November 2023 Update

Hi everyone,

The most notable changes these past few weeks include:

🔍 Prompt Playground in public beta (give us feedback!)

As you may have seen, we opened asked to the Prompt Playground to all Pro and Unlimited users.

The prompt playground allows you to iterate and edit prompts you receive.

You can also play with different models (such as Anthropic's, Google's or event Mistral models) to see how different models could fit your app.

We're working on adding an History as well as even more open-source models to the playground.

If you've started using it, we'll love to get your feedback.

🔈 Support for OpenAI Devday updates

Our Python, JS & LangChain SDKs were updated to support the new tools API and our dashboard will now properly track cost for the newly released models.

We are working for support of the new Assistants API :)

🌑 Dark mode

Working late a night? The dashboard will now follow your system's settings.

💬 Automatic tokenizer for all models

Tokens will now be automatically tracked for all models. If you're using Claude or Google's models, tokens counting and cost calculation are even more precise.

🗃️ Public API & AI Evaluations in beta access

We just released the docs for the Data API which you can find here.

We'll soon add more endpoints to fetch aggregate statistics as well as data from your users. AI Evaluation is a new feature that allow you to test if prompts match certain criterias that you set, using AI.

For example, you can use evaluations to test that your prompt responds correctly in perfect JSON, or that it doesn't contain any bad word.

You can then view statistics and explore the queries that failed (or passed) your criteria.

You can also use evaluators to evaluate the sentiment of your responses, and use that as basis for fine-tuning.

🐛 Support for OpenAI streaming queries in Python & JS

We recently fixed the support for streaming queries (including cost calculation on the Python SDK). It was already working on the JavaScript SDK.

🐥 LangChain support of AWS Bedrock, Google Palm and Anthropic

We fixed support for a lot of Chat classes in LangChain.

🔗 HTTP endpoint for reporting events

If you're working in an environment where our SDKs are not available, you can now use our API endpoint to report events. You can find the docs here but they are still a work in progress.

🐛 And a lot more...

We've also fixed Bedrock and Google support with LangChain, pushed a lot of UI updates to the dashboard and improved the performance of the search and event ingestion.

In a few days we'll release better filtering to make browsing data easier.

And that's all for this month!

Thanks for being a user 🫶