ragflow/api
hsparks.codes d9a24f4fdc feat: Add hierarchical retrieval architecture for production-grade RAG
Implements three-tier retrieval system to address scalability and precision
limitations in production environments with large document collections.

Features:
- Tier 1: Knowledge Base Routing (auto/rule-based/llm-based)
- Tier 2: Document Filtering (metadata-based)
- Tier 3: Chunk Refinement (vector search with parent-child support)

Changes:
- Add HierarchicalRetrieval class with configurable retrieval pipeline
- Add hierarchical_retrieval_config field to Dialog model
- Add database migration for new configuration field
- Add comprehensive unit tests (35 tests, all passing)

Fixes #11610
2025-12-03 11:16:24 +01:00
..
apps Feat: RAG evaluation (#11674) 2025-12-03 17:00:58 +08:00
common Feat:admin api (#10642) 2025-10-18 16:09:48 +08:00
db feat: Add hierarchical retrieval architecture for production-grade RAG 2025-12-03 11:16:24 +01:00
utils feat: Auto-disable Raptor for structured data (Issue #11653) (#11676) 2025-12-03 17:02:29 +08:00
__init__.py Fix: incorrect async chat streamly output (#11679) 2025-12-03 11:15:45 +08:00
constants.py Introduce common/constants.py (#10965) 2025-11-03 16:32:37 +08:00
ragflow_server.py Refa: make RAGFlow more asynchronous (#11601) 2025-12-01 14:24:06 +08:00
settings.py Move api.settings to common.settings (#11036) 2025-11-06 09:36:38 +08:00
validation.py Fix errors detected by Ruff (#3918) 2024-12-08 14:21:12 +08:00