Query Collection (v1) Block (DEPRECATED)

Query the deprecated version of collections in Scout workflows

This block is for customers still using Scout’s v1 of collections.

The Collection block enables querying of a specified collection within a Scout workflow. It supports filtering, querying, and similarity-based search to retrieve relevant data from collections.

Configuration (Required)

Collection
stringRequired

The ID of the collection to query. Ensure the collection ID is correct and exists to avoid errors during execution. This field supports Jinja templating for dynamic ID construction.

limit
integer

Specifies the maximum number of documents to retrieve from the collection. The default value is 10. Adjust this setting based on the specific needs of your task or application.

minimum_similarity
float

Determines the threshold for document similarity in the retrieval process. A value closer to 1.0 requires a higher similarity between the query and the document text, while a value closer to 0.0 allows for more lenient matches. The default value is 0.5.

Filter Collection
list

Filters to apply to the collections metadata. Use appropriate filters to narrow down search results and retrieve precise data.

Query
stringRequired

The query to search for in the collection. This input supports Jinja templating, allowing for dynamic query construction based on workflow state.

See Workflow Logic & State > State Management for details on using dynamic variables in this block.

Outputs

The block outputs a list of results from the collection query, including similarity scores, text, and metadata. This structured output allows for further processing and integration within the workflow.

Usage Context

Use this block to retrieve and filter data from Scout collections by specifying a collection ID, query, and optional filters. It is ideal for workflows that require data extraction and analysis from structured collections.

Best Practices

  • Ensure the collection ID is correct and exists in the system to prevent errors during execution.
  • Use Jinja templating in the query field for dynamic query construction, enabling flexible and adaptable searches.
  • Set appropriate filters to refine search results based on metadata, improving the relevance of retrieved data.
  • Adjust minimum similarity to control the precision of similarity-based searches, tailoring the retrieval process to your specific needs.
Built with