About This Task

We recommend setting the pipeline you plan to use in your app to the Production service level. This ensures the scalability and reliability of the pipeline in production use cases. For more information, see Pipeline Service Levels.

Use the Search Endpoint in Your App

First, generate an API key and save it.

The easiest way is to start with the API Reference documentation. Follow this step-by-step walkthrough of the code:

Or follow these steps:

1. Go to the Search documentation page.
2. Enter the necessary parameters:
   • Type the name of the pipeline to use for the search.
   • Type the name of the workspace containing the pipeline you want to use in your target app.
   • Optionally, add filters. (You can use metadata from your documents as filters to narrow down the search. For more information, see Add Search Filters.)
   • Optionally, add any runtime parameters for the pipeline nodes.
   • Type the queries.
   • In the Bearer field, paste the API key you previously generated.
3. Choose the programming language that you want to use and copy the code.

You can then wrap this code in a function and modify it as needed.

Set Default Pipeline

Consider setting the default pipeline for your app. Use the Set Default Pipeline API endpoint to route all traffic to the pipeline you indicated as default. This way, when you find that you need to tweak or change your pipeline, you can do so without any downtime. Just indicate the new default pipeline and all traffic will be seamlessly routed to this pipeline, without your users ever noticing.

Format Your Search Results

For question answering pipelines, you can highlight the answer in the document, which makes it much easier for the users to spot it. Here is an example of what it looks like:

The response for a question answering pipeline contains the exact position of the answer both in the document (offsets_in_document) and in the context (offsets_in_context). You can use it to format how the answers are displayed.

For more information on the answer and document elements, see Haystack documentation for Answer and Document.

Pipelines on Standby

Unused pipelines go on standby after 12 hours or 30 days to save resources. The time to standby depends on the pipeline service level. Pipelines on standby get automatically activated if you start searching with them, or you can trigger it manually on the Pipelines page. When a pipeline is on standby, your data remains perfectly safe and accessible at any time. For more information, see Production and Development Pipelines.