Method: projects.locations.dataStores.conversations.converse

Converses a conversation.

HTTP request

POST https://discoveryengine.googleapis.com/v1/{name=projects/*/locations/*/dataStores/*/conversations/*}:converse

The URL uses gRPC Transcoding syntax.

Path parameters

Parameters
name

string

Required. The resource name of the Conversation to get. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStoreId}/conversations/{conversationId}. Use projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStoreId}/conversations/- to activate auto session mode, which automatically creates a new conversation inside a conversations.converse session.

Request body

The request body contains data with the following structure:

JSON representation
{
  "query": {
    object (TextInput)
  },
  "servingConfig": string,
  "conversation": {
    object (Conversation)
  },
  "safeSearch": boolean,
  "userLabels": {
    string: string,
    ...
  },
  "summarySpec": {
    object (SummarySpec)
  },
  "filter": string,
  "boostSpec": {
    object (BoostSpec)
  }
}
Fields
query

object (TextInput)

Required. Current user input.

servingConfig

string

The resource name of the Serving Config to use. Format: projects/{project}/locations/{location}/collections/{collection}/dataStores/{dataStoreId}/servingConfigs/{servingConfigId} If this is not set, the default serving config will be used.

conversation

object (Conversation)

The conversation to be used by auto session only. The name field will be ignored as we automatically assign new name for the conversation in auto session.

userLabels

map (key: string, value: string)

The user labels applied to a resource must meet the following requirements:

  • Each resource can have multiple labels, up to a maximum of 64.
  • Each label must be a key-value pair.
  • Keys have a minimum length of 1 character and a maximum length of 63 characters and cannot be empty. Values can be empty and have a maximum length of 63 characters.
  • Keys and values can contain only lowercase letters, numeric characters, underscores, and dashes. All characters must use UTF-8 encoding, and international characters are allowed.
  • The key portion of a label must be unique. However, you can use the same key with multiple resources.
  • Keys must start with a lowercase letter or international character.

See Google Cloud Document for more details.

summarySpec

object (SummarySpec)

A specification for configuring the summary returned in the response.

filter

string

The filter syntax consists of an expression language for constructing a predicate from one or more fields of the documents being filtered. Filter expression is case-sensitive. This will be used to filter search results which may affect the summary response.

If this field is unrecognizable, an INVALID_ARGUMENT is returned.

Filtering in Vertex AI Search is done by mapping the LHS filter key to a key property defined in the Vertex AI Search backend -- this mapping is defined by the customer in their schema. For example a media customer might have a field 'name' in their schema. In this case the filter would look like this: filter --> name:'ANY("king kong")'

For more information about filtering including syntax and filter operators, see Filter

boostSpec

object (BoostSpec)

Boost specification to boost certain documents in search results which may affect the converse response. For more information on boosting, see Boosting

Response body

If successful, the response body contains an instance of ConverseConversationResponse.

Authorization scopes

Requires the following OAuth scope:

  • https://www.googleapis.com/auth/cloud-platform

For more information, see the Authentication Overview.

IAM Permissions

Requires the following IAM permission on the name resource:

  • discoveryengine.conversations.converse

For more information, see the IAM documentation.