AI Observability & Evaluation - Evaluate, troubleshoot, and test your LLM models online and offline.
Project description
# lynxius-python client Lynxius Web App offers advanced AI observability features, security, scalability, integrations with existing ecosystems and easy collaboration across teams.
- warning::warning::warning:
If you’ve landed on this page, you’re likely participating in our closed beta program for [Lynxius](https://www.lynxius.ai/) and are already aware that this page serves as a placeholder. We are on the brink of officially launching our platform along with detailed documentation. In the meantime, here are a few code examples. :warning::warning::warning:
## Lynxius Platform in 3 Minutes [![Video Thumbnail](https://github-public-assets.s3.us-west-1.amazonaws.com/chatdoctorv2_datasetv2labeled.png)](https://github-public-assets.s3.us-west-1.amazonaws.com/Lynxius+Demo.mp4)
## Code Examples
Checkout our tutorials:
[Lynxius to evaluate LLM Summarization and Custom Metrics](./tutorials/AI_medical_scribe_with_UI.ipynb)
[Lynxius to evaluate LLM chatbot applications](./tutorials/ChatDoctor.ipynb)
[Lynxius to boost collaboration with Subject Matter Experts](./tutorials/Datasets.ipynb)
## Create a Development Environment
For local development, start by installing python 3.12.1, creating a virtual environment and installing the dependencies:
`bash python3.12 -m venv .lynxius-python source .lynxius-python/bin/activate pip install -r requirements.txt `
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.