dyj-naj/agentic-rag-knowledge-assistant

github.com/dyj-naj/agentic-rag-knowledge-assistant ↗

Python

20 environment variables found in .env.example

Set these on your host before deploying. Each platform has an “Environment Variables” section in the deploy flow. (showing first 20, more exist in .env.example)

OPENAI_API_KEY secret OpenAI 兼容 API 配置（支持 OpenAI / DeepSeek / 通义千问等）
OPENAI_BASE_URL secret
OPENAI_MODEL secret
EMBEDDING_API_KEY secret Embedding 模型配置（用于向量化）
EMBEDDING_BASE_URL
EMBEDDING_MODEL
EMBEDDING_DIMENSIONS
QDRANT_HOST Qdrant 向量数据库配置
QDRANT_PORT
QDRANT_COLLECTION_NAME
MYSQL_HOST MySQL 数据库配置
MYSQL_PORT
MYSQL_USER
MYSQL_PASSWORD secret
MYSQL_DATABASE
RERANKER_API_KEY secret 重排序模型配置（独立于主模型，用于检索结果精排）千问模型（如 qwen3-rerank）使用 Dashscope 原生 API，无需配置 BASE_URL 其他模型使用 OpenAI 兼容 API，需配置 BASE_URL
RERANKER_BASE_URL
RERANKER_MODEL
RERANKER_TOP_K
RERANKER_CANDIDATES

Best match Fly.io Anything Dockerized — requires the Fly CLI.

macOS

brew install flyctl && fly launch --from https://github.com/dyj-naj/agentic-rag-knowledge-assistant

Linux

curl -L https://fly.io/install.sh | sh && fly launch --from https://github.com/dyj-naj/agentic-rag-knowledge-assistant

Windows (PowerShell)

iwr https://fly.io/install.ps1 -useb | iex; fly launch --from https://github.com/dyj-naj/agentic-rag-knowledge-assistant

Alternative Deploy on Railway Apps that need Postgres, Redis, or background workers.

Or deploy to a different host

Render Full-stack with managed Postgres + Redis. DigitalOcean App Platform Containers, droplets, and managed services.

← Try another repo