Tutorial: Building Your First Document Search App

This tutorial teaches you how to build a document search system in the easiest and fastest possible way. It uses the UI for uploading the sample files and a template for creating the document retrieval pipeline.

  • Level: Beginner
  • Time to complete: 10 minutes
  • Prerequisites:
    • This tutorial assumes a basic knowledge of language models.
    • You must be an Admin to complete this tutorial.
    • Make sure you have a deepset Cloud workspace where the information retrieval pipeline will run.
  • Goal: After completing this tutorial, you will have built a complete English document retrieval system from scratch that can fetch NHS documents.

Upload Files

First, let's get the files the search will run on into deepset Cloud.

  1. Download the .zip file from gdrive and unzip it to a location on your computer.

  2. Log in to deepset Cloud, switch to the right workspace, and go to Files.

    The left navigation with step one on the workspace name and step two on the Files option.
  3. Click Upload Files, drag the files you unpacked in step 1, and drop them to the Upload Files window. (You must select all files in a folder; deepset Cloud doesn't support uploading folders.)

  4. Click Upload and wait until the upload finishes. Even when the upload is finished, the files may take a while to show up in deepset Cloud. That's expected; just wait a while and refresh the page if needed.

Result: Your files have been uploaded and are shown on the Files page. You should have 953 files.

The Files page with the NHS files uploaded.

Create a Pipeline

The next step is to define the components of your search app. We'll use a document search pipeline template with a vector retriever to create the pipeline.

  1. Go to Pipeline Templates.

  2. Choose Document Search as the category, find Semantic Document Search, and click Use Template.

Screenshot displaying a section of 'Document Search' from a webpage offering pipeline templates for professional use. There are four templates listed, with two detailed descriptions visible: 'Date-Driven Hybrid Document Search' and 'Hybrid Document Search (German)', both described as pipelines that combine keyword-matching and semantic searches to return relevant documents. The sidebar on the left highlights 'Document Search' with a red notification bubble indicating '11'. Each template listing has options to 'View Details' or 'Use Template', and the latter is accompanied by a red notification bubble with the number '2'. The page features a clean interface with a color scheme of gray, red, and blue elements.
  1. Type NHS_doc_search as the pipeline name and click Create Pipeline. You're redirected to Pipeline Builder.

  2. Click Deploy . This triggers indexing and prepares your pipeline for search.

    The Deploy button in Studio highlighted
  3. Wait until the status of your pipeline changes to Indexed. This can take a couple of minutes.
    Tip: When you hover your mouse over the status, you can see the number of files already indexed.

    A mouse over the indexing status and a popup window called File Indexing Status with the count of files per each of these statuses: Pending tasks, Indexed, Skipped, Failed, Total

Result: You created and deployed a pipeline, which means your documents have been indexed, and you can now run a search. Your pipeline status is Indexed.
Your pipeline is at the development service level. We recommend you test it before setting it to the production service level.

The Pipelines page with the NHS doc retrieval pipeline shown as indexed and deployed

Try Your Pipeline

Let's see what the pipeline can do.

  1. Go to Playground.
  2. Choose NHS_doc_search as the pipeline.
  3. Type "How do I treat atopic skin?" and search for relevant documents. You should get several documents sorted by the most relevant ones.

Result: Congratulations! You have built a search system that can retrieve documents related to health. You can now ask health-related queries, and it will find relevant documents.

What's Next

Your pipeline is now a development pipeline. Once it's ready for production, change its service level to Production. You can do this on the Pipeline Details page shown after clicking a pipeline name. To learn more, see Pipeline Service Levels.