gmakstutis/ragflow
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
ragflow/api/apps
History
hsparks.codes d104f59e29 feat: Implement hierarchical retrieval architecture (#11610) 
This PR implements the complete three-tier hierarchical retrieval architecture
as specified in issue #11610, enabling production-grade RAG capabilities.

## Tier 1: Knowledge Base Routing
- Auto-route queries to relevant knowledge bases
- Per-KB retrieval parameters (KBRetrievalParams dataclass)
- Rule-based routing with keyword overlap scoring
- LLM-based routing with fallback to rule-based
- Configurable routing methods: auto, rule_based, llm_based, all

## Tier 2: Document Filtering
- Document-level metadata filtering within selected KBs
- Configurable metadata fields for filtering
- LLM-generated filter conditions
- Metadata similarity matching (fuzzy matching)
- Enhanced metadata generation for documents

## Tier 3: Chunk Refinement
- Parent-child chunking with summary mapping
- Custom prompts for keyword extraction
- LLM-based question generation for chunks
- Integration with existing retrieval pipeline

## Metadata Management (Batch CRUD)
- MetadataService with batch operations:
  - batch_get_metadata
  - batch_update_metadata
  - batch_delete_metadata_fields
  - batch_set_metadata_field
  - get_metadata_schema
  - search_by_metadata
  - get_metadata_statistics
  - copy_metadata
- REST API endpoints in metadata_app.py

## Integration
- HierarchicalConfig dataclass for configuration
- Integrated into Dealer class (search.py)
- Wired into agent retrieval tool
- Non-breaking: disabled by default

## Tests
- 48 unit tests covering all components
- Tests for config, routing, filtering, and metadata operations
2025-12-09 07:32:00 +01:00
..
auth Refa: make RAGFlow more asynchronous (#11601) 2025-12-01 14:24:06 +08:00
sdk Fix errors (#11804) 2025-12-08 12:21:18 +08:00
__init__.py Fix errors (#11804) 2025-12-08 12:21:18 +08:00
api_app.py Refa: make RAGFlow more asynchronous (#11601) 2025-12-01 14:24:06 +08:00
canvas_app.py Refa: make RAGFlow more asynchronous (#11601) 2025-12-01 14:24:06 +08:00
chunk_app.py Refa: make RAGFlow more asynchronous 2 (#11689) 2025-12-03 14:19:53 +08:00
connector_app.py Refa: make RAGFlow more asynchronous 2 (#11689) 2025-12-03 14:19:53 +08:00
conversation_app.py Refa: cleanup synchronous functions in chat_model and implement synchronization for conversation and dialog chats (#11779) 2025-12-08 09:43:03 +08:00
dialog_app.py Refa: make RAGFlow more asynchronous (#11601) 2025-12-01 14:24:06 +08:00
document_app.py Refa: make RAGFlow more asynchronous 2 (#11689) 2025-12-03 14:19:53 +08:00
evaluation_app.py Feat: RAG evaluation (#11674) 2025-12-03 17:00:58 +08:00
file2document_app.py Fix: file manager KB link issue. (#11648) 2025-12-02 12:14:27 +08:00
file_app.py Refa: make RAGFlow more asynchronous 2 (#11689) 2025-12-03 14:19:53 +08:00
kb_app.py Refa: make RAGFlow more asynchronous 2 (#11689) 2025-12-03 14:19:53 +08:00
langfuse_app.py Refa: cleanup synchronous functions in chat_model and implement synchronization for conversation and dialog chats (#11779) 2025-12-08 09:43:03 +08:00
llm_app.py Refa: cleanup synchronous functions in chat_model and implement synchronization for conversation and dialog chats (#11779) 2025-12-08 09:43:03 +08:00
mcp_server_app.py Refa: make RAGFlow more asynchronous (#11601) 2025-12-01 14:24:06 +08:00
metadata_app.py feat: Implement hierarchical retrieval architecture (#11610) 2025-12-09 07:32:00 +01:00
plugin_app.py Feat: Alter flask to Quart for async API serving. (#11275) 2025-11-18 17:05:16 +08:00
search_app.py Refa: make RAGFlow more asynchronous (#11601) 2025-12-01 14:24:06 +08:00
system_app.py Feat: Alter flask to Quart for async API serving. (#11275) 2025-11-18 17:05:16 +08:00
tenant_app.py Refa: make RAGFlow more asynchronous (#11601) 2025-12-01 14:24:06 +08:00
user_app.py Refa: make RAGFlow more asynchronous (#11601) 2025-12-01 14:24:06 +08:00