davebb/linear-coding-agent
1
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity
Files
b928352e3626e15418d75dea1fa4827266448afe
linear-coding-agent/generations/library_rag/utils
History
David Blanc Brioir b928352e36 Fix: Appel correct à ingest_document() pour Word 
Corrections finales word_pipeline.py:

1. Signature ingest_document() corrigée:
   AVANT:
   - document_source_id=doc_name  ❌ (paramètre inexistant)

   APRÈS:
   - doc_name=doc_name
   - metadata=metadata
   - language=metadata.get("language", "unknown")
   - toc=toc_flat
   - hierarchy=None  # Word n'a pas de hiérarchie page
   - pages=0  # Word n'a pas de pages

2. Message callback corrigé:
   AVANT:
   - ingestion_result.get('chunks_ingested', 0)  ❌ (champ inexistant)

   APRÈS:
   - ingestion_result.get('count', 0)  ✅ (champ réel)

Test réussi complet:
✅ 48 paragraphes extraits
✅ 2 headings détectés
✅ 37 chunks créés
✅ 37 chunks nettoyés
✅ 37 chunks validés
✅ 37 chunks ingérés dans Weaviate
✅ Coût OCR: €0.0000 (pas d'OCR pour Word!)
✅ Document indexé et recherchable

Le pipeline Word est maintenant 100% fonctionnel de bout en bout.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
2025-12-30 22:49:13 +01:00
..
__init__.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
hierarchy_parser.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
image_extractor.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
llm_chat.py
Fix: Gestion robuste des valeurs None dans .lower()
2025-12-30 22:26:29 +01:00
llm_chunker.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
llm_classifier.py
Fix: Gestion robuste des valeurs None dans .lower()
2025-12-30 22:26:29 +01:00
llm_cleaner.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
llm_metadata.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
llm_structurer.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
llm_toc.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
llm_validator.py
Fix: Gestion robuste des valeurs None dans .lower()
2025-12-30 22:26:29 +01:00
markdown_builder.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
mistral_client.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
ocr_processor.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
ocr_schemas.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
pdf_exporter.py
Ajout des fonctionnalités d'export Word et PDF pour le chat RAG
2025-12-30 14:02:11 +01:00
pdf_pipeline.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
pdf_uploader.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
toc_enricher.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
toc_extractor_markdown.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
toc_extractor_visual.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
toc_extractor.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
tts_generator.py
Ajout nettoyage markdown pour TTS audio
2025-12-30 19:35:01 +01:00
types.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
weaviate_ingest.py
Add Library RAG project and cleanup root directory
2025-12-30 11:57:12 +01:00
word_exporter.py
Ajout des fonctionnalités d'export Word et PDF pour le chat RAG
2025-12-30 14:02:11 +01:00
word_pipeline.py
Fix: Appel correct à ingest_document() pour Word
2025-12-30 22:49:13 +01:00
word_processor.py
Ajout pipeline Word (.docx) pour ingestion RAG
2025-12-30 21:58:43 +01:00
word_toc_extractor.py
Ajout pipeline Word (.docx) pour ingestion RAG
2025-12-30 21:58:43 +01:00