LaVague Weekly Update #5

Welcome to our fifth weekly dev update.

Here's what we got up to last week:

• 📊 The Evaluator module was launched for easy benchmarking of LLMs and retrievers. Find out how to use it do your own benchmarks here.
• 🌊 We held a webinar on the Navigation Engine which you can watch here.
• 📑 We continued to add content to our docs.

🏆 Community Pull Requests merged:

• A LocalLogger module was added which allows you to log to a local file.
• Methods to return the nodes retrieved during the last agentic run were added to the Agent module.
• Caching for API calls was added.

For more issues you can contribute to, you can see the full list of our help wanted GitHub issues here - but below, you can see a few of the tasks we'd love your help on.

📢 Help wanted:

• Start using our evaluation module with different models and configurations and share your results with us on Discord.
• Add tracking of token usage.
• Help us add different export options for the code generated by the LLM.

Coming soon:

• 🌐 A LaVague browser extension.
• 🔒 Safeguards to avoid arbitrary code execution and ensure only certain actions can be executed.
• 🐞 An end-to-end debugging guide in the docs.
• 🌴 Exploration of leveraging.

Thanks for continuing to follow our journey!