Get answers for the given query based on knowledge documents.
HTTP request
POST https://{endpoint}/v2/{parent=projects/*/locations/*}/suggestions:searchKnowledge
Where {endpoint}
is one of the supported service endpoints.
The URLs use gRPC Transcoding syntax.
Path parameters
Parameters | |
---|---|
parent |
Required. The parent resource contains the conversation profile Format: 'projects/ |
Request body
The request body contains data with the following structure:
JSON representation |
---|
{ "query": { object ( |
Fields | |
---|---|
query |
Required. The natural language text query for knowledge search. |
conversation |
Required. The conversation profile used to configure the search. Format: |
session |
Required. The ID of the search session. The sessionId can be combined with Dialogflow V3 Agent ID retrieved from conversation profile or on its own to identify a search session. The search history of the same session will impact the search result. It's up to the API caller to choose an appropriate |
conversation |
Optional. The conversation (between human agent and end user) where the search request is triggered. Format: |
latest |
Optional. The name of the latest conversation message when the request is triggered. Format: |
query |
Optional. The source of the query in the request. |
end |
Optional. Information about the end-user to improve the relevance and accuracy of generative answers. This will be interpreted and used by a language model, so, for good results, the data should be self-descriptive, and in a simple structure. Example:
|
search |
Optional. Configuration specific to search queries with data stores. |
exact |
Optional. Whether to search the query exactly without query rewrite. |
Response body
If successful, the response body contains an instance of SearchKnowledgeResponse
.
Authorization scopes
Requires one of the following OAuth scopes:
https://www.googleapis.com/auth/cloud-platform
https://www.googleapis.com/auth/dialogflow
For more information, see the Authentication Overview.