Class ChatVertexAI

import { ChatVertexAI } from '@langchain/google-vertexai';

const llm = new ChatVertexAI({
  model: "gemini-1.5-pro",
  temperature: 0,
  // 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

AIMessageChunk {
  "content": "\"J'adore programmer\" \n\nHere's why this is the best translation:\n\n* **J'adore** means \"I love\" and conveys a strong passion.\n* **Programmer** is the French verb for \"to program.\"\n\nThis translation is natural and idiomatic in French. \n",
  "additional_kwargs": {},
  "response_metadata": {},
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 9,
    "output_tokens": 63,
    "total_tokens": 72
  }
}
Copy

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

AIMessageChunk {
  "content": "\"",
  "additional_kwargs": {},
  "response_metadata": {},
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": "J'adore programmer\" \n",
  "additional_kwargs": {},
  "response_metadata": {},
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": "",
  "additional_kwargs": {},
  "response_metadata": {},
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": []
}
AIMessageChunk {
  "content": "",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": "stop"
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 9,
    "output_tokens": 8,
    "total_tokens": 17
  }
}
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": "\"J'adore programmer\" \n",
  "additional_kwargs": {},
  "response_metadata": {
    "finishReason": "stop"
  },
  "tool_calls": [],
  "tool_call_chunks": [],
  "invalid_tool_calls": [],
  "usage_metadata": {
    "input_tokens": 9,
    "output_tokens": 8,
    "total_tokens": 17
  }
}
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: 'GetPopulation',
    args: { location: 'New York City, NY' },
    id: '33c1c1f47e2f492799c77d2800a43912',
    type: 'tool_call'
  }
]
Copy

import { z } from 'zod';

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: 'What do you call a cat that loves to bowl?',
  punchline: 'An alley cat!'
}
Copy

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

{ input_tokens: 9, output_tokens: 8, total_tokens: 17 }
Copy

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

{ input_tokens: 9, output_tokens: 8, total_tokens: 17 }
Copy