Docs

Multi Corpora Query

Retrieves query results across multiple Vectara corpora.

GET

Query

Arguments
stringrequired

Question or search text to run across one or more corpora.

array of objectrequired

Array of corpus search objects with corpus_key and optional per-corpus settings.

number

Maximum number of results to retrieve before reranking.

number

Number of search results to skip.

string

Generation preset to use for grounded generation.

number

Maximum number of top search results sent to generation.

string

Language code for the generated response.

Uncommon arguments
object

Context window configuration for each search result.

object

Reranker configuration object.

string

Optional custom prompt template for generation.

object

Optional model parameter overrides for generation.

object

Citation formatting configuration.

boolean

Whether to include a factual consistency score.

boolean

Whether to stream the query response.

boolean

Whether to save this query in history.

boolean

Enable query rewriting and metadata filter extraction.

Field selectionChoose which fields should be included in the response. Learn more
string

Comma-separated response fields to include.

Every app you connect,one REST pattern

Call any app with one REST pattern. MindCloud handles each provider's auth, request shape, and responses for you.

Learn what the Universal API is
One REST patternUse the same request structure across apps like Slack, HubSpot, Salesforce, and thousands more.
Managed connectionsSend a MindCloud connection ID instead of handling provider tokens, refresh logic, and credential storage yourself.
Action-level docsEach action page shows the exact endpoint, required arguments, optional controls, and response behavior for that app version.