Try Gemini 1.5 Pro, our most advanced multimodal model in Vertex AI, and see what you can build with a 1M token context window. Try Gemini 1.5 Pro, our most advanced multimodal model in Vertex AI, and see what you can build with a 1M token context window.

Method: projects.conversations.create

HTTP request
Path parameters
Query parameters
Request body
Response body
Authorization scopes
Try it!

Creates a new conversation. Conversations are auto-completed after 24 hours.

Conversation Lifecycle: There are two stages during a conversation: Automated Agent Stage and Assist Stage.

For Automated Agent Stage, there will be a dialogflow agent responding to user queries.

For Assist Stage, there's no dialogflow agent responding to user queries. But we will provide suggestions which are generated from conversation.

If Conversation.conversation_profile is configured for a dialogflow agent, conversation will start from Automated Agent Stage, otherwise, it will start from Assist Stage. And during Automated Agent Stage, once an Intent with Intent.live_agent_handoff is triggered, conversation will transfer to Assist Stage.

HTTP request

POST https://{endpoint}/v2beta1/{parent=projects/*}/conversations

Where {endpoint} is one of the supported service endpoints.

The URLs use gRPC Transcoding syntax.

Path parameters

Parameters

Parameters
`parent`	`string` Required. Resource identifier of the project creating the conversation. Format: `projects/<Project ID>/locations/<Location ID>`. Authorization requires the following IAM permission on the specified resource `parent`: `dialogflow.conversations.create`

parent

string

Required. Resource identifier of the project creating the conversation. Format: projects/<Project ID>/locations/<Location ID>.

Authorization requires the following IAM permission on the specified resource parent:

dialogflow.conversations.create

Query parameters

Parameters

Parameters
`conversationId`	`string` Optional. Identifier of the conversation. Generally it's auto generated by Google. Only set it if you cannot wait for the response to return a auto-generated one to you. The conversation ID must be compliant with the regression fomula `[a-zA-Z][a-zA-Z0-9_-]*` with the characters length in range of [3,64]. If the field is provided, the caller is resposible for 1. the uniqueness of the ID, otherwise the request will be rejected. 2. the consistency for whether to use custom ID or not under a project to better ensure uniqueness.

conversationId

string

Optional. Identifier of the conversation. Generally it's auto generated by Google. Only set it if you cannot wait for the response to return a auto-generated one to you.

The conversation ID must be compliant with the regression fomula [a-zA-Z][a-zA-Z0-9_-]* with the characters length in range of [3,64]. If the field is provided, the caller is resposible for 1. the uniqueness of the ID, otherwise the request will be rejected. 2. the consistency for whether to use custom ID or not under a project to better ensure uniqueness.

Request body

The request body contains an instance of Conversation.

Response body

If successful, the response body contains a newly created instance of Conversation.

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.