Welcome to ResearchX, where cutting-edge AI meets academic excellence! Powered by LangGraph technology, ResearchX transforms the way you conduct research by orchestrating a team of specialized AI agents to deliver comprehensive, high-quality research reports on any topic.
ResearchX leverages LangGraph to create a seamless, intelligent research experience. Inspired by the groundbreaking STORM paper, our platform assembles an elite team of AI agents that work in harmony to produce detailed, well-structured research reports.
💡 Key Features:
- Generates 5-6 page professional research reports
- Supports multiple export formats (PDF, Word, Markdown)
- Optimized performance using OpenAI's latest models
- Automated research workflow with quality checks
Want to see ResearchX in action? Check out this sample fundamental analysis report on Zomato stock. This report demonstrates our AI agents' capabilities in:
- Comprehensive market analysis
- Data-driven insights
- Professional formatting
- Proper citations and references
Our AI agents work together like a well-oiled machine:
- Chief Editor - Your research orchestrator, coordinating the entire process
- Researcher - Your dedicated research specialist, diving deep into topics
- Editor - Your structure expert, crafting perfect research outlines
- Reviewer - Your quality guardian, ensuring research excellence
- Revisor - Your refinement specialist, polishing content to perfection
- Writer - Your storyteller, weaving research into compelling narratives
- Publisher - Your format master, delivering polished final documents
- Planning - Strategic research outline development
- Data Collection - Comprehensive information gathering
- Analysis & Review - Thorough content validation
- Writing - Professional report compilation
- Publication - Multi-format document delivery
Generally, the process is based on the following stages:
- Planning stage
- Data collection and analysis
- Review and revision
- Writing and submission
- Publication
More specifically (as seen in the architecture diagram) the process is as follows:
- Browser (gpt-researcher) - Browses the internet for initial research based on the given research task.
- Editor - Plans the report outline and structure based on the initial research.
- For each outline topic (in parallel):
- Researcher (gpt-researcher) - Runs an in depth research on the subtopics and writes a draft.
- Reviewer - Validates the correctness of the draft given a set of criteria and provides feedback.
- Revisor - Revises the draft until it is satisfactory based on the reviewer feedback.
- Writer - Compiles and writes the final report including an introduction, conclusion and references section from the given research findings.
- Publisher - Publishes the final report to multi formats such as PDF, Docx, Markdown, etc.
- Clone the repository:
git clone https://github.com/akhil-bot/ResearchX.git
cd ResearchX/multi_agents- Install dependencies:
pip install -r requirements.txt- Set up your environment:
export OPENAI_API_KEY={Your OpenAI API Key}
export TAVILY_API_KEY={Your Tavily API Key}- Launch ResearchX:
python main.pyCustomize your research experience through task.json:
{
"query": "What are the latest developments in quantum computing?",
"model": "gpt-4",
"max_sections": 3,
"publish_formats": {
"markdown": true,
"pdf": true,
"docx": true
},
"include_human_feedback": false,
"source": "web",
"follow_guidelines": true,
"guidelines": [
"Ensure comprehensive coverage of the research question",
"Follow APA formatting guidelines",
"Maintain academic writing standards"
],
"verbose": true
}pip install langgraph-cli
langgraph upFor advanced usage and API documentation, visit our deployment guide.
ResearchX is continuously evolving. Here are some exciting areas we're exploring for future development:
- multi-modal research: Allow users to provide research tasks in different formats (text, voice, image)
- Multi-Language Support: Expand research capabilities to process and generate content in multiple languages
- Domain-Specific Agents: Introduce specialized agents for fields like medical research, legal analysis, and technical documentation
- Real-Time Collaboration: Enable multiple researchers to work on the same project simultaneously
- Source Verification System: Implement advanced fact-checking and source credibility assessment
- Model Flexibility: Support for multiple LLM providers (Claude, PaLM, local models)
- Memory Optimization: Enhanced caching and state management for better performance
- Parallel Processing: Improve multi-agent concurrent operations for faster research
- Custom Agent Creation: Allow users to define and train specialized research agents
- Addition of more free opn source LLMs and tools: Allow users to use more free tools and LLMs to make whole research with zero cost
- multi-modal reports: Generate reports combining different formats (text, voice, image)
- Interactive Web Interface: Develop a user-friendly web dashboard for research management
- Progress Tracking: Real-time visualization of research progress and agent activities
- Custom Templates: User-defined research templates and output formats
- Research History: Maintain and analyze past research projects for better insights
- Citation Management: Integration with reference management systems
- Cloud Storage: Direct export to various cloud storage platforms
- API Ecosystem: Public API for third-party integrations
- Plugin System: Extensible architecture for community-contributed features
- Peer Review System: Implementation of automated and human-in-the-loop validation
- Bias Detection: Tools to identify and mitigate potential biases in research
- Quality Metrics: Comprehensive scoring system for research output
- Automated Testing: Expanded test coverage for reliability
Want to contribute? Check out our contribution guidelines and join our community!
Built with ❤️ by a passionate AI Engineer