> ## Documentation Index
> Fetch the complete documentation index at: https://langchain-5e9cc07a-preview-devupd-1765394015-eccef47.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# ChatGoogleGenerativeAI
> Get started using Gemini [chat models](/oss/python/langchain/models) in LangChain.
Access Google's Generative AI models, including the Gemini family, via the **Gemini Developer API** or **Vertex AI**. The Gemini Developer API offers quick setup with API keys, ideal for individual developers. Vertex AI provides enterprise features and integrates with Google Cloud Platform.
For information on the latest models, model IDs, their features, context windows, etc. head to the [Google AI docs](https://ai.google.dev/gemini-api/docs).
**Vertex AI consolidation & compatibility**
As of `langchain-google-genai` 4.0.0, this package uses the consolidated [`google-genai`](https://googleapis.github.io/python-genai/) SDK instead of the legacy [`google-ai-generativelanguage`](https://googleapis.dev/python/generativelanguage/latest/) SDK.
This migration brings support for Gemini models both via the Gemini Developer API and Gemini API in Vertex AI, superseding certain classes in `langchain-google-vertexai`, such as `ChatVertexAI`.
Read the [full announcement and migration guide](https://github.com/langchain-ai/langchain-google/discussions/1422).
**API Reference**
For detailed documentation of all features and configuration options, head to the [`ChatGoogleGenerativeAI`](https://reference.langchain.com/python/integrations/langchain_google_genai/#langchain_google_genai.ChatGoogleGenerativeAI) API reference.
## Overview
### Integration details
| Class | Package | Local | Serializable | [JS support](https://js.langchain.com/docs/integrations/chat/google_generative_ai) | Downloads | Version |
| :---------------------------------------------------------------------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------------------- | :---: | :----------: | :--------------------------------------------------------------------------------: | :-----------------------------------------------------------------------------------------------------: | :--------------------------------------------------------------------------------------------------: |
| [`ChatGoogleGenerativeAI`](https://reference.langchain.com/python/integrations/langchain_google_genai/#langchain_google_genai.ChatGoogleGenerativeAI) | [`langchain-google-genai`](https://reference.langchain.com/python/integrations/langchain_google_genai) | ❌ | beta | ✅ |  |  |
### Model features
| [Tool calling](/oss/python/langchain/tools) | [Structured output](/oss/python/langchain/structured-output) | JSON mode | [Image input](/oss/python/langchain/messages#multimodal) | Audio input | Video input | [Token-level streaming](/oss/python/langchain/streaming/) | Native async | [Token usage](/oss/python/langchain/models#token-usage) | [Logprobs](/oss/python/langchain/models#log-probabilities) |
| :-----------------------------------------: | :----------------------------------------------------------: | :-------: | :------------------------------------------------------: | :---------: | :---------: | :-------------------------------------------------------: | :----------: | :-----------------------------------------------------: | :--------------------------------------------------------: |
| ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ⚠️ |
## Setup
To access Google AI models you'll need to create a Google Account, get a Google AI API key, and install the `langchain-google-genai` integration package.
### Installation
```python theme={null}
pip install -U langchain-google-genai
```
### Credentials
This integration supports two backends: **Gemini Developer API** and **Vertex AI**. The backend is selected automatically based on your configuration.
#### Backend selection
The backend is determined as follows:
1. If `GOOGLE_GENAI_USE_VERTEXAI` env var is set, uses that value
2. If `credentials` parameter is provided, uses Vertex AI
3. If `project` parameter is provided, uses Vertex AI
4. Otherwise, uses Gemini Developer API
You can also explicitly set `vertexai=True` or `vertexai=False` to override auto-detection.
**Quick setup with API key**
Head to [Google AI Studio](https://ai.google.dev/gemini-api/docs/api-key) to generate an API key:
```python theme={null}
import getpass
import os
if "GOOGLE_API_KEY" not in os.environ:
os.environ["GOOGLE_API_KEY"] = getpass.getpass("Enter your Google AI API key: ")
```
The integration checks for `GOOGLE_API_KEY` first, then `GEMINI_API_KEY` as a fallback.
**Vertex AI using API key authentication**
You can use Vertex AI with API key authentication for simpler setup:
```bash theme={null}
export GEMINI_API_KEY='your-api-key'
export GOOGLE_GENAI_USE_VERTEXAI=true
export GOOGLE_CLOUD_PROJECT='your-project-id'
```
Or programmatically:
```python theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
llm = ChatGoogleGenerativeAI(
model="gemini-2.5-flash",
api_key="your-api-key", # [!code highlight]
project="your-project-id", # [!code highlight]
vertexai=True, # [!code highlight]
)
```
**Vertex AI using service account or ADC**
Set up [Application Default Credentials (ADC)](https://cloud.google.com/docs/authentication/application-default-credentials):
```bash theme={null}
gcloud auth application-default login
```
Set your Google Cloud project:
```bash theme={null}
export GOOGLE_CLOUD_PROJECT='your-project-id'
# Optional: set region (defaults to us-central1)
export GOOGLE_CLOUD_LOCATION='us-central1'
```
Or use service account credentials:
```python theme={null}
from google.oauth2 import service_account
from langchain_google_genai import ChatGoogleGenerativeAI
credentials = service_account.Credentials.from_service_account_file(
"path/to/service-account.json",
scopes=["https://www.googleapis.com/auth/cloud-platform"],
)
llm = ChatGoogleGenerativeAI(
model="gemini-2.5-flash",
credentials=credentials, # [!code highlight]
project="your-project-id", # [!code highlight]
)
```
#### Environment variables
| Variable | Purpose | Backend |
| --------------------------- | ---------------------------------------- | -------------------------------------- |
| `GOOGLE_API_KEY` | API key (primary) | Both (see `GOOGLE_GENAI_USE_VERTEXAI`) |
| `GEMINI_API_KEY` | API key (fallback) | Both (see `GOOGLE_GENAI_USE_VERTEXAI`) |
| `GOOGLE_GENAI_USE_VERTEXAI` | Force Vertex AI backend (`true`/`false`) | Vertex AI |
| `GOOGLE_CLOUD_PROJECT` | GCP project ID | Vertex AI |
| `GOOGLE_CLOUD_LOCATION` | GCP region (default: `us-central1`) | Vertex AI |
To enable automated tracing of your model calls, set your [LangSmith](https://docs.smith.langchain.com/) API key:
```python theme={null}
os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"
```
## Instantiation
Now we can instantiate our model object and generate responses:
```python theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(
model="gemini-3-pro-preview",
temperature=1.0, # Gemini 3.0+ defaults to 1.0
max_tokens=None,
timeout=None,
max_retries=2,
# other params...
)
```
```python theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(
model="gemini-3-pro-preview",
project="your-project-id", # [!code highlight]
location="us-central1", # Optional, defaults to us-central1 [!code highlight]
temperature=1.0, # Gemini 3.0+ defaults to 1.0
max_tokens=None,
timeout=None,
max_retries=2,
# other params...
)
```
Providing `project` automatically selects the Vertex AI backend unless you explicitly set `vertexai=False`.
**Temperature for Gemini 3.0+ models**
If `temperature` is not explicitly set and the model is Gemini 3.0 or later, it will be automatically set to `1.0` instead of the default `0.7` per Google GenAI API best practices. Using `0.7` with Gemini 3.0+ can cause infinite loops, degraded reasoning performance, and failure on complex tasks.
See the [`ChatGoogleGenerativeAI`](https://reference.langchain.com/python/integrations/langchain_google_genai/#langchain_google_genai.ChatGoogleGenerativeAI) API Reference for the full set of available model parameters.
### Proxy configuration
If you need to use a proxy, set these environment variables before initializing:
```bash theme={null}
export HTTPS_PROXY='http://username:password@proxy_uri:port'
export SSL_CERT_FILE='path/to/cert.pem' # Optional: custom SSL certificate
```
For SOCKS5 proxies or advanced proxy configuration, use the `client_args` parameter:
```python theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(
model="gemini-3-pro-preview",
client_args={"proxy": "socks5://user:pass@host:port"},
)
```
## Invocation
```python theme={null}
messages = [
(
"system",
"You are a helpful assistant that translates English to French. Translate the user sentence.",
),
("human", "I love programming."),
]
ai_msg = model.invoke(messages)
ai_msg
```
```output Gemini 3 theme={null}
AIMessage(content=[{'type': 'text', 'text': "J'adore la programmation.", 'extras': {'signature': 'EpoWCpc...'}}], additional_kwargs={}, response_metadata={'prompt_feedback': {'block_reason': 0, 'safety_ratings': []}, 'finish_reason': 'STOP', 'model_name': 'gemini-3-pro-preview', 'safety_ratings': [], 'model_provider': 'google_genai'}, id='lc_run--fb732b64-1ab4-4a28-b93b-dcfb2a164a3d-0', usage_metadata={'input_tokens': 21, 'output_tokens': 779, 'total_tokens': 800, 'input_token_details': {'cache_read': 0}, 'output_token_details': {'reasoning': 772}})
```
```output Gemini 2.5 theme={null}
AIMessage(content="J'adore la programmation.", additional_kwargs={}, response_metadata={'prompt_feedback': {'block_reason': 0, 'safety_ratings': []}, 'finish_reason': 'STOP', 'model_name': 'gemini-2.5-flash', 'safety_ratings': []}, id='run-3b28d4b8-8a62-4e6c-ad4e-b53e6e825749-0', usage_metadata={'input_tokens': 20, 'output_tokens': 7, 'total_tokens': 27, 'input_token_details': {'cache_read': 0}})
```
**Message content shape**
Gemini 3 series models will always return a list of content blocks to capture [thought signatures](#thought-signatures). Use the `.text` property to recover string content.
```python theme={null}
response.content # -> [{"type": "text", "text": "Hello!", "extras": {"signature": "EpQFCp...lKx64r"}}]
response.text # -> "Hello!"
```
```python theme={null}
print(ai_msg.content)
```
```output Gemini 3 theme={null}
[{'type': 'text',
'text': "J'adore la programmation.",
'extras': {'signature': '...'}}]
```
```output Gemini 2.5 theme={null}
J'adore la programmation.
```
## Multimodal usage
Gemini models can accept multimodal inputs (text, images, audio, video) and, for some models, generate multimodal outputs.
### Supported input methods
| Method | [Image](#image-input) | [Video](#video-input) | [Audio](#audio-input) | [PDF](#pdf-input) |
| --------------------------------------- | :-------------------: | :-------------------: | :-------------------: | :---------------: |
| [File upload](#file-upload) (Files API) | ✅ | ✅ | ✅ | ✅ |
| Base64 inline data | ✅ | ✅ | ✅ | ✅ |
| HTTP/HTTPS URLs\* | ✅ | ✅ | ✅ | ✅ |
| GCS URIs (`gs://...`) | ✅ | ✅ | ✅ | ✅ |
\*YouTube URLs are supported for video input in preview.
### File upload
You can upload files to Google's servers and reference them by URI. This works for PDFs, images, videos, and audio files.
```python theme={null}
import time
from google import genai
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
client = genai.Client()
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
# Upload file to Google's servers
myfile = client.files.upload(file="/path/to/your/file.pdf")
while myfile.state.name == "PROCESSING":
time.sleep(2)
myfile = client.files.get(name=myfile.name)
# Reference by file_id in FileContentBlock
message = HumanMessage(
content=[
{"type": "text", "text": "What is in the document?"},
{
"type": "file",
"file_id": myfile.uri, # or myfile.name
"mime_type": "application/pdf",
},
]
)
response = model.invoke([message])
```
Once uploaded, you can reference the file in any of the media-specific sections below using the `file_id` pattern.
### Image input
Provide image inputs along with text using a [`HumanMessage`](https://reference.langchain.com/python/langchain/messages/#langchain.messages.HumanMessage) with a list content format.
```python Image URL theme={null}
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
message = HumanMessage(
content=[
{"type": "text", "text": "Describe the image at the URL."},
{
"type": "image",
"url": "https://picsum.photos/seed/picsum/200/300",
},
]
)
response = model.invoke([message])
```
```python Chat Completions image_url format theme={null}
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
message = HumanMessage(
content=[
{"type": "text", "text": "Describe the image at the URL."},
{"type": "image_url", "image_url": "https://picsum.photos/seed/picsum/200/300"},
]
)
response = model.invoke([message])
```
```python Base64 encoded theme={null}
import base64
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
image_bytes = open("path/to/your/image.jpg", "rb").read()
image_base64 = base64.b64encode(image_bytes).decode("utf-8")
mime_type = "image/jpeg"
message = HumanMessage(
content=[
{"type": "text", "text": "Describe the local image."},
{
"type": "image",
"base64": image_base64,
"mime_type": mime_type,
},
]
)
response = model.invoke([message])
```
```python Uploaded file theme={null}
import time
from google import genai
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
client = genai.Client()
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
# Upload and wait for processing
myfile = client.files.upload(file="/path/to/image.jpg")
while myfile.state.name == "PROCESSING":
time.sleep(2)
myfile = client.files.get(name=myfile.name)
message = HumanMessage(
content=[
{"type": "text", "text": "Describe this image."},
{
"type": "file",
"file_id": myfile.uri,
"mime_type": "image/jpeg",
},
]
)
response = model.invoke([message])
```
Other supported image formats:
* A Google Cloud Storage URI (`gs://...`). Ensure the service account has access.
### PDF input
Provide PDF file inputs along with text.
```python URL theme={null}
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
message = HumanMessage(
content=[
{"type": "text", "text": "Describe the document in a sentence."},
{
"type": "image_url", # (PDFs are treated as images)
"image_url": "https://www.w3.org/WAI/ER/tests/xhtml/testfiles/resources/pdf/dummy.pdf",
},
]
)
response = model.invoke([message])
```
```python Base64 encoded theme={null}
import base64
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
pdf_bytes = open("path/to/your/document.pdf", "rb").read()
pdf_base64 = base64.b64encode(pdf_bytes).decode("utf-8")
mime_type = "application/pdf"
message = HumanMessage(
content=[
{"type": "text", "text": "Describe the document in a sentence."},
{
"type": "file",
"base64": pdf_base64,
"mime_type": mime_type,
},
]
)
response = model.invoke([message])
```
```python Uploaded file theme={null}
import time
from google import genai
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
client = genai.Client()
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
# Upload and wait for processing
myfile = client.files.upload(file="/path/to/document.pdf")
while myfile.state.name == "PROCESSING":
time.sleep(2)
myfile = client.files.get(name=myfile.name)
message = HumanMessage(
content=[
{"type": "text", "text": "Describe the document in a sentence."},
{
"type": "file",
"file_id": myfile.uri,
"mime_type": "application/pdf",
},
]
)
response = model.invoke([message])
```
### Audio input
Provide audio file inputs along with text.
```python URL theme={null}
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
message = HumanMessage(
content=[
{"type": "text", "text": "Summarize this audio in a sentence."},
{
"type": "image_url",
"image_url": "https://example.com/audio.mp3",
},
]
)
response = model.invoke([message])
```
```python Base64 encoded theme={null}
import base64
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
audio_bytes = open("path/to/your/audio.mp3", "rb").read()
audio_base64 = base64.b64encode(audio_bytes).decode("utf-8")
mime_type = "audio/mpeg"
message = HumanMessage(
content=[
{"type": "text", "text": "Summarize this audio in a sentence."},
{
"type": "audio",
"base64": audio_base64,
"mime_type": mime_type,
},
]
)
response = model.invoke([message])
```
```python Uploaded file theme={null}
import time
from google import genai
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
client = genai.Client()
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
# Upload and wait for processing
myfile = client.files.upload(file="/path/to/audio.mp3")
while myfile.state.name == "PROCESSING":
time.sleep(2)
myfile = client.files.get(name=myfile.name)
message = HumanMessage(
content=[
{"type": "text", "text": "Summarize this audio in a sentence."},
{
"type": "file",
"file_id": myfile.uri,
"mime_type": "audio/mpeg",
},
]
)
response = model.invoke([message])
```
### Video input
Provide video file inputs along with text.
```python Base64 encoded theme={null}
import base64
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
video_bytes = open("path/to/your/video.mp4", "rb").read()
video_base64 = base64.b64encode(video_bytes).decode("utf-8")
mime_type = "video/mp4"
message = HumanMessage(
content=[
{"type": "text", "text": "Describe what's in this video in a sentence."},
{
"type": "video",
"base64": video_base64,
"mime_type": mime_type,
},
]
)
response = model.invoke([message])
```
```python Uploaded file theme={null}
import time
from google import genai
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
client = genai.Client()
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
# Upload and wait for processing
myfile = client.files.upload(file="/path/to/video.mp4")
while myfile.state.name == "PROCESSING":
time.sleep(2)
myfile = client.files.get(name=myfile.name)
message = HumanMessage(
content=[
{"type": "text", "text": "Summarize the video in 3 sentences."},
{
"type": "file",
"file_id": myfile.uri,
"mime_type": "video/mp4",
},
]
)
response = model.invoke([message])
```
```python YouTube URL theme={null}
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
message = HumanMessage(
content=[
{"type": "text", "text": "Summarize the video in 3 sentences."},
{
"type": "video",
"url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ",
"mime_type": "video/mp4",
},
]
)
response = model.invoke([message])
```
**YouTube limitations**
* Only public videos are supported (not private or unlisted)
* Free tier: max 8 hours of YouTube video per day
* Feature is currently in preview
### Image generation
Certain models can generate text and images inline. See more information on the [Gemini API docs](https://ai.google.dev/gemini-api/docs/image-generation) for details.
This example demonstrates how to generate and display an image in a Jupyter notebook:
```python theme={null}
import base64
from IPython.display import Image, display
from langchain.messages import AIMessage
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-2.5-flash-image") # [!code highlight]
response = model.invoke("Generate a photorealistic image of a cuddly cat wearing a hat.")
def _get_image_base64(response: AIMessage) -> None:
image_block = next(
block
for block in response.content
if isinstance(block, dict) and block.get("image_url")
)
return image_block["image_url"].get("url").split(",")[-1]
image_base64 = _get_image_base64(response)
display(Image(data=base64.b64decode(image_base64), width=300))
```
Use `image_config` to control resulting image dimensions and quality. See [`genai.types.ImageConfig`](https://googleapis.github.io/python-genai/genai.html#genai.types.ImageConfig)
for a list of supported fields and their values.
Setting `image_config` during instantiation applies the configuration to all invocations, while setting it during invocation overrides the default for that call only; this allows for flexible control over generation parameters on a per-request basis.
```python Instantiation theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(
model="gemini-2.5-flash-image", # [!code highlight]
image_config={ # [!code highlight]
"aspect_ratio": "16:9", # [!code highlight]
}, # [!code highlight]
)
response = model.invoke("Generate a photorealistic image of a cuddly cat wearing a hat.")
```
```python Invocation theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-2.5-flash-image") # [!code highlight]
response = model.invoke(
"Generate a photorealistic image of a cuddly cat wearing a hat.",
image_config={ # [!code highlight]
"aspect_ratio": "1:1", # [!code highlight]
}, # [!code highlight]
)
```
Supported parameters vary by model and backend (Gemini Developer API and Vertex AI each support different subsets of parameters and models).
By default, image generation models may return both text and images (e.g. *"Ok! Here's an image of a..."*).
You can request that the model only return images by setting the `response_modalities` parameter:
```python Instantiation theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI, Modality
model = ChatGoogleGenerativeAI(
model="gemini-2.5-flash-image",
response_modalities=[Modality.IMAGE], # [!code highlight]
)
# All invocations will return only images
response = model.invoke("Generate a photorealistic image of a cuddly cat wearing a hat.")
```
```python Invocation theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI, Modality
model = ChatGoogleGenerativeAI(model="gemini-2.5-flash-image")
# Only this invocation will return images; others may return text+images
response = model.invoke(
"Generate a photorealistic image of a cuddly cat wearing a hat.",
response_modalities=[Modality.IMAGE], # [!code highlight]
)
```
### Audio generation
Certain models can generate audio files. See more information on the [Gemini API docs](https://ai.google.dev/gemini-api/docs/speech-generation) for details.
**Vertex AI Limitation**
Audio generation models are currently in limited preview on Vertex AI and may require allowlist access. If you encounter an `INVALID_ARGUMENT` error when using TTS models with `vertexai=True`, your GCP project may need to be allowlisted.
For more details, see this [Google AI forum discussion](https://discuss.ai.google.dev/t/request-allowlist-access-for-audio-output-in-gemini-2-5-pro-flash-tts-vertex-ai/108067).
```python theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-2.5-flash-preview-tts") # [!code highlight]
response = model.invoke("Please say The quick brown fox jumps over the lazy dog")
# Base64 encoded binary data of the audio
wav_data = response.additional_kwargs.get("audio")
with open("output.wav", "wb") as f:
f.write(wav_data)
```
## Tool calling
You can equip the model with tools to call.
```python theme={null}
from langchain.tools import tool
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
# Define the tool
@tool(description="Get the current weather in a given location")
def get_weather(location: str) -> str:
return "It's sunny."
# Initialize and bind (potentially multiple) tools to the model
model_with_tools = ChatGoogleGenerativeAI(model="gemini-3-pro-preview").bind_tools([get_weather])
# Step 1: Model generates tool calls
messages = [HumanMessage("What's the weather in Boston?")]
ai_msg = model_with_tools.invoke(messages)
messages.append(ai_msg)
# Check the tool calls in the response
print(ai_msg.tool_calls)
# Step 2: Execute tools and collect results
for tool_call in ai_msg.tool_calls:
# Execute the tool with the generated arguments
tool_result = get_weather.invoke(tool_call)
messages.append(tool_result)
# Step 3: Pass results back to model for final response
final_response = model_with_tools.invoke(messages)
final_response
```
```output theme={null}
[{'name': 'get_weather', 'args': {'location': 'Boston'}, 'id': '879b4233-901b-4bbb-af56-3771ca8d3a75', 'type': 'tool_call'}]
```
```output theme={null}
AIMessage(content=[{'type': 'text', 'text': 'The weather in Boston is sunny.'}], additional_kwargs={}, response_metadata={'prompt_feedback': {'block_reason': 0, 'safety_ratings': []}, 'finish_reason': 'STOP', 'model_name': 'gemini-3-pro-preview', 'safety_ratings': [], 'model_provider': 'google_genai'}, id='lc_run--190be543-c974-460b-a708-7257892c3121-0', usage_metadata={'input_tokens': 143, 'output_tokens': 7, 'total_tokens': 150, 'input_token_details': {'cache_read': 0}})
```
## Structured output
Force the model to respond with a specific structure. See the [Gemini API docs](https://ai.google.dev/gemini-api/docs/structured-output) for more info.
```python theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
from pydantic import BaseModel
from typing import Literal
class Feedback(BaseModel):
sentiment: Literal["positive", "neutral", "negative"]
summary: str
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
structured_model = model.with_structured_output(
schema=Feedback.model_json_schema(), method="json_schema"
)
response = structured_model.invoke("The new UI is great!")
response["sentiment"] # "positive"
response["summary"] # "The user expresses positive..."
```
For streaming structured output, merge dictionaries instead of using `+=`:
```python theme={null}
stream = structured_model.stream("The interface is intuitive and beautiful!")
full = next(stream)
for chunk in stream:
full.update(chunk) # Merge dictionaries
print(full) # Complete structured response
# -> {'sentiment': 'positive', 'summary': 'The user praises...'}
```
### Structured output methods
Two methods are supported for structured output:
* **`method="json_schema"` (default)**: Uses Gemini's native structured output. Recommended for better reliability, as it constrains the model's generation process directly rather than relying on post-processing tool calls.
* **`method="function_calling"`**: Uses tool calling to extract structured data.
## Token usage tracking
Access token usage information from the response metadata.
```python theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
result = model.invoke("Explain the concept of prompt engineering in one sentence.")
print(result.content)
print("\nUsage Metadata:")
print(result.usage_metadata)
```
```output theme={null}
Prompt engineering is the art and science of crafting effective text prompts to elicit desired and accurate responses from large language models.
Usage Metadata:
{'input_tokens': 10, 'output_tokens': 24, 'total_tokens': 34, 'input_token_details': {'cache_read': 0}}
```
## Thinking support
With reasoning models, you have the option to adjust the number of internal thinking tokens used (`thinking_budget`) or to disable thinking altogether.
Not all models allow disabling thinking. See the [Gemini models documentation](https://ai.google.dev/gemini-api/docs/models) for details.
To see a thinking model's thoughts, set `include_thoughts=True` to have the model's reasoning summaries included in the response.
```python theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
llm = ChatGoogleGenerativeAI(
model="gemini-3-pro-preview",
thinking_budget=1024, # [!code highlight]
include_thoughts=True, # [!code highlight]
)
response = llm.invoke("How many O's are in Google? How did you verify your answer?")
reasoning_score = response.usage_metadata["output_token_details"]["reasoning"]
print("Response:", response.content)
print("Reasoning tokens used:", reasoning_score)
```
```output theme={null}
Response: [{'type': 'thinking', 'thinking': '**Analyzing and Cou...'}, {'type': 'text', 'text': 'There a...', 'extras': {'signature': 'EroR...'}}]
Reasoning tokens used: 672
```
See the [Gemini API docs](https://ai.google.dev/gemini-api/docs/thinking) for more information on thinking.
### Thought signatures
[Thought signatures](https://ai.google.dev/gemini-api/docs/thinking) are encrypted representations of the model's reasoning processes. They enable Gemini to maintain thought context across multi-turn conversations, since the API is stateless and treats each request independently.
Gemini 3 may raise 4xx errors if thought signatures are not passed back with tool call responses. Upgrade to `langchain-google-genai >= 3.1.0` to ensure this is handled correctly.
Signatures appear in two places in `AIMessage` responses:
* **Text blocks**: Stored in `extras.signature` within the content block
* **Tool calls**: Stored in `additional_kwargs["__gemini_function_call_thought_signatures__"]`
```python theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
llm = ChatGoogleGenerativeAI(
model="gemini-3-pro-preview",
include_thoughts=True, # [!code highlight]
)
response = llm.invoke("How many O's are in Google? How did you verify your answer?")
response.content_blocks[-1]
```
```output theme={null}
{'type': 'text',
'text': 'There are **2** O\'s in the word "Google...',
'extras': {'signature': 'EsUSCsIS...'}}
```
For multi-turn conversations with tool calls, you must pass the full `AIMessage` back to the model so signatures are preserved. This happens automatically when you append the `AIMessage` to your messages list:
```python theme={null}
from langchain.tools import tool
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
@tool
def get_weather(location: str) -> str:
"""Get current weather for a location."""
return f"Weather in {location}: sunny, 22°C"
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview").bind_tools([get_weather])
messages = [HumanMessage("What's the weather in Tokyo?")]
# Step 1: Model returns tool call with thought signature attached
ai_msg = model.invoke(messages)
messages.append(ai_msg) # Preserves thought signature
# Step 2: Execute tool and add result
for tool_call in ai_msg.tool_calls:
result = get_weather.invoke(tool_call)
messages.append(result)
# Step 3: Model receives signature back, continues reasoning coherently
final_response = model.invoke(messages)
```
**Don't reconstruct messages manually.** If you create a new `AIMessage` instead of passing the original object, the signatures will be lost and the API may reject the request.
## Built-in tools
Google Gemini supports a variety of built-in tools, which can be bound to the model in the usual way.
### Google search
See [Gemini docs](https://ai.google.dev/gemini-api/docs/grounding/search-suggestions) for detail.
```python Bind to model theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
model_with_search = model.bind_tools([{"google_search": {}}]) # [!code highlight]
response = model_with_search.invoke("When is the next total solar eclipse in US?")
response.content_blocks
```
```python Use on invocation theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
response = model.invoke(
"When is the next total solar eclipse in US?",
tools=[{"google_search": {}}], # [!code highlight]
)
response.content_blocks
```
```output theme={null}
[{'type': 'text',
'text': 'The next total solar eclipse visible in the contiguous United States will occur on...',
'annotations': [{'type': 'citation',
'id': 'abc123',
'url': '',
'title': '',
'start_index': 0,
'end_index': 99,
'cited_text': 'The next total solar eclipse...',
'extras': {'google_ai_metadata': {'web_search_queries': ['next total solar eclipse in US'],
'grounding_chunk_index': 0,
'confidence_scores': []}}},
...
```
### Google Maps
Certain models support grounding using Google Maps. Maps grounding connects Gemini's generative capabilities with Google Maps' current, factual location data. This enables location-aware applications that provide accurate, geographically specific responses. See [Gemini docs](https://ai.google.dev/gemini-api/docs/maps-grounding) for detail.
```python Bind to model theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-2.5-pro")
model_with_maps = model.bind_tools([{"google_maps": {}}]) # [!code highlight]
response = model_with_maps.invoke(
"What are some good Italian restaurants near the Eiffel Tower in Paris?"
)
```
```python Use on invocation theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-2.5-pro")
response = model.invoke(
"What are some good Italian restaurants near the Eiffel Tower in Paris?",
tools=[{"google_maps": {}}], # [!code highlight]
)
```
The response will include grounding metadata with location information from Google Maps.
You can optionally provide a specific location context using `tool_config` with `lat_lng`. This is useful when you want to ground queries relative to a specific geographic point.
```python Bind to model theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-2.5-pro")
# Provide location context (latitude and longitude)
model_with_maps = model.bind_tools(
[{"google_maps": {}}], # [!code highlight]
tool_config={
"retrieval_config": { # Eiffel Tower
"lat_lng": { # [!code highlight]
"latitude": 48.858844, # [!code highlight]
"longitude": 2.294351, # [!code highlight]
} # [!code highlight]
}
},
)
response = model_with_maps.invoke(
"What Italian restaurants are within a 5 minute walk from here?"
)
```
```python Use on invocation theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-2.5-pro")
response = model.invoke(
"What Italian restaurants are within a 5 minute walk from here?",
tools=[{"google_maps": {}}], # [!code highlight]
tool_config={
"retrieval_config": { # Eiffel Tower
"lat_lng": { # [!code highlight]
"latitude": 48.858844, # [!code highlight]
"longitude": 2.294351, # [!code highlight]
} # [!code highlight]
}
},
)
```
### Code execution
See [Gemini docs](https://ai.google.dev/gemini-api/docs/code-execution?lang=python) for detail.
```python Bind to model theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
model_with_code_interpreter = model.bind_tools([{"code_execution": {}}]) # [!code highlight]
response = model_with_code_interpreter.invoke("Use Python to calculate 3^3.")
response.content_blocks
```
```python Use on invocation theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
response = model.invoke(
"Use Python to calculate 3^3.",
tools=[{"code_execution": {}}], # [!code highlight]
)
response.content_blocks
```
```output theme={null}
[{'type': 'server_tool_call',
'name': 'code_interpreter',
'args': {'code': 'print(3**3)', 'language': },
'id': '...'},
{'type': 'server_tool_result',
'tool_call_id': '',
'status': 'success',
'output': '27\n',
'extras': {'block_type': 'code_execution_result',
'outcome': }},
{'type': 'text', 'text': 'The calculation of 3 to the power of 3 is 27.'}]
```
### Computer use
The Gemini 2.5 Computer Use model (`gemini-2.5-computer-use-preview-10-2025`) can interact with browser environments to automate web tasks like clicking, typing, and scrolling.
**Preview model limitations**
The Computer Use model is in preview and may produce unexpected behavior. Always supervise automated tasks and avoid use with sensitive data or critical operations. See the [Gemini API docs](https://ai.google.dev/gemini-api/docs/computer-use) for safety best practices.
```python Bind to model theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-2.5-computer-use-preview-10-2025") # [!code highlight]
model_with_computer = model.bind_tools([{"computer_use": {}}]) # [!code highlight]
response = model_with_computer.invoke("Please navigate to example.com")
response.content_blocks
```
```python Use on invocation theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
model = ChatGoogleGenerativeAI(model="gemini-2.5-computer-use-preview-10-2025") # [!code highlight]
response = model.invoke(
"Please navigate to example.com",
tools=[{"computer_use": {}}], # [!code highlight]
)
response.content_blocks
```
```output theme={null}
[{'type': 'tool_call',
'id': '08a8b175-16ab-4861-8965-b736d5d4dd7e',
'name': 'open_web_browser',
'args': {}}]
```
You can configure the environment and exclude specific UI actions:
```python Advanced configuration theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI, Environment
model = ChatGoogleGenerativeAI(model="gemini-2.5-computer-use-preview-10-2025") # [!code highlight]
# Specify the environment (browser is default)
model_with_computer = model.bind_tools(
[{"computer_use": {"environment": Environment.ENVIRONMENT_BROWSER}}] # [!code highlight]
)
# Exclude specific UI actions
model_with_computer = model.bind_tools(
[
{
"computer_use": {
"environment": Environment.ENVIRONMENT_BROWSER,
"excludedPredefinedFunctions": [ # [!code highlight]
"drag_and_drop", # [!code highlight]
"key_combination", # [!code highlight]
], # [!code highlight]
}
}
]
)
response = model_with_computer.invoke("Search for Python tutorials")
```
The model returns function calls for UI actions (like `click_at`, `type_text_at`, `scroll`) with normalized coordinates. You'll need to implement the actual execution of these actions in your browser automation framework.
## Safety settings
Gemini models have default safety settings that can be overridden. If you are receiving lots of `'Safety Warnings'` from your models, you can try tweaking the `safety_settings` attribute of the model. For example, to turn off safety blocking for dangerous content, you can construct your LLM as follows:
```python theme={null}
from langchain_google_genai import (
ChatGoogleGenerativeAI,
HarmBlockThreshold,
HarmCategory,
)
llm = ChatGoogleGenerativeAI(
model="gemini-3-pro-preview",
safety_settings={
HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: HarmBlockThreshold.BLOCK_NONE,
},
)
```
For an enumeration of the categories and thresholds available, see Google's [safety setting types](https://ai.google.dev/api/python/google/generativeai/types/SafetySettingDict).
## Context caching
Context caching allows you to store and reuse content (e.g., PDFs, images) for faster processing. The `cached_content` parameter accepts a cache name created via the Google Generative AI API.
This caches a single file and queries it.
```python theme={null}
import time
from google import genai
from google.genai import types
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
client = genai.Client()
# Upload file
file = client.files.upload(file="path/to/your/file")
while file.state.name == "PROCESSING":
time.sleep(2)
file = client.files.get(name=file.name)
# Create cache
model = "gemini-3-pro-preview"
cache = client.caches.create(
model=model,
config=types.CreateCachedContentConfig(
display_name="Cached Content",
system_instruction=(
"You are an expert content analyzer, and your job is to answer "
"the user's query based on the file you have access to."
),
contents=[file],
ttl="300s",
),
)
# Query with LangChain
llm = ChatGoogleGenerativeAI(
model=model,
cached_content=cache.name,
)
message = HumanMessage(content="Summarize the main points of the content.")
llm.invoke([message])
```
This caches two files using `Part` and queries them together.
```python theme={null}
import time
from google import genai
from google.genai.types import CreateCachedContentConfig, Content, Part
from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI
client = genai.Client()
# Upload files
file_1 = client.files.upload(file="./file1")
while file_1.state.name == "PROCESSING":
time.sleep(2)
file_1 = client.files.get(name=file_1.name)
file_2 = client.files.upload(file="./file2")
while file_2.state.name == "PROCESSING":
time.sleep(2)
file_2 = client.files.get(name=file_2.name)
# Create cache with multiple files
contents = [
Content(
role="user",
parts=[
Part.from_uri(file_uri=file_1.uri, mime_type=file_1.mime_type),
Part.from_uri(file_uri=file_2.uri, mime_type=file_2.mime_type),
],
)
]
model = "gemini-3-pro-preview"
cache = client.caches.create(
model=model,
config=CreateCachedContentConfig(
display_name="Cached Contents",
system_instruction=(
"You are an expert content analyzer, and your job is to answer "
"the user's query based on the files you have access to."
),
contents=contents,
ttl="300s",
),
)
# Query with LangChain
llm = ChatGoogleGenerativeAI(
model=model,
cached_content=cache.name,
)
message = HumanMessage(
content="Provide a summary of the key information across both files."
)
llm.invoke([message])
```
See the Gemini API docs on [context caching](https://ai.google.dev/gemini-api/docs/caching?lang=python) for more information.
## Response metadata
Access response metadata from the model response.
```python theme={null}
from langchain_google_genai import ChatGoogleGenerativeAI
llm = ChatGoogleGenerativeAI(model="gemini-3-pro-preview")
response = llm.invoke("Hello!")
response.response_metadata
```
```output theme={null}
{'prompt_feedback': {'block_reason': 0, 'safety_ratings': []},
'finish_reason': 'STOP',
'model_name': 'gemini-3-pro-preview',
'safety_ratings': [],
'model_provider': 'google_genai'}
```
***
## API reference
For detailed documentation of all features and configuration options, head to the [`ChatGoogleGenerativeAI`](https://reference.langchain.com/python/integrations/langchain_google_genai/#langchain_google_genai.ChatGoogleGenerativeAI) API reference.
***
[Edit the source of this page on GitHub.](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/chat/google_generative_ai.mdx)
[Connect these docs programmatically](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.