RetroSearch Browse

Home - News ( United States | United Kingdom | Italy | Germany ) - Football scores

Showing content from https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/function-calling below:

Function calling reference | Generative AI on Vertex AI

Skip to main content Function calling reference

Stay organized with collections Save and categorize content based on your preferences.

Function calling improves the LLM's ability to provide relevant and contextual answers.

You can provide custom functions to a generative AI model with the Function Calling API. The model doesn't directly invoke these functions, but instead generates structured data output that specifies the function name and suggested arguments.

This output enables the calling of external APIs or information systems such as databases, customer relationship management systems, and document repositories. The resulting API output can be used by the LLM to improve response quality.

For more conceptual documentation on function calling, see Function calling.

Supported models

Gemini 2.5 Flash-Lite
Gemini 2.5 Flash with Live API native audio previewPreview
Gemini 2.0 Flash with Live API previewPreview
Vertex AI Model Optimizer scienceExperimental
Gemini 2.5 Pro
Gemini 2.5 Flash
Gemini 2.0 Flash
Gemini 2.0 Flash-Lite

Limitations:

The maximum number of function declarations that can be provided with the request is 128.

Example syntax

Syntax to send a function call API request.

curl

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \

https://${LOCATION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/publishers/google/models/${MODEL_ID}:generateContent \
-d '{
  "contents": [{
    ...
  }],
  "tools": [{
    "function_declarations": [
      {
        ...
      }
    ]
  }]
}'

Parameter list

See examples for implementation details.

FunctionDeclaration

Defines a function that the model can generate JSON inputs for based on OpenAPI 3.0 specifications.

Parameters

name

string

The name of the function to call. Must start with a letter or an underscore. Must be a-z, A-Z, 0-9, or contains underscores, dots, or dashes, with a maximum length of 64.

description

Optional: string

The description and purpose of the function. The model uses this to decide how and whether to call the function. For the best results, we recommend that you include a description.

parameters

Optional: Schema

Describes the parameters of the function in the OpenAPI JSON Schema Object format: OpenAPI 3.0 specification.

response

Optional: Schema

Describes the output from the function in the OpenAPI JSON Schema Object format: OpenAPI 3.0 specification.

For more information, see Function calling

Schema

Defines the format of the input and output data in a function call based on the OpenAPI 3.0 Schema specification.

Parameters type

string

Enum. The type of the data. Must be one of:

STRING
INTEGER
BOOLEAN
NUMBER
ARRAY
OBJECT

description

Optional: string

Description of the data.

enum

Optional: string[]

Possible values of the element of primitive type with enum format.

items

Optional: Schema[]

Schema of the elements of Type.ARRAY

properties

Optional: Schema

Schema of the properties of Type.OBJECT

required

Optional: string[]

Required properties of Type.OBJECT.

nullable

Optional: bool

Indicates if the value may be null.

FunctionCallingConfig

The FunctionCallingConfig controls the behavior of the model and determines what type of function to call.

Parameters

mode

Optional: enum/string[]

AUTO: Default model behavior. The model can make predictions in either a function call form or a natural language response form. The model decides which form to use based on the context.
NONE: The model doesn't make any predictions in the form of function calls.
ANY: The model is constrained to always predict a function call. If allowed_function_names is not provided, the model picks from all of the available function declarations. If allowed_function_names is provided, the model picks from the set of allowed functions.

allowed_function_names

Optional: string[]

Function names to call. Only set when the mode is ANY. Function names should match [FunctionDeclaration.name]. With mode set to ANY, the model will predict a function call from the set of function names provided.

functionCall

A predicted functionCall returned from the model that contains a string representing the functionDeclaration.name and a structured JSON object containing the parameters and their values.

Parameters

name

string

The name of the function to call.

args

Struct

The function parameters and values in JSON object format.

See Function calling for parameter details.

functionResponse

The resulting output from a FunctionCall that contains a string representing the FunctionDeclaration.name. Also contains a structured JSON object with the output from the function (and uses it as context for the model). This should contain the result of a FunctionCall made based on model prediction.

Parameters

name

string

The name of the function to call.

response

Struct

The function response in JSON object format.

Examples Send a function declaration

The following example is a basic example of sending a query and a function declaration to the model.

REST

Before using any of the request data, make the following replacements:

PROJECT_ID: Your project ID.
MODEL_ID: The ID of the model that's being processed.
ROLE: The identity of the entity that creates the message.
TEXT: The prompt to send to the model.
NAME: The name of the function to call.
DESCRIPTION: Description and purpose of the function.
For other fields, see the Parameter list table.

HTTP method and URL:

POST https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/google/models/MODEL_ID:generateContent

Request JSON body:

{
  "contents": [{
    "role": "ROLE",
    "parts": [{
      "text": "TEXT"
    }]
  }],
  "tools": [{
    "function_declarations": [
      {
        "name": "NAME",
        "description": "DESCRIPTION",
        "parameters": {
          "type": "TYPE",
          "properties": {
            "location": {
              "type": "TYPE",
              "description": "DESCRIPTION"
            }
          },
          "required": [
            "location"
          ]
        }
      }
    ]
  }]
}

To send your request, choose one of these options:

curl Note: The following command assumes that you have logged in to the gcloud CLI with your user account by running gcloud init or gcloud auth login , or by using Cloud Shell, which automatically logs you into the gcloud CLI . You can check the currently active account by running gcloud auth list.

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/google/models/MODEL_ID:generateContent"

PowerShell Note: The following command assumes that you have logged in to the gcloud CLI with your user account by running gcloud init or gcloud auth login . You can check the currently active account by running gcloud auth list.

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `

-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://aiplatform.googleapis.com/v1/projects/PROJECT_ID/locations/global/publishers/google/models/MODEL_ID:generateContent" | Select-Object -Expand Content

Example curl command

PROJECT_ID=myproject
LOCATION=us-central1
MODEL_ID=gemini-2.5-flash

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://${LOCATION}-aiplatform.googleapis.com/v1/projects/${PROJECT_ID}/locations/${LOCATION}/publishers/google/models/${MODEL_ID}:generateContent \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [{
        "text": "What is the weather in Boston?"
      }]
    }],
    "tools": [{
      "functionDeclarations": [
        {
          "name": "get_current_weather",
          "description": "Get the current weather in a given location",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {
                "type": "string",
                "description": "The city and state, e.g. San Francisco, CA or a zip code e.g. 95616"
              }
            },
            "required": [
              "location"
            ]
          }
        }
      ]
    }]
  }'

Gen AI SDK for Python Node.js Java Go REST (OpenAI)

You can call the Function Calling API by using the OpenAI library. For more information, see Call Vertex AI models by using the OpenAI library.

Before using any of the request data, make the following replacements:

PROJECT_ID: .
MODEL_ID: The ID of the model that's being processed.

HTTP method and URL:

POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/endpoints/openapi/chat/completions

Request JSON body:

{
  "model": "google/MODEL_ID",
  "messages": [
    {
      "role": "user",
      "content": "What is the weather in Boston?"
    }
  ],
  "tools": [
    {
      "type": "function",
      "function": {
        "name": "get_current_weather",
        "description": "Get the current weather in a given location",
        "parameters": {
          "type": "OBJECT",
          "properties": {
            "location": {
              "type": "string",
              "description": "The city and state, e.g. San Francisco, CA or a zip code e.g. 95616"
            }
           },
          "required": ["location"]
        }
      }
    }
  ]
}

To send your request, choose one of these options:

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/endpoints/openapi/chat/completions"

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `

-Method POST `
-Headers $headers `
-ContentType: "application/json; charset=utf-8" `
-InFile request.json `
-Uri "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/endpoints/openapi/chat/completions" | Select-Object -Expand Content

Python (OpenAI)

You can call the Function Calling API by using the OpenAI library. For more information, see Call Vertex AI models by using the OpenAI library.

Send a function declaration with FunctionCallingConfig

The following example demonstrates how to pass a FunctionCallingConfig to the model.

The functionCallingConfig ensures that the model output is always a specific function call. To configure:

Set the function calling mode to ANY.
Specify the function names that you want to use in allowed_function_names. If allowed_function_names is empty, any of the provided functions can be returned.

REST

PROJECT_ID=myproject
LOCATION=us-central1
MODEL_ID=gemini-2.5-flash

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  https://${LOCATION}-aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/${LOCATION}/publishers/google/models/${MODEL_ID}:generateContent \
  -d '{
    "contents": [{
      "role": "user",
      "parts": [{
        "text": "Do you have the White Pixel 8 Pro 128GB in stock in the US?"
      }]
    }],
    "tools": [{
      "functionDeclarations": [
        {
          "name": "get_product_sku",
          "description": "Get the available inventory for a Google products, e.g: Pixel phones, Pixel Watches, Google Home etc",
          "parameters": {
            "type": "object",
            "properties": {
              "product_name": {"type": "string", "description": "Product name"}
            }
          }
        },
        {
          "name": "get_store_location",
          "description": "Get the location of the closest store",
          "parameters": {
            "type": "object",
            "properties": {
              "location": {"type": "string", "description": "Location"}
            },
          }
        }
      ]
    }],
    "toolConfig": {
        "functionCallingConfig": {
            "mode":"ANY",
            "allowedFunctionNames": ["get_product_sku"]
      }
    },
    "generationConfig": {
      "temperature": 0.95,
      "topP": 1.0,
      "maxOutputTokens": 8192
    }
  }'

Gen AI SDK for Python Node.js Go REST (OpenAI)

You can call the Function Calling API by using the OpenAI library. For more information, see Call Vertex AI models by using the OpenAI library.

Before using any of the request data, make the following replacements:

PROJECT_ID: .
MODEL_ID: The ID of the model that's being processed.

HTTP method and URL:

POST https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/endpoints/openapi/chat/completions

Request JSON body:

{
  "model": "google/MODEL_ID",
  "messages": [
  {
    "role": "user",
    "content": "What is the weather in Boston?"
  }
],
"tools": [
  {
    "type": "function",
    "function": {
      "name": "get_current_weather",
      "description": "Get the current weather in a given location",
      "parameters": {
        "type": "OBJECT",
        "properties": {
          "location": {
            "type": "string",
            "description": "The city and state, e.g. San Francisco, CA or a zip code e.g. 95616"
          }
         },
        "required": ["location"]
      }
    }
  }
],
"tool_choice": "auto"
}

To send your request, choose one of these options:

Save the request body in a file named request.json, and execute the following command:

curl -X POST \
     -H "Authorization: Bearer $(gcloud auth print-access-token)" \
     -H "Content-Type: application/json; charset=utf-8" \
     -d @request.json \
     "https://aiplatform.googleapis.com/v1beta1/projects/PROJECT_ID/locations/global/endpoints/openapi/chat/completions"

Save the request body in a file named request.json, and execute the following command:

$cred = gcloud auth print-access-token
$headers = @{ "Authorization" = "Bearer $cred" }

Invoke-WebRequest `

Python (OpenAI)

You can call the Function Calling API by using the OpenAI library. For more information, see Call Vertex AI models by using the OpenAI library.

What's next

For detailed documentation, see the following:

Function calling

Except as otherwise noted, the content of this page is licensed under the Creative Commons Attribution 4.0 License, and code samples are licensed under the Apache 2.0 License. For details, see the Google Developers Site Policies. Java is a registered trademark of Oracle and/or its affiliates.

Last updated 2025-08-15 UTC.

[[["Easy to understand","easyToUnderstand","thumb-up"],["Solved my problem","solvedMyProblem","thumb-up"],["Other","otherUp","thumb-up"]],[["Hard to understand","hardToUnderstand","thumb-down"],["Incorrect information or sample code","incorrectInformationOrSampleCode","thumb-down"],["Missing the information/samples I need","missingTheInformationSamplesINeed","thumb-down"],["Other","otherDown","thumb-down"]],["Last updated 2025-08-15 UTC."],[],[]]

RetroSearch is an open source project built by @garambo | Open a GitHub Issue

Search and Browse the WWW like it's 1997 | Search results from DuckDuckGo

HTML: 3.2 | Encoding: UTF-8 | Version: 0.7.4