Lightning-Fast Deep Research Report

Deep Research uses a variety of powerful AI models to generate in-depth research reports in just a few minutes. It leverages advanced “Thinking” and “Task” models, combined with an internet connection, to provide fast and insightful analysis on a variety of topics. Your privacy is paramount - all data is processed and stored locally.

✨ Features

• Rapid Deep Research: Generates comprehensive research reports in about 2 minutes, significantly accelerating your research process.
• Multi-platform Support: Supports rapid deployment to Vercel, Cloudflare and other platforms.
• Powered by AI: Utilizes the advanced AI models for accurate and insightful analysis.
• Support for Multi-LLM: Supports a variety of mainstream large language models, including Gemini, OpenAI, Anthropic, Deepseek, Grok, OpenAI Compatible, OpenRouter, Ollama, etc.
• Support Web Search: Supports search engines such as Searxng, Tavily, Firecrawl, Exa, Bocha, etc., allowing LLMs that do not support search to use the web search function more conveniently.
• Thinking & Task Models: Employs sophisticated “Thinking” and “Task” models to balance depth and speed, ensuring high-quality results quickly. Support switching research models.
• Support Further Research: You can refine or adjust the research content at any stage of the project and support re-research from that stage.
• Local Knowledge Base: Supports uploading and processing text, Office, PDF and other resource files to generate local knowledge base.
• Artifact Supports editing of research content, with two editing modes: WYSIWYM and Markdown. It is possible to adjust the reading level, article length and full text translation.
• Research History: Support preservation of research history, you can review previous research results at any time and conduct in-depth research again.
• Local & Server API Support: Offers flexibility with both local and server-side API calling options to suit your needs.
• Privacy-Focused: Your data remains private and secure, as all data is stored locally on your browser.
• Support Multi-Key payload: Support Multi-Key payload to improve API response efficiency.
• Multi-language Support: English、简体中文.
• Built with Modern Technologies: Developed using Next.js 15 and Shadcn UI, ensuring a modern, performant, and visually appealing user experience.
• MIT Licensed: Open-source and freely available for personal and commercial use under the MIT License.

🎯 Roadmap

• Support preservation of research history
• Support editing final report and search results
• Support for other LLM models
• Support file upload and local knowledge base
• Support MCP

🚀 Getting Started

Use Free Gemini (recommend)

1. Get Gemini API Key

2. One-click deployment of the project, you can choose to deploy to Vercel or Cloudflare

   

   Currently the project supports deployment to Cloudflare, but you need to follow How to deploy to Cloudflare Pages to do it.

3. Start using

Use Other LLM

1. Deploy the project to Vercel or Cloudflare
2. Set the LLM API key
3. Set the LLM API base URL (optional)
4. Start using

⌨️ Development

Follow these steps to get Deep Research up and running on your local browser.

Prerequisites

• Node.js (version 18.18.0 or later recommended)
• pnpm or npm or yarn

Installation

1. Clone the repository:

   git clone https://github.com/u14app/deep-research.git
   cd deep-research

2. Install dependencies:

   pnpm install  # or npm install or yarn install

3. Set up Environment Variables:

   You need to modify the file env.tpl to .env, or create a .env file and write the variables to this file.

4. Run the development server:

   pnpm dev  # or npm run dev or yarn dev

   Open your browser and visit http://localhost:3000 to access Deep Research.

Custom Model List

The project allow custom model list, but only works in proxy mode. Please add an environment variable named NEXT_PUBLIC_MODEL_LIST in the .env file or environment variables page.

Custom model lists use , to separate multiple models. If you want to disable a model, use the - symbol followed by the model name, i.e. -existing-model-name. To only allow the specified model to be available, use -all,+new-model-name.

🚢 Deployment

Vercel

Cloudflare

Currently the project supports deployment to Cloudflare, but you need to follow How to deploy to Cloudflare Pages to do it.

Docker

The Docker version needs to be 20 or above, otherwise it will prompt that the image cannot be found.

⚠️ Note: Most of the time, the docker version will lag behind the latest version by 1 to 2 days, so the “update exists” prompt will continue to appear after deployment, which is normal.

docker pull xiangfa/deep-research:latest
docker run -d --name deep-research -p 3333:3000 xiangfa/deep-research

You can also specify additional environment variables:

docker run -d --name deep-research \
   -p 3333:3000 \
   -e ACCESS_PASSWORD=your-password \
   -e GOOGLE_GENERATIVE_AI_API_KEY=AIzaSy... \
   xiangfa/deep-research

or build your own docker image:

docker build -t deep-research .
docker run -d --name deep-research -p 3333:3000 deep-research

If you need to specify other environment variables, please add -e key=value to the above command to specify it.

Deploy using docker-compose.yml:

version: '3.9'
services:
   deep-research:
      image: xiangfa/deep-research
      container_name: deep-research
      environment:
         - ACCESS_PASSWORD=your-password
         - GOOGLE_GENERATIVE_AI_API_KEY=AIzaSy...
      ports:
         - 3333:3000

or build your own docker compose:

docker compose -f docker-compose.yml build

Static Deployment

You can also build a static page version directly, and then upload all files in the out directory to any website service that supports static pages, such as Github Page, Cloudflare, Vercel, etc..

pnpm build:export

⚙️ Configuration

As mentioned in the “Getting Started” section, Deep Research utilizes the following environment variables for server-side API configurations:

Please refer to the file env.tpl for all available environment variables.

Important Notes on Environment Variables:

• Privacy Reminder: These environment variables are primarily used for server-side API calls. When using the local API mode, no API keys or server-side configurations are needed, further enhancing your privacy.

• Multi-key Support: Supports multiple keys, each key is separated by ,, i.e. key1,key2,key3.

• Security Setting: By setting ACCESS_PASSWORD, you can better protect the security of the server API.

• Make variables effective: After adding or modifying this environment variable, please redeploy the project for the changes to take effect.

🪄 How it works

1. Research topic

   • Input research topic
   • Use local research resources (optional)
   • Start thinking (or rethinking)

2. Propose your ideas

   • The system asks questions based on the user’s research topic to confirm the research direction
   • Answer system questions (optional)
   • Write a research plan (or rewrite the research plan)
   • The system outputs the research plan
   • Start in-depth research (or re-research)
   • The system generates SERP queries

3. Information collection

   • Initial research
     • Start the first round of data collection
     • Retrieve local research resources based on SERP queries
     • Extract learning points related to SERP queries from local research resources
     • Collect information from the Internet based on SERP queries
     • Extract learning points related to SERP queries from materials collected on the Internet
     • Complete the first round of information collection
   • In-depth research (this process can be repeated)
     • Propose research suggestions (optional)
     • Start a new round of information collection (the process is the same as the initial research)

4. Generate Final Report

   • Make a writing request (optional)
   • Summarize all research materials into a comprehensive Markdown report
   • Include all sources and references
   • Organize information in a clear and easy to read format
   • Regenerate research report (optional)

flowchart TD

    subgraph Phase 1: Research Topic
        A[Input Research Topic]
        Think[Start Thinking / Rethinking]
        OptLocal{Use Local Resources?}
        UseLocal[Use Local Research Resources]
    end

    subgraph Phase 2: Propose Idea
        SysQuest[System asks Questions]
        OptAnswer{Answer Questions?}
        AnswerQuest[Answer System Questions]
        WritePlan[Write / Rewrite Research Plan]
        PlanOutput[System Outputs Research Plan]
        StartDeep[Start Deep Research / Re-Research]
        GenSERP[System Generates SERP Queries]
    end

    subgraph Phase 3: Information Gathering Cycle
        GatherData[Gather Data based on SERP Queries Local & Web]
        Extract[Extract Learnings]
        LearningsAccumulated((Learnings))
        DecideMore{More Research Needed?}
        OptSuggest{Propose Suggestions?}
        Suggest[Propose Research Suggestions]
    end

    subgraph Phase 4: Generate Final Report
        OptWriteReq{Provide Writing Requirements?}
        WriteReq[Provide Writing Requirements]
        Compile[Compile All Research into Report]
        ReportOut["Markdown Report<br/>(incl. sources & references)"]
        OptRegen{Regenerate Report?}
        Regen[Regenerate Research Report]
        End((End))
    end

    %% Phase 1 Flow
    A --> Think;
    Think --> OptLocal;
    OptLocal -- Yes --> UseLocal;
    OptLocal -- No --> SysQuest;
    UseLocal --> SysQuest;

    %% Phase 2 Flow
    SysQuest --> OptAnswer;
    OptAnswer -- Yes --> AnswerQuest;
    OptAnswer -- No --> WritePlan;
    AnswerQuest --> WritePlan;
    WritePlan --> PlanOutput;
    PlanOutput --> StartDeep;
    StartDeep --> GenSERP;

    %% Phase 3 Flow (Internal Loop)
    GenSERP --> GatherData;
    GatherData --> Extract;
    Extract --> LearningsAccumulated;
    LearningsAccumulated --> DecideMore;
    DecideMore -- Yes (Continue Gathering) --> OptSuggest;
    OptSuggest -- Yes --> Suggest;
    Suggest --> GatherData;
    OptSuggest -- No --> GatherData;

    %% Exit Phase 3 to Phase 4
    DecideMore -- No (Proceed to Report) --> OptWriteReq;

    %% Loops for "Re-" Actions
    StartDeep -- Rethink Topic --> Think;
    StartDeep -- Rewrite Plan --> WritePlan;
    DecideMore -- Start New Deep Research Cycle --> StartDeep;

    %% Phase 4 Flow (Internal Loop)
    OptWriteReq -- Yes --> WriteReq;
    OptWriteReq -- No --> Compile;
    WriteReq --> Compile;
    Compile --> ReportOut;
    ReportOut --> OptRegen;
    OptRegen -- Yes --> Regen;
    Regen --> Compile;
    OptRegen -- No --> End;

    %% Styling (similar categories to example)
    classDef input fill:#7bed9f,stroke:#2ed573,color:black;
    classDef process fill:#70a1ff,stroke:#1e90ff,color:black;
    classDef decision fill:#ffa502,stroke:#ff7f50,color:black;
    classDef optional fill:#dfe6e9,stroke:#b2bec3,color:black;
    classDef io fill:#ff4757,stroke:#ff6b81,color:black;
    classDef loop fill:#a8e6cf,stroke:#3b7a57,color:black;
    classDef startEnd fill:#bcaaa4,stroke:#795548,color:black;

🙋 FAQs

Why does my Ollama or SearXNG not work properly and displays the error TypeError: Failed to fetch?

If your request generates CORS due to browser security restrictions, you need to configure parameters for Ollama or SearXNG to allow cross-domain requests. You can also consider using the server proxy mode, which is a backend server that makes requests, which can effectively avoid cross-domain issues.

🛡️ Privacy

Deep Research is designed with your privacy in mind. All research data and generated reports are stored locally on your machine. We do not collect or transmit any of your research data to external servers (unless you are explicitly using server-side API calls, in which case data is sent to API through your configured proxy if any). Your privacy is our priority.

🙏 Acknowledgements

• Next.js - The React framework for building performant web applications.
• Shadcn UI - Beautifully designed components that helped streamline the UI development.
• AI SDKs - Powering the intelligent research capabilities of Deep Research.
• Deep Research - Thanks to the project dzhng/deep-research for inspiration.

🤝 Contributing

We welcome contributions to Deep Research! If you have ideas for improvements, bug fixes, or new features, please feel free to:

1. Fork the repository.
2. Create a new branch for your feature or bug fix.
3. Make your changes and commit them.
4. Submit a pull request.

For major changes, please open an issue first to discuss your proposed changes.

✉️ Contact

If you have any questions, suggestions, or feedback, please create a new issue.

📝 License

Deep Research is released under the MIT License. This license allows for free use, modification, and distribution for both commercial and non-commercial purposes.