Nimble Search

AI-powered search engine. (Perplexity Clone)

Run local LLMs (llama3, gemma, mistral, phi3), custom LLMs through LiteLLM, or use cloud models (Groq/Llama3, OpenAI/gpt4-o).

Please feel free to contact me on 𝕏 or create an issue if you have any questions.

💻 Live Demo

nimble-search.vercel.app (Cloud models only)

📖 Overview

• 🛠️ Tech Stack
• 🏃🏿‍♂️ Getting Started
• 🚀 Deploy

🛣️ Roadmap

• Add support for local LLMs through Ollama
• Docker deployment setup
• Add support for searxng. Eliminates the need for external dependencies.
• Create a pre-built Docker Image
• Add support for custom LLMs through LiteLLM
• Chat History
• Expert Search
• Chat with local files

🛠️ Tech Stack

• Frontend: Next.js
• Backend: FastAPI
• Search API: SearXNG, Tavily, Serper, Bing
• Logging: Logfire
• Rate Limiting: Redis
• UI Components: shadcn/ui

Features

• Search with multiple search providers (Tavily, Searxng, Serper, Bing)
• Answer questions with cloud models (OpenAI/gpt4-o, OpenAI/gpt3.5-turbo, Groq/Llama3)
• Answer questions with local models (llama3, mistral, gemma, phi3)
• Answer questions with any custom LLMs through LiteLLM
• Search with an agent that plans and executes the search for better results

🏃🏿‍♂️ Getting Started Locally

Prerequisites

• Docker
• Ollama (for running local models)
  • Download any of the supported models: llama3, mistral, gemma, phi3
  • Start the Ollama server with ollama serve

Get API Keys

• Tavily (Optional)
• Serper (Optional)
• OpenAI (Optional)
• Bing (Optional)
• Groq (Optional)

Quick Start

git clone https://github.com/gauravmandall/nimble-search.git
cd nimble-search && cp .env-template .env

Modify the .env file with your API keys (optional, not required if using Ollama).

Start the app:

docker-compose -f docker-compose.dev.yaml up -d

Wait for the app to start then visit http://localhost:3000.

For custom setup instructions, see custom-setup-instructions.md.

🚀 Deploy

Backend

After deploying the backend, copy the web service URL (e.g., https://your-backend.onrender.com).

Frontend

Use the backend URL in the NEXT_PUBLIC_API_URL environment variable when deploying with Vercel.

And you're done! 🥳

Use Nimble Search as Your Default Search Engine

To set Nimble Search as your default search engine:

1. Visit your browser's settings.
2. Navigate to 'Search Engines'.
3. Create a new search engine entry using the URL: http://localhost:3000/?q=%s.
4. Add the search engine.