K2-k2/Multi-Agent-Research-Crew

1---2title: Multi Agent Research Crew3emoji: 👩‍💻4colorFrom: indigo5colorTo: green6sdk: streamlit7sdk_version: 1.40.08app_file: app.py9pinned: false10license: mit11---12 13### 🚀 Multi-Agent Research Crew14A high-efficiency, memory-optimized AI research assistant built with **Streamlit**, **CrewAI**, and **Google Gemini**. This application orchestrates a collaborative team of AI agents to research complex topics and synthesize them into professional blog posts.15 16## 🌟 Overview17This project demonstrates how to leverage **agentic workflows** to solve multi-step problems. Instead of a single prompt-response interaction, this app utilizes two specialized agents:181.  **Lead Researcher:** Scours the topic to identify 5 critical, data-driven facts.192.  **Tech Blogger:** Transforms those facts into a polished, Markdown-formatted article.20 21## 🛠️ Key Features22* **Secure API Management:** Uses a sidebar input for your Gemini API key to keep it out of your source code.23* **Memory Optimization:** Configured with `memory=False` and `allow_delegation=False` to run efficiently on standard consumer hardware.24* **Persistent Results:** Utilizes Streamlit Session State to ensure your research results survive UI refreshes.25* **Markdown Exports:** Download your generated blog post instantly as a `.md` file.26 27## 💻 Local Installation & Setup28 29Follow these steps to get the Research Crew running on your machine:30 311. Clone the Repository:32   ```bash33   git clone [https://huggingface.co/spaces/K2-k2/Multi-Agent-Research-Crew](https://huggingface.co/spaces/K2-k2/Multi-Agent-Research-Crew)34 352. Create a Virtual Environment (Recommended):36   ```bash37   # Windows38   python -m venv venv39   venv\Scripts\activate40 41   # macOS/Linux42   python3 -m venv venv43   source venv/bin/activate44 453. Install Dependencies:46Ensure you have a **requirements.txt** file, then run:47   ```bash48   pip install streamlit crewai langchain-google-genai49 504. Run the Application:51   ```bash52   streamlit run app.py53 54## 🏗️ Architecture55The app follows a **Sequential Process** to ensure quality control:56 57| Agent | Role | Responsibility |58| :--- | :--- | :--- |59| **Researcher** | Data Discovery | Fact-checking and trend identification. |60| **Writer** | Content Synthesis | Narrative structure and Markdown formatting. |61 62**1. Input:** You provide a research topic and your Google Gemini API Key.63 64**2. Execution:** The Researcher agent finds the data, then passes it to the Writer agent.65 66**3. Output:** A formatted Markdown blog post is displayed and made available for download.67 68---69## 👨‍💻 About the Project70Developed by **Kesar Agarwal** an aspiring AI Engineer focused on creating accessible, agentic AI tools.71 72 73 74 75 76 77 78 79 80Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference