You can design, evaluate, deploy, and monitor your LLM apps using an intuitive user interface and a powerful REST API. Along the way, you can easily involve your colleagues and end-users to make sure you end up with a pipeline delivering true value for your use case. Just share the link to your pipeline prototype to let others test it and give you feedback without needing to log in or set up accounts.
When your pipeline’s been tested, evaluated, and deployed, you can connect deepset Cloud to your target application using the REST API and use it wherever you need.
deepset Cloud helps you through all the steps of creating an NLP application:
- deepset Cloud offers file preprocessing nodes that you can use in your indexing pipeline to preprocess your data and prepare them for search.
- In deepset Cloud, you work with pipelines. Pipelines are made up of nodes. Each node has a different task. For example, a Retriever node retrieves the documents that best match the query. Then, you can have a Ranker node that ranks the documents by the most relevant. Then, Ranker can pass the documents on to the PromptNode that uses them to generate an answer, and so on.
The output of one node is used by another node. Nodes are like building blocks - you can mix and match different nodes or replace a node with another node to create the perfect search system.
- Use deepset Cloud experiments to collect metrics about your pipeline performance and tweak it to achieve even better results.
- Demo your app to your colleagues and let them test it, all in the deepset Cloud UI. Just share a link to your pipeline prototype. No need to create accounts or invite anyone to your deepset Cloud workspace.
You can use deepset Cloud to design your search system by combining different nodes into pipelines using an intuitive interface. Here are the most important features it offers:
- Design pipelines using Designer with a preview that helps you understand how data flows through your pipeline.
- Use Prompt Studio for prompt engineering to find the optimal setup for your use case.
- Run experiments to identify the best pipeline for your use case.
- Run searches on your file set with the pipelines you created.
- Show your work to others, let them test it, and collect their feedback.
- Deploy your pipeline and let deepset Cloud take care of all the scaling.
- Monitor your pipelines. For RAG pipelines, you can observe their groundedness using the Groundedness Observability view.
- Integrate the search in your application and deliver more relevant search results to your users.
- Interact with deepset Cloud using a powerful REST API.
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.
Haystack is deepset's open source NLP framework for creating search systems. deepset Cloud uses Haystack's nodes and methods. If you've already worked with Haystack, you can reuse this work in deepset Cloud.
The Haystack version that deepset Cloud uses is 1.24.
Updated 3 days ago