Tencent/WeKnora
LLM-powered framework for deep document understanding, semantic retrieval, and context-aware answers using RAG paradigm.
Combines multimodal document preprocessing (handling heterogeneous file types), semantic vector indexing with multiple backend support (Milvus, Weaviate), and intelligent hybrid retrieval with reranking. Features modular architecture enabling IM bot integration (WeCom, Feishu, Slack, Telegram, DingTalk), MCP tool extension, and agentic workflows with specialized skills (Data Analyst, reasoning) alongside streaming inference for context-aware responses.
13,362 stars. Actively maintained with 289 commits in the last 30 days.
Stars
13,362
Forks
1,546
Language
Go
License
—
Category
Last pushed
Mar 12, 2026
Commits (30d)
289
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/rag/Tencent/WeKnora"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.