DEDUPED Hot AI repos. Real use cases. What people build. Get the Monday 5

How to run a knowledge-graph RAG server with a web UI with LightRAG

Install the LightRAG Server, point it at your models and query documents through the WebUI.

Short answer: Install the server as a tool with uv tool install "lightrag-hku[api]"; then copy the example config with cp env.example .env and set your LLM and embedding settings; start it with lightrag-server. All steps.

  • Top pick
  • Research
  • Intermediate
  • 45 minutes
  • From the README
  • Claude Code
  • Codex
  • Cursor

insecure-default. The server binds to all interfaces by default and every endpoint is public without auth, so configure authentication or bind to 127.0.0.1 first.

Who it is forA researcher who wants answers that connect people, companies and events across many documents.

The problemPlain vector RAG returns fragments and misses how entities relate across files.

The outcomeA local LightRAG server where you insert documents, ask questions and see the knowledge graph.

What you need first

  • Python with uv (recommended) or pip, or Docker Compose
  • An LLM and an embedding model configured in .env
  • Optional: storage backends such as PostgreSQL, Neo4j or OpenSearch

Steps

  1. Install the server as a tool with uv tool install "lightrag-hku[api]"
  2. Copy the example config with cp env.example .env and set your LLM and embedding settings
  3. Start it with lightrag-server
  4. Open the WebUI to insert documents, query them and visualize the graph
  5. Before exposing it on a network, set LIGHTRAG_API_KEY or AUTH_ACCOUNTS with TOKEN_SECRET in .env

Prompt for your agent

Install HKUDS/LightRAG Server with uv, configure .env for <LLM> and <embedding model>, bind it to 127.0.0.1, and load <documents>. Then ask <question> and show me the entities and relations it used.

Caveat. Graph extraction quality depends heavily on the LLM; the README notes improvements for open models such as Qwen3-30B-A3B.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for HKUDS/LightRAG and "Run a knowledge-graph RAG server with a web UI"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer