Working in deepset AI Platform

In deepset AI Platform, you work within workspaces where you keep your data and pipelines. You can have multiple workspaces, each with different content. There are three interfaces (GUI, API, and SDK) you can use to interact with deepset AI Platform, depending on what's most convenient to you.

Workspaces

In deepset AI Platform, you work within organizations to which you were invited. Each organization may have multiple workspaces with different data. Each workspace keeps its content separate and doesn't share it with other workspaces.

Pipelines, indexes, files, and jobs are specific to a workspace. When you delete a workspace, all these data are deleted as well.

When you create a workspace, only you, as the creator and the Admin users in the organization, have access to it. To permit other users to access your workspaces, you must grant them access. For details, see Manage User Access.

After logging in, you land on the Home page, where you can view your workspace statistics, the number of searches run last week, and the details of the last five searches. These include the top answer (the answer with the highest relevance score) and the top file (the file containing the top answer). The search time is in seconds.

You can quickly switch between workspaces. Just click the workspace name and choose the one you want to switch to.

Navigation

Here's an explanation of what each navigation item does:

Navigation Step	Action
Workspace name	Switch between workspaces Create a workspace (just type the name of the new workspace). You can create up to 100 workspaces. After creating a workspace, only the workspace creator and Admin users in the organization can access it. Grant access to other users if you want them to use your workspace.
Home	Access the guided workflow to create a pipeline. Check your workspace statistics, like the number of files or latest searches.
Files	Upload files. These are the files your pipeline uses for search. Manage existing files (view, delete, preview, filter by metadata).
Indexes	Create indexes. Manage existing indexes: enable, disable, view details. Click an index name to view its details, the query pipelines using it, and logs.
Pipeline Templates	Choose a template. View templates.
Pipelines	Create pipelines. Manage existing pipelines organized by their service level (deploy, undeploy, edit, view pipeline details, share pipelines, check groundedness, and export user feedback). Click the name of a pipeline to check its details, such as feedback, queries, observability dashboard, logs, and so on.
Jobs	Schedule jobs to run asynchronously. Currently, you can run batch question answering across the filest in the workspace.
Playground	Test your pipelines.
Prompt Explorer	Engineer your prompts, try out different prompts, and compare them across up to three pipelines. Choose a prompt from a library of curated prompts.
Groundedness	Check how well your RAG system is grounded in your documents.

Profile Settings

Clicking your initials in the top right corner opens a menu with additional settings. This table explains what each menu item does.

Menu Item	Action
Personal Details	View your profile details, such as name, last name, and role.
Organization	View the organizations you have access to. Switch between organizations. View and invite users to your organizations.
Workspaces	View workspaces in an organization. Manage access to workspaces: add and delete users. Add workspaces. Delete workspaces.
Connections	Connect deepset AI Platform to service and model providers. Once you establish a connection, you don't need to pass any API keys in your pipelines when using models or services from the connected providers. Add and delete API keys.
Secrets	Add and delete secrets to connect to providers and services not listed on the Connections page. To learn more, see Add Secrets to Connect to Third Party Providers.
Usage	Check your usage of the platform. Check pipelines hours used in the current usage cycle. View pipelines by hours used and service level.

Three Interfaces

You can work in deepset AI Platform through one of these interfaces:

An intuitive, user-friendly graphical user interface, where you can see real-life updates and get immediate feedback on your actions.
REST API for a platform-independent way to communicate with deepset AI Platform. It supports all the tasks available in GUI.
An open source SDK package you can customize. Currently, it contains methods for efficient file operations, such as upload or listing.

Updated about 9 hours ago