Skip to content

Seamless web search integration for LLM agents. Transforms natural language queries into structured web data, enabling AI models to access real-time information through a clean API.

Notifications You must be signed in to change notification settings

anhnh2002/titan-sight

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Titan Sight

Seamless web search integration for LLM agents. Transforms natural language queries into structured web data, enabling AI models to access real-time information through a clean API.

Titan Sight Logo

Features

  • Multi-Level Caching System

    • Query-level caching with Redis using vector similarity search
    • Page-level content caching with MongoDB for URL-based retrieval
  • Multiple Search Providers

  • Flexible LLM Integration

    • OpenAI-compatible API interface
    • Configurable models for result summarization
    • Token-aware content truncation

Quick Start

  1. Config enviroment variables: Copy .env.example to .env and configure the missing variables

  2. Build the Docker image:

docker build -t titan-sight:0.1.0 .
  1. Create required network:
docker network create titan_sight_net
  1. Start services:
docker-compose up -d

API Usage

Search Endpoint

curl -X 'GET' \
  'http://localhost:6969/v1/search?query=What%20is%20the%20weather%20like%20today%20in%20Hanoi%3F&provider=google&max_num_result=3&enable_cache=true' \
  -H 'accept: application/json'

Response:

{
  "query": "What is the weather like today in Hanoi?",
  "results": [
    {
      "title": "Weather Forecast Hanoi",
      "url": "https://weather.com/...",
      "content": "Current conditions in Hanoi...",
      "details": "Full page content...",
      "answer": "Currently in Hanoi: 24°C, Clear skies..."
    },
    ...
  ]
}

System Architecture

  • FastAPI Backend: Handles API requests and orchestrates search operations
  • Redis Cache: Stores query embeddings for fast similarity search
  • MongoDB: Persists webpage content for frequently accessed URLs
  • SearXNG: Self-hosted metasearch engine component

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

About

Seamless web search integration for LLM agents. Transforms natural language queries into structured web data, enabling AI models to access real-time information through a clean API.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published