Google AI for Developers

curl -X POST https://generativelanguage.googleapis.com/v1beta/interactions \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gemini-flash-latest",
    "input": [
      {
        "type": "text",
        "text": "What is in this picture?"
      },
      {
        "type": "image",
        "data": "BASE64_ENCODED_IMAGE",
        "mime_type": "image/png"
      }
    ]
  }'

from google import genai

client = genai.Client()
response = client.interactions.create(
    model="gemini-flash-latest",
    input=[
        {"type": "text", "text": "What is in this picture?"},
        {
            "type": "image",
            "data": "BASE64_ENCODED_IMAGE",
            "mime_type": "image/png",
        },
    ],
)
print(response.output_text)

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

const ai = new GoogleGenAI({});
const interaction = await ai.interactions.create({
  model: 'gemini-flash-latest',
  input: [
    {type: 'text', text: 'What is in this picture?'},
    {type: 'image', data: 'BASE64_ENCODED_IMAGE', mime_type: 'image/png'},
  ],
});
console.log(interaction.output_text);

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Content;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.operations.CreateInteractionResponse;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.ImageContent;
import com.google.genai.gaos.models.interactions.ImageContentMimeType;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.TextContent;

Client client = new Client();
List content =
    List.of(
        TextContent.builder().text("What is in this picture?").build(),
        ImageContent.builder()
            .data("BASE64_ENCODED_IMAGE")
            .mimeType(ImageContentMimeType.IMAGE_PNG)
            .build());
CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model("gemini-flash-latest")
        .input(InteractionsInput.ofContent(content))
        .build();
CreateInteractionResponse response =
    client.interactions.create(CreateInteractionRequestBody.of(params));
Interaction interaction =
    response.interaction().orElseThrow(() -> new RuntimeException("No interaction returned"));
System.out.println(interaction.outputText().orElse(""));

package main

import (
    "context"
    "fmt"
    "log"
    "google.golang.org/genai"
    gaos_interactions "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    contents := []gaos_interactions.Content{
        gaos_interactions.NewContent(gaos_interactions.TextContent{
            Text: "What is in this picture?",
        }),
        gaos_interactions.NewContent(gaos_interactions.ImageContent{
            Data:     genai.Ptr("BASE64_ENCODED_IMAGE"),
            MimeType: gaos_interactions.ImageContentMimeTypeImagePng.ToPointer(),
        }),
    }

    body := operations.NewCreateInteractionRequestBody(gaos_interactions.CreateModelInteraction{
        Model: gaos_interactions.Model("gemini-flash-latest"),
        Input: genai.Ptr(gaos_interactions.NewInteractionsInput(contents)),
    })

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{Body: body})
    if err != nil {
        log.Fatal(err)
    }

    if res.Interaction != nil && res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

Example Request