We're hosting an Evals meetup next week (Tuesday the 16th) in SF with ragas

We'll go through the latest Evals research and general Evaluation techniques from the trenches.

Space is limited:
lu.ma/llm-evals

In RAG, generation is just as important as retrieval:

Virtual workshop coming up April 17 with Mikyo and Qdrant on LLM retrieval strategies:

arize.com/resource/llm-r…

Build and instrument a full-stack chatbot with arize-phoenix and LlamaIndex 🦙 (open-source package + create-llama for the full-stack template)

Check it out! 👇

Our team did some research on how well LLMs can analyze patterns in temporal data. If you're launching a stock picker or something that requires time series data this is a must-read:

Our Deep Dive with Arize AI is now live!

ARIZE IS EXPANDING THE FIELD OF AI OBSERVABILITY 📈

Co-founder and CPO Aparna Dhinakaran walks us through LLM observability, Phoenix, and their goals for 2024...

Link below 👇

Connor Shorten DSPy 🤝 @Weaviate • vector database 🤝 Us!

For anyone interested Phoenix is fully open source and fully private 🔐 Your data is your own!

Great work Connor Shorten ! Let us know if there is more visibility you need!

github.com/Arize-ai/phoen…

Arize AI is building a new way to evaluate and observe LLM applications with Google Cloud.

Learn how Arize AI integrates with #VertexAI to give organizations total visibility into every layer of these applications ↓

The ability of popular LLMs to adhere to instructions and deliver helpful responses can often be attributed to RLHF.

Tomorrow we'll breakdown a recent paper that discusses what's essential when it comes to reinforcement learning in the era of #LLMs

arize.com/resource/commu…

Opus Claude-3 is 🔥 (we did some tests) ⤵️

Want to learn how to read AI research papers? Check out out upcoming workshop with DeepLearning.AI

Save the date! Arize: Observe SHACK15 🥳

On July 11, hear about cutting-edge research, real-world insights from AI engineers, and useful workshops to evaluate and troubleshoot AI in production.

Calls for speakers and partners are now open: arize.com/observe-2024/

Our team ran some new evals on Gemini. More here:

Phoenix now supports DSPy! 🎉

With DSPy, you can declare the architecture of your LLM app and automatically generate prompts and fine-tune models to optimize for your specific task.

Try out the notebook: colab.research.google.com/github/Arize-a…

Omar Khattab #LLMs #AI