Farfalle

Visit Tool

Farfalle is an open-source AI search engine that allows self-hosting with local or cloud LLMs. It supports various search providers and offers an agent that plans and executes searches for improved results.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Yes

Skill level

Technical

About

What is farfalle?

Farfalle is an open-source AI-powered search engine designed for self-hosting, offering flexibility with both local and cloud Large Language Models. Users can integrate local LLMs such as Llama3, Gemma, Mistral, and Phi3 via Ollama, or leverage cloud models like Groq/Llama3 and OpenAI/gpt4-o. The platform also supports custom LLMs through LiteLLM. Farfalle features multiple search providers including Tavily, SearXNG, Serper, and Bing, and enhances search quality with an agent that plans and executes queries. Its tech stack includes Next.js for the frontend, FastAPI for the backend, and Redis for rate limiting, making it a robust solution for those seeking a customizable and powerful AI search experience.

Best used for

Ideal for developers who need to build custom AI search engines, integrate various LLMs for diverse queries, and deploy self-hosted solutions. Especially valuable for startup founders looking to create specialized search applications with advanced features and flexible model support.

Common actions

build search engine

integrate LLMs

customize search

deploy AI models

"AI Agents"github copilotface swappingautomated workflowcollaborationdeepfakeopen-sourceworkflowslow-code/no-code

Capabilities

Key features

Self-hostable search engine
Local LLM support
Cloud LLM integration
Custom LLM integration
Multiple search providers
Agent-based search execution
Chat history

Target Audience

developerdata scientiststartup founder

Integrations

ollamaopenaigroqlitellmsearxngtavilyserperbing+ 1 more

Pricing & Plans

Open Source

Free

FAQs

What types of LLMs can Farfalle integrate?

Farfalle supports a wide range of LLMs, including local models like Llama3, Gemma, Mistral, and Phi3 via Ollama, as well as cloud models such as Groq/Llama3 and OpenAI/gpt4-o. It also allows integration of custom LLMs through LiteLLM.

What search providers can be used with Farfalle?

Farfalle is designed to work with multiple search providers to enhance results. Currently, it supports integration with SearXNG, Tavily, Serper, and Bing, offering flexibility in how search queries are executed and information is retrieved.

Is Farfalle suitable for non-technical users?

Farfalle is primarily aimed at technical users, particularly developers and data scientists, due to its self-hosting requirements and the need for configuration with various LLMs and APIs. It requires familiarity with Docker and command-line operations.

Trending

Subcategories trending in Research & Education

Academic Research Study Assistants Knowledge Management Course Creation Scientific Computing Summarization

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce