 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2116 (process_request_thread) running_jobs=[]
2026-09-21 15:13:58,089 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=7006 cost=0.006029 models=['google/gemini-2.5-flash'] thread=Thread-2105 (process_request_thread)
2026-09-21 15:13:58,088 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor fe4c4359-2d94-4a96-ac75-83c36dce130d Template-Transformation abgeschlossen 
{"duration_ms": 10728.411436080933, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:58,085 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor fe4c4359-2d94-4a96-ac75-83c36dce130d LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151358_template_transform.json", "tokens": 7006}
2026-09-21 15:13:58,083 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor fe4c4359-2d94-4a96-ac75-83c36dce130d LLM Request erstellt 
{"purpose": "template_transform", "tokens": 7006, "duration": 10728.411436080933, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:58,083 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor fe4c4359-2d94-4a96-ac75-83c36dce130d 1 LLM-Requests hinzugefügt
2026-09-21 15:13:57,497 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 1199611a-10be-4c9a-b659-712fd639c552 Sende Anfrage an LLM Provider
2026-09-21 15:13:57,497 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 1199611a-10be-4c9a-b659-712fd639c552 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 7088, "estimated_text_tokens": 2414, "estimated_system_tokens": 1812, "estimated_template_tokens": 2040, "total_estimated_tokens": 6266}
2026-09-21 15:13:57,495 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 1199611a-10be-4c9a-b659-712fd639c552 Verwende direkt übergebenes Template-Inhalt (Länge: 11350)
2026-09-21 15:13:57,495 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 1199611a-10be-4c9a-b659-712fd639c552 Starte Template-Transformation:
2026-09-21 15:13:57,495 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 1199611a-10be-4c9a-b659-712fd639c552 Transformer Init Timings 
{"total_init_ms": 230.03, "super_init_ms": 142.71, "config_load_ms": 21.07, "client_init_ms": 0.02, "transcriber_init_ms": 65.78}
2026-09-21 15:13:57,494 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 1199611a-10be-4c9a-b659-712fd639c552 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:57,265 DEBUG base_processor.py:init_logger:386 TransformerProcessor 1199611a-10be-4c9a-b659-712fd639c552 Logger initialisiert
2026-09-21 15:13:57,263 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2115 (process_request_thread) running_jobs=[]
2026-09-21 15:13:55,887 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=310 cost=0 models=['voyage-3-large'] thread=Thread-2114 (process_request_thread)
2026-09-21 15:13:55,881 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor c55c2c1d-44cd-4741-9ff7-67d49341de69 Embedding (client) abgeschlossen 
{"extra": {"document_id": "e508e483-56fb-4f7c-9f60-cf2ebe3b94d9", "chunks": 1, "duration_seconds": 0.2552328109741211}}
2026-09-21 15:13:55,881 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor c55c2c1d-44cd-4741-9ff7-67d49341de69 1 LLM-Requests hinzugefügt
2026-09-21 15:13:55,626 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor c55c2c1d-44cd-4741-9ff7-67d49341de69 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:55,626 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor c55c2c1d-44cd-4741-9ff7-67d49341de69 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:55,626 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor c55c2c1d-44cd-4741-9ff7-67d49341de69 Starte Chunking (client) 
{"extra": {"document_id": "e508e483-56fb-4f7c-9f60-cf2ebe3b94d9"}}
2026-09-21 15:13:55,625 INFO rag_processor.py:__init__:127 RAGProcessor c55c2c1d-44cd-4741-9ff7-67d49341de69 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:55,513 DEBUG base_processor.py:init_logger:386 RAGProcessor c55c2c1d-44cd-4741-9ff7-67d49341de69 Logger initialisiert
2026-09-21 15:13:55,512 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2114 (process_request_thread) running_jobs=[]
2026-09-21 15:13:55,506 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor c319a76d-88ed-45fa-9b83-9b57c78b71c5 Sende Anfrage an LLM Provider
2026-09-21 15:13:55,505 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor c319a76d-88ed-45fa-9b83-9b57c78b71c5 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 7842, "estimated_text_tokens": 2792, "estimated_system_tokens": 1812, "estimated_template_tokens": 2040, "total_estimated_tokens": 6644}
2026-09-21 15:13:55,502 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor c319a76d-88ed-45fa-9b83-9b57c78b71c5 Verwende direkt übergebenes Template-Inhalt (Länge: 11350)
2026-09-21 15:13:55,502 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor c319a76d-88ed-45fa-9b83-9b57c78b71c5 Starte Template-Transformation:
2026-09-21 15:13:55,501 DEBUG transformer_processor.py:__init__:199 TransformerProcessor c319a76d-88ed-45fa-9b83-9b57c78b71c5 Transformer Init Timings 
{"total_init_ms": 213.59, "super_init_ms": 127.77, "config_load_ms": 20.99, "client_init_ms": 0.01, "transcriber_init_ms": 64.13}
2026-09-21 15:13:55,501 DEBUG transformer_processor.py:__init__:179 TransformerProcessor c319a76d-88ed-45fa-9b83-9b57c78b71c5 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:55,404 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=922 cost=0 models=['voyage-3-large'] thread=Thread-2112 (process_request_thread)
2026-09-21 15:13:55,363 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor b9ac04fa-794e-44e4-b52d-06ae2240e4aa Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vd2lydHNjaGFmdGVuLWRyZWllY2stMDJfd2Vya3RhZXRpZ2tlaXQtdW5kLWZ1ZXItc29yZ2UtZ2xlaWNod3VlcmRpZy1hbmVya2VubmVuLm1k", "chunks": 4, "duration_seconds": 0.6673822402954102}}
2026-09-21 15:13:55,362 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor b9ac04fa-794e-44e4-b52d-06ae2240e4aa 1 LLM-Requests hinzugefügt
2026-09-21 15:13:55,288 DEBUG base_processor.py:init_logger:386 TransformerProcessor c319a76d-88ed-45fa-9b83-9b57c78b71c5 Logger initialisiert
2026-09-21 15:13:55,286 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2113 (process_request_thread) running_jobs=[]
2026-09-21 15:13:54,696 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor b9ac04fa-794e-44e4-b52d-06ae2240e4aa Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 4, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:54,695 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor b9ac04fa-794e-44e4-b52d-06ae2240e4aa Chunking abgeschlossen (client): 4 Chunks erstellt
2026-09-21 15:13:54,695 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor b9ac04fa-794e-44e4-b52d-06ae2240e4aa Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vd2lydHNjaGFmdGVuLWRyZWllY2stMDJfd2Vya3RhZXRpZ2tlaXQtdW5kLWZ1ZXItc29yZ2UtZ2xlaWNod3VlcmRpZy1hbmVya2VubmVuLm1k"}}
2026-09-21 15:13:54,695 INFO rag_processor.py:__init__:127 RAGProcessor b9ac04fa-794e-44e4-b52d-06ae2240e4aa RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:54,562 DEBUG base_processor.py:init_logger:386 RAGProcessor b9ac04fa-794e-44e4-b52d-06ae2240e4aa Logger initialisiert
2026-09-21 15:13:54,561 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2112 (process_request_thread) running_jobs=[]
2026-09-21 15:13:53,556 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 8bcb5dc3-6f82-40a8-8196-b3361ba4e496 Sende Anfrage an LLM Provider
2026-09-21 15:13:53,555 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 8bcb5dc3-6f82-40a8-8196-b3361ba4e496 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 6498, "estimated_text_tokens": 2412, "estimated_system_tokens": 1812, "estimated_template_tokens": 2040, "total_estimated_tokens": 6264}
2026-09-21 15:13:53,554 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 8bcb5dc3-6f82-40a8-8196-b3361ba4e496 Verwende direkt übergebenes Template-Inhalt (Länge: 11350)
2026-09-21 15:13:53,554 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 8bcb5dc3-6f82-40a8-8196-b3361ba4e496 Starte Template-Transformation:
2026-09-21 15:13:53,554 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 8bcb5dc3-6f82-40a8-8196-b3361ba4e496 Transformer Init Timings 
{"total_init_ms": 204.74, "super_init_ms": 120.38, "config_load_ms": 21.08, "client_init_ms": 0.02, "transcriber_init_ms": 62.93}
2026-09-21 15:13:53,553 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 8bcb5dc3-6f82-40a8-8196-b3361ba4e496 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:53,349 DEBUG base_processor.py:init_logger:386 TransformerProcessor 8bcb5dc3-6f82-40a8-8196-b3361ba4e496 Logger initialisiert
2026-09-21 15:13:53,347 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2111 (process_request_thread) running_jobs=[]
2026-09-21 15:13:52,557 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=275 cost=0 models=['voyage-3-large'] thread=Thread-2110 (process_request_thread)
2026-09-21 15:13:52,551 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 165857b1-348d-4290-8b4c-390a0c75b3a4 Embedding (client) abgeschlossen 
{"extra": {"document_id": "2259a40a-6705-44fb-843b-21be954691d5", "chunks": 1, "duration_seconds": 0.2453782558441162}}
2026-09-21 15:13:52,551 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 165857b1-348d-4290-8b4c-390a0c75b3a4 1 LLM-Requests hinzugefügt
2026-09-21 15:13:52,350 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6564 cost=0.005126 models=['google/gemini-2.5-flash'] thread=Thread-2101 (process_request_thread)
2026-09-21 15:13:52,350 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 64f10dd7-a3ac-47a2-a075-502ae3b8af48 Template-Transformation abgeschlossen 
{"duration_ms": 6527.344703674316, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:52,348 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 64f10dd7-a3ac-47a2-a075-502ae3b8af48 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151352_template_transform.json", "tokens": 6564}
2026-09-21 15:13:52,348 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 64f10dd7-a3ac-47a2-a075-502ae3b8af48 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6564, "duration": 6527.344703674316, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:52,348 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 64f10dd7-a3ac-47a2-a075-502ae3b8af48 1 LLM-Requests hinzugefügt
2026-09-21 15:13:52,306 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 165857b1-348d-4290-8b4c-390a0c75b3a4 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:52,306 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 165857b1-348d-4290-8b4c-390a0c75b3a4 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:52,306 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 165857b1-348d-4290-8b4c-390a0c75b3a4 Starte Chunking (client) 
{"extra": {"document_id": "2259a40a-6705-44fb-843b-21be954691d5"}}
2026-09-21 15:13:52,305 INFO rag_processor.py:__init__:127 RAGProcessor 165857b1-348d-4290-8b4c-390a0c75b3a4 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:52,167 DEBUG base_processor.py:init_logger:386 RAGProcessor 165857b1-348d-4290-8b4c-390a0c75b3a4 Logger initialisiert
2026-09-21 15:13:52,166 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2110 (process_request_thread) running_jobs=[]
2026-09-21 15:13:52,093 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=811 cost=0 models=['voyage-3-large'] thread=Thread-2109 (process_request_thread)
2026-09-21 15:13:52,078 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 37032421-1630-4d4a-97cf-23443c57392a Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0xM19jb21tb25zZ2VtYWVzcy1maW5hbnppZXJlbi5tZA==", "chunks": 3, "duration_seconds": 0.5102448463439941}}
2026-09-21 15:13:52,078 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 37032421-1630-4d4a-97cf-23443c57392a 1 LLM-Requests hinzugefügt
2026-09-21 15:13:51,568 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 37032421-1630-4d4a-97cf-23443c57392a Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:51,568 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 37032421-1630-4d4a-97cf-23443c57392a Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:51,568 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 37032421-1630-4d4a-97cf-23443c57392a Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0xM19jb21tb25zZ2VtYWVzcy1maW5hbnppZXJlbi5tZA=="}}
2026-09-21 15:13:51,567 INFO rag_processor.py:__init__:127 RAGProcessor 37032421-1630-4d4a-97cf-23443c57392a RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:51,457 DEBUG base_processor.py:init_logger:386 RAGProcessor 37032421-1630-4d4a-97cf-23443c57392a Logger initialisiert
2026-09-21 15:13:51,456 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2109 (process_request_thread) running_jobs=[]
2026-09-21 15:13:51,412 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 7304b175-eb6a-4142-8363-eb27710f2b7c Sende Anfrage an LLM Provider
2026-09-21 15:13:51,411 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 7304b175-eb6a-4142-8363-eb27710f2b7c Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 7075, "estimated_text_tokens": 2630, "estimated_system_tokens": 1812, "estimated_template_tokens": 2040, "total_estimated_tokens": 6482}
2026-09-21 15:13:51,410 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 7304b175-eb6a-4142-8363-eb27710f2b7c Verwende direkt übergebenes Template-Inhalt (Länge: 11350)
2026-09-21 15:13:51,409 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 7304b175-eb6a-4142-8363-eb27710f2b7c Starte Template-Transformation:
2026-09-21 15:13:51,409 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 7304b175-eb6a-4142-8363-eb27710f2b7c Transformer Init Timings 
{"total_init_ms": 191.52, "super_init_ms": 107.42, "config_load_ms": 21.12, "client_init_ms": 0.01, "transcriber_init_ms": 62.66}
2026-09-21 15:13:51,409 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 7304b175-eb6a-4142-8363-eb27710f2b7c Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:51,218 DEBUG base_processor.py:init_logger:386 TransformerProcessor 7304b175-eb6a-4142-8363-eb27710f2b7c Logger initialisiert
2026-09-21 15:13:51,217 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2108 (process_request_thread) running_jobs=[]
2026-09-21 15:13:49,368 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6073 cost=0.004688 models=['google/gemini-2.5-flash'] thread=Thread-2099 (process_request_thread)
2026-09-21 15:13:49,367 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor dd557996-69d7-4ec1-ac22-2ddc36c39a30 Template-Transformation abgeschlossen 
{"duration_ms": 5342.755556106567, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:49,365 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor dd557996-69d7-4ec1-ac22-2ddc36c39a30 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151349_template_transform.json", "tokens": 6073}
2026-09-21 15:13:49,364 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor dd557996-69d7-4ec1-ac22-2ddc36c39a30 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6073, "duration": 5342.755556106567, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:49,364 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor dd557996-69d7-4ec1-ac22-2ddc36c39a30 1 LLM-Requests hinzugefügt
2026-09-21 15:13:49,081 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=266 cost=0 models=['voyage-3-large'] thread=Thread-2107 (process_request_thread)
2026-09-21 15:13:49,078 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 0d53f2dd-fa8b-4646-967a-3ffdec78027e Embedding (client) abgeschlossen 
{"extra": {"document_id": "221bfa24-7100-4caa-a0be-488d34dcc382", "chunks": 1, "duration_seconds": 0.2507476806640625}}
2026-09-21 15:13:49,078 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 0d53f2dd-fa8b-4646-967a-3ffdec78027e 1 LLM-Requests hinzugefügt
2026-09-21 15:13:48,828 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 0d53f2dd-fa8b-4646-967a-3ffdec78027e Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:48,828 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 0d53f2dd-fa8b-4646-967a-3ffdec78027e Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:48,827 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 0d53f2dd-fa8b-4646-967a-3ffdec78027e Starte Chunking (client) 
{"extra": {"document_id": "221bfa24-7100-4caa-a0be-488d34dcc382"}}
2026-09-21 15:13:48,827 INFO rag_processor.py:__init__:127 RAGProcessor 0d53f2dd-fa8b-4646-967a-3ffdec78027e RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:48,707 DEBUG base_processor.py:init_logger:386 RAGProcessor 0d53f2dd-fa8b-4646-967a-3ffdec78027e Logger initialisiert
2026-09-21 15:13:48,706 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2107 (process_request_thread) running_jobs=[]
2026-09-21 15:13:48,639 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=757 cost=0 models=['voyage-3-large'] thread=Thread-2106 (process_request_thread)
2026-09-21 15:13:48,626 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 391bf532-dbd3-4117-9f6b-0fc39025379d Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0xMl9jb21tb25zLXVuZC1rb21tZXJ6LWF1c2VpbmFuZGVyaGFsdGVuLm1k", "chunks": 3, "duration_seconds": 0.46956396102905273}}
2026-09-21 15:13:48,626 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 391bf532-dbd3-4117-9f6b-0fc39025379d 1 LLM-Requests hinzugefügt
2026-09-21 15:13:48,157 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 391bf532-dbd3-4117-9f6b-0fc39025379d Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:48,157 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 391bf532-dbd3-4117-9f6b-0fc39025379d Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:48,157 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 391bf532-dbd3-4117-9f6b-0fc39025379d Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0xMl9jb21tb25zLXVuZC1rb21tZXJ6LWF1c2VpbmFuZGVyaGFsdGVuLm1k"}}
2026-09-21 15:13:48,156 INFO rag_processor.py:__init__:127 RAGProcessor 391bf532-dbd3-4117-9f6b-0fc39025379d RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:48,028 DEBUG base_processor.py:init_logger:386 RAGProcessor 391bf532-dbd3-4117-9f6b-0fc39025379d Logger initialisiert
2026-09-21 15:13:48,027 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2106 (process_request_thread) running_jobs=[]
2026-09-21 15:13:47,354 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor fe4c4359-2d94-4a96-ac75-83c36dce130d Sende Anfrage an LLM Provider
2026-09-21 15:13:47,354 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor fe4c4359-2d94-4a96-ac75-83c36dce130d Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 6111, "estimated_text_tokens": 2300, "estimated_system_tokens": 1812, "estimated_template_tokens": 2040, "total_estimated_tokens": 6152}
2026-09-21 15:13:47,352 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor fe4c4359-2d94-4a96-ac75-83c36dce130d Verwende direkt übergebenes Template-Inhalt (Länge: 11350)
2026-09-21 15:13:47,352 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor fe4c4359-2d94-4a96-ac75-83c36dce130d Starte Template-Transformation:
2026-09-21 15:13:47,352 DEBUG transformer_processor.py:__init__:199 TransformerProcessor fe4c4359-2d94-4a96-ac75-83c36dce130d Transformer Init Timings 
{"total_init_ms": 190.93, "super_init_ms": 104.57, "config_load_ms": 21.28, "client_init_ms": 0.02, "transcriber_init_ms": 64.73}
2026-09-21 15:13:47,351 DEBUG transformer_processor.py:__init__:179 TransformerProcessor fe4c4359-2d94-4a96-ac75-83c36dce130d Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:47,161 DEBUG base_processor.py:init_logger:386 TransformerProcessor fe4c4359-2d94-4a96-ac75-83c36dce130d Logger initialisiert
2026-09-21 15:13:47,160 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2105 (process_request_thread) running_jobs=[]
2026-09-21 15:13:46,996 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=168 cost=0 models=['voyage-3-large'] thread=Thread-2104 (process_request_thread)
2026-09-21 15:13:46,992 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 3faa034a-109e-43ff-a7e9-9bcf54b636b2 Embedding (client) abgeschlossen 
{"extra": {"document_id": "ab0f525c-7dfe-49ab-ab26-4a19073cdaa0", "chunks": 1, "duration_seconds": 0.23807215690612793}}
2026-09-21 15:13:46,992 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 3faa034a-109e-43ff-a7e9-9bcf54b636b2 1 LLM-Requests hinzugefügt
2026-09-21 15:13:46,755 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 3faa034a-109e-43ff-a7e9-9bcf54b636b2 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:46,754 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 3faa034a-109e-43ff-a7e9-9bcf54b636b2 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:46,754 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 3faa034a-109e-43ff-a7e9-9bcf54b636b2 Starte Chunking (client) 
{"extra": {"document_id": "ab0f525c-7dfe-49ab-ab26-4a19073cdaa0"}}
2026-09-21 15:13:46,754 INFO rag_processor.py:__init__:127 RAGProcessor 3faa034a-109e-43ff-a7e9-9bcf54b636b2 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:46,647 DEBUG base_processor.py:init_logger:386 RAGProcessor 3faa034a-109e-43ff-a7e9-9bcf54b636b2 Logger initialisiert
2026-09-21 15:13:46,646 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2104 (process_request_thread) running_jobs=[]
2026-09-21 15:13:46,612 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=328 cost=0 models=['voyage-3-large'] thread=Thread-2103 (process_request_thread)
2026-09-21 15:13:46,609 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 73614bf4-28fa-45d8-88df-66b08732a6bf Embedding (client) abgeschlossen 
{"extra": {"document_id": "4b6a0c49-c38f-4ec9-a48f-ab21de9f3a2f", "chunks": 1, "duration_seconds": 0.2635924816131592}}
2026-09-21 15:13:46,609 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 73614bf4-28fa-45d8-88df-66b08732a6bf 1 LLM-Requests hinzugefügt
2026-09-21 15:13:46,575 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=662 cost=0 models=['voyage-3-large'] thread=Thread-2102 (process_request_thread)
2026-09-21 15:13:46,569 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 1bf9266c-d23c-4b11-8a65-2623967c1c86 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0xMV9laW5oZWd1bmdlbi11bmQtdmVyZWlubmFobXVuZ2VuLWRhendpc2NoZW5mdW5rZW4ubWQ=", "chunks": 3, "duration_seconds": 0.544424295425415}}
2026-09-21 15:13:46,568 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 1bf9266c-d23c-4b11-8a65-2623967c1c86 1 LLM-Requests hinzugefügt
2026-09-21 15:13:46,346 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 73614bf4-28fa-45d8-88df-66b08732a6bf Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:46,346 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 73614bf4-28fa-45d8-88df-66b08732a6bf Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:46,345 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 73614bf4-28fa-45d8-88df-66b08732a6bf Starte Chunking (client) 
{"extra": {"document_id": "4b6a0c49-c38f-4ec9-a48f-ab21de9f3a2f"}}
2026-09-21 15:13:46,345 INFO rag_processor.py:__init__:127 RAGProcessor 73614bf4-28fa-45d8-88df-66b08732a6bf RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:46,231 DEBUG base_processor.py:init_logger:386 RAGProcessor 73614bf4-28fa-45d8-88df-66b08732a6bf Logger initialisiert
2026-09-21 15:13:46,230 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2103 (process_request_thread) running_jobs=[]
2026-09-21 15:13:46,125 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=1041 cost=0 models=['voyage-3-large'] thread=Thread-2100 (process_request_thread)
2026-09-21 15:13:46,114 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor eba16bd6-44eb-40df-9fec-c9ad3974f3d7 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0xMF9iZXppZWh1bmdzaGFmdGlna2VpdC1kZXMtaGFiZW5zLXZlcmFua2Vybi5tZA==", "chunks": 5, "duration_seconds": 0.6423556804656982}}
2026-09-21 15:13:46,114 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor eba16bd6-44eb-40df-9fec-c9ad3974f3d7 1 LLM-Requests hinzugefügt
2026-09-21 15:13:46,025 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 1bf9266c-d23c-4b11-8a65-2623967c1c86 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:46,025 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 1bf9266c-d23c-4b11-8a65-2623967c1c86 Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:46,024 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 1bf9266c-d23c-4b11-8a65-2623967c1c86 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0xMV9laW5oZWd1bmdlbi11bmQtdmVyZWlubmFobXVuZ2VuLWRhendpc2NoZW5mdW5rZW4ubWQ="}}
2026-09-21 15:13:46,024 INFO rag_processor.py:__init__:127 RAGProcessor 1bf9266c-d23c-4b11-8a65-2623967c1c86 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:45,883 DEBUG base_processor.py:init_logger:386 RAGProcessor 1bf9266c-d23c-4b11-8a65-2623967c1c86 Logger initialisiert
2026-09-21 15:13:45,882 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2102 (process_request_thread) running_jobs=[]
2026-09-21 15:13:45,848 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6065 cost=0.004292 models=['google/gemini-2.5-flash'] thread=Thread-2096 (process_request_thread)
2026-09-21 15:13:45,847 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor d1e47302-a5c2-4e30-8416-1bac8412a23a Template-Transformation abgeschlossen 
{"duration_ms": 6184.155225753784, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:45,846 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor d1e47302-a5c2-4e30-8416-1bac8412a23a LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151345_template_transform.json", "tokens": 6065}
2026-09-21 15:13:45,845 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor d1e47302-a5c2-4e30-8416-1bac8412a23a LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6065, "duration": 6184.155225753784, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:45,845 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor d1e47302-a5c2-4e30-8416-1bac8412a23a 1 LLM-Requests hinzugefügt
2026-09-21 15:13:45,820 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 64f10dd7-a3ac-47a2-a075-502ae3b8af48 Sende Anfrage an LLM Provider
2026-09-21 15:13:45,820 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 64f10dd7-a3ac-47a2-a075-502ae3b8af48 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 4170, "estimated_text_tokens": 822, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4536}
2026-09-21 15:13:45,818 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 64f10dd7-a3ac-47a2-a075-502ae3b8af48 Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:45,818 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 64f10dd7-a3ac-47a2-a075-502ae3b8af48 Starte Template-Transformation:
2026-09-21 15:13:45,818 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 64f10dd7-a3ac-47a2-a075-502ae3b8af48 Transformer Init Timings 
{"total_init_ms": 196.16, "super_init_ms": 110.47, "config_load_ms": 20.93, "client_init_ms": 0.02, "transcriber_init_ms": 64.44}
2026-09-21 15:13:45,817 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 64f10dd7-a3ac-47a2-a075-502ae3b8af48 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:45,622 DEBUG base_processor.py:init_logger:386 TransformerProcessor 64f10dd7-a3ac-47a2-a075-502ae3b8af48 Logger initialisiert
2026-09-21 15:13:45,620 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2101 (process_request_thread) running_jobs=[]
2026-09-21 15:13:45,472 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor eba16bd6-44eb-40df-9fec-c9ad3974f3d7 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 5, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:45,472 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor eba16bd6-44eb-40df-9fec-c9ad3974f3d7 Chunking abgeschlossen (client): 5 Chunks erstellt
2026-09-21 15:13:45,472 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor eba16bd6-44eb-40df-9fec-c9ad3974f3d7 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0xMF9iZXppZWh1bmdzaGFmdGlna2VpdC1kZXMtaGFiZW5zLXZlcmFua2Vybi5tZA=="}}
2026-09-21 15:13:45,471 INFO rag_processor.py:__init__:127 RAGProcessor eba16bd6-44eb-40df-9fec-c9ad3974f3d7 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:45,348 DEBUG base_processor.py:init_logger:386 RAGProcessor eba16bd6-44eb-40df-9fec-c9ad3974f3d7 Logger initialisiert
2026-09-21 15:13:45,346 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2100 (process_request_thread) running_jobs=[]
2026-09-21 15:13:44,020 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor dd557996-69d7-4ec1-ac22-2ddc36c39a30 Sende Anfrage an LLM Provider
2026-09-21 15:13:44,020 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor dd557996-69d7-4ec1-ac22-2ddc36c39a30 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3422, "estimated_text_tokens": 734, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4448}
2026-09-21 15:13:44,018 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor dd557996-69d7-4ec1-ac22-2ddc36c39a30 Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:44,018 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor dd557996-69d7-4ec1-ac22-2ddc36c39a30 Starte Template-Transformation:
2026-09-21 15:13:44,017 DEBUG transformer_processor.py:__init__:199 TransformerProcessor dd557996-69d7-4ec1-ac22-2ddc36c39a30 Transformer Init Timings 
{"total_init_ms": 194.18, "super_init_ms": 108.28, "config_load_ms": 22.36, "client_init_ms": 0.02, "transcriber_init_ms": 63.15}
2026-09-21 15:13:44,017 DEBUG transformer_processor.py:__init__:179 TransformerProcessor dd557996-69d7-4ec1-ac22-2ddc36c39a30 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:43,823 DEBUG base_processor.py:init_logger:386 TransformerProcessor dd557996-69d7-4ec1-ac22-2ddc36c39a30 Logger initialisiert
2026-09-21 15:13:43,822 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2099 (process_request_thread) running_jobs=[]
2026-09-21 15:13:43,696 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6340 cost=0.004799 models=['google/gemini-2.5-flash'] thread=Thread-2093 (process_request_thread)
2026-09-21 15:13:43,695 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 97bb7372-81dc-449f-bf02-f53d82d9aa71 Template-Transformation abgeschlossen 
{"duration_ms": 5831.345558166504, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:43,693 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 97bb7372-81dc-449f-bf02-f53d82d9aa71 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151343_template_transform.json", "tokens": 6340}
2026-09-21 15:13:43,692 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 97bb7372-81dc-449f-bf02-f53d82d9aa71 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6340, "duration": 5831.345558166504, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:43,692 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 97bb7372-81dc-449f-bf02-f53d82d9aa71 1 LLM-Requests hinzugefügt
2026-09-21 15:13:43,185 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=288 cost=0 models=['voyage-3-large'] thread=Thread-2098 (process_request_thread)
2026-09-21 15:13:43,182 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 92ca6f4f-5876-48a1-afd5-03bc7bd9f5c6 Embedding (client) abgeschlossen 
{"extra": {"document_id": "e0423732-8f5b-4875-a7f6-eee9c3ecbf3a", "chunks": 1, "duration_seconds": 0.2596735954284668}}
2026-09-21 15:13:43,182 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 92ca6f4f-5876-48a1-afd5-03bc7bd9f5c6 1 LLM-Requests hinzugefügt
2026-09-21 15:13:43,017 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6388 cost=0.005065 models=['google/gemini-2.5-flash'] thread=Thread-2090 (process_request_thread)
2026-09-21 15:13:43,016 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor f833f2bf-c796-4fdd-a475-0fdb77145016 Template-Transformation abgeschlossen 
{"duration_ms": 7368.1299686431885, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:43,015 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor f833f2bf-c796-4fdd-a475-0fdb77145016 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151343_template_transform.json", "tokens": 6388}
2026-09-21 15:13:43,014 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor f833f2bf-c796-4fdd-a475-0fdb77145016 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6388, "duration": 7368.1299686431885, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:43,014 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor f833f2bf-c796-4fdd-a475-0fdb77145016 1 LLM-Requests hinzugefügt
2026-09-21 15:13:42,923 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 92ca6f4f-5876-48a1-afd5-03bc7bd9f5c6 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:42,922 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 92ca6f4f-5876-48a1-afd5-03bc7bd9f5c6 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:42,922 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 92ca6f4f-5876-48a1-afd5-03bc7bd9f5c6 Starte Chunking (client) 
{"extra": {"document_id": "e0423732-8f5b-4875-a7f6-eee9c3ecbf3a"}}
2026-09-21 15:13:42,922 INFO rag_processor.py:__init__:127 RAGProcessor 92ca6f4f-5876-48a1-afd5-03bc7bd9f5c6 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:42,810 DEBUG base_processor.py:init_logger:386 RAGProcessor 92ca6f4f-5876-48a1-afd5-03bc7bd9f5c6 Logger initialisiert
2026-09-21 15:13:42,809 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2098 (process_request_thread) running_jobs=[]
2026-09-21 15:13:42,738 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=796 cost=0 models=['voyage-3-large'] thread=Thread-2097 (process_request_thread)
2026-09-21 15:13:42,731 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 0ad4e144-e5c0-437c-aea1-8bcce5011529 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wOV9yZWdlbHZlcnN0b2Vzc2UtbmFjaHZvbGx6aWVoZW4tdW5kLWFiZ2VzdHVmdC1zYW5rdGlvbmllcmVuLm1k", "chunks": 3, "duration_seconds": 1.9987590312957764}}
2026-09-21 15:13:42,730 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 0ad4e144-e5c0-437c-aea1-8bcce5011529 1 LLM-Requests hinzugefügt
2026-09-21 15:13:40,732 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 0ad4e144-e5c0-437c-aea1-8bcce5011529 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:40,732 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 0ad4e144-e5c0-437c-aea1-8bcce5011529 Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:40,732 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 0ad4e144-e5c0-437c-aea1-8bcce5011529 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wOV9yZWdlbHZlcnN0b2Vzc2UtbmFjaHZvbGx6aWVoZW4tdW5kLWFiZ2VzdHVmdC1zYW5rdGlvbmllcmVuLm1k"}}
2026-09-21 15:13:40,731 INFO rag_processor.py:__init__:127 RAGProcessor 0ad4e144-e5c0-437c-aea1-8bcce5011529 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:40,623 DEBUG base_processor.py:init_logger:386 RAGProcessor 0ad4e144-e5c0-437c-aea1-8bcce5011529 Logger initialisiert
2026-09-21 15:13:40,622 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2097 (process_request_thread) running_jobs=[]
2026-09-21 15:13:39,661 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor d1e47302-a5c2-4e30-8416-1bac8412a23a Sende Anfrage an LLM Provider
2026-09-21 15:13:39,660 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor d1e47302-a5c2-4e30-8416-1bac8412a23a Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3612, "estimated_text_tokens": 788, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4502}
2026-09-21 15:13:39,658 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor d1e47302-a5c2-4e30-8416-1bac8412a23a Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:39,658 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor d1e47302-a5c2-4e30-8416-1bac8412a23a Starte Template-Transformation:
2026-09-21 15:13:39,657 DEBUG transformer_processor.py:__init__:199 TransformerProcessor d1e47302-a5c2-4e30-8416-1bac8412a23a Transformer Init Timings 
{"total_init_ms": 212.54, "super_init_ms": 122.23, "config_load_ms": 24.16, "client_init_ms": 0.01, "transcriber_init_ms": 65.59}
2026-09-21 15:13:39,657 DEBUG transformer_processor.py:__init__:179 TransformerProcessor d1e47302-a5c2-4e30-8416-1bac8412a23a Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:39,445 DEBUG base_processor.py:init_logger:386 TransformerProcessor d1e47302-a5c2-4e30-8416-1bac8412a23a Logger initialisiert
2026-09-21 15:13:39,444 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2096 (process_request_thread) running_jobs=[]
2026-09-21 15:13:39,278 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=278 cost=0 models=['voyage-3-large'] thread=Thread-2095 (process_request_thread)
2026-09-21 15:13:39,274 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 50b249b0-0cc8-43a4-ad3c-d59000123aea Embedding (client) abgeschlossen 
{"extra": {"document_id": "dcd17799-94ff-46a0-bd8b-04bcbdab90b6", "chunks": 1, "duration_seconds": 0.24608445167541504}}
2026-09-21 15:13:39,274 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 50b249b0-0cc8-43a4-ad3c-d59000123aea 1 LLM-Requests hinzugefügt
2026-09-21 15:13:39,029 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 50b249b0-0cc8-43a4-ad3c-d59000123aea Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:39,028 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 50b249b0-0cc8-43a4-ad3c-d59000123aea Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:39,028 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 50b249b0-0cc8-43a4-ad3c-d59000123aea Starte Chunking (client) 
{"extra": {"document_id": "dcd17799-94ff-46a0-bd8b-04bcbdab90b6"}}
2026-09-21 15:13:39,028 INFO rag_processor.py:__init__:127 RAGProcessor 50b249b0-0cc8-43a4-ad3c-d59000123aea RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:38,913 DEBUG base_processor.py:init_logger:386 RAGProcessor 50b249b0-0cc8-43a4-ad3c-d59000123aea Logger initialisiert
2026-09-21 15:13:38,912 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2095 (process_request_thread) running_jobs=[]
2026-09-21 15:13:38,848 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=815 cost=0 models=['voyage-3-large'] thread=Thread-2094 (process_request_thread)
2026-09-21 15:13:38,841 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 3b97ecb2-239d-4a13-9037-4be17a4b3343 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wOF9yZWdlbGVpbmhhbHR1bmctY29tbW9uc2ludGVybi1iZW9iYWNodGVuLm1k", "chunks": 3, "duration_seconds": 0.8995866775512695}}
2026-09-21 15:13:38,841 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 3b97ecb2-239d-4a13-9037-4be17a4b3343 1 LLM-Requests hinzugefügt
2026-09-21 15:13:38,311 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6347 cost=0.004802 models=['google/gemini-2.5-flash'] thread=Thread-2088 (process_request_thread)
2026-09-21 15:13:38,310 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 98adb13c-2fc2-45b5-92c2-28ff7e20ea3c Template-Transformation abgeschlossen 
{"duration_ms": 6287.833690643311, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:38,307 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 98adb13c-2fc2-45b5-92c2-28ff7e20ea3c LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151338_template_transform.json", "tokens": 6347}
2026-09-21 15:13:38,306 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 98adb13c-2fc2-45b5-92c2-28ff7e20ea3c LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6347, "duration": 6287.833690643311, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:38,306 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 98adb13c-2fc2-45b5-92c2-28ff7e20ea3c 1 LLM-Requests hinzugefügt
2026-09-21 15:13:37,942 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 3b97ecb2-239d-4a13-9037-4be17a4b3343 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:37,942 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 3b97ecb2-239d-4a13-9037-4be17a4b3343 Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:37,941 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 3b97ecb2-239d-4a13-9037-4be17a4b3343 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wOF9yZWdlbGVpbmhhbHR1bmctY29tbW9uc2ludGVybi1iZW9iYWNodGVuLm1k"}}
2026-09-21 15:13:37,941 INFO rag_processor.py:__init__:127 RAGProcessor 3b97ecb2-239d-4a13-9037-4be17a4b3343 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:37,860 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 97bb7372-81dc-449f-bf02-f53d82d9aa71 Sende Anfrage an LLM Provider
2026-09-21 15:13:37,860 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 97bb7372-81dc-449f-bf02-f53d82d9aa71 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3830, "estimated_text_tokens": 770, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4484}
2026-09-21 15:13:37,854 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=220 cost=0 models=['voyage-3-large'] thread=Thread-2092 (process_request_thread)
2026-09-21 15:13:37,844 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 97bb7372-81dc-449f-bf02-f53d82d9aa71 Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:37,844 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 97bb7372-81dc-449f-bf02-f53d82d9aa71 Starte Template-Transformation:
2026-09-21 15:13:37,843 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 97bb7372-81dc-449f-bf02-f53d82d9aa71 Transformer Init Timings 
{"total_init_ms": 228.27, "super_init_ms": 101.29, "config_load_ms": 20.93, "client_init_ms": 0.01, "transcriber_init_ms": 100.36}
2026-09-21 15:13:37,838 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 97bb7372-81dc-449f-bf02-f53d82d9aa71 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:37,837 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 1ed3ed1c-9f96-4932-b4de-961c4bfd773d Embedding (client) abgeschlossen 
{"extra": {"document_id": "92fb021f-3785-4b8e-aa33-accce2a6b1ae", "chunks": 1, "duration_seconds": 0.2846953868865967}}
2026-09-21 15:13:37,823 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 1ed3ed1c-9f96-4932-b4de-961c4bfd773d 1 LLM-Requests hinzugefügt
2026-09-21 15:13:37,799 DEBUG base_processor.py:init_logger:386 RAGProcessor 3b97ecb2-239d-4a13-9037-4be17a4b3343 Logger initialisiert
2026-09-21 15:13:37,798 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2094 (process_request_thread) running_jobs=[]
2026-09-21 15:13:37,615 DEBUG base_processor.py:init_logger:386 TransformerProcessor 97bb7372-81dc-449f-bf02-f53d82d9aa71 Logger initialisiert
2026-09-21 15:13:37,614 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2093 (process_request_thread) running_jobs=[]
2026-09-21 15:13:37,552 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 1ed3ed1c-9f96-4932-b4de-961c4bfd773d Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:37,552 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 1ed3ed1c-9f96-4932-b4de-961c4bfd773d Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:37,552 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 1ed3ed1c-9f96-4932-b4de-961c4bfd773d Starte Chunking (client) 
{"extra": {"document_id": "92fb021f-3785-4b8e-aa33-accce2a6b1ae"}}
2026-09-21 15:13:37,552 INFO rag_processor.py:__init__:127 RAGProcessor 1ed3ed1c-9f96-4932-b4de-961c4bfd773d RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:37,441 DEBUG base_processor.py:init_logger:386 RAGProcessor 1ed3ed1c-9f96-4932-b4de-961c4bfd773d Logger initialisiert
2026-09-21 15:13:37,440 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2092 (process_request_thread) running_jobs=[]
2026-09-21 15:13:37,364 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=751 cost=0 models=['voyage-3-large'] thread=Thread-2091 (process_request_thread)
2026-09-21 15:13:37,350 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor a827e6e1-c7e3-471a-b46c-e68e3ddf45f3 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wN19hdWYtaGV0ZXJhcmNoaWUtYmF1ZW4ubWQ=", "chunks": 3, "duration_seconds": 1.54307222366333}}
2026-09-21 15:13:37,349 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor a827e6e1-c7e3-471a-b46c-e68e3ddf45f3 1 LLM-Requests hinzugefügt
2026-09-21 15:13:35,807 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor a827e6e1-c7e3-471a-b46c-e68e3ddf45f3 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:35,807 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor a827e6e1-c7e3-471a-b46c-e68e3ddf45f3 Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:35,807 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor a827e6e1-c7e3-471a-b46c-e68e3ddf45f3 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wN19hdWYtaGV0ZXJhcmNoaWUtYmF1ZW4ubWQ="}}
2026-09-21 15:13:35,806 INFO rag_processor.py:__init__:127 RAGProcessor a827e6e1-c7e3-471a-b46c-e68e3ddf45f3 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:35,694 DEBUG base_processor.py:init_logger:386 RAGProcessor a827e6e1-c7e3-471a-b46c-e68e3ddf45f3 Logger initialisiert
2026-09-21 15:13:35,693 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2091 (process_request_thread) running_jobs=[]
2026-09-21 15:13:35,645 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor f833f2bf-c796-4fdd-a475-0fdb77145016 Sende Anfrage an LLM Provider
2026-09-21 15:13:35,645 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor f833f2bf-c796-4fdd-a475-0fdb77145016 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3934, "estimated_text_tokens": 848, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4562}
2026-09-21 15:13:35,644 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor f833f2bf-c796-4fdd-a475-0fdb77145016 Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:35,644 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor f833f2bf-c796-4fdd-a475-0fdb77145016 Starte Template-Transformation:
2026-09-21 15:13:35,643 DEBUG transformer_processor.py:__init__:199 TransformerProcessor f833f2bf-c796-4fdd-a475-0fdb77145016 Transformer Init Timings 
{"total_init_ms": 202.44, "super_init_ms": 119.73, "config_load_ms": 21.03, "client_init_ms": 0.02, "transcriber_init_ms": 61.33}
2026-09-21 15:13:35,643 DEBUG transformer_processor.py:__init__:179 TransformerProcessor f833f2bf-c796-4fdd-a475-0fdb77145016 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:35,608 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6154 cost=0.004722 models=['google/gemini-2.5-flash'] thread=Thread-2083 (process_request_thread)
2026-09-21 15:13:35,607 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 330c940f-ec9a-4b51-a4a6-59672ac857ad Template-Transformation abgeschlossen 
{"duration_ms": 5868.104934692383, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:35,605 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 330c940f-ec9a-4b51-a4a6-59672ac857ad LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151335_template_transform.json", "tokens": 6154}
2026-09-21 15:13:35,604 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 330c940f-ec9a-4b51-a4a6-59672ac857ad LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6154, "duration": 5868.104934692383, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:35,604 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 330c940f-ec9a-4b51-a4a6-59672ac857ad 1 LLM-Requests hinzugefügt
2026-09-21 15:13:35,441 DEBUG base_processor.py:init_logger:386 TransformerProcessor f833f2bf-c796-4fdd-a475-0fdb77145016 Logger initialisiert
2026-09-21 15:13:35,440 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2090 (process_request_thread) running_jobs=[]
2026-09-21 15:13:33,486 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=241 cost=0 models=['voyage-3-large'] thread=Thread-2089 (process_request_thread)
2026-09-21 15:13:33,483 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 2470213b-d95b-4f58-b462-ce821bce4a52 Embedding (client) abgeschlossen 
{"extra": {"document_id": "28bd4efb-8b4a-44e6-98f5-ebd90ebfa0ce", "chunks": 1, "duration_seconds": 0.24807167053222656}}
2026-09-21 15:13:33,483 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 2470213b-d95b-4f58-b462-ce821bce4a52 1 LLM-Requests hinzugefügt
2026-09-21 15:13:33,450 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=5935 cost=0.004473 models=['google/gemini-2.5-flash'] thread=Thread-2081 (process_request_thread)
2026-09-21 15:13:33,449 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 31a022d2-0cfb-48e2-84f3-06806a135154 Template-Transformation abgeschlossen 
{"duration_ms": 5873.063802719116, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:33,447 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 31a022d2-0cfb-48e2-84f3-06806a135154 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151333_template_transform.json", "tokens": 5935}
2026-09-21 15:13:33,446 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 31a022d2-0cfb-48e2-84f3-06806a135154 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 5935, "duration": 5873.063802719116, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:33,446 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 31a022d2-0cfb-48e2-84f3-06806a135154 1 LLM-Requests hinzugefügt
2026-09-21 15:13:33,235 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 2470213b-d95b-4f58-b462-ce821bce4a52 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:33,235 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 2470213b-d95b-4f58-b462-ce821bce4a52 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:33,235 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 2470213b-d95b-4f58-b462-ce821bce4a52 Starte Chunking (client) 
{"extra": {"document_id": "28bd4efb-8b4a-44e6-98f5-ebd90ebfa0ce"}}
2026-09-21 15:13:33,235 INFO rag_processor.py:__init__:127 RAGProcessor 2470213b-d95b-4f58-b462-ce821bce4a52 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:33,097 DEBUG base_processor.py:init_logger:386 RAGProcessor 2470213b-d95b-4f58-b462-ce821bce4a52 Logger initialisiert
2026-09-21 15:13:33,096 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2089 (process_request_thread) running_jobs=[]
2026-09-21 15:13:33,031 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=738 cost=0 models=['voyage-3-large'] thread=Thread-2087 (process_request_thread)
2026-09-21 15:13:33,008 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 8d985eb2-b00c-40a8-975d-6b8d771be29c Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wNl9hdWdlbmhvZWhlLWluLXVuZC1kdXJjaC1vcmdhbmlzYXRpb25zc3RydWt0dXJlbi1lcm1vZWdsaWNoZW4ubWQ=", "chunks": 3, "duration_seconds": 1.183812141418457}}
2026-09-21 15:13:33,007 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 8d985eb2-b00c-40a8-975d-6b8d771be29c 1 LLM-Requests hinzugefügt
2026-09-21 15:13:32,017 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 98adb13c-2fc2-45b5-92c2-28ff7e20ea3c Sende Anfrage an LLM Provider
2026-09-21 15:13:32,017 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 98adb13c-2fc2-45b5-92c2-28ff7e20ea3c Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 4011, "estimated_text_tokens": 774, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4488}
2026-09-21 15:13:32,014 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 98adb13c-2fc2-45b5-92c2-28ff7e20ea3c Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:32,014 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 98adb13c-2fc2-45b5-92c2-28ff7e20ea3c Starte Template-Transformation:
2026-09-21 15:13:32,014 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 98adb13c-2fc2-45b5-92c2-28ff7e20ea3c Transformer Init Timings 
{"total_init_ms": 266.56, "super_init_ms": 182.94, "config_load_ms": 22.4, "client_init_ms": 0.02, "transcriber_init_ms": 60.83}
2026-09-21 15:13:32,013 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 98adb13c-2fc2-45b5-92c2-28ff7e20ea3c Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:31,980 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=225 cost=0 models=['voyage-3-large'] thread=Thread-2086 (process_request_thread)
2026-09-21 15:13:31,978 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 10b8769f-9e10-4e0a-bf6c-c6ba4689badd Embedding (client) abgeschlossen 
{"extra": {"document_id": "977fd4ef-69da-4616-ad25-0989d274299c", "chunks": 1, "duration_seconds": 0.3015432357788086}}
2026-09-21 15:13:31,977 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 10b8769f-9e10-4e0a-bf6c-c6ba4689badd 1 LLM-Requests hinzugefügt
2026-09-21 15:13:31,825 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 8d985eb2-b00c-40a8-975d-6b8d771be29c Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:31,824 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 8d985eb2-b00c-40a8-975d-6b8d771be29c Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:31,824 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 8d985eb2-b00c-40a8-975d-6b8d771be29c Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wNl9hdWdlbmhvZWhlLWluLXVuZC1kdXJjaC1vcmdhbmlzYXRpb25zc3RydWt0dXJlbi1lcm1vZWdsaWNoZW4ubWQ="}}
2026-09-21 15:13:31,817 INFO rag_processor.py:__init__:127 RAGProcessor 8d985eb2-b00c-40a8-975d-6b8d771be29c RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:31,747 DEBUG base_processor.py:init_logger:386 TransformerProcessor 98adb13c-2fc2-45b5-92c2-28ff7e20ea3c Logger initialisiert
2026-09-21 15:13:31,746 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2088 (process_request_thread) running_jobs=[]
2026-09-21 15:13:31,676 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 10b8769f-9e10-4e0a-bf6c-c6ba4689badd Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:31,676 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 10b8769f-9e10-4e0a-bf6c-c6ba4689badd Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:31,676 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 10b8769f-9e10-4e0a-bf6c-c6ba4689badd Starte Chunking (client) 
{"extra": {"document_id": "977fd4ef-69da-4616-ad25-0989d274299c"}}
2026-09-21 15:13:31,676 INFO rag_processor.py:__init__:127 RAGProcessor 10b8769f-9e10-4e0a-bf6c-c6ba4689badd RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:31,664 DEBUG base_processor.py:init_logger:386 RAGProcessor 8d985eb2-b00c-40a8-975d-6b8d771be29c Logger initialisiert
2026-09-21 15:13:31,658 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2087 (process_request_thread) running_jobs=[]
2026-09-21 15:13:31,557 DEBUG base_processor.py:init_logger:386 RAGProcessor 10b8769f-9e10-4e0a-bf6c-c6ba4689badd Logger initialisiert
2026-09-21 15:13:31,556 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2086 (process_request_thread) running_jobs=[]
2026-09-21 15:13:31,496 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=653 cost=0 models=['voyage-3-large'] thread=Thread-2084 (process_request_thread)
2026-09-21 15:13:31,489 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 8dbba612-ef79-4b29-8f2a-e1d8c815abdc Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wNV9jb21tb25zLW1pdC1oYWxiZHVyY2hsYWVzc2lnZW4tbWVtYnJhbmVuLXVtZ2ViZW4ubWQ=", "chunks": 3, "duration_seconds": 1.5844054222106934}}
2026-09-21 15:13:31,489 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 8dbba612-ef79-4b29-8f2a-e1d8c815abdc 1 LLM-Requests hinzugefügt
2026-09-21 15:13:30,623 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=363 cost=0 models=['voyage-3-large'] thread=Thread-2085 (process_request_thread)
2026-09-21 15:13:30,620 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor ce52c560-199e-4d94-9ee2-d81e9c876663 Embedding (client) abgeschlossen 
{"extra": {"document_id": "ff5fe4e1-1587-4f51-ad6a-e5e5b64f0861", "chunks": 1, "duration_seconds": 0.2601473331451416}}
2026-09-21 15:13:30,620 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor ce52c560-199e-4d94-9ee2-d81e9c876663 1 LLM-Requests hinzugefügt
2026-09-21 15:13:30,360 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor ce52c560-199e-4d94-9ee2-d81e9c876663 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:30,360 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor ce52c560-199e-4d94-9ee2-d81e9c876663 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:30,360 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor ce52c560-199e-4d94-9ee2-d81e9c876663 Starte Chunking (client) 
{"extra": {"document_id": "ff5fe4e1-1587-4f51-ad6a-e5e5b64f0861"}}
2026-09-21 15:13:30,359 INFO rag_processor.py:__init__:127 RAGProcessor ce52c560-199e-4d94-9ee2-d81e9c876663 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:30,252 DEBUG base_processor.py:init_logger:386 RAGProcessor ce52c560-199e-4d94-9ee2-d81e9c876663 Logger initialisiert
2026-09-21 15:13:30,251 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2085 (process_request_thread) running_jobs=[]
2026-09-21 15:13:30,181 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=966 cost=0 models=['voyage-3-large'] thread=Thread-2082 (process_request_thread)
2026-09-21 15:13:30,173 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor c5b2ce47-9d3e-4a2f-88ed-7d1e0b76e2d8 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wNF9nZW1laW5zdGltbWlnLWVudHNjaGVpZGVuLm1k", "chunks": 4, "duration_seconds": 1.6541552543640137}}
2026-09-21 15:13:30,172 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor c5b2ce47-9d3e-4a2f-88ed-7d1e0b76e2d8 1 LLM-Requests hinzugefügt
2026-09-21 15:13:29,905 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 8dbba612-ef79-4b29-8f2a-e1d8c815abdc Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:29,905 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 8dbba612-ef79-4b29-8f2a-e1d8c815abdc Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:29,905 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 8dbba612-ef79-4b29-8f2a-e1d8c815abdc Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wNV9jb21tb25zLW1pdC1oYWxiZHVyY2hsYWVzc2lnZW4tbWVtYnJhbmVuLXVtZ2ViZW4ubWQ="}}
2026-09-21 15:13:29,904 INFO rag_processor.py:__init__:127 RAGProcessor 8dbba612-ef79-4b29-8f2a-e1d8c815abdc RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:29,765 DEBUG base_processor.py:init_logger:386 RAGProcessor 8dbba612-ef79-4b29-8f2a-e1d8c815abdc Logger initialisiert
2026-09-21 15:13:29,764 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2084 (process_request_thread) running_jobs=[]
2026-09-21 15:13:29,735 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 330c940f-ec9a-4b51-a4a6-59672ac857ad Sende Anfrage an LLM Provider
2026-09-21 15:13:29,735 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 330c940f-ec9a-4b51-a4a6-59672ac857ad Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3706, "estimated_text_tokens": 788, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4502}
2026-09-21 15:13:29,733 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 330c940f-ec9a-4b51-a4a6-59672ac857ad Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:29,733 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 330c940f-ec9a-4b51-a4a6-59672ac857ad Starte Template-Transformation:
2026-09-21 15:13:29,733 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 330c940f-ec9a-4b51-a4a6-59672ac857ad Transformer Init Timings 
{"total_init_ms": 191.61, "super_init_ms": 114.74, "config_load_ms": 22.54, "client_init_ms": 0.02, "transcriber_init_ms": 54.0}
2026-09-21 15:13:29,733 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 330c940f-ec9a-4b51-a4a6-59672ac857ad Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:29,542 DEBUG base_processor.py:init_logger:386 TransformerProcessor 330c940f-ec9a-4b51-a4a6-59672ac857ad Logger initialisiert
2026-09-21 15:13:29,540 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2083 (process_request_thread) running_jobs=[]
2026-09-21 15:13:29,405 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6270 cost=0.004649 models=['google/gemini-2.5-flash'] thread=Thread-2078 (process_request_thread)
2026-09-21 15:13:29,405 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 38cf2488-1ca5-404e-9089-fe1eb084acdd Template-Transformation abgeschlossen 
{"duration_ms": 5844.794511795044, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:29,403 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 38cf2488-1ca5-404e-9089-fe1eb084acdd LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151329_template_transform.json", "tokens": 6270}
2026-09-21 15:13:29,403 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 38cf2488-1ca5-404e-9089-fe1eb084acdd LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6270, "duration": 5844.794511795044, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:29,402 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 38cf2488-1ca5-404e-9089-fe1eb084acdd 1 LLM-Requests hinzugefügt
2026-09-21 15:13:28,519 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor c5b2ce47-9d3e-4a2f-88ed-7d1e0b76e2d8 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 4, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:28,519 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor c5b2ce47-9d3e-4a2f-88ed-7d1e0b76e2d8 Chunking abgeschlossen (client): 4 Chunks erstellt
2026-09-21 15:13:28,519 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor c5b2ce47-9d3e-4a2f-88ed-7d1e0b76e2d8 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wNF9nZW1laW5zdGltbWlnLWVudHNjaGVpZGVuLm1k"}}
2026-09-21 15:13:28,518 INFO rag_processor.py:__init__:127 RAGProcessor c5b2ce47-9d3e-4a2f-88ed-7d1e0b76e2d8 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:28,393 DEBUG base_processor.py:init_logger:386 RAGProcessor c5b2ce47-9d3e-4a2f-88ed-7d1e0b76e2d8 Logger initialisiert
2026-09-21 15:13:28,392 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2082 (process_request_thread) running_jobs=[]
2026-09-21 15:13:27,572 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 31a022d2-0cfb-48e2-84f3-06806a135154 Sende Anfrage an LLM Provider
2026-09-21 15:13:27,572 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 31a022d2-0cfb-48e2-84f3-06806a135154 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3391, "estimated_text_tokens": 768, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4482}
2026-09-21 15:13:27,568 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 31a022d2-0cfb-48e2-84f3-06806a135154 Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:27,568 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 31a022d2-0cfb-48e2-84f3-06806a135154 Starte Template-Transformation:
2026-09-21 15:13:27,567 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 31a022d2-0cfb-48e2-84f3-06806a135154 Transformer Init Timings 
{"total_init_ms": 180.53, "super_init_ms": 105.3, "config_load_ms": 19.97, "client_init_ms": 0.01, "transcriber_init_ms": 54.69}
2026-09-21 15:13:27,567 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 31a022d2-0cfb-48e2-84f3-06806a135154 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:27,387 DEBUG base_processor.py:init_logger:386 TransformerProcessor 31a022d2-0cfb-48e2-84f3-06806a135154 Logger initialisiert
2026-09-21 15:13:27,386 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2081 (process_request_thread) running_jobs=[]
2026-09-21 15:13:27,373 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6080 cost=0.004374 models=['google/gemini-2.5-flash'] thread=Thread-2077 (process_request_thread)
2026-09-21 15:13:27,372 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor b50f875a-aaf4-4b91-9bd3-aff6ced27b4a Template-Transformation abgeschlossen 
{"duration_ms": 5506.226062774658, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:27,371 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor b50f875a-aaf4-4b91-9bd3-aff6ced27b4a LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151327_template_transform.json", "tokens": 6080}
2026-09-21 15:13:27,370 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor b50f875a-aaf4-4b91-9bd3-aff6ced27b4a LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6080, "duration": 5506.226062774658, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:27,370 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor b50f875a-aaf4-4b91-9bd3-aff6ced27b4a 1 LLM-Requests hinzugefügt
2026-09-21 15:13:27,238 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=224 cost=0 models=['voyage-3-large'] thread=Thread-2080 (process_request_thread)
2026-09-21 15:13:27,235 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 9ecdc7f4-bc14-4aeb-8911-7d3b6d576aba Embedding (client) abgeschlossen 
{"extra": {"document_id": "81dfab23-b0d7-45ef-ba86-77132f36810b", "chunks": 1, "duration_seconds": 0.24575209617614746}}
2026-09-21 15:13:27,234 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 9ecdc7f4-bc14-4aeb-8911-7d3b6d576aba 1 LLM-Requests hinzugefügt
2026-09-21 15:13:26,989 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 9ecdc7f4-bc14-4aeb-8911-7d3b6d576aba Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:26,989 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 9ecdc7f4-bc14-4aeb-8911-7d3b6d576aba Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:26,989 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 9ecdc7f4-bc14-4aeb-8911-7d3b6d576aba Starte Chunking (client) 
{"extra": {"document_id": "81dfab23-b0d7-45ef-ba86-77132f36810b"}}
2026-09-21 15:13:26,988 INFO rag_processor.py:__init__:127 RAGProcessor 9ecdc7f4-bc14-4aeb-8911-7d3b6d576aba RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:26,867 DEBUG base_processor.py:init_logger:386 RAGProcessor 9ecdc7f4-bc14-4aeb-8911-7d3b6d576aba Logger initialisiert
2026-09-21 15:13:26,865 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2080 (process_request_thread) running_jobs=[]
2026-09-21 15:13:26,788 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=736 cost=0 models=['voyage-3-large'] thread=Thread-2079 (process_request_thread)
2026-09-21 15:13:26,779 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor daf8bb93-8bb8-4bed-9751-e2fb5084ac1f Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wM19pbS12ZXJ0cmF1ZW5zcmF1bS10cmFuc3BhcmVudC1zZWluLm1k", "chunks": 3, "duration_seconds": 0.5963566303253174}}
2026-09-21 15:13:26,779 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor daf8bb93-8bb8-4bed-9751-e2fb5084ac1f 1 LLM-Requests hinzugefügt
2026-09-21 15:13:26,204 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6147 cost=0.004904 models=['google/gemini-2.5-flash'] thread=Thread-2072 (process_request_thread)
2026-09-21 15:13:26,203 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 5a8f553c-fd6f-4c35-8b1e-5716deb4e03e Template-Transformation abgeschlossen 
{"duration_ms": 6668.044567108154, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:26,202 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 5a8f553c-fd6f-4c35-8b1e-5716deb4e03e LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151326_template_transform.json", "tokens": 6147}
2026-09-21 15:13:26,201 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 5a8f553c-fd6f-4c35-8b1e-5716deb4e03e LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6147, "duration": 6668.044567108154, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:26,201 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 5a8f553c-fd6f-4c35-8b1e-5716deb4e03e 1 LLM-Requests hinzugefügt
2026-09-21 15:13:26,183 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor daf8bb93-8bb8-4bed-9751-e2fb5084ac1f Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:26,183 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor daf8bb93-8bb8-4bed-9751-e2fb5084ac1f Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:26,183 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor daf8bb93-8bb8-4bed-9751-e2fb5084ac1f Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wM19pbS12ZXJ0cmF1ZW5zcmF1bS10cmFuc3BhcmVudC1zZWluLm1k"}}
2026-09-21 15:13:26,182 INFO rag_processor.py:__init__:127 RAGProcessor daf8bb93-8bb8-4bed-9751-e2fb5084ac1f RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:26,074 DEBUG base_processor.py:init_logger:386 RAGProcessor daf8bb93-8bb8-4bed-9751-e2fb5084ac1f Logger initialisiert
2026-09-21 15:13:26,074 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2079 (process_request_thread) running_jobs=[]
2026-09-21 15:13:23,850 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6003 cost=0.004454 models=['google/gemini-2.5-flash'] thread=Thread-2070 (process_request_thread)
2026-09-21 15:13:23,849 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 7bb28b3f-8b0b-4658-80c1-6ed42811ac76 Template-Transformation abgeschlossen 
{"duration_ms": 6364.190578460693, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:23,846 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 7bb28b3f-8b0b-4658-80c1-6ed42811ac76 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151323_template_transform.json", "tokens": 6003}
2026-09-21 15:13:23,845 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 7bb28b3f-8b0b-4658-80c1-6ed42811ac76 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6003, "duration": 6364.190578460693, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:23,844 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 7bb28b3f-8b0b-4658-80c1-6ed42811ac76 1 LLM-Requests hinzugefügt
2026-09-21 15:13:23,557 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 38cf2488-1ca5-404e-9089-fe1eb084acdd Sende Anfrage an LLM Provider
2026-09-21 15:13:23,557 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 38cf2488-1ca5-404e-9089-fe1eb084acdd Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 4046, "estimated_text_tokens": 768, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4482}
2026-09-21 15:13:23,555 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 38cf2488-1ca5-404e-9089-fe1eb084acdd Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:23,555 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 38cf2488-1ca5-404e-9089-fe1eb084acdd Starte Template-Transformation:
2026-09-21 15:13:23,555 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 38cf2488-1ca5-404e-9089-fe1eb084acdd Transformer Init Timings 
{"total_init_ms": 226.72, "super_init_ms": 150.61, "config_load_ms": 20.47, "client_init_ms": 0.02, "transcriber_init_ms": 55.32}
2026-09-21 15:13:23,554 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 38cf2488-1ca5-404e-9089-fe1eb084acdd Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:23,328 DEBUG base_processor.py:init_logger:386 TransformerProcessor 38cf2488-1ca5-404e-9089-fe1eb084acdd Logger initialisiert
2026-09-21 15:13:23,326 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2078 (process_request_thread) running_jobs=[]
2026-09-21 15:13:21,973 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=185 cost=0 models=['voyage-3-large'] thread=Thread-2076 (process_request_thread)
2026-09-21 15:13:21,970 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 75343cb3-767f-429b-ae3d-7bab65bba08e Embedding (client) abgeschlossen 
{"extra": {"document_id": "f8a9c8e2-aa15-4fdc-b107-f1a56d95a9c8", "chunks": 1, "duration_seconds": 0.32369089126586914}}
2026-09-21 15:13:21,969 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 75343cb3-767f-429b-ae3d-7bab65bba08e 1 LLM-Requests hinzugefügt
2026-09-21 15:13:21,888 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=288 cost=0 models=['voyage-3-large'] thread=Thread-2075 (process_request_thread)
2026-09-21 15:13:21,883 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor ccbbf448-88ae-4b3b-be76-d3dc26953ad8 Embedding (client) abgeschlossen 
{"extra": {"document_id": "0de6535e-3303-4566-b2c8-36b63ae2d647", "chunks": 1, "duration_seconds": 0.3270399570465088}}
2026-09-21 15:13:21,883 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor ccbbf448-88ae-4b3b-be76-d3dc26953ad8 1 LLM-Requests hinzugefügt
2026-09-21 15:13:21,863 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor b50f875a-aaf4-4b91-9bd3-aff6ced27b4a Sende Anfrage an LLM Provider
2026-09-21 15:13:21,863 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor b50f875a-aaf4-4b91-9bd3-aff6ced27b4a Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3640, "estimated_text_tokens": 746, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4460}
2026-09-21 15:13:21,861 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor b50f875a-aaf4-4b91-9bd3-aff6ced27b4a Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:21,861 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor b50f875a-aaf4-4b91-9bd3-aff6ced27b4a Starte Template-Transformation:
2026-09-21 15:13:21,861 DEBUG transformer_processor.py:__init__:199 TransformerProcessor b50f875a-aaf4-4b91-9bd3-aff6ced27b4a Transformer Init Timings 
{"total_init_ms": 214.06, "super_init_ms": 133.98, "config_load_ms": 23.88, "client_init_ms": 0.02, "transcriber_init_ms": 55.79}
2026-09-21 15:13:21,861 DEBUG transformer_processor.py:__init__:179 TransformerProcessor b50f875a-aaf4-4b91-9bd3-aff6ced27b4a Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:21,648 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 75343cb3-767f-429b-ae3d-7bab65bba08e Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:21,647 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 75343cb3-767f-429b-ae3d-7bab65bba08e Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:21,647 DEBUG base_processor.py:init_logger:386 TransformerProcessor b50f875a-aaf4-4b91-9bd3-aff6ced27b4a Logger initialisiert
2026-09-21 15:13:21,646 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 75343cb3-767f-429b-ae3d-7bab65bba08e Starte Chunking (client) 
{"extra": {"document_id": "f8a9c8e2-aa15-4fdc-b107-f1a56d95a9c8"}}
2026-09-21 15:13:21,646 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2077 (process_request_thread) running_jobs=[]
2026-09-21 15:13:21,644 INFO rag_processor.py:__init__:127 RAGProcessor 75343cb3-767f-429b-ae3d-7bab65bba08e RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:21,557 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor ccbbf448-88ae-4b3b-be76-d3dc26953ad8 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:21,557 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor ccbbf448-88ae-4b3b-be76-d3dc26953ad8 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:21,556 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor ccbbf448-88ae-4b3b-be76-d3dc26953ad8 Starte Chunking (client) 
{"extra": {"document_id": "0de6535e-3303-4566-b2c8-36b63ae2d647"}}
2026-09-21 15:13:21,556 INFO rag_processor.py:__init__:127 RAGProcessor ccbbf448-88ae-4b3b-be76-d3dc26953ad8 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:21,492 DEBUG base_processor.py:init_logger:386 RAGProcessor 75343cb3-767f-429b-ae3d-7bab65bba08e Logger initialisiert
2026-09-21 15:13:21,491 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2076 (process_request_thread) running_jobs=[]
2026-09-21 15:13:21,408 DEBUG base_processor.py:init_logger:386 RAGProcessor ccbbf448-88ae-4b3b-be76-d3dc26953ad8 Logger initialisiert
2026-09-21 15:13:21,407 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2075 (process_request_thread) running_jobs=[]
2026-09-21 15:13:21,405 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=1206 cost=0 models=['voyage-3-large'] thread=Thread-2073 (process_request_thread)
2026-09-21 15:13:21,390 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 0ae25e18-4371-400d-94f0-f556d87ac190 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDlfZWlnZW5lLWdvdmVybmFuY2UtcmVmbGVrdGllcmVuLm1k", "chunks": 5, "duration_seconds": 1.1176273822784424}}
2026-09-21 15:13:21,389 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 0ae25e18-4371-400d-94f0-f556d87ac190 1 LLM-Requests hinzugefügt
2026-09-21 15:13:21,318 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=848 cost=0 models=['voyage-3-large'] thread=Thread-2074 (process_request_thread)
2026-09-21 15:13:21,305 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor df0cb386-d2d3-4364-911a-a2db91847aba Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wMV9zaWNoLWluLXZpZWxmYWx0LWdlbWVpbnNhbS1hdXNyaWNodGVuLm1k", "chunks": 4, "duration_seconds": 0.8516688346862793}}
2026-09-21 15:13:21,305 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor df0cb386-d2d3-4364-911a-a2db91847aba 1 LLM-Requests hinzugefügt
2026-09-21 15:13:20,454 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor df0cb386-d2d3-4364-911a-a2db91847aba Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 4, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:20,454 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor df0cb386-d2d3-4364-911a-a2db91847aba Chunking abgeschlossen (client): 4 Chunks erstellt
2026-09-21 15:13:20,453 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor df0cb386-d2d3-4364-911a-a2db91847aba Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vc296aWFsZXMtcXVhZHJhdC0wMV9zaWNoLWluLXZpZWxmYWx0LWdlbWVpbnNhbS1hdXNyaWNodGVuLm1k"}}
2026-09-21 15:13:20,453 INFO rag_processor.py:__init__:127 RAGProcessor df0cb386-d2d3-4364-911a-a2db91847aba RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:20,343 DEBUG base_processor.py:init_logger:386 RAGProcessor df0cb386-d2d3-4364-911a-a2db91847aba Logger initialisiert
2026-09-21 15:13:20,343 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2074 (process_request_thread) running_jobs=[]
2026-09-21 15:13:20,272 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 0ae25e18-4371-400d-94f0-f556d87ac190 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 5, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:20,272 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 0ae25e18-4371-400d-94f0-f556d87ac190 Chunking abgeschlossen (client): 5 Chunks erstellt
2026-09-21 15:13:20,272 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 0ae25e18-4371-400d-94f0-f556d87ac190 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDlfZWlnZW5lLWdvdmVybmFuY2UtcmVmbGVrdGllcmVuLm1k"}}
2026-09-21 15:13:20,271 INFO rag_processor.py:__init__:127 RAGProcessor 0ae25e18-4371-400d-94f0-f556d87ac190 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:19,955 DEBUG base_processor.py:init_logger:386 RAGProcessor 0ae25e18-4371-400d-94f0-f556d87ac190 Logger initialisiert
2026-09-21 15:13:19,954 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2073 (process_request_thread) running_jobs=[]
2026-09-21 15:13:19,533 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 5a8f553c-fd6f-4c35-8b1e-5716deb4e03e Sende Anfrage an LLM Provider
2026-09-21 15:13:19,532 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 5a8f553c-fd6f-4c35-8b1e-5716deb4e03e Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3447, "estimated_text_tokens": 770, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4484}
2026-09-21 15:13:19,531 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 5a8f553c-fd6f-4c35-8b1e-5716deb4e03e Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:19,531 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 5a8f553c-fd6f-4c35-8b1e-5716deb4e03e Starte Template-Transformation:
2026-09-21 15:13:19,531 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 5a8f553c-fd6f-4c35-8b1e-5716deb4e03e Transformer Init Timings 
{"total_init_ms": 183.59, "super_init_ms": 110.05, "config_load_ms": 20.36, "client_init_ms": 0.01, "transcriber_init_ms": 52.88}
2026-09-21 15:13:19,530 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 5a8f553c-fd6f-4c35-8b1e-5716deb4e03e Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:19,347 DEBUG base_processor.py:init_logger:386 TransformerProcessor 5a8f553c-fd6f-4c35-8b1e-5716deb4e03e Logger initialisiert
2026-09-21 15:13:19,346 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2072 (process_request_thread) running_jobs=[]
2026-09-21 15:13:18,069 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6144 cost=0.004637 models=['google/gemini-2.5-flash'] thread=Thread-2065 (process_request_thread)
2026-09-21 15:13:18,069 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor ab342f4f-5418-4311-83dd-159d6c8c54a7 Template-Transformation abgeschlossen 
{"duration_ms": 6250.586986541748, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:18,067 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor ab342f4f-5418-4311-83dd-159d6c8c54a7 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151318_template_transform.json", "tokens": 6144}
2026-09-21 15:13:18,066 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor ab342f4f-5418-4311-83dd-159d6c8c54a7 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6144, "duration": 6250.586986541748, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:18,066 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor ab342f4f-5418-4311-83dd-159d6c8c54a7 1 LLM-Requests hinzugefügt
2026-09-21 15:13:18,025 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=265 cost=0 models=['voyage-3-large'] thread=Thread-2071 (process_request_thread)
2026-09-21 15:13:18,022 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 25d6c6d2-8977-44b6-95a3-6b9e93b819ef Embedding (client) abgeschlossen 
{"extra": {"document_id": "b378099e-90e7-40d7-a530-72b55324f044", "chunks": 1, "duration_seconds": 0.2499678134918213}}
2026-09-21 15:13:18,022 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 25d6c6d2-8977-44b6-95a3-6b9e93b819ef 1 LLM-Requests hinzugefügt
2026-09-21 15:13:17,824 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=7118 cost=0.006302 models=['google/gemini-2.5-flash'] thread=Thread-2061 (process_request_thread)
2026-09-21 15:13:17,823 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor a1a721b9-86a3-460a-89b1-c84a73200b20 Template-Transformation abgeschlossen 
{"duration_ms": 8013.127088546753, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:17,821 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor a1a721b9-86a3-460a-89b1-c84a73200b20 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151317_template_transform.json", "tokens": 7118}
2026-09-21 15:13:17,821 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor a1a721b9-86a3-460a-89b1-c84a73200b20 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 7118, "duration": 8013.127088546753, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:17,821 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor a1a721b9-86a3-460a-89b1-c84a73200b20 1 LLM-Requests hinzugefügt
2026-09-21 15:13:17,772 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 25d6c6d2-8977-44b6-95a3-6b9e93b819ef Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:17,772 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 25d6c6d2-8977-44b6-95a3-6b9e93b819ef Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:17,772 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 25d6c6d2-8977-44b6-95a3-6b9e93b819ef Starte Chunking (client) 
{"extra": {"document_id": "b378099e-90e7-40d7-a530-72b55324f044"}}
2026-09-21 15:13:17,771 INFO rag_processor.py:__init__:127 RAGProcessor 25d6c6d2-8977-44b6-95a3-6b9e93b819ef RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:17,661 DEBUG base_processor.py:init_logger:386 RAGProcessor 25d6c6d2-8977-44b6-95a3-6b9e93b819ef Logger initialisiert
2026-09-21 15:13:17,660 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2071 (process_request_thread) running_jobs=[]
2026-09-21 15:13:17,600 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=737 cost=0 models=['voyage-3-large'] thread=Thread-2069 (process_request_thread)
2026-09-21 15:13:17,593 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 5505e26e-6099-476a-8c7f-03fd17bbbbab Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDhfcml0dWFsZS1kZXMtbWl0ZWluYW5kZXJzLWV0YWJsaWVyZW4tdW5kLXBmbGVnZW4ubWQ=", "chunks": 3, "duration_seconds": 1.3552289009094238}}
2026-09-21 15:13:17,593 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 5505e26e-6099-476a-8c7f-03fd17bbbbab 1 LLM-Requests hinzugefügt
2026-09-21 15:13:17,479 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 7bb28b3f-8b0b-4658-80c1-6ed42811ac76 Sende Anfrage an LLM Provider
2026-09-21 15:13:17,479 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 7bb28b3f-8b0b-4658-80c1-6ed42811ac76 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3553, "estimated_text_tokens": 788, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4502}
2026-09-21 15:13:17,476 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 7bb28b3f-8b0b-4658-80c1-6ed42811ac76 Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:17,476 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 7bb28b3f-8b0b-4658-80c1-6ed42811ac76 Starte Template-Transformation:
2026-09-21 15:13:17,476 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 7bb28b3f-8b0b-4658-80c1-6ed42811ac76 Transformer Init Timings 
{"total_init_ms": 189.1, "super_init_ms": 112.23, "config_load_ms": 20.66, "client_init_ms": 0.01, "transcriber_init_ms": 55.74}
2026-09-21 15:13:17,475 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 7bb28b3f-8b0b-4658-80c1-6ed42811ac76 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:17,287 DEBUG base_processor.py:init_logger:386 TransformerProcessor 7bb28b3f-8b0b-4658-80c1-6ed42811ac76 Logger initialisiert
2026-09-21 15:13:17,286 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2070 (process_request_thread) running_jobs=[]
2026-09-21 15:13:16,238 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 5505e26e-6099-476a-8c7f-03fd17bbbbab Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:16,238 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 5505e26e-6099-476a-8c7f-03fd17bbbbab Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:16,238 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 5505e26e-6099-476a-8c7f-03fd17bbbbab Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDhfcml0dWFsZS1kZXMtbWl0ZWluYW5kZXJzLWV0YWJsaWVyZW4tdW5kLXBmbGVnZW4ubWQ="}}
2026-09-21 15:13:16,237 INFO rag_processor.py:__init__:127 RAGProcessor 5505e26e-6099-476a-8c7f-03fd17bbbbab RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:16,126 DEBUG base_processor.py:init_logger:386 RAGProcessor 5505e26e-6099-476a-8c7f-03fd17bbbbab Logger initialisiert
2026-09-21 15:13:16,125 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2069 (process_request_thread) running_jobs=[]
2026-09-21 15:13:14,621 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=251 cost=0 models=['voyage-3-large'] thread=Thread-2068 (process_request_thread)
2026-09-21 15:13:14,618 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 8952ebe8-6ad5-4097-a808-7c2ce639dfd6 Embedding (client) abgeschlossen 
{"extra": {"document_id": "d8605719-1f9e-4d55-8229-b9e8dcea3796", "chunks": 1, "duration_seconds": 0.2483079433441162}}
2026-09-21 15:13:14,618 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 8952ebe8-6ad5-4097-a808-7c2ce639dfd6 1 LLM-Requests hinzugefügt
2026-09-21 15:13:14,370 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 8952ebe8-6ad5-4097-a808-7c2ce639dfd6 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:14,370 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 8952ebe8-6ad5-4097-a808-7c2ce639dfd6 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:14,370 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 8952ebe8-6ad5-4097-a808-7c2ce639dfd6 Starte Chunking (client) 
{"extra": {"document_id": "d8605719-1f9e-4d55-8229-b9e8dcea3796"}}
2026-09-21 15:13:14,369 INFO rag_processor.py:__init__:127 RAGProcessor 8952ebe8-6ad5-4097-a808-7c2ce639dfd6 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:14,253 DEBUG base_processor.py:init_logger:386 RAGProcessor 8952ebe8-6ad5-4097-a808-7c2ce639dfd6 Logger initialisiert
2026-09-21 15:13:14,252 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2068 (process_request_thread) running_jobs=[]
2026-09-21 15:13:14,177 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=735 cost=0 models=['voyage-3-large'] thread=Thread-2067 (process_request_thread)
2026-09-21 15:13:14,170 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 49167762-667e-49b7-ba9c-06b347fbdbde Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDdfa29uZmxpa3RlLWJlemllaHVuZ3N3YWhyZW5kLWJlYXJiZWl0ZW4ubWQ=", "chunks": 3, "duration_seconds": 0.6443295478820801}}
2026-09-21 15:13:14,169 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 49167762-667e-49b7-ba9c-06b347fbdbde 1 LLM-Requests hinzugefügt
2026-09-21 15:13:14,034 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6210 cost=0.004697 models=['google/gemini-2.5-flash'] thread=Thread-2060 (process_request_thread)
2026-09-21 15:13:14,034 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 73cd3051-926d-4f94-8c6c-8cb63fb8e7eb Template-Transformation abgeschlossen 
{"duration_ms": 5998.98624420166, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:14,032 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 73cd3051-926d-4f94-8c6c-8cb63fb8e7eb LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151314_template_transform.json", "tokens": 6210}
2026-09-21 15:13:14,032 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 73cd3051-926d-4f94-8c6c-8cb63fb8e7eb LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6210, "duration": 5998.98624420166, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:14,032 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 73cd3051-926d-4f94-8c6c-8cb63fb8e7eb 1 LLM-Requests hinzugefügt
2026-09-21 15:13:13,525 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 49167762-667e-49b7-ba9c-06b347fbdbde Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:13,525 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 49167762-667e-49b7-ba9c-06b347fbdbde Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:13,525 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 49167762-667e-49b7-ba9c-06b347fbdbde Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDdfa29uZmxpa3RlLWJlemllaHVuZ3N3YWhyZW5kLWJlYXJiZWl0ZW4ubWQ="}}
2026-09-21 15:13:13,525 INFO rag_processor.py:__init__:127 RAGProcessor 49167762-667e-49b7-ba9c-06b347fbdbde RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:13,414 DEBUG base_processor.py:init_logger:386 RAGProcessor 49167762-667e-49b7-ba9c-06b347fbdbde Logger initialisiert
2026-09-21 15:13:13,413 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2067 (process_request_thread) running_jobs=[]
2026-09-21 15:13:12,123 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=262 cost=0 models=['voyage-3-large'] thread=Thread-2066 (process_request_thread)
2026-09-21 15:13:12,120 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 359cbdb9-b256-4967-a7d7-9c9870c67728 Embedding (client) abgeschlossen 
{"extra": {"document_id": "c1e7c37e-cf21-4f57-9c89-02721817f2f7", "chunks": 1, "duration_seconds": 0.2579352855682373}}
2026-09-21 15:13:12,120 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 359cbdb9-b256-4967-a7d7-9c9870c67728 1 LLM-Requests hinzugefügt
2026-09-21 15:13:11,869 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=196 cost=0 models=['voyage-3-large'] thread=Thread-2064 (process_request_thread)
2026-09-21 15:13:11,865 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor fc78d1cc-6d7d-458d-b5bc-54363d7f0072 Embedding (client) abgeschlossen 
{"extra": {"document_id": "c0d4b758-0e0d-404d-9188-47841a7811d7", "chunks": 1, "duration_seconds": 0.32765984535217285}}
2026-09-21 15:13:11,865 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor fc78d1cc-6d7d-458d-b5bc-54363d7f0072 1 LLM-Requests hinzugefügt
2026-09-21 15:13:11,863 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 359cbdb9-b256-4967-a7d7-9c9870c67728 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:11,862 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 359cbdb9-b256-4967-a7d7-9c9870c67728 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:11,862 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 359cbdb9-b256-4967-a7d7-9c9870c67728 Starte Chunking (client) 
{"extra": {"document_id": "c1e7c37e-cf21-4f57-9c89-02721817f2f7"}}
2026-09-21 15:13:11,862 INFO rag_processor.py:__init__:127 RAGProcessor 359cbdb9-b256-4967-a7d7-9c9870c67728 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:11,815 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor ab342f4f-5418-4311-83dd-159d6c8c54a7 Sende Anfrage an LLM Provider
2026-09-21 15:13:11,814 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor ab342f4f-5418-4311-83dd-159d6c8c54a7 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3688, "estimated_text_tokens": 824, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4538}
2026-09-21 15:13:11,812 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor ab342f4f-5418-4311-83dd-159d6c8c54a7 Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:11,812 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor ab342f4f-5418-4311-83dd-159d6c8c54a7 Starte Template-Transformation:
2026-09-21 15:13:11,812 DEBUG transformer_processor.py:__init__:199 TransformerProcessor ab342f4f-5418-4311-83dd-159d6c8c54a7 Transformer Init Timings 
{"total_init_ms": 328.07, "super_init_ms": 168.3, "config_load_ms": 27.97, "client_init_ms": 0.01, "transcriber_init_ms": 131.45}
2026-09-21 15:13:11,812 DEBUG transformer_processor.py:__init__:179 TransformerProcessor ab342f4f-5418-4311-83dd-159d6c8c54a7 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:11,669 DEBUG base_processor.py:init_logger:386 RAGProcessor 359cbdb9-b256-4967-a7d7-9c9870c67728 Logger initialisiert
2026-09-21 15:13:11,663 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2066 (process_request_thread) running_jobs=[]
2026-09-21 15:13:11,564 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=683 cost=0 models=['voyage-3-large'] thread=Thread-2063 (process_request_thread)
2026-09-21 15:13:11,551 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor a37859af-3b10-488b-b722-3ea50070acdd Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDZfc2VsYnN0dmVyYW50d29ydGxpY2gtdW5kLWVpbmZ1ZWhsZW5kLWtvbW11bml6aWVyZW4ubWQ=", "chunks": 3, "duration_seconds": 0.6178364753723145}}
2026-09-21 15:13:11,551 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor a37859af-3b10-488b-b722-3ea50070acdd 1 LLM-Requests hinzugefügt
2026-09-21 15:13:11,538 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor fc78d1cc-6d7d-458d-b5bc-54363d7f0072 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:11,538 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor fc78d1cc-6d7d-458d-b5bc-54363d7f0072 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:11,538 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor fc78d1cc-6d7d-458d-b5bc-54363d7f0072 Starte Chunking (client) 
{"extra": {"document_id": "c0d4b758-0e0d-404d-9188-47841a7811d7"}}
2026-09-21 15:13:11,537 INFO rag_processor.py:__init__:127 RAGProcessor fc78d1cc-6d7d-458d-b5bc-54363d7f0072 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:11,484 DEBUG base_processor.py:init_logger:386 TransformerProcessor ab342f4f-5418-4311-83dd-159d6c8c54a7 Logger initialisiert
2026-09-21 15:13:11,483 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2065 (process_request_thread) running_jobs=[]
2026-09-21 15:13:11,375 DEBUG base_processor.py:init_logger:386 RAGProcessor fc78d1cc-6d7d-458d-b5bc-54363d7f0072 Logger initialisiert
2026-09-21 15:13:11,373 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2064 (process_request_thread) running_jobs=[]
2026-09-21 15:13:11,348 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=5948 cost=0.004369 models=['google/gemini-2.5-flash'] thread=Thread-2058 (process_request_thread)
2026-09-21 15:13:11,346 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 7532d46d-5e56-47b5-94b7-44428d5a055e Template-Transformation abgeschlossen 
{"duration_ms": 5509.783983230591, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:11,344 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 7532d46d-5e56-47b5-94b7-44428d5a055e LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151311_template_transform.json", "tokens": 5948}
2026-09-21 15:13:11,343 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 7532d46d-5e56-47b5-94b7-44428d5a055e LLM Request erstellt 
{"purpose": "template_transform", "tokens": 5948, "duration": 5509.783983230591, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:11,342 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 7532d46d-5e56-47b5-94b7-44428d5a055e 1 LLM-Requests hinzugefügt
2026-09-21 15:13:11,294 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=655 cost=0 models=['voyage-3-large'] thread=Thread-2062 (process_request_thread)
2026-09-21 15:13:11,281 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 91f8244f-7b07-4429-aa00-7f363bb561bc Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDVfbmF0dXJ2ZXJidW5kZW5zZWluLXZlcnRpZWZlbi5tZA==", "chunks": 3, "duration_seconds": 0.530097484588623}}
2026-09-21 15:13:11,280 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 91f8244f-7b07-4429-aa00-7f363bb561bc 1 LLM-Requests hinzugefügt
2026-09-21 15:13:10,934 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor a37859af-3b10-488b-b722-3ea50070acdd Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:10,933 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor a37859af-3b10-488b-b722-3ea50070acdd Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:10,933 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor a37859af-3b10-488b-b722-3ea50070acdd Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDZfc2VsYnN0dmVyYW50d29ydGxpY2gtdW5kLWVpbmZ1ZWhsZW5kLWtvbW11bml6aWVyZW4ubWQ="}}
2026-09-21 15:13:10,933 INFO rag_processor.py:__init__:127 RAGProcessor a37859af-3b10-488b-b722-3ea50070acdd RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:10,812 DEBUG base_processor.py:init_logger:386 RAGProcessor a37859af-3b10-488b-b722-3ea50070acdd Logger initialisiert
2026-09-21 15:13:10,811 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2063 (process_request_thread) running_jobs=[]
2026-09-21 15:13:10,751 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 91f8244f-7b07-4429-aa00-7f363bb561bc Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:10,751 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 91f8244f-7b07-4429-aa00-7f363bb561bc Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:10,751 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 91f8244f-7b07-4429-aa00-7f363bb561bc Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDVfbmF0dXJ2ZXJidW5kZW5zZWluLXZlcnRpZWZlbi5tZA=="}}
2026-09-21 15:13:10,750 INFO rag_processor.py:__init__:127 RAGProcessor 91f8244f-7b07-4429-aa00-7f363bb561bc RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:10,613 DEBUG base_processor.py:init_logger:386 RAGProcessor 91f8244f-7b07-4429-aa00-7f363bb561bc Logger initialisiert
2026-09-21 15:13:10,611 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2062 (process_request_thread) running_jobs=[]
2026-09-21 15:13:09,807 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor a1a721b9-86a3-460a-89b1-c84a73200b20 Sende Anfrage an LLM Provider
2026-09-21 15:13:09,807 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor a1a721b9-86a3-460a-89b1-c84a73200b20 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 4718, "estimated_text_tokens": 800, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4514}
2026-09-21 15:13:09,805 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor a1a721b9-86a3-460a-89b1-c84a73200b20 Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:09,805 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor a1a721b9-86a3-460a-89b1-c84a73200b20 Starte Template-Transformation:
2026-09-21 15:13:09,805 DEBUG transformer_processor.py:__init__:199 TransformerProcessor a1a721b9-86a3-460a-89b1-c84a73200b20 Transformer Init Timings 
{"total_init_ms": 208.38, "super_init_ms": 119.94, "config_load_ms": 20.21, "client_init_ms": 0.02, "transcriber_init_ms": 67.86}
2026-09-21 15:13:09,804 DEBUG transformer_processor.py:__init__:179 TransformerProcessor a1a721b9-86a3-460a-89b1-c84a73200b20 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:09,596 DEBUG base_processor.py:init_logger:386 TransformerProcessor a1a721b9-86a3-460a-89b1-c84a73200b20 Logger initialisiert
2026-09-21 15:13:09,595 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2061 (process_request_thread) running_jobs=[]
2026-09-21 15:13:08,700 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6010 cost=0.004384 models=['google/gemini-2.5-flash'] thread=Thread-2054 (process_request_thread)
2026-09-21 15:13:08,699 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor a405b923-f11b-4051-99dd-4656fca2071b Template-Transformation abgeschlossen 
{"duration_ms": 7144.93203163147, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:08,698 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor a405b923-f11b-4051-99dd-4656fca2071b LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151308_template_transform.json", "tokens": 6010}
2026-09-21 15:13:08,698 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor a405b923-f11b-4051-99dd-4656fca2071b LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6010, "duration": 7144.93203163147, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:08,697 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor a405b923-f11b-4051-99dd-4656fca2071b 1 LLM-Requests hinzugefügt
2026-09-21 15:13:08,474 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=5828 cost=0.004256 models=['google/gemini-2.5-flash'] thread=Thread-2049 (process_request_thread)
2026-09-21 15:13:08,473 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 5abd6593-1f6d-43a2-a894-fd13d85b1cc8 Template-Transformation abgeschlossen 
{"duration_ms": 8735.211849212646, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:08,471 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor 5abd6593-1f6d-43a2-a894-fd13d85b1cc8 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151308_template_transform.json", "tokens": 5828}
2026-09-21 15:13:08,470 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor 5abd6593-1f6d-43a2-a894-fd13d85b1cc8 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 5828, "duration": 8735.211849212646, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:08,469 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor 5abd6593-1f6d-43a2-a894-fd13d85b1cc8 1 LLM-Requests hinzugefügt
2026-09-21 15:13:08,032 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 73cd3051-926d-4f94-8c6c-8cb63fb8e7eb Sende Anfrage an LLM Provider
2026-09-21 15:13:08,032 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 73cd3051-926d-4f94-8c6c-8cb63fb8e7eb Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3751, "estimated_text_tokens": 776, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4490}
2026-09-21 15:13:08,030 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 73cd3051-926d-4f94-8c6c-8cb63fb8e7eb Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:08,030 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 73cd3051-926d-4f94-8c6c-8cb63fb8e7eb Starte Template-Transformation:
2026-09-21 15:13:08,030 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 73cd3051-926d-4f94-8c6c-8cb63fb8e7eb Transformer Init Timings 
{"total_init_ms": 225.05, "super_init_ms": 130.58, "config_load_ms": 27.64, "client_init_ms": 0.01, "transcriber_init_ms": 66.49}
2026-09-21 15:13:08,030 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 73cd3051-926d-4f94-8c6c-8cb63fb8e7eb Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:07,805 DEBUG base_processor.py:init_logger:386 TransformerProcessor 73cd3051-926d-4f94-8c6c-8cb63fb8e7eb Logger initialisiert
2026-09-21 15:13:07,803 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2060 (process_request_thread) running_jobs=[]
2026-09-21 15:13:06,610 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=233 cost=0 models=['voyage-3-large'] thread=Thread-2059 (process_request_thread)
2026-09-21 15:13:06,607 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 52078f24-290e-483e-b72c-0a2a29846a8a Embedding (client) abgeschlossen 
{"extra": {"document_id": "41e18825-6c4a-4f9c-8005-1d70de90d936", "chunks": 1, "duration_seconds": 0.3075723648071289}}
2026-09-21 15:13:06,607 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 52078f24-290e-483e-b72c-0a2a29846a8a 1 LLM-Requests hinzugefügt
2026-09-21 15:13:06,300 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 52078f24-290e-483e-b72c-0a2a29846a8a Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:06,300 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 52078f24-290e-483e-b72c-0a2a29846a8a Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:06,300 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 52078f24-290e-483e-b72c-0a2a29846a8a Starte Chunking (client) 
{"extra": {"document_id": "41e18825-6c4a-4f9c-8005-1d70de90d936"}}
2026-09-21 15:13:06,298 INFO rag_processor.py:__init__:127 RAGProcessor 52078f24-290e-483e-b72c-0a2a29846a8a RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:06,173 DEBUG base_processor.py:init_logger:386 RAGProcessor 52078f24-290e-483e-b72c-0a2a29846a8a Logger initialisiert
2026-09-21 15:13:06,171 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2059 (process_request_thread) running_jobs=[]
2026-09-21 15:13:06,085 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=741 cost=0 models=['voyage-3-large'] thread=Thread-2057 (process_request_thread)
2026-09-21 15:13:06,077 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 925e41a0-034c-49c2-9c1e-f2c66b7c5696 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDRfc2l0dWllcnRlbS13aXNzZW4tdmVydHJhdWVuLm1k", "chunks": 3, "duration_seconds": 0.4839909076690674}}
2026-09-21 15:13:06,077 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 925e41a0-034c-49c2-9c1e-f2c66b7c5696 1 LLM-Requests hinzugefügt
2026-09-21 15:13:05,832 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 7532d46d-5e56-47b5-94b7-44428d5a055e Sende Anfrage an LLM Provider
2026-09-21 15:13:05,831 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 7532d46d-5e56-47b5-94b7-44428d5a055e Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3597, "estimated_text_tokens": 768, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4482}
2026-09-21 15:13:05,829 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 7532d46d-5e56-47b5-94b7-44428d5a055e Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:05,829 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 7532d46d-5e56-47b5-94b7-44428d5a055e Starte Template-Transformation:
2026-09-21 15:13:05,829 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 7532d46d-5e56-47b5-94b7-44428d5a055e Transformer Init Timings 
{"total_init_ms": 203.49, "super_init_ms": 117.5, "config_load_ms": 21.75, "client_init_ms": 0.01, "transcriber_init_ms": 63.85}
2026-09-21 15:13:05,828 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 7532d46d-5e56-47b5-94b7-44428d5a055e Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:05,625 DEBUG base_processor.py:init_logger:386 TransformerProcessor 7532d46d-5e56-47b5-94b7-44428d5a055e Logger initialisiert
2026-09-21 15:13:05,624 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2058 (process_request_thread) running_jobs=[]
2026-09-21 15:13:05,593 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 925e41a0-034c-49c2-9c1e-f2c66b7c5696 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:05,593 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 925e41a0-034c-49c2-9c1e-f2c66b7c5696 Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:05,593 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 925e41a0-034c-49c2-9c1e-f2c66b7c5696 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDRfc2l0dWllcnRlbS13aXNzZW4tdmVydHJhdWVuLm1k"}}
2026-09-21 15:13:05,592 INFO rag_processor.py:__init__:127 RAGProcessor 925e41a0-034c-49c2-9c1e-f2c66b7c5696 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:05,459 DEBUG base_processor.py:init_logger:386 RAGProcessor 925e41a0-034c-49c2-9c1e-f2c66b7c5696 Logger initialisiert
2026-09-21 15:13:05,457 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2057 (process_request_thread) running_jobs=[]
2026-09-21 15:13:04,409 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=256 cost=0 models=['voyage-3-large'] thread=Thread-2056 (process_request_thread)
2026-09-21 15:13:04,406 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 1c5fd4e0-e396-4f31-b751-0b5be7ccecb4 Embedding (client) abgeschlossen 
{"extra": {"document_id": "43bfaa2a-9f96-4560-aa39-3c1a23ee2f5d", "chunks": 1, "duration_seconds": 0.26491713523864746}}
2026-09-21 15:13:04,406 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 1c5fd4e0-e396-4f31-b751-0b5be7ccecb4 1 LLM-Requests hinzugefügt
2026-09-21 15:13:04,142 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 1c5fd4e0-e396-4f31-b751-0b5be7ccecb4 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:04,142 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 1c5fd4e0-e396-4f31-b751-0b5be7ccecb4 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:04,142 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 1c5fd4e0-e396-4f31-b751-0b5be7ccecb4 Starte Chunking (client) 
{"extra": {"document_id": "43bfaa2a-9f96-4560-aa39-3c1a23ee2f5d"}}
2026-09-21 15:13:04,141 INFO rag_processor.py:__init__:127 RAGProcessor 1c5fd4e0-e396-4f31-b751-0b5be7ccecb4 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:04,010 DEBUG base_processor.py:init_logger:386 RAGProcessor 1c5fd4e0-e396-4f31-b751-0b5be7ccecb4 Logger initialisiert
2026-09-21 15:13:04,009 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2056 (process_request_thread) running_jobs=[]
2026-09-21 15:13:03,933 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=766 cost=0 models=['voyage-3-large'] thread=Thread-2055 (process_request_thread)
2026-09-21 15:13:03,926 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 1412abb7-598f-4603-9dcd-f3d616c5a667 Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDNfZ2VnZW5zZWl0aWdrZWl0LWJlaHV0c2FtLWF1c3VlYmVuLm1k", "chunks": 3, "duration_seconds": 0.5197827816009521}}
2026-09-21 15:13:03,926 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 1412abb7-598f-4603-9dcd-f3d616c5a667 1 LLM-Requests hinzugefügt
2026-09-21 15:13:03,407 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 1412abb7-598f-4603-9dcd-f3d616c5a667 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:03,407 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 1412abb7-598f-4603-9dcd-f3d616c5a667 Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:03,406 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 1412abb7-598f-4603-9dcd-f3d616c5a667 Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDNfZ2VnZW5zZWl0aWdrZWl0LWJlaHV0c2FtLWF1c3VlYmVuLm1k"}}
2026-09-21 15:13:03,406 INFO rag_processor.py:__init__:127 RAGProcessor 1412abb7-598f-4603-9dcd-f3d616c5a667 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:03,265 DEBUG base_processor.py:init_logger:386 RAGProcessor 1412abb7-598f-4603-9dcd-f3d616c5a667 Logger initialisiert
2026-09-21 15:13:03,264 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2055 (process_request_thread) running_jobs=[]
2026-09-21 15:13:03,088 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=5972 cost=0.00448 models=['google/gemini-2.5-flash'] thread=Thread-2048 (process_request_thread)
2026-09-21 15:13:03,087 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor bfd313f9-4630-41cc-afb6-6e061e9f5201 Template-Transformation abgeschlossen 
{"duration_ms": 5543.496131896973, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:03,085 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor bfd313f9-4630-41cc-afb6-6e061e9f5201 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151303_template_transform.json", "tokens": 5972}
2026-09-21 15:13:03,084 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor bfd313f9-4630-41cc-afb6-6e061e9f5201 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 5972, "duration": 5543.496131896973, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:03,083 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor bfd313f9-4630-41cc-afb6-6e061e9f5201 1 LLM-Requests hinzugefügt
2026-09-21 15:13:01,660 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=225 cost=0 models=['voyage-3-large'] thread=Thread-2053 (process_request_thread)
2026-09-21 15:13:01,657 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 479b31f4-18cf-4edc-b5ae-6c0804742a12 Embedding (client) abgeschlossen 
{"extra": {"document_id": "da8e5181-d189-4285-8c47-b413af6f1d6b", "chunks": 1, "duration_seconds": 0.3045082092285156}}
2026-09-21 15:13:01,656 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 479b31f4-18cf-4edc-b5ae-6c0804742a12 1 LLM-Requests hinzugefügt
2026-09-21 15:13:01,552 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor a405b923-f11b-4051-99dd-4656fca2071b Sende Anfrage an LLM Provider
2026-09-21 15:13:01,552 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor a405b923-f11b-4051-99dd-4656fca2071b Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3718, "estimated_text_tokens": 728, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4442}
2026-09-21 15:13:01,550 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor a405b923-f11b-4051-99dd-4656fca2071b Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:13:01,549 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor a405b923-f11b-4051-99dd-4656fca2071b Starte Template-Transformation:
2026-09-21 15:13:01,549 DEBUG transformer_processor.py:__init__:199 TransformerProcessor a405b923-f11b-4051-99dd-4656fca2071b Transformer Init Timings 
{"total_init_ms": 261.35, "super_init_ms": 174.25, "config_load_ms": 20.78, "client_init_ms": 0.03, "transcriber_init_ms": 65.9}
2026-09-21 15:13:01,549 DEBUG transformer_processor.py:__init__:179 TransformerProcessor a405b923-f11b-4051-99dd-4656fca2071b Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:13:01,363 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 479b31f4-18cf-4edc-b5ae-6c0804742a12 Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:01,357 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 479b31f4-18cf-4edc-b5ae-6c0804742a12 Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:01,352 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 479b31f4-18cf-4edc-b5ae-6c0804742a12 Starte Chunking (client) 
{"extra": {"document_id": "da8e5181-d189-4285-8c47-b413af6f1d6b"}}
2026-09-21 15:13:01,342 INFO rag_processor.py:__init__:127 RAGProcessor 479b31f4-18cf-4edc-b5ae-6c0804742a12 RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:01,288 DEBUG base_processor.py:init_logger:386 TransformerProcessor a405b923-f11b-4051-99dd-4656fca2071b Logger initialisiert
2026-09-21 15:13:01,287 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2054 (process_request_thread) running_jobs=[]
2026-09-21 15:13:01,198 DEBUG base_processor.py:init_logger:386 RAGProcessor 479b31f4-18cf-4edc-b5ae-6c0804742a12 Logger initialisiert
2026-09-21 15:13:01,197 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2053 (process_request_thread) running_jobs=[]
2026-09-21 15:13:01,173 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=6004 cost=0.004525 models=['google/gemini-2.5-flash'] thread=Thread-2047 (process_request_thread)
2026-09-21 15:13:01,172 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor e984d4a7-5e17-4ce0-99ea-0213b876c174 Template-Transformation abgeschlossen 
{"duration_ms": 5597.163200378418, "model": "google/gemini-2.5-flash"}
2026-09-21 15:13:01,171 DEBUG transcription_utils.py:create_llm_request:465 TransformerProcessor e984d4a7-5e17-4ce0-99ea-0213b876c174 LLM Interaktion gespeichert 
{"file": "cache/transformer/temp/debug/llm/20260921_151301_template_transform.json", "tokens": 6004}
2026-09-21 15:13:01,170 DEBUG transcription_utils.py:create_llm_request:426 TransformerProcessor e984d4a7-5e17-4ce0-99ea-0213b876c174 LLM Request erstellt 
{"purpose": "template_transform", "tokens": 6004, "duration": 5597.163200378418, "model": "google/gemini-2.5-flash", "processor": "WhisperTranscriber"}
2026-09-21 15:13:01,170 DEBUG base_processor.py:add_llm_requests:533 TransformerProcessor e984d4a7-5e17-4ce0-99ea-0213b876c174 1 LLM-Requests hinzugefügt
2026-09-21 15:13:01,121 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=721 cost=0 models=['voyage-3-large'] thread=Thread-2052 (process_request_thread)
2026-09-21 15:13:01,115 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 6e7bfcca-87b1-4235-9cfd-ea94dd52a18f Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDJfb2huZS16d2FlbmdlLWJlaXRyYWdlbi5tZA==", "chunks": 3, "duration_seconds": 0.48253703117370605}}
2026-09-21 15:13:01,115 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 6e7bfcca-87b1-4235-9cfd-ea94dd52a18f 1 LLM-Requests hinzugefügt
2026-09-21 15:13:00,854 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=245 cost=0 models=['voyage-3-large'] thread=Thread-2051 (process_request_thread)
2026-09-21 15:13:00,851 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 60622a2d-e5ae-4703-b2a4-35166e41bcef Embedding (client) abgeschlossen 
{"extra": {"document_id": "b95a5be2-4877-4d62-a0dc-6d2bedca1154", "chunks": 1, "duration_seconds": 0.29146289825439453}}
2026-09-21 15:13:00,850 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 60622a2d-e5ae-4703-b2a4-35166e41bcef 1 LLM-Requests hinzugefügt
2026-09-21 15:13:00,633 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 6e7bfcca-87b1-4235-9cfd-ea94dd52a18f Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:00,633 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 6e7bfcca-87b1-4235-9cfd-ea94dd52a18f Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:13:00,632 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 6e7bfcca-87b1-4235-9cfd-ea94dd52a18f Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDJfb2huZS16d2FlbmdlLWJlaXRyYWdlbi5tZA=="}}
2026-09-21 15:13:00,632 INFO rag_processor.py:__init__:127 RAGProcessor 6e7bfcca-87b1-4235-9cfd-ea94dd52a18f RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:00,565 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 60622a2d-e5ae-4703-b2a4-35166e41bcef Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 1, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:13:00,565 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 60622a2d-e5ae-4703-b2a4-35166e41bcef Chunking abgeschlossen (client): 1 Chunks erstellt
2026-09-21 15:13:00,559 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 60622a2d-e5ae-4703-b2a4-35166e41bcef Starte Chunking (client) 
{"extra": {"document_id": "b95a5be2-4877-4d62-a0dc-6d2bedca1154"}}
2026-09-21 15:13:00,547 INFO rag_processor.py:__init__:127 RAGProcessor 60622a2d-e5ae-4703-b2a4-35166e41bcef RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:13:00,426 DEBUG base_processor.py:init_logger:386 RAGProcessor 6e7bfcca-87b1-4235-9cfd-ea94dd52a18f Logger initialisiert
2026-09-21 15:13:00,425 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2052 (process_request_thread) running_jobs=[]
2026-09-21 15:13:00,351 DEBUG base_processor.py:init_logger:386 RAGProcessor 60622a2d-e5ae-4703-b2a4-35166e41bcef Logger initialisiert
2026-09-21 15:13:00,350 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2051 (process_request_thread) running_jobs=[]
2026-09-21 15:13:00,275 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/rag/embed-text processor=rag status=running tokens=766 cost=0 models=['voyage-3-large'] thread=Thread-2050 (process_request_thread)
2026-09-21 15:13:00,267 INFO rag_processor.py:embed_document_for_client:610 RAGProcessor 47e5956a-7794-4442-865f-09585ef3677c Embedding (client) abgeschlossen 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDFfZ2VtZWluc2FtZS1hYnNpY2h0ZW4tdW5kLXdlcnRlLWt1bHRpdmllcmVuLm1k", "chunks": 3, "duration_seconds": 0.4877605438232422}}
2026-09-21 15:13:00,267 DEBUG base_processor.py:add_llm_requests:533 RAGProcessor 47e5956a-7794-4442-865f-09585ef3677c 1 LLM-Requests hinzugefügt
2026-09-21 15:12:59,780 INFO rag_processor.py:embed_document_for_client:555 RAGProcessor 47e5956a-7794-4442-865f-09585ef3677c Starte Embedding-Generierung (client) 
{"extra": {"chunk_count": 3, "embedding_model": "voyage-3-large", "embedding_dimensions": 2048}}
2026-09-21 15:12:59,780 INFO rag_processor.py:embed_document_for_client:549 RAGProcessor 47e5956a-7794-4442-865f-09585ef3677c Chunking abgeschlossen (client): 3 Chunks erstellt
2026-09-21 15:12:59,779 INFO rag_processor.py:embed_document_for_client:547 RAGProcessor 47e5956a-7794-4442-865f-09585ef3677c Starte Chunking (client) 
{"extra": {"document_id": "V2ViLUVudHfDvHJmZS9tdXN0ZXJrYXJ0ZW4vbWl0ZWluYW5kZXIta3JlaXMtMDFfZ2VtZWluc2FtZS1hYnNpY2h0ZW4tdW5kLXdlcnRlLWt1bHRpdmllcmVuLm1k"}}
2026-09-21 15:12:59,779 INFO rag_processor.py:__init__:127 RAGProcessor 47e5956a-7794-4442-865f-09585ef3677c RAGProcessor initialisiert 
{"extra": {"embedding_model": "voyage-3-large", "embedding_dimensions": 2048, "chunk_size": 1000, "chunk_overlap": 200}}
2026-09-21 15:12:59,734 INFO transcription_utils.py:transform_by_template:1215 TransformerProcessor 5abd6593-1f6d-43a2-a894-fd13d85b1cc8 Sende Anfrage an LLM Provider
2026-09-21 15:12:59,733 INFO transcription_utils.py:transform_by_template:1199 TransformerProcessor 5abd6593-1f6d-43a2-a894-fd13d85b1cc8 Token-Prüfung vor Template-Transformation 
{"model": "deepseek/deepseek-v4-flash-latest", "model_limit": 8192, "text_length": 3297, "estimated_text_tokens": 810, "estimated_system_tokens": 1722, "estimated_template_tokens": 1992, "total_estimated_tokens": 4524}
2026-09-21 15:12:59,717 INFO transcription_utils.py:transform_by_template:1070 TransformerProcessor 5abd6593-1f6d-43a2-a894-fd13d85b1cc8 Verwende direkt übergebenes Template-Inhalt (Länge: 10212)
2026-09-21 15:12:59,717 INFO transcription_utils.py:transform_by_template:1055 TransformerProcessor 5abd6593-1f6d-43a2-a894-fd13d85b1cc8 Starte Template-Transformation:
2026-09-21 15:12:59,716 DEBUG transformer_processor.py:__init__:199 TransformerProcessor 5abd6593-1f6d-43a2-a894-fd13d85b1cc8 Transformer Init Timings 
{"total_init_ms": 239.35, "super_init_ms": 110.91, "config_load_ms": 22.33, "client_init_ms": 0.02, "transcriber_init_ms": 105.7}
2026-09-21 15:12:59,716 DEBUG transformer_processor.py:__init__:179 TransformerProcessor 5abd6593-1f6d-43a2-a894-fd13d85b1cc8 Transformer Processor initialisiert 
{"model": "deepseek/deepseek-v4-flash-latest", "temperature": 0.1, "max_tokens": 4000, "target_format": "text", "max_concurrent_requests": 10, "timeout_seconds": 120, "templates_dir": "resources/templates"}
2026-09-21 15:12:59,644 DEBUG base_processor.py:init_logger:386 RAGProcessor 47e5956a-7794-4442-865f-09585ef3677c Logger initialisiert
2026-09-21 15:12:59,642 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/rag/embed-text processor=rag thread=Thread-2050 (process_request_thread) running_jobs=[]
2026-09-21 15:12:59,477 DEBUG base_processor.py:init_logger:386 TransformerProcessor 5abd6593-1f6d-43a2-a894-fd13d85b1cc8 Logger initialisiert
2026-09-21 15:12:59,476 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_in method=POST path=/api/transformer/template processor=transformer thread=Thread-2049 (process_request_thread) running_jobs=[]
2026-09-21 15:12:58,370 INFO metrics_trace.py:log_metrics_event:54 MetricsTrace metrics-trace [METRICS-TRACE] http_out path=/api/transformer/template processor=transformer status=running tokens=5933 cost=0.004398 models=['google/gemini-2.5-flash'] thread=Thread-2046 (process_request_thread)
2026-09-21 15:12:58,369 INFO transcription_utils.py:transform_by_template:1490 TransformerProcessor 5ce7f376-9da7-4013-89e4-cca7743aa04c Template-Transformation abgeschlossen 
{"duration_ms": 4771.5349197387695, "model": "google/gemini-2.5-flash"}