How mimshad1999/multi-agent-research-system works
ResearchMind accepts a topic through its Streamlit interface or command-line pipeline, searches for sources, scrapes selected content, drafts a report, and critiques it. The app also displays the research and report and offers a Markdown download. The sampled source confirms these orchestration paths and the search/scrape tools; unsampled app sections may contain additional presentation details.
Main entry points: pipeline.py CLI Pipeline · app.py Streamlit App · agents.py Search Agent · tools.py Web Search Tool
Components 12
User Interface
- Streamlit App
app.py
Pipeline Orchestration
- CLI Pipeline
pipeline.py
Research Tools
- Search Agent
agents.py - Reader Agent
agents.py - Web Search Tool
tools.py - URL Scraper
tools.py
Report Generation
- Writer Chain
agents.py - Critic Chain
agents.py
Other components
- Researcher
- Tavily Search
- Web Pages
- Groq LLM
Connections 21
- Researcher → Streamlit App: enters topic
- Researcher → CLI Pipeline: enters topic
- Streamlit App → Search Agent: invokes
- Streamlit App → Reader Agent: invokes
- Streamlit App → Writer Chain: invokes
- Streamlit App → Critic Chain: invokes
- CLI Pipeline → Search Agent: invokes
- CLI Pipeline → Reader Agent: invokes
- CLI Pipeline → Writer Chain: invokes
- CLI Pipeline → Critic Chain: invokes
- Search Agent → Web Search Tool: dispatches
- Reader Agent → URL Scraper: dispatches
- Web Search Tool → Tavily Search: searches
- Tavily Search → Web Search Tool: returns results
- URL Scraper → Web Pages: fetches page
- Web Pages → URL Scraper: returns HTML
- Search Agent → Groq LLM: uses model
- Reader Agent → Groq LLM: uses model
- Writer Chain → Groq LLM: uses model
- Critic Chain → Groq LLM: uses model
- CLI Pipeline → Researcher: returns state