d

deep-searcher

DeepSearcher is a deep research and search tool based on private data.

🇨🇳 DomesticFreeOpen sourceResearch开源LLMPython向量数据库
Platforms: Self-hosted
Region
Domestic
Pricing
Free
Open source
Yes
GitHub Stars
★ 7.9k
Source
GitHub
Added
2026-06-05
Last verified
2026-06-05

Overview

DeepSearcher is a deep research and search tool based on private data, written in Python. It combines advanced large language models (such as OpenAI o3, Qwen3, etc.) with vector databases (like Milvus) to enable efficient search, evaluation, and reasoning over private data, delivering accurate answers and comprehensive reports. Suitable for enterprise knowledge management, intelligent question-answering systems, and information retrieval scenarios.

Key features

  • Supports multiple large language models
  • Compatible with multiple vector databases
  • Flexible embedding options
  • Document loading functionality
  • Ensures data security

Use cases

Enterprise knowledge managementIntelligent question-answering systemsInformation retrieval

Pros

  • Highly accurate answers
  • Comprehensive report generation
  • Supports multiple embedding models
  • Data security assurance

Limitations / notes

  • Requires API key configuration
  • Some features are still under development

Who it's for

Enterprise usersDevelopersResearchers

This overview was compiled by AI from public sources and may contain inaccuracies — please refer to the official site.

FAQ

How can I install DeepSearcher?

It can be installed via pip or cloned from GitHub and dependencies synchronized using uv.

Which large language models are supported?

Supports multiple large language models such as OpenAI o3, Qwen3, DeepSeek, etc.

Similar agents

Something wrong? Let us know on the About page and we'll fix it.