https://github.com/tirendazacademy/tracking-agents-with-comet

Monitoring agents with Comet ML
https://github.com/tirendazacademy/tracking-agents-with-comet

Last synced: 8 months ago
JSON representation

Monitoring agents with Comet ML

• Host: GitHub
• URL: https://github.com/tirendazacademy/tracking-agents-with-comet
• Owner: TirendazAcademy
• Created: 2023-07-19T11:10:30.000Z (about 2 years ago)
• Default Branch: main
• Last Pushed: 2024-02-21T18:14:33.000Z (over 1 year ago)
• Last Synced: 2025-01-01T05:27:01.723Z (9 months ago)
• Language: Jupyter Notebook
• Size: 43 KB
• Stars: 2
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
[![](https://img.shields.io/badge/Python-blue?style=plastic&logo=python&logoColor=white)]()

[![](https://img.shields.io/badge/OpenAI-0002A1?style=plastic&logo=openai&logoColor=white)]()

[![](https://img.shields.io/badge/Comet-D71313?style=plastic&logo=cometml&logoColor=white)]()

[![](https://img.shields.io/badge/LangChain-E14D2A?style=plastic&logo=langchain&logoColor=white)]()

This project aims to show how to monitor LLMs experiments. To run the LLM agent, we used [LangChain](https://python.langchain.com/docs/get_started/introduction.html) and OpenAI libraries. By leveraging [Comet](https://www.comet.com/site/products/llmops/)'s tools, we tracked this agent. 

To solve the hallucination, we first collect data with web scraping and then add this data to our LLM model. As a result, we obtained a language model that makes better predictions. 

### Install Python Dependencies

1. Open a terminal or command prompt.

2. Navigate to the directory where tracking-agents.ipynb is located (the cloned repo).

3. Execute the following command to install the required Python dependencies: `pip install -r requirements.txt`

4. This command will install the necessary packages specified in the requirements.txt file.