This project is an AI-powered research tool that helps you quickly gather and synthesize information from the web. Simply enter a topic, and the assistant will generate a comprehensive article summarizing the latest news and insights.
This project is an internet research assistant built using Python, Streamlit, and Swarm AI. It allows users to enter a search query and receive a polished, publication-ready article based on the latest web search results.
1730292579767.mp4
- Objective conclusions for manual research can take weeks, requiring vast resources and time.
- LLMs trained on outdated information can hallucinate, becoming irrelevant for current research tasks.
- Current LLMs have token limitations, insufficient for generating long research reports.
- Limited web sources in existing services lead to misinformation and shallow results.
- Selective web sources can introduce bias into research tasks.
- It runs everythings locally keeping the user data private.
- Web Search: Uses DuckDuckGo to search the web for the latest news and information on a given topic.
- Research Analysis: Analyzes and synthesizes the search results, removing duplicates, identifying related themes, and verifying information consistency.
- Article Generation: Transforms the analyzed research results into a well-formatted and engaging article.
- Streamlit UI: Provides a user-friendly interface for entering search queries and viewing the generated articles.
1.Create a virtual environment
python -m venv env
2.Activate the environment
env\Scripts\activate
3.Install Ollama
4.Clone this repository:
git clone https://github.com/Shyamnath-Sankar/ollama-researcher.git
5.Install the necessary libraries:
pip install -r requirement.txt
6.Download model from ollama set the model name in .env
llm = <modelname>
4.To run
streamlit run app.py
Contributions are welcome! Please feel free to submit pull requests or issues.