google-genai 0.8.0__tar.gz → 1.3.0__tar.gz

{google_genai-0.8.0 → google_genai-1.3.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: google-genai
-Version: 0.8.0
+Version: 1.3.0
 Summary: GenAI Python SDK
 Author-email: Google LLC <googleapis-packages@google.com>
 License: Apache-2.0
@@ -21,9 +21,11 @@ Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: google-auth<3.0.0dev,>=2.14.1
+Requires-Dist: httpx<1.0.0dev,>=0.28.1
 Requires-Dist: pydantic<3.0.0dev,>=2.0.0
 Requires-Dist: requests<3.0.0dev,>=2.28.1
 Requires-Dist: websockets<15.0dev,>=13.0
+Requires-Dist: typing-extensions<5.0.0dev,>=4.11.0
 
 # Google Gen AI SDK
 
@@ -34,7 +36,7 @@ Requires-Dist: websockets<15.0dev,>=13.0
 
 -----
 
-Google Gen AI Python SDK provides an interface for developers to integrate Google's generative models into their Python applications. It supports the [Gemini Developer API](https://ai.google.dev/gemini-api/docs) and [Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/overview) APIs. This is an early release. API is subject to change. Please do not use this SDK in production environments at this stage.
+Google Gen AI Python SDK provides an interface for developers to integrate Google's generative models into their Python applications. It supports the [Gemini Developer API](https://ai.google.dev/gemini-api/docs) and [Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/overview) APIs.
 
 ## Installation
 
@@ -56,13 +58,65 @@ different services ([Gemini Developer API](https://ai.google.dev/gemini-api/docs
 
 ```python
 # Only run this block for Gemini Developer API
-client = genai.Client(api_key="GEMINI_API_KEY")
+client = genai.Client(api_key='GEMINI_API_KEY')
 ```
 
 ```python
 # Only run this block for Vertex AI API
 client = genai.Client(
-    vertexai=True, project="your-project-id", location="us-central1"
+    vertexai=True, project='your-project-id', location='us-central1'
+)
+```
+
+**(Optional) Using environment variables:**
+
+You can create a client by configuring the necessary environment variables.
+Configuration setup instructions depends on whether you're using the Gemini API
+on Vertex AI or the ML Dev Gemini API.
+
+**ML Dev Gemini API:** Set `GOOGLE_API_KEY` as shown below:
+
+```bash
+export GOOGLE_API_KEY='your-api-key'
+```
+
+**Vertex AI API:** Set `GOOGLE_GENAI_USE_VERTEXAI`, `GOOGLE_CLOUD_PROJECT`
+and `GOOGLE_CLOUD_LOCATION`, as shown below:
+
+```bash
+export GOOGLE_GENAI_USE_VERTEXAI=true
+export GOOGLE_CLOUD_PROJECT='your-project-id'
+export GOOGLE_CLOUD_LOCATION='us-central1'
+```
+
+```python
+client = genai.Client()
+```
+
+### API Selection
+
+By default, the SDK uses the beta API endpoints provided by Google to support
+preview features in the APIs. The stable API endpoints can be selected by
+setting the API version to `v1`.
+
+To set the API version use `http_options`. For example, to set the API version
+to `v1` for Vertex AI:
+
+```python
+client = genai.Client(
+    vertexai=True,
+    project='your-project-id',
+    location='us-central1',
+    http_options=types.HttpOptions(api_version='v1')
+)
+```
+
+To set the API version to `v1alpha` for the Gemini Developer API:
+
+```python
+client = genai.Client(
+    api_key='GEMINI_API_KEY',
+    http_options=types.HttpOptions(api_version='v1alpha')
 )
 ```
 
@@ -82,7 +136,7 @@ The `client.models` modules exposes model inferencing and model getters.
 
 ```python
 response = client.models.generate_content(
-    model="gemini-2.0-flash-exp", contents="why is the sky blue?"
+    model='gemini-2.0-flash-001', contents='Why is the sky blue?'
 )
 print(response.text)
 ```
@@ -90,29 +144,60 @@ print(response.text)
 #### with uploaded file (Gemini API only)
 download the file in console.
 
-```cmd
+```sh
 !wget -q https://storage.googleapis.com/generativeai-downloads/data/a11.txt
 ```
 
 python code.
 
 ```python
-file = client.files.upload(path="a11.txt")
+file = client.files.upload(file='a11.txt')
 response = client.models.generate_content(
-    model="gemini-2.0-flash-exp",
-    contents=["Could you summarize this file?", file]
+    model='gemini-2.0-flash-001',
+    contents=['Could you summarize this file?', file]
 )
 print(response.text)
 ```
 
+#### How to structure `contents`
+There are several ways to structure the `contents` in your request.
+
+Provide a single string as shown in the text example above:
+
+```python
+contents='Can you recommend some things to do in Boston and New York in the winter?'
+```
+
+Provide a single `Content` instance with multiple `Part` instances:
+
+```python
+contents=types.Content(parts=[
+    types.Part.from_text(text='Can you recommend some things to do in Boston in the winter?'),
+    types.Part.from_text(text='Can you recommend some things to do in New York in the winter?')
+], role='user')
+```
+
+When sending more than one input type, provide a list with multiple `Content`
+instances:
+
+```python
+contents=[
+    'What is this a picture of?',
+    types.Part.from_uri(
+        file_uri='gs://generativeai-downloads/images/scones.jpg',
+        mime_type='image/jpeg',
+    ),
+],
+```
+
 ### System Instructions and Other Configs
 
 ```python
 response = client.models.generate_content(
-    model="gemini-2.0-flash-exp",
-    contents="high",
+    model='gemini-2.0-flash-001',
+    contents='high',
     config=types.GenerateContentConfig(
-        system_instruction="I say high, you say low",
+        system_instruction='I say high, you say low',
         temperature=0.3,
     ),
 )
@@ -126,8 +211,8 @@ dictionaries. You can get the type from `google.genai.types`.
 
 ```python
 response = client.models.generate_content(
-    model="gemini-2.0-flash-exp",
-    contents=types.Part.from_text(text="Why is the sky blue?"),
+    model='gemini-2.0-flash-001',
+    contents=types.Part.from_text(text='Why is the sky blue?'),
     config=types.GenerateContentConfig(
         temperature=0,
         top_p=0.95,
@@ -135,7 +220,7 @@ response = client.models.generate_content(
         candidate_count=1,
         seed=5,
         max_output_tokens=100,
-        stop_sequences=["STOP!"],
+        stop_sequences=['STOP!'],
         presence_penalty=0.0,
         frequency_penalty=0.0,
     ),
@@ -144,53 +229,17 @@ response = client.models.generate_content(
 print(response.text)
 ```
 
-### Thinking
-
-The Gemini 2.0 Flash Thinking model is an experimental model that could return
-"thoughts" as part of its response.
-
-#### Gemini Developer API
-
-Thinking config is only available in v1alpha for Gemini AI API.
-
-```python
-response = client.models.generate_content(
-    model='gemini-2.0-flash-thinking-exp',
-    contents='What is the sum of natural numbers from 1 to 100?',
-    config=types.GenerateContentConfig(
-        thinking_config=types.ThinkingConfig(include_thoughts=True),
-        http_options=types.HttpOptions(api_version='v1alpha'),
-    )
-)
-for part in response.candidates[0].content.parts:
-    print(part)
-```
-
-#### Vertex AI API
-
-```python
-response = client.models.generate_content(
-    model='gemini-2.0-flash-thinking-exp-01-21',
-    contents='What is the sum of natural numbers from 1 to 100?',
-    config=types.GenerateContentConfig(
-        thinking_config=types.ThinkingConfig(include_thoughts=True),
-    )
-)
-for part in response.candidates[0].content.parts:
-    print(part)
-```
-
 ### List Base Models
 
 To retrieve tuned models, see [list tuned models](#list-tuned-models).
 
 ```python
-for model in client.models.list(config={'query_base':True}):
+for model in client.models.list():
     print(model)
 ```
 
 ```python
-pager = client.models.list(config={"page_size": 10, 'query_base':True})
+pager = client.models.list(config={'page_size': 10})
 print(pager.page_size)
 print(pager[0])
 pager.next_page()
@@ -200,12 +249,12 @@ print(pager[0])
 #### Async
 
 ```python
-async for job in await client.aio.models.list(config={'query_base':True}):
+async for job in await client.aio.models.list():
     print(job)
 ```
 
 ```python
-async_pager = await client.aio.models.list(config={"page_size": 10, 'query_base':True})
+async_pager = await client.aio.models.list(config={'page_size': 10})
 print(async_pager.page_size)
 print(async_pager[0])
 await async_pager.next_page()
@@ -216,13 +265,13 @@ print(async_pager[0])
 
 ```python
 response = client.models.generate_content(
-    model="gemini-2.0-flash-exp",
-    contents="Say something bad.",
+    model='gemini-2.0-flash-001',
+    contents='Say something bad.',
     config=types.GenerateContentConfig(
         safety_settings=[
             types.SafetySetting(
-                category="HARM_CATEGORY_HATE_SPEECH",
-                threshold="BLOCK_ONLY_HIGH",
+                category='HARM_CATEGORY_HATE_SPEECH',
+                threshold='BLOCK_ONLY_HIGH',
             )
         ]
     ),
@@ -235,7 +284,7 @@ print(response.text)
 #### Automatic Python function Support
 
 You can pass a Python function directly and it will be automatically
-called and responded.
+called and responded by default.
 
 ```python
 def get_current_weather(location: str) -> str:
@@ -244,17 +293,41 @@ def get_current_weather(location: str) -> str:
     Args:
       location: The city and state, e.g. San Francisco, CA
     """
-    return "sunny"
+    return 'sunny'
 
 
 response = client.models.generate_content(
-    model="gemini-2.0-flash-exp",
-    contents="What is the weather like in Boston?",
+    model='gemini-2.0-flash-001',
+    contents='What is the weather like in Boston?',
     config=types.GenerateContentConfig(tools=[get_current_weather]),
 )
 
 print(response.text)
 ```
+#### Disabling automatic function calling
+If you pass in a python function as a tool directly, and do not want
+automatic function calling, you can disable automatic function calling
+as follows:
+
+```python
+response = client.models.generate_content(
+  model='gemini-2.0-flash-001',
+  contents='What is the weather like in Boston?',
+  config=types.GenerateContentConfig(
+    tools=[get_current_weather],
+    automatic_function_calling=types.AutomaticFunctionCallingConfig(
+      disable=True
+    ),
+  ),
+)
+```
+
+With automatic function calling disabled, you will get a list of function call
+parts in the response:
+
+```python
+function_calls: Optional[List[types.FunctionCall]] = response.function_calls
+```
 
 #### Manually declare and invoke a function for function calling
 
@@ -266,25 +339,25 @@ Then you will receive a function call part in the response.
 
 ```python
 function = types.FunctionDeclaration(
-    name="get_current_weather",
-    description="Get the current weather in a given location",
+    name='get_current_weather',
+    description='Get the current weather in a given location',
     parameters=types.Schema(
-        type="OBJECT",
+        type='OBJECT',
         properties={
-            "location": types.Schema(
-                type="STRING",
-                description="The city and state, e.g. San Francisco, CA",
+            'location': types.Schema(
+                type='STRING',
+                description='The city and state, e.g. San Francisco, CA',
             ),
         },
-        required=["location"],
+        required=['location'],
     ),
 )
 
 tool = types.Tool(function_declarations=[function])
 
 response = client.models.generate_content(
-    model="gemini-2.0-flash-exp",
-    contents="What is the weather like in Boston?",
+    model='gemini-2.0-flash-001',
+    contents='What is the weather like in Boston?',
     config=types.GenerateContentConfig(tools=[tool]),
 )
 
@@ -298,33 +371,34 @@ The following example shows how to do it for a simple function invocation.
 
 ```python
 user_prompt_content = types.Content(
-    role="user",
-    parts=[types.Part.from_text(text="What is the weather like in Boston?")],
+    role='user',
+    parts=[types.Part.from_text(text='What is the weather like in Boston?')],
 )
 function_call_part = response.function_calls[0]
+function_call_content = response.candidates[0].content
 
 
 try:
     function_result = get_current_weather(
         **function_call_part.function_call.args
     )
-    function_response = {"result": function_result}
+    function_response = {'result': function_result}
 except (
     Exception
 ) as e:  # instead of raising the exception, you can let the model handle it
-    function_response = {"error": str(e)}
+    function_response = {'error': str(e)}
 
 
 function_response_part = types.Part.from_function_response(
-    name=function_call_part.function_call.name,
+    name=function_call_part.name,
     response=function_response,
 )
 function_response_content = types.Content(
-    role="tool", parts=[function_response_part]
+    role='tool', parts=[function_response_part]
 )
 
 response = client.models.generate_content(
-    model="gemini-2.0-flash-exp",
+    model='gemini-2.0-flash-001',
     contents=[
         user_prompt_content,
         function_call_content,
@@ -338,6 +412,66 @@ response = client.models.generate_content(
 print(response.text)
 ```
 
+#### Function calling with `ANY` tools config mode
+
+If you configure function calling mode to be `ANY`, then the model will always
+return function call parts. If you also pass a python function as a tool, by
+default the SDK will perform automatic function calling until the remote calls exceed the
+maximum remote call for automatic function calling (default to 10 times).
+
+If you'd like to disable automatic function calling in `ANY` mode:
+
+```python
+def get_current_weather(location: str) -> str:
+    """Returns the current weather.
+
+    Args:
+      location: The city and state, e.g. San Francisco, CA
+    """
+    return "sunny"
+
+response = client.models.generate_content(
+    model="gemini-2.0-flash-001",
+    contents="What is the weather like in Boston?",
+    config=types.GenerateContentConfig(
+        tools=[get_current_weather],
+        automatic_function_calling=types.AutomaticFunctionCallingConfig(
+            disable=True
+        ),
+        tool_config=types.ToolConfig(
+            function_calling_config=types.FunctionCallingConfig(mode='ANY')
+        ),
+    ),
+)
+```
+
+If you'd like to set `x` number of automatic function call turns, you can
+configure the maximum remote calls to be `x + 1`.
+Assuming you prefer `1` turn for automatic function calling.
+
+```python
+def get_current_weather(location: str) -> str:
+    """Returns the current weather.
+
+    Args:
+      location: The city and state, e.g. San Francisco, CA
+    """
+    return "sunny"
+
+response = client.models.generate_content(
+    model="gemini-2.0-flash-001",
+    contents="What is the weather like in Boston?",
+    config=types.GenerateContentConfig(
+        tools=[get_current_weather],
+        automatic_function_calling=types.AutomaticFunctionCallingConfig(
+            maximum_remote_calls=2
+        ),
+        tool_config=types.ToolConfig(
+            function_calling_config=types.FunctionCallingConfig(mode='ANY')
+        ),
+    ),
+)
+```
 ### JSON Response Schema
 
 #### Pydantic Model Schema support
@@ -359,10 +493,10 @@ class CountryInfo(BaseModel):
 
 
 response = client.models.generate_content(
-    model="gemini-2.0-flash-exp",
-    contents="Give me information for the United States.",
+    model='gemini-2.0-flash-001',
+    contents='Give me information for the United States.',
     config=types.GenerateContentConfig(
-        response_mime_type="application/json",
+        response_mime_type='application/json',
         response_schema=CountryInfo,
     ),
 )
@@ -371,30 +505,30 @@ print(response.text)
 
 ```python
 response = client.models.generate_content(
-    model="gemini-2.0-flash-exp",
-    contents="Give me information for the United States.",
+    model='gemini-2.0-flash-001',
+    contents='Give me information for the United States.',
     config=types.GenerateContentConfig(
-        response_mime_type="application/json",
+        response_mime_type='application/json',
         response_schema={
-            "required": [
-                "name",
-                "population",
-                "capital",
-                "continent",
-                "gdp",
-                "official_language",
-                "total_area_sq_mi",
+            'required': [
+                'name',
+                'population',
+                'capital',
+                'continent',
+                'gdp',
+                'official_language',
+                'total_area_sq_mi',
             ],
-            "properties": {
-                "name": {"type": "STRING"},
-                "population": {"type": "INTEGER"},
-                "capital": {"type": "STRING"},
-                "continent": {"type": "STRING"},
-                "gdp": {"type": "INTEGER"},
-                "official_language": {"type": "STRING"},
-                "total_area_sq_mi": {"type": "INTEGER"},
+            'properties': {
+                'name': {'type': 'STRING'},
+                'population': {'type': 'INTEGER'},
+                'capital': {'type': 'STRING'},
+                'continent': {'type': 'STRING'},
+                'gdp': {'type': 'INTEGER'},
+                'official_language': {'type': 'STRING'},
+                'total_area_sq_mi': {'type': 'INTEGER'},
             },
-            "type": "OBJECT",
+            'type': 'OBJECT',
         },
     ),
 )
@@ -417,7 +551,7 @@ class InstrumentEnum(Enum):
   KEYBOARD = 'Keyboard'
 
 response = client.models.generate_content(
-      model='gemini-2.0-flash-exp',
+      model='gemini-2.0-flash-001',
       contents='What instrument plays multiple notes at once?',
       config={
           'response_mime_type': 'text/x.enum',
@@ -442,7 +576,7 @@ class InstrumentEnum(Enum):
   KEYBOARD = 'Keyboard'
 
 response = client.models.generate_content(
-      model='gemini-2.0-flash-exp',
+      model='gemini-2.0-flash-001',
       contents='What instrument plays multiple notes at once?',
       config={
           'response_mime_type': 'application/json',
@@ -458,9 +592,9 @@ print(response.text)
 
 ```python
 for chunk in client.models.generate_content_stream(
-    model="gemini-2.0-flash-exp", contents="Tell me a story in 300 words."
+    model='gemini-2.0-flash-001', contents='Tell me a story in 300 words.'
 ):
-    print(chunk.text, end="")
+    print(chunk.text, end='')
 ```
 
 #### Streaming for image content
@@ -470,35 +604,35 @@ you can use the `from_uri` class method to create a `Part` object.
 
 ```python
 for chunk in client.models.generate_content_stream(
-    model="gemini-2.0-flash-exp",
+    model='gemini-2.0-flash-001',
     contents=[
-        "What is this image about?",
+        'What is this image about?',
         types.Part.from_uri(
-            file_uri="gs://generativeai-downloads/images/scones.jpg",
-            mime_type="image/jpeg",
+            file_uri='gs://generativeai-downloads/images/scones.jpg',
+            mime_type='image/jpeg',
         ),
     ],
 ):
-    print(chunk.text, end="")
+    print(chunk.text, end='')
 ```
 
 If your image is stored in your local file system, you can read it in as bytes
 data and use the `from_bytes` class method to create a `Part` object.
 
 ```python
-YOUR_IMAGE_PATH = "your_image_path"
-YOUR_IMAGE_MIME_TYPE = "your_image_mime_type"
-with open(YOUR_IMAGE_PATH, "rb") as f:
+YOUR_IMAGE_PATH = 'your_image_path'
+YOUR_IMAGE_MIME_TYPE = 'your_image_mime_type'
+with open(YOUR_IMAGE_PATH, 'rb') as f:
     image_bytes = f.read()
 
 for chunk in client.models.generate_content_stream(
-    model="gemini-2.0-flash-exp",
+    model='gemini-2.0-flash-001',
     contents=[
-        "What is this image about?",
+        'What is this image about?',
         types.Part.from_bytes(data=image_bytes, mime_type=YOUR_IMAGE_MIME_TYPE),
     ],
 ):
-    print(chunk.text, end="")
+    print(chunk.text, end='')
 ```
 
 ### Async
@@ -511,7 +645,7 @@ of `client.models.generate_content`
 
 ```python
 response = await client.aio.models.generate_content(
-    model="gemini-2.0-flash-exp", contents="Tell me a story in 300 words."
+    model='gemini-2.0-flash-001', contents='Tell me a story in 300 words.'
 )
 
 print(response.text)
@@ -521,17 +655,17 @@ print(response.text)
 
 ```python
 async for chunk in await client.aio.models.generate_content_stream(
-    model="gemini-2.0-flash-exp", contents="Tell me a story in 300 words."
+    model='gemini-2.0-flash-001', contents='Tell me a story in 300 words.'
 ):
-    print(chunk.text, end="")
+    print(chunk.text, end='')
 ```
 
 ### Count Tokens and Compute Tokens
 
 ```python
 response = client.models.count_tokens(
-    model="gemini-2.0-flash-exp",
-    contents="why is the sky blue?",
+    model='gemini-2.0-flash-001',
+    contents='why is the sky blue?',
 )
 print(response)
 ```
@@ -542,8 +676,8 @@ Compute tokens is only supported in Vertex AI.
 
 ```python
 response = client.models.compute_tokens(
-    model="gemini-2.0-flash-exp",
-    contents="why is the sky blue?",
+    model='gemini-2.0-flash-001',
+    contents='why is the sky blue?',
 )
 print(response)
 ```
@@ -552,8 +686,8 @@ print(response)
 
 ```python
 response = await client.aio.models.count_tokens(
-    model="gemini-2.0-flash-exp",
-    contents="why is the sky blue?",
+    model='gemini-2.0-flash-001',
+    contents='why is the sky blue?',
 )
 print(response)
 ```
@@ -562,8 +696,8 @@ print(response)
 
 ```python
 response = client.models.embed_content(
-    model="text-embedding-004",
-    contents="why is the sky blue?",
+    model='text-embedding-004',
+    contents='why is the sky blue?',
 )
 print(response)
 ```
@@ -571,8 +705,8 @@ print(response)
 ```python
 # multiple contents with config
 response = client.models.embed_content(
-    model="text-embedding-004",
-    contents=["why is the sky blue?", "What is your age?"],
+    model='text-embedding-004',
+    contents=['why is the sky blue?', 'What is your age?'],
     config=types.EmbedContentConfig(output_dimensionality=10),
 )
 
@@ -588,13 +722,12 @@ Support for generate images in Gemini Developer API is behind an allowlist
 ```python
 # Generate Image
 response1 = client.models.generate_images(
-    model="imagen-3.0-generate-002",
-    prompt="An umbrella in the foreground, and a rainy night sky in the background",
+    model='imagen-3.0-generate-002',
+    prompt='An umbrella in the foreground, and a rainy night sky in the background',
     config=types.GenerateImagesConfig(
-        negative_prompt="human",
         number_of_images=1,
         include_rai_reason=True,
-        output_mime_type="image/jpeg",
+        output_mime_type='image/jpeg',
     ),
 )
 response1.generated_images[0].image.show()
@@ -607,12 +740,12 @@ Upscale image is only supported in Vertex AI.
 ```python
 # Upscale the generated image from above
 response2 = client.models.upscale_image(
-    model="imagen-3.0-generate-001",
+    model='imagen-3.0-generate-001',
     image=response1.generated_images[0].image,
-    upscale_factor="x2",
+    upscale_factor='x2',
     config=types.UpscaleImageConfig(
         include_rai_reason=True,
-        output_mime_type="image/jpeg",
+        output_mime_type='image/jpeg',
     ),
 )
 response2.generated_images[0].image.show()
@@ -637,26 +770,53 @@ raw_ref_image = RawReferenceImage(
 mask_ref_image = MaskReferenceImage(
     reference_id=2,
     config=types.MaskReferenceConfig(
-        mask_mode="MASK_MODE_BACKGROUND",
+        mask_mode='MASK_MODE_BACKGROUND',
         mask_dilation=0,
     ),
 )
 
 response3 = client.models.edit_image(
-    model="imagen-3.0-capability-001",
-    prompt="Sunlight and clear sky",
+    model='imagen-3.0-capability-001',
+    prompt='Sunlight and clear sky',
     reference_images=[raw_ref_image, mask_ref_image],
     config=types.EditImageConfig(
-        edit_mode="EDIT_MODE_INPAINT_INSERTION",
+        edit_mode='EDIT_MODE_INPAINT_INSERTION',
         number_of_images=1,
-        negative_prompt="human",
         include_rai_reason=True,
-        output_mime_type="image/jpeg",
+        output_mime_type='image/jpeg',
     ),
 )
 response3.generated_images[0].image.show()
 ```
 
+### Veo
+
+#### Generate Videos
+
+Support for generate videos in Vertex and Gemini Developer API is behind an allowlist
+
+```python
+# Create operation
+operation = client.models.generate_videos(
+    model='veo-2.0-generate-001',
+    prompt='A neon hologram of a cat driving at top speed',
+    config=types.GenerateVideosConfig(
+        number_of_videos=1,
+        fps=24,
+        duration_seconds=5,
+        enhance_prompt=True,
+    ),
+)
+
+# Poll operation
+while not operation.done:
+    time.sleep(20)
+    operation = client.operations.get(operation)
+
+video = operation.result.generated_videos[0].video
+video.show()
+```
+
 ## Chats
 
 Create a chat session to start a multi-turn conversations with the model.
@@ -664,32 +824,32 @@ Create a chat session to start a multi-turn conversations with the model.
 ### Send Message
 
 ```python
-chat = client.chats.create(model="gemini-2.0-flash-exp")
-response = chat.send_message("tell me a story")
+chat = client.chats.create(model='gemini-2.0-flash-001')
+response = chat.send_message('tell me a story')
 print(response.text)
 ```
 
 ### Streaming
 
 ```python
-chat = client.chats.create(model="gemini-2.0-flash-exp")
-for chunk in chat.send_message_stream("tell me a story"):
+chat = client.chats.create(model='gemini-2.0-flash-001')
+for chunk in chat.send_message_stream('tell me a story'):
     print(chunk.text)
 ```
 
 ### Async
 
 ```python
-chat = client.aio.chats.create(model="gemini-2.0-flash-exp")
-response = await chat.send_message("tell me a story")
+chat = client.aio.chats.create(model='gemini-2.0-flash-001')
+response = await chat.send_message('tell me a story')
 print(response.text)
 ```
 
 ### Async Streaming
 
 ```python
-chat = client.aio.chats.create(model="gemini-2.0-flash-exp")
-async for chunk in await chat.send_message_stream("tell me a story"):
+chat = client.aio.chats.create(model='gemini-2.0-flash-001')
+async for chunk in await chat.send_message_stream('tell me a story'):
     print(chunk.text)
 ```
 
@@ -705,17 +865,24 @@ Files are only supported in Gemini Developer API.
 ### Upload
 
 ```python
-file1 = client.files.upload(path="2312.11805v3.pdf")
-file2 = client.files.upload(path="2403.05530.pdf")
+file1 = client.files.upload(file='2312.11805v3.pdf')
+file2 = client.files.upload(file='2403.05530.pdf')
 
 print(file1)
 print(file2)
 ```
 
+### Get
+
+```python
+file1 = client.files.upload(file='2312.11805v3.pdf')
+file_info = client.files.get(name=file1.name)
+```
+
 ### Delete
 
 ```python
-file3 = client.files.upload(path="2312.11805v3.pdf")
+file3 = client.files.upload(file='2312.11805v3.pdf')
 
 client.files.delete(name=file3.name)
 ```
@@ -729,32 +896,32 @@ client.files.delete(name=file3.name)
 ```python
 if client.vertexai:
     file_uris = [
-        "gs://cloud-samples-data/generative-ai/pdf/2312.11805v3.pdf",
-        "gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf",
+        'gs://cloud-samples-data/generative-ai/pdf/2312.11805v3.pdf',
+        'gs://cloud-samples-data/generative-ai/pdf/2403.05530.pdf',
     ]
 else:
     file_uris = [file1.uri, file2.uri]
 
 cached_content = client.caches.create(
-    model="gemini-1.5-pro-002",
+    model='gemini-1.5-pro-002',
     config=types.CreateCachedContentConfig(
         contents=[
             types.Content(
-                role="user",
+                role='user',
                 parts=[
                     types.Part.from_uri(
-                        file_uri=file_uris[0], mime_type="application/pdf"
+                        file_uri=file_uris[0], mime_type='application/pdf'
                     ),
                     types.Part.from_uri(
                         file_uri=file_uris[1],
-                        mime_type="application/pdf",
+                        mime_type='application/pdf',
                     ),
                 ],
             )
         ],
-        system_instruction="What is the sum of the two pdfs?",
-        display_name="test cache",
-        ttl="3600s",
+        system_instruction='What is the sum of the two pdfs?',
+        display_name='test cache',
+        ttl='3600s',
     ),
 )
 ```
@@ -769,8 +936,8 @@ cached_content = client.caches.get(name=cached_content.name)
 
 ```python
 response = client.models.generate_content(
-    model="gemini-1.5-pro-002",
-    contents="Summarize the pdfs",
+    model='gemini-1.5-pro-002',
+    contents='Summarize the pdfs',
     config=types.GenerateContentConfig(
         cached_content=cached_content.name,
     ),
@@ -790,17 +957,17 @@ tuning through `tune`.
 
 ```python
 if client.vertexai:
-    model = "gemini-1.5-pro-002"
+    model = 'gemini-1.5-pro-002'
     training_dataset = types.TuningDataset(
-        gcs_uri="gs://cloud-samples-data/ai-platform/generative_ai/gemini-1_5/text/sft_train_data.jsonl",
+        gcs_uri='gs://cloud-samples-data/ai-platform/generative_ai/gemini-1_5/text/sft_train_data.jsonl',
     )
 else:
-    model = "models/gemini-1.0-pro-001"
+    model = 'models/gemini-1.0-pro-001'
     training_dataset = types.TuningDataset(
         examples=[
             types.TuningExample(
-                text_input=f"Input text {i}",
-                output=f"Output text {i}",
+                text_input=f'Input text {i}',
+                output=f'Output text {i}',
             )
             for i in range(5)
         ],
@@ -812,7 +979,7 @@ tuning_job = client.tunings.tune(
     base_model=model,
     training_dataset=training_dataset,
     config=types.CreateTuningJobConfig(
-        epoch_count=1, tuned_model_display_name="test_dataset_examples model"
+        epoch_count=1, tuned_model_display_name='test_dataset_examples model'
     ),
 )
 print(tuning_job)
@@ -830,8 +997,8 @@ import time
 
 running_states = set(
     [
-        "JOB_STATE_PENDING",
-        "JOB_STATE_RUNNING",
+        'JOB_STATE_PENDING',
+        'JOB_STATE_RUNNING',
     ]
 )
 
@@ -846,7 +1013,7 @@ while tuning_job.state in running_states:
 ```python
 response = client.models.generate_content(
     model=tuning_job.tuned_model.endpoint,
-    contents="why is the sky blue?",
+    contents='why is the sky blue?',
 )
 
 print(response.text)
@@ -864,12 +1031,12 @@ print(tuned_model)
 To retrieve base models, see [list base models](#list-base-models).
 
 ```python
-for model in client.models.list(config={"page_size": 10}):
+for model in client.models.list(config={'page_size': 10, 'query_base': False}):
     print(model)
 ```
 
 ```python
-pager = client.models.list(config={"page_size": 10})
+pager = client.models.list(config={'page_size': 10, 'query_base': False})
 print(pager.page_size)
 print(pager[0])
 pager.next_page()
@@ -879,12 +1046,12 @@ print(pager[0])
 #### Async
 
 ```python
-async for job in await client.aio.models.list(config={"page_size": 10}):
+async for job in await client.aio.models.list(config={'page_size': 10, 'query_base': False}):
     print(job)
 ```
 
 ```python
-async_pager = await client.aio.models.list(config={"page_size": 10})
+async_pager = await client.aio.models.list(config={'page_size': 10, 'query_base': False})
 print(async_pager.page_size)
 print(async_pager[0])
 await async_pager.next_page()
@@ -899,7 +1066,7 @@ model = pager[0]
 model = client.models.update(
     model=model.name,
     config=types.UpdateModelConfig(
-        display_name="my tuned model", description="my tuned model description"
+        display_name='my tuned model', description='my tuned model description'
     ),
 )
 
@@ -910,12 +1077,12 @@ print(model)
 ### List Tuning Jobs
 
 ```python
-for job in client.tunings.list(config={"page_size": 10}):
+for job in client.tunings.list(config={'page_size': 10}):
     print(job)
 ```
 
 ```python
-pager = client.tunings.list(config={"page_size": 10})
+pager = client.tunings.list(config={'page_size': 10})
 print(pager.page_size)
 print(pager[0])
 pager.next_page()
@@ -925,12 +1092,12 @@ print(pager[0])
 #### Async
 
 ```python
-async for job in await client.aio.tunings.list(config={"page_size": 10}):
+async for job in await client.aio.tunings.list(config={'page_size': 10}):
     print(job)
 ```
 
 ```python
-async_pager = await client.aio.tunings.list(config={"page_size": 10})
+async_pager = await client.aio.tunings.list(config={'page_size': 10})
 print(async_pager.page_size)
 print(async_pager[0])
 await async_pager.next_page()
@@ -946,8 +1113,8 @@ Only supported in Vertex AI.
 ```python
 # Specify model and source file only, destination and job display name will be auto-populated
 job = client.batches.create(
-    model="gemini-1.5-flash-002",
-    src="bq://my-project.my-dataset.my-table",
+    model='gemini-1.5-flash-002',
+    src='bq://my-project.my-dataset.my-table',
 )
 
 job
@@ -963,10 +1130,10 @@ job.state
 ```python
 completed_states = set(
     [
-        "JOB_STATE_SUCCEEDED",
-        "JOB_STATE_FAILED",
-        "JOB_STATE_CANCELLED",
-        "JOB_STATE_PAUSED",
+        'JOB_STATE_SUCCEEDED',
+        'JOB_STATE_FAILED',
+        'JOB_STATE_CANCELLED',
+        'JOB_STATE_PAUSED',
     ]
 )
 
@@ -1020,3 +1187,20 @@ delete_job = client.batches.delete(name=job.name)
 
 delete_job
 ```
+
+## Error Handling
+
+To handle errors raised by the model service, the SDK provides this [APIError](https://github.com/googleapis/python-genai/blob/main/google/genai/errors.py) class.
+
+```python
+from google.genai import errors
+
+try:
+  client.models.generate_content(
+      model="invalid-model-name",
+      contents="What is your name?",
+  )
+except errors.APIError as e:
+  print(e.code) # 404
+  print(e.message)
+```