ChatGoogleGenerativeAI

pip install -U langchain-google-genai

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: ")

os.environ["LANGSMITH_API_KEY"] = getpass.getpass("Enter your LangSmith API key: ")
os.environ["LANGSMITH_TRACING"] = "true"

from langchain_google_genai import ChatGoogleGenerativeAI

llm = ChatGoogleGenerativeAI(
    model="gemini-2.5-flash",
    temperature=0,
    max_tokens=None,
    timeout=None,
    max_retries=2,
    # other params...
)

messages = [
    (
        "system",
        "You are a helpful assistant that translates English to French. Translate the user sentence.",
    ),
    ("human", "I love programming."),
]
ai_msg = llm.invoke(messages)
ai_msg

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}})

print(ai_msg.content)

J'adore la programmation.

import base64

from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI

# Example using a public URL (remains the same)
message_url = HumanMessage(
    content=[
        {
            "type": "text",
            "text": "Describe the image at the URL.",
        },
        {"type": "image_url", "image_url": "https://picsum.photos/seed/picsum/200/300"},
    ]
)
result_url = llm.invoke([message_url])
print(f"Response for URL image: {result_url.content}")

# Example using a local image file encoded in base64
image_file_path = "/Users/philschmid/projects/google-gemini/langchain/docs/static/img/agents_vs_chains.png"

with open(image_file_path, "rb") as image_file:
    encoded_image = base64.b64encode(image_file.read()).decode("utf-8")

message_local = HumanMessage(
    content=[
        {"type": "text", "text": "Describe the local image."},
        {"type": "image_url", "image_url": f"data:image/png;base64,{encoded_image}"},
    ]
)
result_local = llm.invoke([message_local])
print(f"Response for local image: {result_local.content}")

import base64

from langchain.messages import HumanMessage

# Ensure you have an audio file named 'example_audio.mp3' or provide the correct path.
audio_file_path = "example_audio.mp3"
audio_mime_type = "audio/mpeg"


with open(audio_file_path, "rb") as audio_file:
    encoded_audio = base64.b64encode(audio_file.read()).decode("utf-8")

message = HumanMessage(
    content=[
        {"type": "text", "text": "Transcribe the audio."},
        {
            "type": "media",
            "data": encoded_audio,  # Use base64 string directly
            "mime_type": audio_mime_type,
        },
    ]
)
response = llm.invoke([message])  # Uncomment to run
print(f"Response for audio: {response.content}")

import base64

from langchain.messages import HumanMessage
from langchain_google_genai import ChatGoogleGenerativeAI

# Ensure you have a video file named 'example_video.mp4' or provide the correct path.
video_file_path = "example_video.mp4"
video_mime_type = "video/mp4"


with open(video_file_path, "rb") as video_file:
    encoded_video = base64.b64encode(video_file.read()).decode("utf-8")

message = HumanMessage(
    content=[
        {"type": "text", "text": "Describe the first few frames of the video."},
        {
            "type": "media",
            "data": encoded_video,  # Use base64 string directly
            "mime_type": video_mime_type,
        },
    ]
)
response = llm.invoke([message])  # Uncomment to run
print(f"Response for video: {response.content}")

# Running in a Jupyter notebook environment
import base64

from IPython.display import Image, display
from langchain.messages import AIMessage
from langchain_google_genai import ChatGoogleGenerativeAI, Modality

llm = ChatGoogleGenerativeAI(model="models/gemini-2.5-flash-image")

message = {
    "role": "user",
    "content": "Generate a photorealistic image of a cuddly cat wearing a hat.",
}

response = llm.invoke(
    [message],
    response_modalities=[Modality.TEXT, Modality.IMAGE],
)


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))

from langchain_google_genai import ChatGoogleGenerativeAI

llm = ChatGoogleGenerativeAI(model="gemini-2.5-flash-preview-tts")

response = llm.invoke(
    "Please say The quick brown fox jumps over the lazy dog",
    generation_config=dict(response_modalities=["AUDIO"]),
)

# 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)

from langchain.tools import tool
from langchain.messages import HumanMessage, ToolMessage
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-2.5-flash-lite").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)

[{'name': 'get_weather', 'args': {'location': 'Boston'}, 'id': 'fb91e46d-e3f7-445b-a62f-50ae024bcdac', 'type': 'tool_call'}]

AIMessage(content='The weather in Boston is sunny.', additional_kwargs={}, response_metadata={'prompt_feedback': {'block_reason': 0, 'safety_ratings': []}, 'finish_reason': 'STOP', 'model_name': 'gemini-2.5-flash-lite', 'safety_ratings': [], 'model_provider': 'google_genai'}, id='lc_run--3fb38729-285b-4b43-aa3e-499cbc910544-0', usage_metadata={'input_tokens': 83, 'output_tokens': 7, 'total_tokens': 90, 'input_token_details': {'cache_read': 0}})

from langchain_google_genai import ChatGoogleGenerativeAI
from pydantic import BaseModel
from typing import Literal


class Feedback(BaseModel):
    sentiment: Literal["positive", "neutral", "negative"]
    summary: str


llm = ChatGoogleGenerativeAI(model="gemini-2.5-pro")
structured_llm = llm.with_structured_output(
    schema=Feedback.model_json_schema(), method="json_schema"
)

response = structured_llm.invoke("The new UI is great!")
response["sentiment"]  # "positive"
response["summary"]  # "The user expresses positive..."

stream = structured_llm.stream("The interface is intuitive and beautiful!")
full = next(stream)
for chunk in stream:
    full.update(chunk)  # Merge dictionaries
print(full)  # Complete structured response

from langchain_google_genai import ChatGoogleGenerativeAI

llm = ChatGoogleGenerativeAI(model="gemini-2.5-flash-lite")

result = llm.invoke("Explain the concept of prompt engineering in one sentence.")

print(result.content)
print("\nUsage Metadata:")
print(result.usage_metadata)

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}}

from google.ai.generativelanguage_v1beta.types import Tool as GenAITool

resp = llm.invoke(
    "When is the next total solar eclipse in US?",
    tools=[GenAITool(google_search={})],
)

print(resp.content)

The next total solar eclipse visible in the United States will occur on August 23, 2044. However, the path of totality will only pass through Montana, North Dakota, and South Dakota.

For a total solar eclipse that crosses a significant portion of the continental U.S., you'll have to wait until August 12, 2045. This eclipse will start in California and end in Florida.

from google.ai.generativelanguage_v1beta.types import Tool as GenAITool

resp = llm.invoke(
    "What is 2*2, use python",
    tools=[GenAITool(code_execution={})],
)

for c in resp.content:
    if isinstance(c, dict):
        if c["type"] == "code_execution_result":
            print(f"Code execution result: {c['code_execution_result']}")
        elif c["type"] == "executable_code":
            print(f"Executable code: {c['executable_code']}")
    else:
        print(c)

Executable code: print(2*2)

Code execution result: 4

2*2 is 4.

from langchain_google_genai import ChatGoogleGenerativeAI

llm = ChatGoogleGenerativeAI(
    model="models/gemini-2.5-flash",
    thinking_budget=1024
)

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)

from langchain_google_genai import (
    ChatGoogleGenerativeAI,
    HarmBlockThreshold,
    HarmCategory,
)

llm = ChatGoogleGenerativeAI(
        model="gemini-2.5-pro",
        safety_settings={
        HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: HarmBlockThreshold.BLOCK_NONE,
    },
)