Gemini Interactions API Skill

export GOOGLE_GENAI_USE_ENTERPRISE=true
export GOOGLE_CLOUD_PROJECT="your-project-id"
export GOOGLE_CLOUD_LOCATION="global"

from google import genai

# The SDK automatically picks up the environment variables
client = genai.Client()

import { GoogleGenAI } from "@google/genai";

// The SDK automatically picks up the environment variables
const ai = new GoogleGenAI();

from google import genai
import google.auth

_, project_id = google.auth.default()
client = genai.Client(enterprise=True, project=project_id, location="global")

import { GoogleGenAI } from "@google/genai";

const ai = new GoogleGenAI({
    enterprise: {
        project: "your-project-id",
        location: "global"
    }
});

interaction = client.interactions.create(
    agent="your-agent-id",  # GEAP: target a provisioned agent, not a base model
    input="Explain serverless computing in one sentence."
)
# Use the output_text convenience accessor (combined text from the trailing model_output steps)
print(interaction.output_text)

const interaction = await ai.interactions.create({
    agent: "your-agent-id", // GEAP: target a provisioned agent, not a base model
    input: "Explain serverless computing in one sentence."
});
console.log(interaction.output_text);

# Turn 1: Introduce ourselves
# Interactions are stored by default (store=True); pass store=False to disable
# server-side retention (which also disables previous_interaction_id and background).
turn1 = client.interactions.create(
    agent="your-agent-id",
    input="Hi! My name is John. I am working on AI agents.",
    store=True
)
print(f"Turn 1: {turn1.output_text}")

# Turn 2: Refer back to the stored turn state
turn2 = client.interactions.create(
    agent="your-agent-id",
    input="What is my name?",
    previous_interaction_id=turn1.id
)
print(f"Turn 2: {turn2.output_text}")

// Turn 1 (interactions are stored by default; pass store: false to disable)
const turn1 = await ai.interactions.create({
    agent: "your-agent-id",
    input: "Hi! My name is John. I am working on AI agents.",
    store: true
});

// Turn 2
const turn2 = await ai.interactions.create({
    agent: "your-agent-id",
    input: "What is my name?",
    previousInteractionId: turn1.id
});
console.log(turn2.output_text);

# The stream yields typed events, not full interaction snapshots. The sequence is:
# interaction.created -> (step.start -> step.delta(s) -> step.stop)+ -> interaction.completed
for event in client.interactions.create(
    agent="your-agent-id",
    input="Write a short poem about debugging.",
    stream=True
):
    if event.event_type == "step.delta":
        if event.delta.type == "text":
            print(event.delta.text, end="", flush=True)
    elif event.event_type == "interaction.completed":
        print()

// The stream yields typed events, not full interaction snapshots. The sequence is:
// interaction.created -> (step.start -> step.delta(s) -> step.stop)+ -> interaction.completed
const responseStream = await ai.interactions.create({
    agent: "your-agent-id",
    input: "Write a short poem about debugging.",
    stream: true
});

for await (const event of responseStream) {
    if (event.event_type === "step.delta") {
        if (event.delta.type === "text") {
            process.stdout.write(event.delta.text);
        }
    } else if (event.event_type === "interaction.completed") {
        console.log();
    }
}

from pydantic import BaseModel, Field

class Book(BaseModel):
    title: str = Field(description="The title of the book")
    author: str = Field(description="The book's author")
    year_published: int

interaction = client.interactions.create(
    agent="your-agent-id",
    input="Recommend one famous sci-fi book.",
    response_format=Book
)

# The text will be a valid JSON matching the Book schema
print(interaction.output_text)

import { Type } from "@google/genai";

const BookSchema = {
    type: Type.OBJECT,
    properties: {
        title: { type: Type.STRING, description: "The title of the book" },
        author: { type: Type.STRING, description: "The book's author" },
        yearPublished: { type: Type.INTEGER }
    },
    required: ["title", "author", "yearPublished"]
};

const interaction = await ai.interactions.create({
    agent: "your-agent-id",
    input: "Recommend one famous sci-fi book.",
    responseFormat: BookSchema
});

console.log(interaction.output_text);

import json

def get_stock_price(ticker: str) -> float:
    """Gets the stock price for a given ticker symbol."""
    if ticker.upper() == "GOOG":
        return 175.50
    return 100.0

# Turn 1: Pass tools to the model
interaction = client.interactions.create(
    agent="your-agent-id",
    input="What is the stock price of GOOG?",
    tools=[get_stock_price]
)

# In the flat steps schema, a tool request is a top-level step of type
# "function_call" with flat `name` and `arguments` fields (no nested tool_calls).
for step in interaction.steps:
    if step.type == "function_call" and step.name == "get_stock_price":
        ticker_arg = step.arguments.get("ticker")
        price = get_stock_price(ticker_arg)

        # Turn 2: Submit the result back as a function_result step. Reference the
        # originating call via call_id=step.id, and pass tools again (turn-scoped).
        final_turn = client.interactions.create(
            agent="your-agent-id",
            input=[
                {
                    "type": "function_result",
                    "name": step.name,
                    "call_id": step.id,
                    "result": [{"type": "text", "text": json.dumps(price)}],
                }
            ],
            tools=[get_stock_price],
            previous_interaction_id=interaction.id
        )
        print(final_turn.output_text)

import { Type } from "@google/genai";

// Define local tool
function getStockPrice({ ticker }: { ticker: string }): number {
    if (ticker.toUpperCase() === "GOOG") {
        return 175.50;
    }
    return 100.00;
}

// Turn 1: Pass tools to the model
const toolDeclaration = {
    functionDeclarations: [{
        name: "getStockPrice",
        description: "Gets the stock price for a given ticker symbol.",
        parameters: {
            type: Type.OBJECT,
            properties: {
                ticker: { type: Type.STRING, description: "The stock ticker symbol" }
            },
            required: ["ticker"]
        }
    }]
};

const interaction = await ai.interactions.create({
    agent: "your-agent-id",
    input: "What is the stock price of GOOG?",
    tools: [toolDeclaration]
});

// In the flat steps schema, a tool request is a top-level step of type
// "function_call" with flat `name` and `arguments` fields (no nested toolCalls).
const fcStep = interaction.steps.find(s => s.type === "function_call");
if (fcStep && fcStep.name === "getStockPrice") {
    const tickerArg = fcStep.arguments.ticker as string;
    const price = getStockPrice({ ticker: tickerArg });

    // Turn 2: Submit the result back as a function_result step. Reference the
    // originating call via call_id=fcStep.id, and pass tools again (turn-scoped).
    const finalTurn = await ai.interactions.create({
        agent: "your-agent-id",
        input: [{
            type: "function_result",
            name: fcStep.name,
            call_id: fcStep.id,
            result: [{ type: "text", text: JSON.stringify(price) }]
        }],
        tools: [toolDeclaration],
        previousInteractionId: interaction.id
    });
    console.log(finalTurn.output_text);
}

POST https://aiplatform.googleapis.com/v1beta1/projects/{PROJECT_ID}/locations/{LOCATION}/interactions

AGENT_ID="your-agent-id"
ACCESS_TOKEN=$(gcloud auth print-access-token)

curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/global/interactions" \
  -H "Authorization: Bearer ${ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "'"${AGENT_ID}"'",
    "input": [{
      "type": "user_input",
      "content": [{
        "type": "text",
        "text": "Explain serverless computing in one sentence."
      }]
    }]
  }'

{
  "id": "your-interaction-id",
  "status": "completed",
  "steps": [
    {
      "type": "model_output",
      "content": [
        {
          "type": "text",
          "text": "Serverless computing is a cloud execution model where the cloud provider dynamically manages the allocation and provisioning of servers, charging customers based on actual usage rather than pre-purchased capacity."
        }
      ]
    }
  ],
  "usage": {
    "total_tokens": 24751,
    "total_input_tokens": 23894,
    "total_output_tokens": 857
  },
  "created": "2026-05-08T10:44:43Z",
  "updated": "2026-05-08T10:44:43Z",
  "environment_id": "your-environment-id",
  "object": "interaction"
}

curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/global/interactions" \
  -H "Authorization: Bearer ${ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "'"${AGENT_ID}"'",
    "store": true,
    "previous_interaction_id": "YOUR_PREVIOUS_INTERACTION_ID",
    "input": [{
      "type": "user_input",
      "content": [{
        "type": "text",
        "text": "Can you elaborate on that?"
      }]
    }]
  }'

curl -X POST "https://aiplatform.googleapis.com/v1beta1/projects/${PROJECT_ID}/locations/global/interactions" \
  -H "Authorization: Bearer ${ACCESS_TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "agent": "'"${AGENT_ID}"'",
    "stream": true,
    "input": [{
      "type": "user_input",
      "content": [{
        "type": "text",
        "text": "Write a long story about space travel."
      }]
    }]
  }'