Loading repository data…
Loading repository data…
omaaartamer / repository
A LangGraph-based research assistant that helps find, analyze, and summarize scientific papers. Built with Mistral LLM (via Ollama) and Flask, this agent can search papers through CORE API, process PDFs, and provide structured research summaries.
A transparent discovery signal based on current public GitHub metadata.
This score does not audit code, security, maintainers, documentation quality, or suitability. Verify the repository and its current documentation before adoption.
A LangGraph-based research assistant that helps users find, analyze, and summarize scientific papers using the CORE API.
This project implements a research assistant agent that can:
Original Implementation:
Solution:
Workflow Management:
Solution:
Challenges:
Solution:
pip install -r requirements.txt
# Install Ollama
curl https://ollama.ai/install.sh | sh
# Pull Mistral model
ollama pull mistral
# Create .env file
CORE_API_KEY=your_key_here
Run the application:
python run.py
Project Structure
.
├── run.py # Flask app entry point
├── requirements.txt # Project dependencies
├── flaskApp/ # Flask application
│ ├── __init__.py
│ ├── config.py
│ ├── views.py
│ ├── static/
│ └── templates/
└── agent/ # Agent implementation
├── __init__.py
├── models.py # Pydantic models
├── core_wrapper.py # CORE API wrapper
├── mistral_wrapper.py # LLM wrapper
├── prompts.py # System prompts
├── tools.py # Agent tools
├── utils.py # Helper functions
└── workflow.py # LangGraph workflow
The original implementation and research was done by:
This project maintains the core functionality and workflow of the original implementation while adapting it for web deployment and local LLM usage.
While the integration of tools and API is functional, the locally hosted Mistral model shows some limitations:
Hallucinations:
Comparison with OpenAI Models:
Model Enhancement:
Integration Refinement:
Alternative Approaches:
Note: For production use cases requiring high accuracy and reliability, consider using OpenAI's models or other cloud-based solutions.