#45 · Primary category: AI Content Readers & Aggregators

farfalle

fastapi generative-ui gpt-4o groq llm nextjs ollama openai perplexity react search-engine shadcn-ui tailwindcss

🔍 AI search engine - self-host with local or cloud LLMs

Project last updated:09/27/24

GitHub Stars

3.5K

Forks

319

Contributors

5

License

Apache-2.0

Why we included this project

Farfalle is a self-hosted AI search engine that answers queries with a written response and references, pulling results from SearXNG, Tavily, Serper, or Bing and passing them to an LLM. The model choice is flexible: run local models like Llama 3 or Mistral through Ollama, use cloud APIs such as OpenAI or Groq, or connect any provider via LiteLLM, which makes it easy to stay fully on-premises or keep costs down. An optional agent mode plans and refines searches for tougher questions, and chat history keeps follow-ups in context. If you need a Perplexity-style answer engine for your own users, this is a complete base to deploy and build on.

Articles for this project

No articles for this project yet.

To suggest a topic or contribute an article, contact us.

Related projects in this category