eabdadfb62
Features: - FastAPI server with OpenAI-compatible endpoints (/v1/chat/completions, /v1/models) - RAG system with document processing and vector storage - Support for multiple document formats (PDF, DOCX, HTML, text, code) - Streaming response support - Tool integration with website_downloader - Document management API endpoints - GLM-4.7-Flash integration via z-ai-web-dev-sdk - Works transparently with Open WebUI and other OpenAI clients Components: - main.py: FastAPI application with OpenAI-compatible API - rag/: RAG system (document processor, vector store, retriever) - tools/: Tool manager with website_downloader integration - .env.example: Configuration template
27 lines
486 B
Plaintext
27 lines
486 B
Plaintext
# DocRAG Configuration
|
|
# Copy this file to .env and fill in your values
|
|
|
|
# Server Configuration
|
|
HOST=0.0.0.0
|
|
PORT=8000
|
|
DEBUG=false
|
|
|
|
# Model Configuration
|
|
MODEL_NAME=DocRAG-GLM-4.7
|
|
UPSTREAM_MODEL=glm-4.7
|
|
|
|
# API Keys
|
|
ZAI_API_KEY=your-zai-api-key-here
|
|
|
|
# RAG Configuration
|
|
EMBEDDING_MODEL=text-embedding-3-small
|
|
VECTOR_STORE_PATH=./data/vectors
|
|
DOCUMENTS_PATH=./data/documents
|
|
CHUNK_SIZE=1000
|
|
CHUNK_OVERLAP=200
|
|
TOP_K_RESULTS=5
|
|
|
|
# Tool Configuration
|
|
ENABLE_TOOLS=true
|
|
MAX_TOOL_ITERATIONS=3
|