Data Processing

• Preprocess your data using out-of-the-box components that can handle different file types. For more information, see Converters and PreProcessing Data with Pipeline Components.
• Process your files using services from:
  • Azure Document Intelligence
  • Unstructured
  • DeepL

For more information, see Using Hosted Models and External Services.

Data Sources

Use your own OpenSearch cluster, S3 bucket, or Snowflake database to store the data your deepset Cloud pipelines run on. For more information, see Setting Up Your VPC and Use Snowflake Database.

Visual Editor for Building AI-Powered Apps

Create powerful and highly flexible pipelines to power your AI apps using Studio, an intuitive visual editor.

• Drag and drop pipeline components onto the canvas to visualize and configure your pipeline.
• Choose your pipeline building blocks from an extensive library of pre-built components.
• Switch between visual editing and YAML code with real-time synchronization.

To learn more, see Create a Pipeline in Studio.

Pipeline Templates

Create an app in no time with ready-made templates that cover numerous use cases. Our templates are tested and curated, and they work out of the box. For a list of available templates with explanations, see Pipeline Templates.

Prompt Engineering

• Test and edit your prompts in Prompt Studio, or use prompt templates curated by deepset.
• Save your prompts to use later or update them in your pipelines directly from Prompt Studio.
• Compare prompts across up to three pipelines.

For details, see Engineering Prompts.

Model Agnostic

Easily swap LLMs thanks to deepset Cloud's model agnostic approach. Currently supported models are:

• Cohere command family of models
• Google AI Gemini models
• OpenAI models starting with GPT-3.5-turbo and later.
• Models hosted on:
  • Amazon Bedrock
    No need for a Bedrock account; you can use models hosted there through deepset's account. See Use Amazon Bedrock and SageMaker Models.
  • Amazon SageMaker
  • Azure
  • Hugging Face
  • NVIDIA
  • VoyageAI

For details, see Using Hosted Models and External Services.

Batch Question Answering

Use the Jobs functionality to seamlessly gather consistent information across your datasets. With Jobs, you can:

• Process queries in bulk.
• Run your query set once on all your files or repeat the queries per individual file.
• Easily format the results and share them with anyone without the need to log in.

Shareable Pipeline Prototypes

Show your prototypes to others, let them test, and collect their feedback. Customize prototypes with your brand colors and logos and share them with anyone without needing to set up accounts or log in. For details, see Share a Pipeline Prototype.

Collect feedback from users using our extensive feedback feature that makes it possible to collect, group, and analyze feedback items. See Collect User Feedback.

Before sharing your prototype, you can easily test it using the Playground. To read more, see Testing Your Pipeline.

Dependable Infrastructure

• Deploy your pipeline and let deepset Cloud take care of all the scaling.
• Indicate which pipelines are in production and which are in development to ensure they meet the requirement of reliability and resources. See also Pipeline Service Levels.

Monitoring

Monitor the groundedness of your RAG pipelines and analyze the referenced documents. For details, see Check the Groundedness Score.

REST API

Interact with deepset Cloud using a powerful REST API. Plug deepset Cloud pipelines into your interface to use them in your apps.

And More..

Have a look at our video for an overview of what you can do with deepset Cloud:

For licensing information about third-party software used in deepset Cloud, see Third-Party Software.