### Install google-genai with uv

Source: https://github.com/googleapis/python-genai/blob/main/README.md

Installs the Google GenAI Python client library using uv, an alternative Python package installer.

```sh
uv pip install google-genai
```

--------------------------------

### Install Google Gen AI SDK with uv

Source: https://github.com/googleapis/python-genai/blob/main/docs/_sources/index.rst.txt

Use uv to install the Google Gen AI Python SDK.

```shell
uv pip install google-genai
```

--------------------------------

### Download File for Upload Example

Source: https://github.com/googleapis/python-genai/blob/main/docs/index.html

Downloads a sample text file from Google Cloud Storage using "wget" for use in file upload examples.

```bash
!wget -q https://storage.googleapis.com/generativeai-downloads/data/a11.txt
```

--------------------------------

### Install Google Gen AI SDK with uv

Source: https://github.com/googleapis/python-genai/blob/main/docs/index.html

Use uv to install the Google Gen AI Python SDK into your environment.

```bash
uv pip install google-genai
```

--------------------------------

### Install google-genai with pip

Source: https://github.com/googleapis/python-genai/blob/main/README.md

Installs the Google GenAI Python client library using pip, the standard Python package installer.

```sh
pip install google-genai
```

--------------------------------

### Install Google Gen AI SDK with pip

Source: https://github.com/googleapis/python-genai/blob/main/docs/_sources/index.rst.txt

Use pip to install the Google Gen AI Python SDK.

```shell
pip install google-genai
```

--------------------------------

### Install Google Gen AI SDK with pip

Source: https://github.com/googleapis/python-genai/blob/main/docs/index.html

Use pip to install the Google Gen AI Python SDK into your environment.

```bash
pip install google-genai
```

--------------------------------

### Generate Multimodal Content Stream with Google GenAI Python Client

Source: https://github.com/googleapis/python-genai/blob/main/docs/genai.html

This example demonstrates streaming multimodal content generation, combining a text prompt with an image URI. Ensure the client is initialized as shown in the previous example.

```python
async for chunk in await client.aio.models.generate_content_stream(
  model='gemini-2.0-flash',
  contents=[
    types.Part.from_text('What is shown in this image?'),
    types.Part.from_uri('gs://generativeai-downloads/images/scones.jpg',
    'image/jpeg')
  ]
):
  print(chunk.text)
# The image shows a flat lay arrangement of freshly baked blueberry
# scones.
```

--------------------------------

### Initialize MCP Client for Experimental Support (Python)

Source: https://github.com/googleapis/python-genai/blob/main/docs/_sources/index.rst.txt

This snippet shows the initial setup for using experimental Model Context Protocol (MCP) support, including importing necessary libraries and initializing the GenAI client.

```python
import os
    import asyncio
    from datetime import datetime
    from mcp import ClientSession, StdioServerParameters
    from mcp.client.stdio import stdio_client
    from google import genai

    client = genai.Client()

    # Create server parameters for stdio connection
```

--------------------------------

### Create a client using environment variables

Source: https://github.com/googleapis/python-genai/blob/main/docs/_sources/index.rst.txt

Initialize a `genai.Client` without explicit parameters when environment variables are configured.

```python
from google import genai

client = genai.Client()
```

--------------------------------

### get(*, name, config=None)

Source: https://github.com/googleapis/python-genai/blob/main/docs/genai.html

Gets metadata about a FileSearchStore.

```APIDOC
## get(*, name, config=None)

### Description
Gets metadata about a FileSearchStore.

### Method Signature
get(*, name, config=None)

### Parameters
- **name** (str) - Required - The resource name of the FileSearchStore. Example: FileSearchStores/my-file-search-store-123
- **config** (GetFileSearchStoreConfig | None) - Optional - Optional parameters for the request.

### Returns
FileSearchStore - A FileSearchStore object containing the metadata.
```

--------------------------------

### client.models.generate_content (with system_instruction)

Source: https://github.com/googleapis/python-genai/blob/main/docs/index.html

Demonstrates how to call `generate_content` with a `system_instruction` and other basic configuration parameters like `max_output_tokens` and `temperature`.

```APIDOC
## SDK Method: client.models.generate_content

### Description
This method sends a request to the model to generate content, allowing for basic configuration including a system instruction to guide the model's behavior.

### Method
generate_content

### Parameters
#### Method Parameters
- **model** (string) - Required - The identifier of the model to use (e.g., 'gemini-2.0-flash-001').
- **contents** (string) - Required - The input content for the model.
- **config** (types.GenerateContentConfig) - Optional - Configuration settings for content generation.
  - **system_instruction** (string) - Optional - An instruction provided to the model to influence its behavior.
  - **max_output_tokens** (integer) - Optional - The maximum number of tokens to generate in the response.
  - **temperature** (float) - Optional - Controls the randomness of the output. Lower values (near 0) make the output more deterministic.

### Request Example
```python
from google.genai import types

response = client.models.generate_content(
    model='gemini-2.0-flash-001',
    contents='high',
    config=types.GenerateContentConfig(
        system_instruction='I say high, you say low',
        max_output_tokens=3,
        temperature=0.3,
    ),
)
print(response.text)
```

### Response
#### Success Response
- **text** (string) - The generated text content from the model.
```

--------------------------------

### get(name, config=None)

Source: https://github.com/googleapis/python-genai/blob/main/docs/genai.html

Gets a batch job.

```APIDOC
## get

### Description
Gets a batch job.

### Signature
async get(*, name, config=None)

### Parameters
- **name** (str)
- **config** (None)
```

--------------------------------

### get(name, config)

Source: https://github.com/googleapis/python-genai/blob/main/docs/genai.html

Gets metadata about a FileSearchStore asynchronously.

```APIDOC
## get(name, config)

### Description
Gets metadata about a FileSearchStore.

### Parameters
- **name** (str) - Required - The resource name of the FileSearchStore. Example: FileSearchStores/my-file-search-store-123
- **config** (GetFileSearchStoreConfig | None) - Optional - Optional parameters for the request.

### Returns
FileSearchStore - A FileSearchStore object containing the metadata.
```

--------------------------------

### Download a file (Python)

Source: https://github.com/googleapis/python-genai/blob/main/docs/genai.html

This example demonstrates how to find a downloadable file by iterating through the file list and then download its data. Files created by upload cannot be downloaded.

```python
for file client.files.list():
  if file.download_uri is not None:
    break
else:
  raise ValueError('No files found with a `download_uri`.')
data = client.files.download(file=file)
# data = client.files.download(file=file.name)
# data = client.files.download(file=file.uri)
```

--------------------------------

### Python Custom Parser Rubrics Example

Source: https://github.com/googleapis/python-genai/blob/main/docs/genai.html

An example of the list of dictionaries expected when the custom parsing function returns rubrics.

```python
[ { \"content\": {\"property\": {\"description\": \"The response is factual.\"}}, \"type\": \"FACTUALITY\", \"importance\": \"HIGH\" }, { \"content\": {\"property\": {\"description\": \"The response is fluent.\"}}, \"type\": \"FLUENCY\", \"importance\": \"MEDIUM\" } ]
```

--------------------------------

### create(config)

Source: https://github.com/googleapis/python-genai/blob/main/docs/genai.html

Creates a File Search Store synchronously.

```APIDOC
## create(config)

### Description
Creates a File Search Store.

### Parameters
- **config** (CreateFileSearchStoreConfig | None) - Optional - Optional parameters for the request.

### Returns
FileSearchStore
```

--------------------------------

### Generate video from image with Veo using Python GenAI

Source: https://github.com/googleapis/python-genai/blob/main/docs/index.html

This example demonstrates generating a video from an input image and an optional prompt. It shows how to load an image from a local file and poll the asynchronous operation for the generated video. Video generation is currently in public preview.

```python
from google.genai import types

# Read local image (uses mimetypes.guess_type to infer mime type)
image = types.Image.from_file(location="local/path/file.png")

# Create operation
operation = client.models.generate_videos(
    model='veo-2.0-generate-001',
    # Prompt is optional if image is provided
    prompt='Night sky',
    image=image,
    config=types.GenerateVideosConfig(
        number_of_videos=1,
        duration_seconds=5,
        enhance_prompt=True,
        # Can also pass an Image into last_frame for frame interpolation
    ),
)

# Poll operation
while not operation.done:
    time.sleep(20)
    operation = client.operations.get(operation)

video = operation.response.generated_videos[0].video
video.show()
```

--------------------------------

### Python Custom Parser Metric Result Example

Source: https://github.com/googleapis/python-genai/blob/main/docs/genai.html

An example of the dictionary expected when the custom parsing function returns a single metric result.

```python
{ \"score\": 0.8, \"explanation\": \"The model followed most instructions.\", \"rubric_verdicts\": [...] }
```

--------------------------------

### Create a client for Gemini Developer API

Source: https://github.com/googleapis/python-genai/blob/main/docs/index.html

Initialize a `genai.Client` instance for the Gemini Developer API using an API key.

```python
from google import genai

# Only run this block for Gemini Developer API
client = genai.Client(api_key='GEMINI_API_KEY')
```

--------------------------------

### Create a client for Gemini Developer API

Source: https://github.com/googleapis/python-genai/blob/main/docs/_sources/index.rst.txt

Initialize a `genai.Client` for the Gemini Developer API, providing your API key.

```python
from google import genai

# Only run this block for Gemini Developer API
client = genai.Client(api_key='GEMINI_API_KEY')
```

--------------------------------

### Function Parameters Schema Example (YAML-like)

Source: https://github.com/googleapis/python-genai/blob/main/docs/genai.html

This example shows a simple schema for function parameters, defining one required string parameter and one optional integer parameter.

```YAML
type: OBJECT properties: param1: type: STRING param2: type: INTEGER required: - param1
```

--------------------------------

### AsyncLive.connect()

Source: https://github.com/googleapis/python-genai/blob/main/docs/index.html

Asynchronously establishes a live connection.

```APIDOC
## AsyncLive.connect()

### Description
Asynchronously establishes a live connection.

### Class
`AsyncLive`

### Method
`connect()`
```

--------------------------------

### Create a client for Vertex AI API

Source: https://github.com/googleapis/python-genai/blob/main/docs/index.html

Initialize a `genai.Client` instance for the Vertex AI API, specifying project and location.

```python
from google import genai

# Only run this block for Vertex AI API
client = genai.Client(
    vertexai=True, project='your-project-id', location='us-central1'
)
```

--------------------------------

### Start Live Session from Audio Stream (Deprecated)

Source: https://github.com/googleapis/python-genai/blob/main/docs/genai.html

This deprecated method starts a live session from an audio stream, processing audio responses. It is recommended to use send_client_content, send_realtime_input, or send_tool_response instead.

```python
client = genai.Client(api_key=API_KEY)
config = {'response_modalities': ['AUDIO']}
async def audio_stream():
  stream = read_audio()
  for data in stream:
    yield data
async with client.aio.live.connect(model='...', config=config) as session:
  for audio in session.start_stream(stream = audio_stream(),
  mime_type = 'audio/pcm'):
    play_audio_chunk(audio.data)
```

--------------------------------

### Example Return Values for Custom Parsing Function

Source: https://github.com/googleapis/python-genai/blob/main/docs/genai.html

Illustrates the expected JSON structure for the return value of a custom parsing function, showing examples for both rubric results (a list of dictionaries) and a single metric result (a dictionary).

```json
[ { "content": {"property": {"description": "The response is factual."}}, "type": "FACTUALITY", "importance": "HIGH" }, { "content": {"property": {"description": "The response is fluent."}}, "type": "FLUENCY", "importance": "MEDIUM" } ]
```

```json
{ "score": 0.8, "explanation": "The model followed most instructions.", "rubric_verdicts": [...] }
```

--------------------------------

### Create a client for Vertex AI API

Source: https://github.com/googleapis/python-genai/blob/main/docs/_sources/index.rst.txt

Initialize a `genai.Client` for the Vertex AI API, specifying `vertexai=True`, project ID, and location.

```python
from google import genai

# Only run this block for Vertex AI API
client = genai.Client(
    vertexai=True, project='your-project-id', location='us-central1'
)
```

--------------------------------

### Configure generate_content with system instructions in Python

Source: https://github.com/googleapis/python-genai/blob/main/docs/index.html

Call `client.models.generate_content` with `types.GenerateContentConfig` to set system instructions, maximum output tokens, and temperature for model responses.

```python
from google.genai import types

response = client.models.generate_content(
    model='gemini-2.0-flash-001',
    contents='high',
    config=types.GenerateContentConfig(
        system_instruction='I say high, you say low',
        max_output_tokens=3,
        temperature=0.3,
    ),
)
print(response.text)
```

--------------------------------

### AsyncSession.start_stream()

Source: https://github.com/googleapis/python-genai/blob/main/docs/index.html

Asynchronously starts a streaming session.

```APIDOC
## AsyncSession.start_stream()

### Description
Asynchronously starts a streaming session.

### Class
`AsyncSession`

### Method
`start_stream()`
```

--------------------------------

### Configure Gemini Model with System Instructions and Parameters (Python)

Source: https://github.com/googleapis/python-genai/blob/main/README.md

Use GenerateContentConfig to set system instructions, control response length with max_output_tokens, and adjust randomness with temperature for deterministic outputs.

```python
from google.genai import types

response = client.models.generate_content(
    model='gemini-3.5-flash',
    contents='high',
    config=types.GenerateContentConfig(
        system_instruction='I say high, you say low',
        max_output_tokens=3,
        temperature=0.3,
    ),
)
print(response.text)
```

--------------------------------

### Caches.get

Source: https://github.com/googleapis/python-genai/blob/main/docs/genai.html

Gets cached content configurations synchronously.

```APIDOC
## Caches.get

### Description
Gets cached content configurations.

### Signature
```python
get(*, name, config=None)
```

### Parameters
- **name** (string) - Required - The server-generated resource name.
- **config** (dict) - Optional - Optional configuration for the get request.

### Returns
[`CachedContent`](#genai.types.CachedContent)

### Usage Example
```python
client.caches.get(name= ... ) // The server-generated resource name.
```
```

--------------------------------

### AsyncCaches.get

Source: https://github.com/googleapis/python-genai/blob/main/docs/genai.html

Gets cached content configurations asynchronously.

```APIDOC
## AsyncCaches.get

### Description
Gets cached content configurations.

### Signature
```python
async get(*, name, config=None)
```

### Parameters
- **name** (string) - Required - The server-generated resource name.
- **config** (dict) - Optional - Optional configuration for the get request.

### Returns
[`CachedContent`](#genai.types.CachedContent)

### Usage Example
```python
await client.aio.caches.get(name= ... ) // The server-generated resource name.
```
```

--------------------------------

### AsyncSession.start_stream()

Source: https://github.com/googleapis/python-genai/blob/main/docs/modules.html

Asynchronously starts a stream within the session.

```APIDOC
## `AsyncSession.start_stream()`

### Description
Asynchronously starts a stream within the session.

### Class
`AsyncSession`

### Method
`start_stream`

### Signature
`AsyncSession.start_stream()`
```