Prompt Hub

Manage, iterate, and deploy your prompts in one place

As teams grow in size, it becomes tricky for subject matter experts who are not developers to help with prompt development. Prompt Hub is a centralized repository for teams to manage, iterate, and deploy prompt templates. It's a collaborative workspace to version control templates and use them across playground, tasks, APIs, and experiments.

Access our Prompt Hub API reference here

Key features

1. Version control your templates to track updates and revert when needed

2. Save templates directly from prompt playground, including LLM parameters, messages, tools, and metadata.

3. Access templates via API

4. Evaluate results versioned by prompt template

Save new prompts

Any playground template can be saved to the Prompt Hub. The Prompt Hub stores the template along with LLM parameters, function definitions, and other metadata necessary to reproduce the LLM call.

User provides a unique Prompt Name, description, version description, and tags, which will be saved as metadata associated with the prompt in the Prompt Hub.

The Prompt Hub listing page displays all prompts saved in the space. Users can search for prompts by name using the search bar and sort them by criteria such as 'Last Updated' or 'Name' for easy navigation.

By clicking on a specific prompt, the user can view its metadata, version history, and the associated prompt template and LLM parameters for the selected version.

Load prompts in prompt hub to playground

A saved prompt can be loaded into the Prompt Playground for iteration. This can be done directly from the prompt version view, the Prompt Hub listing page, or within the Prompt Playground itself.

User selects 'Edit in Prompt Playground' to load Version 2 of the RAG Prompt w/out Hallucinations into the Prompt Playground.

User selects the play button to load the latest version of the prompt into the playground.

User selects 'Load Prompt' to load a prompt name and version into the playground.

Edit prompts and create new versions

Once the prompt is loaded into the Prompt Playground, you can freely make changes and test the updated template on a dataset. You can modify the system template is modified to instruct the LLM to provide concise, one-sentence responses. Instead of creating a new prompt, the user updates the version of the existing prompt directly, preserving the connection to the original template from the Prompt Hub.

Save changes as a new prompt or creating a new version of an existing prompt

Provide a description of their changes to track context across changes

Learn more