Welcome to the world of Lunary, an open-source tool designed to enhance observability and prompt management evaluations for large language models (LLMs). This guide will walk you through the setup process, highlight its features, and offer troubleshooting tips to ensure a smooth experience. Let’s dive in!

Key Features of Lunary

Lunary offers a plethora of features to elevate your LLM applications:

• Analytics (cost, token usage, latency)
• Monitoring (logs, traces, user tracking)
• Prompt Templates (versioning, team collaboration)
• Create fine-tuning datasets
• Chat feedback tracking
• Evaluations

Moreover, it’s designed to work with any model—not just OpenAI’s—and can be easily integrated into your existing setup in about two minutes. Plus, it’s self-hostable!

1-Minute Demo

Check out a quick demo of Lunary’s features on GitHub.

Integration Modules

Lunary offers integration modules for:

• JavaScript
• Python

It supports:

• LangChain (both JS and Python)
• OpenAI Module
• LiteLLM

You can also use Lunary with other LLMs by manually sending events.

Documentation and Support

Detailed documentation is available on the website. If you need help or have questions, feel free to chat with us or email our support team at hello@lunary.ai. We’re here to assist you!

Running Lunary Locally

Follow these steps to run Lunary on your local machine:

1. Clone the repository
2. Set up a PostgreSQL instance (version 15 minimum)
3. Copy the content of packages/backend.env.example to packages/backend.env and fill in the missing values
4. Copy the content of packages/frontend.env.example to packages/frontend.env
5. Run npm install
6. Run npm run migrate:db
7. Run npm run dev

You can now access the dashboard at http://localhost:8080. When using our JS or Python SDK, make sure to set the environment variable LUNARY_API_URL to http://localhost:3333. Use LUNARY_VERBOSE=True to view all events sent by the SDK.

Troubleshooting Tips

If you encounter issues while setting up or using Lunary, here are some troubleshooting ideas:

• Database Connection Issues: Ensure that your PostgreSQL instance is running and that you’ve correctly filled in the environment variable files.
• Environment Variable Setup: Double-check that you’ve set the LUNARY_API_URL correctly and that it’s accessible.
• Network Problems: Verify that there are no firewall settings blocking connections to the local ports used by Lunary.

For further assistance, you can always chat with us on the website or email us. For more insights, updates, or to collaborate on AI development projects, stay connected with fxis.ai.

Conclusion

At fxis.ai, we believe that such advancements are crucial for the future of AI, as they enable more comprehensive and effective solutions. Our team is continually exploring new methodologies to push the envelope in artificial intelligence, ensuring that our clients benefit from the latest technological innovations.