RAGFlow is an agent-native database: a Retrieval-Augmented Generation (RAG) engine that grew into context infrastructure.
Go agent-harnessagent-native-databaseagentic-aiagentic-retrievalagentic-searchaiai-agentscontext-enginecontext-engineeringcontext-managementharness-engineeringknowledge-compilationragretrieval-augmented-generationretrieval-harnesssearch-harness
Commits on main
fix(embedding): omit unsupported user field for OVH AI endpoint (#19758)
709a91e Andrej Kratky committed 2 months ago
Revert "feat(agent): support document_ids in retrieval node and tool" (#19837)
501424f Wang Qi committed 2 months ago
Fix: store <think>content</think> to conversation_message (#19836)
d8fd370 Wang Qi committed 2 months ago
fix: improve UI wording and localization for parsing and chunking settings (#19839)
0ae1c0a YanZhang committed 2 months ago
fix(model): move PaddleOCR api_key unwrapping from the generic provider flow into the drivers (#19823)
1705cc0 euvre committed 2 months ago
Go: add generic Go integration test CI job (infinity) (#19702)
4b055c5 xugangqiang committed 2 months ago
fix(parser): recover DOCX text boxes in the Python chunkers (#19735)
012e0a7 Lukas committed 2 months ago
refactor(agent-form): remove maxTokens switch field from sub-agent form (#19830)
1e66f21 chanx committed 2 months ago
Fix: Restrict the parser operator so that it can only be followed by a chunker, and a chunker cannot be followed by another chunker. (#19833)
faa0d8c balibabu committed 2 months ago
Fix: Negative values can be entered for the maximum number of reflection rounds. (#19819)
7c44afe balibabu committed 2 months ago
Fix authorization for OpenAI-compatible agent completions (#19817)
2018079 Mahshooq Zubair committed 2 months ago
fix(compiler): keep LLM runtime params when saving a document pipeline config (#19554)
a230f1e euvre committed 2 months ago
fix(document): skip active and completed tasks on batch ingest (#19786)
132413d jay77721 committed 2 months ago
fix(parser): move PDF TOC and header/footer removal to box level (#19779)
5f1a69f jay77721 committed 2 months ago
feat: add Cheaper Inference as an OpenAI-compatible model provider (#19748)
46277eb aiapienthusiast committed 2 months ago
Enhance LLM_DEBUG with took and first token time, short embedding to 3 float (#19816)
8363fc7 Wang Qi committed 2 months ago
fix(api): return empty documents when doc_ids filter is empty (#19809)
3472337 Jin Hai committed 2 months ago
feat(go-syncer): add checkpoint resume for MySQL/PostgreSQL connectors (#19762)
1ff3d96 mkaaad committed 2 months ago
fix(deepdoc): disable ORT BFC memory arena for pooled inference sessions (#19800)
2d0757a xugangqiang committed 2 months ago