Raphaël MANSUY
454b2650c3
cherry-pick 94f24a66
2025-12-04 19:17:43 +08:00
Raphaël MANSUY
81e19b5def
cherry-pick 3eb3a075
2025-12-04 19:17:43 +08:00
Raphaël MANSUY
4c93aa3f64
cherry-pick fdf0fe04
2025-12-04 19:17:43 +08:00
Raphaël MANSUY
e49cda6724
cherry-pick 1101562e (resolved)
2025-12-04 19:17:43 +08:00
Raphaël MANSUY
a7b1698ce6
cherry-pick 7bf9d1e8 (resolved)
2025-12-04 19:17:43 +08:00
Raphaël MANSUY
c445571d29
cherry-pick f3740d82 (resolved)
2025-12-04 19:17:43 +08:00
Raphaël MANSUY
fa68267da5
cherry-pick a81c122f (resolved)
2025-12-04 19:17:43 +08:00
Raphaël MANSUY
67cbf63644
cherry-pick f402ad27
2025-12-04 19:17:43 +08:00
Raphaël MANSUY
e4f14b2907
cherry-pick 289337b2
2025-12-04 19:17:42 +08:00
Raphaël MANSUY
bf1a8cf8ba
cherry-pick dde728a3
2025-12-04 19:17:42 +08:00
Raphaël MANSUY
f9f4555b48
cherry-pick ef659a1e
2025-12-04 19:15:05 +08:00
Raphaël MANSUY
196033bf75
cherry-pick 87de2b3e
2025-12-04 19:15:05 +08:00
Raphaël MANSUY
57c1330b54
cherry-pick 3efb1716
2025-12-04 19:15:05 +08:00
Raphaël MANSUY
a3fb244631
cherry-pick 2b160163
2025-12-04 19:15:05 +08:00
Raphaël MANSUY
2a247bdda1
cherry-pick 0244699d
2025-12-04 19:15:04 +08:00
Raphaël MANSUY
4501740849
cherry-pick fa887d81
2025-12-04 19:15:04 +08:00
Raphaël MANSUY
7e53eaabee
cherry-pick e7d2803a
2025-12-04 19:15:04 +08:00
Raphaël MANSUY
cfc9348de6
cherry-pick 95cd0ece
2025-12-04 19:15:04 +08:00
Raphaël MANSUY
5a9677396b
cherry-pick 4438ba41
2025-12-04 19:15:04 +08:00
Raphaël MANSUY
d3d59b0dca
cherry-pick 186c8f0e
2025-12-04 19:15:04 +08:00
Raphaël MANSUY
aff704e58a
cherry-pick c434879c
2025-12-04 19:15:03 +08:00
Raphaël MANSUY
a4d6692e2d
cherry-pick 61b57cbb
2025-12-04 19:15:03 +08:00
Raphaël MANSUY
fce5dc6be6
cherry-pick c46c1b26
2025-12-04 19:15:03 +08:00
Raphaël MANSUY
fae72fab75
cherry-pick 754d2ad2
2025-12-04 19:14:31 +08:00
Raphaël MANSUY
96f23d59af
cherry-pick fc40a369
2025-12-04 19:14:30 +08:00
Raphaël MANSUY
7fa3cab355
cherry-pick 162370b6
2025-12-04 19:14:29 +08:00
Raphaël MANSUY
af3b2cf118
cherry-pick 0b3d3150
2025-12-04 19:14:29 +08:00
Raphaël MANSUY
84ac688666
cherry-pick 83d99e14
2025-12-04 19:14:29 +08:00
Raphaël MANSUY
250640e8a5
cherry-pick ea8d55ab
2025-12-04 19:14:28 +08:00
Raphaël MANSUY
086191ae5a
cherry-pick 56e0365c
2025-12-04 19:14:28 +08:00
Raphaël MANSUY
49b0953ac1
cherry-pick 4ab4a7ac
2025-12-04 19:14:28 +08:00
Raphaël MANSUY
d2ffd7794d
cherry-pick e5addf4d
2025-12-04 19:14:27 +08:00
Raphaël MANSUY
759980e522
cherry-pick ab4d7ac2
2025-12-04 19:14:27 +08:00
Raphaël MANSUY
778e6d57c4
cherry-pick 6b2af2b5
2025-12-04 19:14:27 +08:00
Raphaël MANSUY
7f5afd0a4d
cherry-pick 5dec4dea
2025-12-04 19:14:27 +08:00
Raphaël MANSUY
c83a76786a
cherry-pick 14a6c24e
2025-12-04 19:14:27 +08:00
Raphaël MANSUY
da7683a001
cherry-pick de4ed736
2025-12-04 19:14:26 +08:00
Raphaël MANSUY
395b76cdc9
cherry-pick a624a950
2025-12-04 19:14:26 +08:00
Raphaël MANSUY
f389b0d63a
cherry-pick 0b2a15c4
2025-12-04 19:14:26 +08:00
Raphaël MANSUY
3c8507358c
cherry-pick 03cc6262
2025-12-04 19:14:26 +08:00
Raphaël MANSUY
0166a38d01
cherry-pick ce28f30c
2025-12-04 19:14:26 +08:00
Raphaël MANSUY
cacea8ab56
cherry-pick 33a1482f
2025-12-04 19:14:26 +08:00
yangdx
d0e3c8a4a3
Fix duplicate document responses to return original track_id
...
- Return existing track_id for duplicates
- Remove track_id generation in reprocess
- Update reprocess response documentation
- Clarify track_id behavior in comments
- Update API response examples
(cherry picked from commit 8d28b95966
2025-12-04 19:11:24 +08:00
yangdx
21fc61ecd2
Add content deduplication check for document insertion endpoints
...
• Check content hash before insertion
• Return duplicated status if exists
• Use sanitized text for hash computation
• Apply to both single and batch inserts
• Prevent duplicate content processing
(cherry picked from commit 19c16bc464
2025-12-04 19:11:23 +08:00
netbrah
b65ef37569
Add Cohere reranker config, chunking, and tests
...
(cherry picked from commit a05bbf105e
2025-12-04 19:11:22 +08:00
anouarbm
7ce251c319
docs: Add documentation and examples for include_chunk_content parameter
...
Added comprehensive documentation for the new include_chunk_content parameter
that enables retrieval of actual chunk text content in API responses.
Documentation Updates:
- Added "Include Chunk Content in References" section to API README
- Explained use cases: RAG evaluation, debugging, citations, transparency
- Provided JSON request/response examples
- Clarified parameter interaction with include_references
OpenAPI/Swagger Examples:
- Added "Response with chunk content" example to /query endpoint
- Shows complete reference structure with content field
- Demonstrates realistic chunk text content
This makes the feature discoverable through:
1. API documentation (README.md)
2. Interactive Swagger UI (http://localhost:9621/docs )
3. Code examples for developers
(cherry picked from commit 963ad4c637
2025-12-04 19:11:20 +08:00
anouarbm
349c1945db
Optimize RAGAS evaluation with parallel execution and chunk content enrichment
...
Added efficient RAG evaluation system with optimized API calls and comprehensive benchmarking.
Key Features:
- Single API call per evaluation (2x faster than before)
- Parallel evaluation based on MAX_ASYNC environment variable
- Chunk content enrichment in /query endpoint responses
- Comprehensive benchmark statistics (moyennes)
- NaN-safe metric calculations
API Changes:
- Added include_chunk_content parameter to QueryRequest (backward compatible)
- /query endpoint enriches references with actual chunk content when requested
- No breaking changes - default behavior unchanged
Evaluation Improvements:
- Parallel execution using asyncio.Semaphore (respects MAX_ASYNC)
- Shared HTTP client with connection pooling
- Proper timeout handling (3min connect, 5min read)
- Debug output for context retrieval verification
- Benchmark statistics with averages, min/max scores
Results:
- Moyenne RAGAS Score: 0.9772
- Perfect Faithfulness: 1.0000
- Perfect Context Recall: 1.0000
- Perfect Context Precision: 1.0000
- Excellent Answer Relevance: 0.9087
(cherry picked from commit 0bbef9814e
2025-12-04 19:11:20 +08:00
yangdx
5febb88824
Fix missing workspace parameter in update flags status call
...
(cherry picked from commit 1745b30a5f
2025-12-04 19:11:18 +08:00
yangdx
94ae13a037
Refactor workspace handling to use default workspace and namespace locks
...
- Remove DB-specific workspace configs
- Add default workspace auto-setting
- Replace global locks with namespace locks
- Simplify pipeline status management
- Remove redundant graph DB locking
(cherry picked from commit 926960e957
2025-12-04 19:11:17 +08:00
yangdx
dfab175c16
Fix workspace isolation for pipeline status across all operations
...
- Fix final_namespace error in get_namespace_data()
- Fix get_workspace_from_request return type
- Add workspace param to pipeline status calls
(cherry picked from commit 52c812b9a0
2025-12-04 19:11:16 +08:00
