### Discussion Implement new tools to use Grounding with Google Maps, similar to how Grounding with Google Search works. ### Testing Integration tests. Unit tests. Node standalone app. Updated Quickstart React-based app (not part of this PR). ### API Changes - Grounding with Google Maps support, see internal doc: go/fal-maps-grounding-api - TemplateToolConfig, see internal doc: go/firebase-ai-server-prompt-template
6.9 KiB
Project: /docs/reference/js/_project.yaml Book: /docs/reference/_book.yaml page_type: reference
{% comment %} DO NOT EDIT THIS FILE! This is generated by the JS SDK team, and any local changes will be overwritten. Changes should be made in the source code at https://github.com/firebase/firebase-js-sdk {% endcomment %}
TemplateGenerativeModel class
This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.
GenerativeModel APIs that execute on a server-side template.
This class should only be instantiated with getTemplateGenerativeModel().
Signature:
export declare class TemplateGenerativeModel
Constructors
| Constructor | Modifiers | Description |
|---|---|---|
| (constructor)(ai, requestOptions) | (Public Preview) Constructs a new instance of the TemplateGenerativeModel class |
Properties
| Property | Modifiers | Type | Description |
|---|---|---|---|
| requestOptions | RequestOptions | (Public Preview) Additional options to use when making requests. |
Methods
| Method | Modifiers | Description |
|---|---|---|
| generateContent(templateId, templateVariables, singleRequestOptions, templateToolConfig) | (Public Preview) Makes a single non-streaming call to the model and returns an object containing a single GenerateContentResponse. | |
| generateContentStream(templateId, templateVariables, singleRequestOptions, templateToolConfig) | (Public Preview) Makes a single streaming call to the model and returns an object containing an iterable stream that iterates over all chunks in the streaming response as well as a promise that returns the final aggregated response. | |
| startChat(params) | (Public Preview) Starts a TemplateChatSession that will use this template to respond to messages. |
TemplateGenerativeModel.(constructor)
This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.
Constructs a new instance of the TemplateGenerativeModel class
Signature:
constructor(ai: AI, requestOptions?: RequestOptions);
Parameters
| Parameter | Type | Description |
|---|---|---|
| ai | AI | |
| requestOptions | RequestOptions |
TemplateGenerativeModel.requestOptions
This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.
Additional options to use when making requests.
Signature:
requestOptions?: RequestOptions;
TemplateGenerativeModel.generateContent()
This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.
Makes a single non-streaming call to the model and returns an object containing a single GenerateContentResponse.
Signature:
generateContent(templateId: string, templateVariables: Record<string, unknown>, singleRequestOptions?: SingleRequestOptions, templateToolConfig?: TemplateToolConfig): Promise<GenerateContentResult>;
Parameters
| Parameter | Type | Description |
|---|---|---|
| templateId | string | The ID of the server-side template to execute. |
| templateVariables | Record<string, unknown> | A key-value map of variables to populate the template with. |
| singleRequestOptions | SingleRequestOptions | Optional. Options to use for this request. |
| templateToolConfig | TemplateToolConfig | Optional. Configuration for tools to use with this request. |
Returns:
Promise<GenerateContentResult>
TemplateGenerativeModel.generateContentStream()
This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.
Makes a single streaming call to the model and returns an object containing an iterable stream that iterates over all chunks in the streaming response as well as a promise that returns the final aggregated response.
Signature:
generateContentStream(templateId: string, templateVariables: Record<string, unknown>, singleRequestOptions?: SingleRequestOptions, templateToolConfig?: TemplateToolConfig): Promise<GenerateContentStreamResult>;
Parameters
| Parameter | Type | Description |
|---|---|---|
| templateId | string | The ID of the server-side template to execute. |
| templateVariables | Record<string, unknown> | A key-value map of variables to populate the template with. |
| singleRequestOptions | SingleRequestOptions | Optional.Options to use for this request. |
| templateToolConfig | TemplateToolConfig | Optional. Configuration for tools to use with this request. |
Returns:
Promise<GenerateContentStreamResult>
TemplateGenerativeModel.startChat()
This API is provided as a preview for developers and may change based on feedback that we receive. Do not use this API in a production environment.
Starts a TemplateChatSession that will use this template to respond to messages.
Signature:
startChat(params: StartTemplateChatParams): TemplateChatSession;
Parameters
| Parameter | Type | Description |
|---|---|---|
| params | StartTemplateChatParams | Configurations for the chat, including the template ID and input variables. |
Returns: