Gemini API multi-turn conversations (chat) | Typeerror for text

[ayush7801]

Hi, I am getting this typeerror for text key being undefined even when I am requesting with the same request body as in documentation. I am using NodeJS.

Code given in documentation - docs

const { GoogleGenerativeAI } = require("@google/generative-ai");

// Access your API key as an environment variable (see "Set up your API key" above)
const genAI = new GoogleGenerativeAI(process.env.API_KEY);

async function run() {
  // For text-only input, use the gemini-pro model
  const model = genAI.getGenerativeModel({ model: "gemini-pro"});

  const chat = model.startChat({
    history: [
      {
        role: "user",
        parts: [{ text: "Hello, I have 2 dogs in my house." }],
      },
      {
        role: "model",
        parts: [{ text: "Great to meet you. What would you like to know?" }],
      },
    ],
    generationConfig: {
      maxOutputTokens: 100,
    },
  });

  const msg = "How many paws are in my house?";

  const result = await chat.sendMessage(msg);
  const response = await result.response;
  const text = response.text();
  console.log(text);
}

run();

Response I am getting -
Cannot read properties of undefined (reading 'text') , with response code 500.

Your help is appriciated.

[Rakesh-46-VR]

I tried the same code as you have given above and currently it seems to work well. It gives errors if you don't load env properly.
In my case I had to use the dotenv lib to load the env variables into process.env and then things worked out ,

I think the documentation is correct as of now..

This the code which i had tried :

import { configDotenv } from "dotenv";

configDotenv()

const genAI = new GoogleGenerativeAI(process.env.API_KEY);

async function run() {
  // For text-only input, use the gemini-pro model
  const model = genAI.getGenerativeModel({ model: "gemini-1.5-pro" });

  console.log()
  const chat = model.startChat({
    history: [
      {
        role: "user",
        parts: [{ text: "Hello, I have 2 dogs in my house." }],
      },
      {
        role: "model",
        parts: [{ text: "Great to meet you. What would you like to know?" }],
      },
    ],
    generationConfig: {
      maxOutputTokens: 100,
    },
  });

  const msg = "How many paws are in my house?";

  const result = await chat.sendMessage(msg);
  const response = await result.response;
  const text = response.text();
  console.log(text);
}

run();

Output

Assuming your dogs have the usual four paws each, and you have two dogs, there are 2 dogs * 4 paws/dog = 8 dog paws.  Of course, you also have two feet, so depending on whether you want to include human paws, there are either 8 or 10 paws total.

[0xbadshah]

This error is actually inconsistent. Sometimes it appears and sometimes it doesn't. One thing I found was this error is pretty common when using any sort of maxOutputTokens limit. If I remove that config, the response might take time but I didn't find the error.
(Tested against gemini-2.5-pro-exp-03-25 with temperature 0)