what is Deep Research?
Deep Research is an agent-based tool designed for advanced web search and research capabilities, utilizing HuggingFace's smolagents framework as an MCP server.
how to use Deep Research?
To use Deep Research, clone the repository, set up the required environment variables, and start the MCP server using the command uv run deep_research.py.
key features of Deep Research?
- Web search and information gathering
- PDF and document analysis
- Image analysis and description
- YouTube transcript retrieval
- Archive site search
use cases of Deep Research?
- Conducting comprehensive web searches for academic research.
- Analyzing and extracting information from PDF documents.
- Describing and analyzing images for research purposes.
- Retrieving transcripts from YouTube videos for content analysis.
- Searching archived websites for historical data.
FAQ from Deep Research?
- What are the system requirements for Deep Research?
You need Python 3.11 or higher and the
uvpackage manager, along with specific API keys.
- How do I obtain the required API keys?
You can sign up at the respective services like OpenAI, HuggingFace, and Serper.dev to get the necessary API keys.
- Is there a license for this project?
Yes, the project is provided under a specific license, which can be found in the repository.
Deep Research MCP Server
Deep Research is an agent-based tool that provides web search and advanced research capabilities. It leverages HuggingFace's smolagents and is implemented as an MCP server.
This project is based on HuggingFace's open_deep_research example.
Features
- Web search and information gathering
- PDF and document analysis
- Image analysis and description
- YouTube transcript retrieval
- Archive site search
Requirements
- Python 3.11 or higher
uvpackage manager- The following API keys:
- OpenAI API key
- HuggingFace token
- SerpAPI key
Installation
- Clone the repository:
git clone https://github.com/Hajime-Y/deep-research-mcp.git
cd deep-research-mcp
- Create a virtual environment and install dependencies:
uv venv
source .venv/bin/activate # For Linux or Mac
# .venv\Scripts\activate # For Windows
uv sync
Environment Variables
Create a .env file in the root directory of the project and set the following environment variables:
OPENAI_API_KEY=your_openai_api_key
HF_TOKEN=your_huggingface_token
SERPER_API_KEY=your_serper_api_key
You can obtain a SERPER_API_KEY by signing up at Serper.dev.
Usage
Start the MCP server:
uv run deep_research.py
This will launch the deep_research agent as an MCP server.
Key Components
deep_research.py: Entry point for the MCP servercreate_agent.py: Agent creation and configurationscripts/: Various tools and utilitiestext_web_browser.py: Text-based web browsertext_inspector_tool.py: File inspection toolvisual_qa.py: Image analysis toolmdconvert.py: Converts various file formats to Markdown
License
This project is provided under the [License Name].
Acknowledgements
This project uses code from HuggingFace's smolagents and Microsoft's autogen projects.
