Class ChatGoogleGenerativeAI

import { ChatGoogleGenerativeAI } from '@langchain/google-genai';

const llm = new ChatGoogleGenerativeAI({
  model: "gemini-1.5-flash",
  temperature: 0,
  maxRetries: 2,
  // apiKey: "...",
  // other params...
});
Copy

const input = `Translate "I love programming" into French.`;

// Models also accept a list of chat messages or a formatted prompt
const result = await llm.invoke(input);
console.log(result);
Copy

AIMessage {
  "content": "There are a few ways to translate \"I love programming\" into French, depending on the level of formality and nuance you want to convey:\n\n**Formal:**\n\n* **J'aime la programmation.** (This is the most literal and formal translation.)\n\n**Informal:**\n\n* **J'adore programmer.** (This is a more enthusiastic and informal translation.)\n* **J'aime beaucoup programmer.** (This is a slightly less enthusiastic but still informal translation.)\n\n**More specific:**\n\n* **J'aime beaucoup coder.** (This specifically refers to writing code.)\n* **J'aime beaucoup développer des logiciels.** (This specifically refers to developing software.)\n\nThe best translation will depend on the context and your intended audience. \n",
  "response_metadata": {
    "finishReason": "STOP",
    "index": 0,
    "safetyRatings": [
      {
        "category": "HARM_CATEGORY_SEXUALLY_EXPLICIT",
        "probability": "NEGLIGIBLE"
      },
      {
        "category": "HARM_CATEGORY_HATE_SPEECH",
        "probability": "NEGLIGIBLE"
      },
      {
        "category": "HARM_CATEGORY_HARASSMENT",
        "probability": "NEGLIGIBLE"
      },
      {
        "category": "HARM_CATEGORY_DANGEROUS_CONTENT",
        "probability": "NEGLIGIBLE"
      }
    ]
  },
  "usage_metadata": {
    "input_tokens": 10,
    "output_tokens": 149,
    "total_tokens": 159
  }
}
Copy

for await (const chunk of await llm.stream(input)) {
  console.log(chunk);
}
Copy

AIMessageChunk {
  "content": "There",
  "response_metadata": {
    "index": 0
  }
  "usage_metadata": {
    "input_tokens": 10,
    "output_tokens": 1,
    "total_tokens": 11
  }
}
AIMessageChunk {
  "content": " are a few ways to translate \"I love programming\" into French, depending on",
}
AIMessageChunk {
  "content": " the level of formality and nuance you want to convey:\n\n**Formal:**\n\n",
}
AIMessageChunk {
  "content": "* **J'aime la programmation.** (This is the most literal and formal translation.)\n\n**Informal:**\n\n* **J'adore programmer.** (This",
}
AIMessageChunk {
  "content": " is a more enthusiastic and informal translation.)\n* **J'aime beaucoup programmer.** (This is a slightly less enthusiastic but still informal translation.)\n\n**More",
}
AIMessageChunk {
  "content": " specific:**\n\n* **J'aime beaucoup coder.** (This specifically refers to writing code.)\n* **J'aime beaucoup développer des logiciels.** (This specifically refers to developing software.)\n\nThe best translation will depend on the context and",
}
AIMessageChunk {
  "content": " your intended audience. \n",
}
Copy

import { AIMessageChunk } from '@langchain/core/messages';
import { concat } from '@langchain/core/utils/stream';

const stream = await llm.stream(input);
let full: AIMessageChunk | undefined;
for await (const chunk of stream) {
  full = !full ? chunk : concat(full, chunk);
}
console.log(full);
Copy

AIMessageChunk {
  "content": "There are a few ways to translate \"I love programming\" into French, depending on the level of formality and nuance you want to convey:\n\n**Formal:**\n\n* **J'aime la programmation.** (This is the most literal and formal translation.)\n\n**Informal:**\n\n* **J'adore programmer.** (This is a more enthusiastic and informal translation.)\n* **J'aime beaucoup programmer.** (This is a slightly less enthusiastic but still informal translation.)\n\n**More specific:**\n\n* **J'aime beaucoup coder.** (This specifically refers to writing code.)\n* **J'aime beaucoup développer des logiciels.** (This specifically refers to developing software.)\n\nThe best translation will depend on the context and your intended audience. \n",
  "usage_metadata": {
    "input_tokens": 10,
    "output_tokens": 277,
    "total_tokens": 287
  }
}
Copy

import { z } from 'zod';

const GetWeather = {
  name: "GetWeather",
  description: "Get the current weather in a given location",
  schema: z.object({
    location: z.string().describe("The city and state, e.g. San Francisco, CA")
  }),
}

const GetPopulation = {
  name: "GetPopulation",
  description: "Get the current population in a given location",
  schema: z.object({
    location: z.string().describe("The city and state, e.g. San Francisco, CA")
  }),
}

const llmWithTools = llm.bindTools([GetWeather, GetPopulation]);
const aiMsg = await llmWithTools.invoke(
  "Which city is hotter today and which is bigger: LA or NY?"
);
console.log(aiMsg.tool_calls);
Copy

[
  {
    name: 'GetWeather',
    args: { location: 'Los Angeles, CA' },
    type: 'tool_call'
  },
  {
    name: 'GetWeather',
    args: { location: 'New York, NY' },
    type: 'tool_call'
  },
  {
    name: 'GetPopulation',
    args: { location: 'Los Angeles, CA' },
    type: 'tool_call'
  },
  {
    name: 'GetPopulation',
    args: { location: 'New York, NY' },
    type: 'tool_call'
  }
]
Copy

const Joke = z.object({
  setup: z.string().describe("The setup of the joke"),
  punchline: z.string().describe("The punchline to the joke"),
  rating: z.number().optional().describe("How funny the joke is, from 1 to 10")
}).describe('Joke to tell user.');

const structuredLlm = llm.withStructuredOutput(Joke, { name: "Joke" });
const jokeResult = await structuredLlm.invoke("Tell me a joke about cats");
console.log(jokeResult);
Copy

{
  setup: "Why don\\'t cats play poker?",
  punchline: "Why don\\'t cats play poker? Because they always have an ace up their sleeve!"
}
Copy

import { HumanMessage } from '@langchain/core/messages';

const imageUrl = "https://example.com/image.jpg";
const imageData = await fetch(imageUrl).then(res => res.arrayBuffer());
const base64Image = Buffer.from(imageData).toString('base64');

const message = new HumanMessage({
  content: [
    { type: "text", text: "describe the weather in this image" },
    {
      type: "image_url",
      image_url: { url: `data:image/jpeg;base64,${base64Image}` },
    },
  ]
});

const imageDescriptionAiMsg = await llm.invoke([message]);
console.log(imageDescriptionAiMsg.content);
Copy

The weather in the image appears to be clear and sunny. The sky is mostly blue with a few scattered white clouds, indicating fair weather. The bright sunlight is casting shadows on the green, grassy hill, suggesting it is a pleasant day with good visibility. There are no signs of rain or stormy conditions.
Copy

const aiMsgForMetadata = await llm.invoke(input);
console.log(aiMsgForMetadata.usage_metadata);
Copy

{ input_tokens: 10, output_tokens: 149, total_tokens: 159 }
Copy

const aiMsgForResponseMetadata = await llm.invoke(input);
console.log(aiMsgForResponseMetadata.response_metadata);
Copy

{
  finishReason: 'STOP',
  index: 0,
  safetyRatings: [
    {
      category: 'HARM_CATEGORY_SEXUALLY_EXPLICIT',
      probability: 'NEGLIGIBLE'
    },
    {
      category: 'HARM_CATEGORY_HATE_SPEECH',
      probability: 'NEGLIGIBLE'
    },
    { category: 'HARM_CATEGORY_HARASSMENT', probability: 'NEGLIGIBLE' },
    {
      category: 'HARM_CATEGORY_DANGEROUS_CONTENT',
      probability: 'NEGLIGIBLE'
    }
  ]
}
Copy

This example will show you how to pass documents such as PDFs to Google Generative AI through messages.

const pdfPath = "/Users/my_user/Downloads/invoice.pdf";
const pdfBase64 = await fs.readFile(pdfPath, "base64");

const response = await llm.invoke([
  ["system", "Use the provided documents to answer the question"],
  [
    "user",
    [
      {
        type: "application/pdf", // If the `type` field includes a single slash (`/`), it will be treated as inline data.
        data: pdfBase64,
      },
      {
        type: "text",
        text: "Summarize the contents of this PDF",
      },
    ],
  ],
]);

console.log(response.content);
Copy

This is a billing invoice from Twitter Developers for X API Basic Access. The transaction date is January 7, 2025,
and the amount is $194.34, which has been paid. The subscription period is from January 7, 2025 21:02 to February 7, 2025 00:00 (UTC).
The tax is $0.00, with a tax rate of 0%. The total amount is $194.34. The payment was made using a Visa card ending in 7022,
expiring in 12/2026. The billing address is Brace Sproul, 1234 Main Street, San Francisco, CA, US 94103. The company being billed is
X Corp, located at 865 FM 1209 Building 2, Bastrop, TX, US 78602. Terms and conditions apply.
Copy