Search - Upstash Documentation

Search Command for Python SDK

The search method is designed to retrieve the most relevant documents from the database, using AI-powered search capabilities.

For more details on how the search algorithm works, please refer to our advanced settings documentation.

Arguments

Payloaddictrequired

querystringrequired

The search query string.

limitintrequired

The maximum number of results to return. Defaults to 10.

rerankingbool

Whether to enable AI-powered reranking of results. Disabled by default.

filterstring

A filter for narrowing down the search results based on content fields.

semantic_weightnumber

Optional relevance balance between semantic and keyword search (0-1 range, defaults to 0.75). For instance, 0.2 applies 20% semantic matching with 80% full-text matching. You can learn more about how Upstash Search works from our docs.

input_enrichmentboolean

Optional boolean to enhance queries before searching (enabled by default).

Response

DocumentsList[DocumentScore]required

This field is null if no document with the specified ID is found.

idstring | numberrequired

The ID of the resulting document.

contentRecord<string, unknown>

The main content of the document.

metadataRecord<string, unknown>

Additional metadata for the document.

scorefloatrequired

Similarity score of the document

Basic Search

results = index.search(    query="space opera",    limit=2)print(results)

Search with Reranking

results = index.search(    query="space opera",    limit=2,    reranking=True)print(results)

Search with Filter

results = index.search(    query="space",     limit=2,     filter="category = 'classic'")print(results)