Spaces:
Sleeping
Sleeping
Commit History
-
feat: strict Graph-RAG reasoning engine with JSON path output + validation script
9af036a -
feat: switch retrieval to knowledge-graph GraphRAG
45e4316 -
fix: auto-detect qdrant creds and make gemini dependency optional
0cde735 -
feat: add /vector_store_status endpoint for qdrant health and point count
8360b8a -
feat: add optional Qdrant Cloud vector persistence with memory fallback
f3792c3
-
fix: collapse single newlines to spaces in PDF extraction so chunk overlap works correctly
22e26d7 -
fix: rejoin hyphenated line-breaks in PDF text extraction
2b6183f -
feat: add GET /chunks endpoint with pagination and keyword filter
52f5749 -
feat: add /chunk_context endpoint to expose neighbouring chunks
120a644 -
fix: filter weak retrieval chunks and recalibrate confidence
205582d -
feat: grounded answering with confidence metadata and strict mode
479b930 -
feat: streaming LLM responses via SSE /query/stream endpoint
11df44e -
docs: rewrite README — professional structure, API reference, config table
92f4bab
-
fix: prevent embedding dimension mismatch when provider falls back mid-ingest
53894f4
-
fix: track active embed provider to prevent dimension mismatch on query
4e3ffdb -
fix: skip retries, instant HF fallback on Gemini failure
c25cdee -
fix: use InferenceClient for HF embeddings (old endpoint 410 Gone)
6561cad -
fix: auto-fallback to HF embeddings when Gemini rate-limited
b863f9d -
fix: retry with backoff on Gemini 429 rate limit
b898d5b -
migrate to google-genai SDK + update LLM models
3216e85 -
fix: embedding shape for query + add LLM error logging
1373e6f -
fix: use gemini-embedding-001 model
3c330af -
fix colorFrom in README metadata
aa01bb2 -
add HF Spaces config to README
e35d9ea -
initial deploy
a83d8b2