For each search result, there is a relevance score telling you how confident the model is about this answer. To learn more about these scores, see Relevance Scores.

Prerequisites

• If you're asking your colleague to run a search with your pipeline to test it, have a look at Guidelines for Onboarding Your Users.
• You must have a deployed pipeline.

Run a Search from the UI

1. Log in to deepset Cloud.
2. Click Search.
3. Select the pipeline and filters that you want to use.
   Note: Filters are available only if the files have metadata. You can add metadata to your files when you're uploading them. These metadata then act as filters during search.
4. Ask a question and click Search.

Answers to your query are displayed on the page. For each answer, you can open or download the document that contains it. To do that, hover over the three dots icon next to the document name.

You can also give feedback for each answer. Use the thumbs-up and thumbs-down icons. This way you can let the pipeline creator know how the pipeline's doing.

As the pipeline creator, you can then export the users' feedback to a CSV file and analyze it.