0xrphl/light-rag-marketing-assets-agent

Python

14 environment variables found in .env.example

Set these on your host before deploying. Each platform has an “Environment Variables” section in the deploy flow.

LIGHTRAG_URL ── LightRAG Server ──────────────────────────────────────────────────────
OPENAI_API_KEY secret ── API Keys ───────────────────────────────────────────────────────────── OpenAI (used by LightRAG for entity extraction + embeddings)
ANTHROPIC_API_KEY secret Anthropic (optional — for advanced querying agents)
ANTHROPIC_MODEL secret
GEMINI_API_KEY secret Gemini (used for image vision analysis)
GEMINI_MODEL
LLM_BINDING ── LightRAG Models ─────────────────────────────────────────────────────
LLM_MODEL
EMBEDDING_BINDING
EMBEDDING_MODEL
NEO4J_URI ── Neo4j ────────────────────────────────────────────────────────────────
NEO4J_USERNAME
NEO4J_PASSWORD secret
IMAGES_DIR ── Images Directory ─────────────────────────────────────────────────────

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

macOS

brew install flyctl && fly launch --from https://github.com/0xrphl/light-rag-marketing-assets-agent

Linux

curl -L https://fly.io/install.sh | sh && fly launch --from https://github.com/0xrphl/light-rag-marketing-assets-agent

Windows (PowerShell)

iwr https://fly.io/install.ps1 -useb | iex; fly launch --from https://github.com/0xrphl/light-rag-marketing-assets-agent

Or deploy to a different host