Hegel AI (YC S23)

Open source tools for evaluating LLMs, prompts, and vector databases

[Hegel AI (YC S23) @hegel_ai]

We’re excited to announce the launch of LLM monitoring and online evaluation! This builds on our SDK for prompt and model experimentation, and our playground for team-wide LLM evaluation, to provide a way for teams to track and measure LLMs after deployment.

[Hegel AI (YC S23) @hegel_ai]

@kevinyun @davj We have TypeScript support for tracking models in prod
https://t.co/3WnkOILVeb

[Hegel AI (YC S23) @hegel_ai]

We're excited to work with @osventuresllc to make AI development easy, safe, and reliable!
https://t.co/BYOV9VO3OQ

[Hegel AI (YC S23) @hegel_ai]

What's the best language for writing an AI app backend?

#LLMs #GenerativeAI #AI

[Hegel AI (YC S23) @hegel_ai]

Check out the full release notes here: https://t.co/UGLEfdjuxH

[Hegel AI (YC S23) @hegel_ai]

PromptTools 0.0.45 officially introduces monitoring and observability to the SDK. Teams can now evaluate LLMs in both development and production with Hegel AI.

#llmops #opensource

[Hegel AI (YC S23) @hegel_ai]

Checkout this spotlight for the latest prompttools feature, OpenAI Moderation Support, available in our open-source SDK: https://t.co/SlKzNUIFHY

[Hegel AI (YC S23) @hegel_ai]

You can get started evaluating prompts right away here: https://t.co/SlKzNUIFHY

[Hegel AI (YC S23) @hegel_ai]

We’re excited to announce the launch of LLM monitoring and online evaluation! This builds on our SDK for prompt and model experimentation, and our playground for team-wide LLM evaluation, to provide a way for teams to track and measure LLMs after deployment.

[Hegel AI (YC S23) @hegel_ai]

If you want to get started logging and evaluating LLM responses from your production apps, signup at https://t.co/O8F8sBq9mk

[Hegel AI (YC S23) @hegel_ai]

If you're interested in piloting our hosted playground, reach out to [email protected], or sign up at https://t.co/NGLI5ngikH, and we'll get you onboarded

[Hegel AI (YC S23) @hegel_ai]

PromptTools release 0.0.41 is our most excited update yet!

* We've launched integrations between our SDK and hosted playground that allows developers to run, store, and share experiments
* The playground supports auto-evaluation leveraging GPT-4 for feedback
* It supports multiple modes of interaction: instruction, prompt template, model comparison, and chat message

#llmops #promptengineering #llms

[Hegel AI (YC S23) @hegel_ai]

Checkout the full release notes here: https://t.co/mavggWHqGb

[Hegel AI (YC S23) @hegel_ai]

It provides multiple interfaces for composing LLM prompts from combinations of messages, gather feedback, and share experiments with colleagues

[Hegel AI (YC S23) @hegel_ai]

We're super excited to announce the launch of our enterprise playground! It's an improvement on our open source playground that provides more features for teams to collaborate on experimentation.

[Hegel AI (YC S23) @hegel_ai]

Hegel AI's experimentation platform is now live on product hunt! We'd love it if you give us an upvote and shared the product with your network: https://t.co/EkwOHUc3tk

[Hegel AI (YC S23) @hegel_ai]

It's based on our open source SDK for running experiments, prompttools: https://t.co/SlKzNUIFHY

[Hegel AI (YC S23) @hegel_ai]

We're super excited to announce the launch of our enterprise playground! It's an improvement on our open source playground that provides more features for teams to collaborate on experimentation.

[Hegel AI (YC S23) @hegel_ai]

You can check it out and sign up here: https://t.co/p0EJO9CiiX