You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.

45 lines
1.9 KiB

2 weeks ago
# 🔍 DeepSearcher
![DeepSearcher](./assets/pic/logo.png)
<div align="center">
<a href="https://opensource.org/licenses/Apache-2.0">
<img height="28" src="https://img.shields.io/badge/License-Apache%202.0-blue.svg?style=flat" alt="License">
</a>
<a href="https://twitter.com/zilliz_universe">
<img height="28" src="https://img.shields.io/badge/Follow-%40Zilliz-1DA1F2?style=flat&logo=twitter" alt="Twitter">
</a>
<a href="https://discord.gg/mKc3R95yE5">
<img height="28" src="https://img.shields.io/badge/Discord-Join%20Chat-5865F2?style=flat&logo=discord&logoColor=white" alt="Discord">
</a>
</div>
---
## ✨ Overview
DeepSearcher combines cutting-edge LLMs (OpenAI o1, o3-mini, DeepSeek, Grok 3, Claude 4 Sonnet, Llama 4, QwQ, etc.) and Vector Databases (Milvus, Zilliz Cloud etc.) to perform search, evaluation, and reasoning based on private data, providing highly accurate answers and comprehensive reports.
> **Perfect for:** Enterprise knowledge management, intelligent Q&A systems, and information retrieval scenarios.
![Architecture](./assets/pic/deep-searcher-arch.png)
## 🚀 Key Features
| Feature | Description |
|---------|-------------|
| 🔒 **Private Data Search** | Maximizes utilization of enterprise internal data while ensuring data security. When necessary, integrates online content for more accurate answers. |
| 🗄️ **Vector Database Management** | Supports Milvus and other vector databases, allowing data partitioning for efficient retrieval. |
| 🧩 **Flexible Embedding Options** | Compatible with multiple embedding models for optimal selection based on your needs. |
| 🤖 **Multiple LLM Support** | Supports DeepSeek, OpenAI, and other large models for intelligent Q&A and content generation. |
| 📄 **Document Loader** | Supports local file loading, with web crawling capabilities under development. |
## 🎬 Demo
![Demo](./assets/pic/demo.gif)