GraphRAG Studio — initial commit: multimodal RAG system with KG visualization
Full-stack application for document-to-knowledge-graph pipeline: - Backend: FastAPI + LangGraph ReAct agent + DeepSeek + MinerU parsing - Frontend: React 19 + Vite + D3.js + shadcn/ui - Pipeline: MinerU parsing → LangExtract entity extraction → KG building Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
10
backend/.env.example
Normal file
10
backend/.env.example
Normal file
@@ -0,0 +1,10 @@
|
||||
# DeepSeek API (required for entity extraction + QA)
|
||||
DEEPSEEK_API_KEY=your_deepseek_api_key_here
|
||||
DEEPSEEK_BASE_URL=https://api.deepseek.com
|
||||
|
||||
# MinerU (required for document parsing)
|
||||
MINERU_API_TOKEN=your_mineru_api_token_here
|
||||
|
||||
# MinerU venv path (absolute path to python.exe)
|
||||
MINERU_PYTHON=F:/GraphRAGAgent/mineru_mvp/.venv/Scripts/python.exe
|
||||
MINERU_PIPELINE=F:/GraphRAGAgent/mineru_mvp/pipeline.py
|
||||
Reference in New Issue
Block a user