google-genai 1.14.0__py3-none-any.whl → 1.15.0__py3-none-any.whl

{google_genai-1.14.0.dist-info → google_genai-1.15.0.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: google-genai
-Version: 1.14.0
+Version: 1.15.0
 Summary: GenAI Python SDK
 Author-email: Google LLC <googleapis-packages@google.com>
 License: Apache-2.0
@@ -61,11 +61,15 @@ Please run one of the following code blocks to create a client for
 different services ([Gemini Developer API](https://ai.google.dev/gemini-api/docs) or [Vertex AI](https://cloud.google.com/vertex-ai/generative-ai/docs/learn/overview)).
 
 ```python
+from google import genai
+
 # Only run this block for Gemini Developer API
 client = genai.Client(api_key='GEMINI_API_KEY')
 ```
 
 ```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'
@@ -94,6 +98,8 @@ export GOOGLE_CLOUD_LOCATION='us-central1'
 ```
 
 ```python
+from google import genai
+
 client = genai.Client()
 ```
 
@@ -107,6 +113,9 @@ To set the API version use `http_options`. For example, to set the API version
 to `v1` for Vertex AI:
 
 ```python
+from google import genai
+from google.genai import types
+
 client = genai.Client(
     vertexai=True,
     project='your-project-id',
@@ -118,6 +127,9 @@ client = genai.Client(
 To set the API version to `v1alpha` for the Gemini Developer API:
 
 ```python
+from google import genai
+from google.genai import types
+
 client = genai.Client(
     api_key='GEMINI_API_KEY',
     http_options=types.HttpOptions(api_version='v1alpha')
@@ -133,6 +145,7 @@ Pydantic model types are available in the `types` module.
 ## Models
 
 The `client.models` modules exposes model inferencing and model getters.
+See the 'Create a client' section above to initialize a client.
 
 ### Generate Content
 
@@ -174,6 +187,8 @@ This is the canonical way to provide contents, SDK will not do any conversion.
 ##### Provide a `types.Content` instance
 
 ```python
+from google.genai import types
+
 contents = types.Content(
   role='user',
   parts=[types.Part.from_text(text='Why is the sky blue?')]
@@ -238,6 +253,8 @@ Where a `types.UserContent` is a subclass of `types.Content`, the
 ##### Provide a function call part
 
 ```python
+from google.genai import types
+
 contents = types.Part.from_function_call(
   name='get_weather_by_location',
   args={'location': 'Boston'}
@@ -265,6 +282,8 @@ Where a `types.ModelContent` is a subclass of `types.Content`, the
 ##### Provide a list of function call parts
 
 ```python
+from google.genai import types
+
 contents = [
   types.Part.from_function_call(
     name='get_weather_by_location',
@@ -302,6 +321,8 @@ Where a `types.ModelContent` is a subclass of `types.Content`, the
 ##### Provide a non function call part
 
 ```python
+from google.genai import types
+
 contents = types.Part.from_uri(
   file_uri: 'gs://generativeai-downloads/images/scones.jpg',
   mime_type: 'image/jpeg',
@@ -324,6 +345,8 @@ The SDK converts all non function call parts into a content with a `user` role.
 ##### Provide a list of non function call parts
 
 ```python
+from google.genai import types
+
 contents = [
   types.Part.from_text('What is this image about?'),
   types.Part.from_uri(
@@ -363,11 +386,17 @@ If you put a list within a list, the inner list can only contain
 ### System Instructions and Other Configs
 
 The output of the model can be influenced by several optional settings
-available in generate_content's config parameter. For example, the
-variability and length of the output can be influenced by the temperature
-and max_output_tokens respectively.
+available in generate_content's config parameter. For example, increasing
+`max_output_tokens` is essential for longer model responses. To make a model more
+deterministic, lowering the `temperature` parameter reduces randomness, with
+values near 0 minimizing variability. Capabilities and parameter defaults for
+each model is shown in the
+[Vertex AI docs](https://cloud.google.com/vertex-ai/generative-ai/docs/models/gemini/2-5-flash)
+and [Gemini API docs](https://ai.google.dev/gemini-api/docs/models) respectively.
 
 ```python
+from google.genai import types
+
 response = client.models.generate_content(
     model='gemini-2.0-flash-001',
     contents='high',
@@ -386,6 +415,8 @@ All API methods support Pydantic types for parameters as well as
 dictionaries. You can get the type from `google.genai.types`.
 
 ```python
+from google.genai import types
+
 response = client.models.generate_content(
     model='gemini-2.0-flash-001',
     contents=types.Part.from_text(text='Why is the sky blue?'),
@@ -422,7 +453,7 @@ pager.next_page()
 print(pager[0])
 ```
 
-#### Async
+#### List Base Models (Asynchronous)
 
 ```python
 async for job in await client.aio.models.list():
@@ -440,6 +471,8 @@ print(async_pager[0])
 ### Safety Settings
 
 ```python
+from google.genai import types
+
 response = client.models.generate_content(
     model='gemini-2.0-flash-001',
     contents='Say something bad.',
@@ -463,6 +496,8 @@ You can pass a Python function directly and it will be automatically
 called and responded by default.
 
 ```python
+from google.genai import types
+
 def get_current_weather(location: str) -> str:
     """Returns the current weather.
 
@@ -486,6 +521,8 @@ automatic function calling, you can disable automatic function calling
 as follows:
 
 ```python
+from google.genai import types
+
 response = client.models.generate_content(
   model='gemini-2.0-flash-001',
   contents='What is the weather like in Boston?',
@@ -514,6 +551,8 @@ The following example shows how to declare a function and pass it as a tool.
 Then you will receive a function call part in the response.
 
 ```python
+from google.genai import types
+
 function = types.FunctionDeclaration(
     name='get_current_weather',
     description='Get the current weather in a given location',
@@ -546,6 +585,8 @@ the model.
 The following example shows how to do it for a simple function invocation.
 
 ```python
+from google.genai import types
+
 user_prompt_content = types.Content(
     role='user',
     parts=[types.Part.from_text(text='What is the weather like in Boston?')],
@@ -598,6 +639,8 @@ maximum remote call for automatic function calling (default to 10 times).
 If you'd like to disable automatic function calling in `ANY` mode:
 
 ```python
+from google.genai import types
+
 def get_current_weather(location: str) -> str:
     """Returns the current weather.
 
@@ -626,6 +669,8 @@ configure the maximum remote calls to be `x + 1`.
 Assuming you prefer `1` turn for automatic function calling.
 
 ```python
+from google.genai import types
+
 def get_current_weather(location: str) -> str:
     """Returns the current weather.
 
@@ -660,6 +705,7 @@ Schemas can be provided as Pydantic Models.
 
 ```python
 from pydantic import BaseModel
+from google.genai import types
 
 
 class CountryInfo(BaseModel):
@@ -684,6 +730,8 @@ print(response.text)
 ```
 
 ```python
+from google.genai import types
+
 response = client.models.generate_content(
     model='gemini-2.0-flash-001',
     contents='Give me information for the United States.',
@@ -743,7 +791,8 @@ print(response.text)
 
 #### JSON Response
 
-You can also set response_mime_type to 'application/json', the response will be identical but in quotes.
+You can also set response_mime_type to 'application/json', the response will be
+identical but in quotes.
 
 ```python
 from enum import Enum
@@ -766,7 +815,10 @@ response = client.models.generate_content(
 print(response.text)
 ```
 
-### Streaming
+### Generate Content (Synchronous Streaming)
+
+Generate content in a streaming format so that the model outputs streams back
+to you, rather than being returned as one chunk.
 
 #### Streaming for text content
 
@@ -783,6 +835,8 @@ If your image is stored in [Google Cloud Storage](https://cloud.google.com/stora
 you can use the `from_uri` class method to create a `Part` object.
 
 ```python
+from google.genai import types
+
 for chunk in client.models.generate_content_stream(
     model='gemini-2.0-flash-001',
     contents=[
@@ -800,6 +854,8 @@ 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
+from google.genai import types
+
 YOUR_IMAGE_PATH = 'your_image_path'
 YOUR_IMAGE_MIME_TYPE = 'your_image_mime_type'
 with open(YOUR_IMAGE_PATH, 'rb') as f:
@@ -815,10 +871,10 @@ for chunk in client.models.generate_content_stream(
     print(chunk.text, end='')
 ```
 
-### Async
+### Generate Content (Asynchronous Non Streaming)
 
 `client.aio` exposes all the analogous [`async` methods](https://docs.python.org/3/library/asyncio.html)
-that are available on `client`
+that are available on `client`. Note that it applies to all the modules.
 
 For example, `client.aio.models.generate_content` is the `async` version
 of `client.models.generate_content`
@@ -831,7 +887,8 @@ response = await client.aio.models.generate_content(
 print(response.text)
 ```
 
-### Streaming
+### Generate Content (Asynchronous Streaming)
+
 
 ```python
 async for chunk in await client.aio.models.generate_content_stream(
@@ -883,6 +940,8 @@ print(response)
 ```
 
 ```python
+from google.genai import types
+
 # multiple contents with config
 response = client.models.embed_content(
     model='text-embedding-004',
@@ -900,6 +959,8 @@ print(response)
 Support for generate images in Gemini Developer API is behind an allowlist
 
 ```python
+from google.genai import types
+
 # Generate Image
 response1 = client.models.generate_images(
     model='imagen-3.0-generate-002',
@@ -918,6 +979,8 @@ response1.generated_images[0].image.show()
 Upscale image is only supported in Vertex AI.
 
 ```python
+from google.genai import types
+
 # Upscale the generated image from above
 response2 = client.models.upscale_image(
     model='imagen-3.0-generate-001',
@@ -939,6 +1002,7 @@ Edit image is only supported in Vertex AI.
 
 ```python
 # Edit the generated image from above
+from google.genai import types
 from google.genai.types import RawReferenceImage, MaskReferenceImage
 
 raw_ref_image = RawReferenceImage(
@@ -976,6 +1040,8 @@ response3.generated_images[0].image.show()
 Support for generate videos in Vertex and Gemini Developer API is behind an allowlist
 
 ```python
+from google.genai import types
+
 # Create operation
 operation = client.models.generate_videos(
     model='veo-2.0-generate-001',
@@ -999,17 +1065,22 @@ video.show()
 
 ## Chats
 
-Create a chat session to start a multi-turn conversations with the model.
+Create a chat session to start a multi-turn conversations with the model. Then,
+use `chat.send_message` function multiple times within the same chat session so
+that it can reflect on its previous responses (i.e., engage in an ongoing
+ conversation). See the 'Create a client' section above to initialize a client.
 
-### Send Message
+### Send Message (Synchronous Non-Streaming)
 
 ```python
 chat = client.chats.create(model='gemini-2.0-flash-001')
 response = chat.send_message('tell me a story')
 print(response.text)
+response = chat.send_message('summarize the story you told me in 1 sentence')
+print(response.text)
 ```
 
-### Streaming
+### Send Message (Synchronous Streaming)
 
 ```python
 chat = client.chats.create(model='gemini-2.0-flash-001')
@@ -1017,7 +1088,7 @@ for chunk in chat.send_message_stream('tell me a story'):
     print(chunk.text)
 ```
 
-### Async
+### Send Message (Asynchronous Non-Streaming)
 
 ```python
 chat = client.aio.chats.create(model='gemini-2.0-flash-001')
@@ -1025,7 +1096,7 @@ response = await chat.send_message('tell me a story')
 print(response.text)
 ```
 
-### Async Streaming
+### Send Message (Asynchronous Streaming)
 
 ```python
 chat = client.aio.chats.create(model='gemini-2.0-flash-001')
@@ -1035,7 +1106,8 @@ async for chunk in await chat.send_message_stream('tell me a story'):
 
 ## Files
 
-Files are only supported in Gemini Developer API.
+Files are only supported in Gemini Developer API. See the 'Create a client'
+section above to initialize a client.
 
 ```cmd
 !gsutil cp gs://cloud-samples-data/generative-ai/pdf/2312.11805v3.pdf .
@@ -1069,11 +1141,14 @@ client.files.delete(name=file3.name)
 
 ## Caches
 
-`client.caches` contains the control plane APIs for cached content
+`client.caches` contains the control plane APIs for cached content. See the
+'Create a client' section above to initialize a client.
 
 ### Create
 
 ```python
+from google.genai import types
+
 if client.vertexai:
     file_uris = [
         'gs://cloud-samples-data/generative-ai/pdf/2312.11805v3.pdf',
@@ -1115,6 +1190,8 @@ cached_content = client.caches.get(name=cached_content.name)
 ### Generate Content with Caches
 
 ```python
+from google.genai import types
+
 response = client.models.generate_content(
     model='gemini-2.0-flash-001',
     contents='Summarize the pdfs',
@@ -1128,7 +1205,8 @@ print(response.text)
 ## Tunings
 
 `client.tunings` contains tuning job APIs and supports supervised fine
-tuning through `tune`.
+tuning through `tune`. See the 'Create a client' section above to initialize a
+client.
 
 ### Tune
 
@@ -1136,6 +1214,8 @@ tuning through `tune`.
 -   Gemini Developer API supports tuning from inline examples
 
 ```python
+from google.genai import types
+
 if client.vertexai:
     model = 'gemini-2.0-flash-001'
     training_dataset = types.TuningDataset(
@@ -1155,6 +1235,8 @@ else:
 ```
 
 ```python
+from google.genai import types
+
 tuning_job = client.tunings.tune(
     base_model=model,
     training_dataset=training_dataset,
@@ -1241,6 +1323,8 @@ print(async_pager[0])
 ### Update Tuned Model
 
 ```python
+from google.genai import types
+
 model = pager[0]
 
 model = client.models.update(
@@ -1286,7 +1370,8 @@ print(async_pager[0])
 
 ## Batch Prediction
 
-Only supported in Vertex AI.
+Only supported in Vertex AI. See the 'Create a client' section above to
+initialize a client.
 
 ### Create
 

{google_genai-1.14.0.dist-info → google_genai-1.15.0.dist-info}/RECORD

@@ -1,30 +1,30 @@
 google/genai/__init__.py,sha256=IYw-PcsdgjSpS1mU_ZcYkTfPocsJ4aVmrDxP7vX7c6Y,709
-google/genai/_api_client.py,sha256=aNke14tWOoR7k-vbQuIpx62gX-t3FH0hYaE3QBbA7_0,37679
+google/genai/_api_client.py,sha256=fFYeZ8TZnl4zm6XPCvjrnUbHPHgr_qZ3HxWhVnOHJ1U,37869
 google/genai/_api_module.py,sha256=66FsFq9N8PdTegDyx3am3NHpI0Bw7HBmifUMCrZsx_Q,902
-google/genai/_automatic_function_calling_util.py,sha256=MB4lzbiLuosYXYafJq9d8QhTfK21cSkIwyzZr6W5Hjw,10294
+google/genai/_automatic_function_calling_util.py,sha256=wFFKTvlLpeqiP6zgH1LwWW3DYYWeLoJ_DkytVHJ89rI,10297
 google/genai/_base_url.py,sha256=E5H4dew14Y16qfnB3XRnjSCi19cJVlkaMNoM_8ip-PM,1597
 google/genai/_common.py,sha256=mBI8hEiztd3M_kBRTja0cprdGEoH5xNFCUykWDTtl-A,10573
 google/genai/_extra_utils.py,sha256=3wyzcRi29qgcxB2PvqzvY1sqPwYQHt5KCemI9RaKE9s,14824
-google/genai/_live_converters.py,sha256=d90poMynT4okhYcWrQKpVk6WiYWyj9HsOBguaKN96Ks,72232
+google/genai/_live_converters.py,sha256=VANY82SZueOJX2ek03IUyvgyP-acbj1NKm-IjhpMMQw,74810
 google/genai/_replay_api_client.py,sha256=pppcP0yAmXk8LS9uKXNBN1bJyoTDUDdt-WqfhdmgNZk,20006
 google/genai/_test_api_client.py,sha256=XNOWq8AkYbqInv1aljNGlFXsv8slQIWTYy_hdcCetD0,4797
 google/genai/_transformers.py,sha256=9Njw7X2nP3ySUy2282olQIxFYoE6dOOJ363HKr4pd5A,34514
 google/genai/batches.py,sha256=gyNb--psM7cqXEP5RsJ908ismvsFFlDNRxt7mCwhYgM,34943
-google/genai/caches.py,sha256=3rx4GSoCQa76HAoMAcjgbCYmH7BBdM_Y1jf8BDxiOLU,58408
+google/genai/caches.py,sha256=5Z-c84DuccMQCVITYLLTj0NRH2KKNXl4gzAkpEBiUnw,59761
 google/genai/chats.py,sha256=6K9wuH3yDngdbZCYNA13G7GeMsya100QQdS0_jt6m1A,16978
 google/genai/client.py,sha256=OkJxW-9_Mi7O1B_HxdBgHQgeM7mEIn1eQQIMkiaunTE,10477
 google/genai/errors.py,sha256=d22FmoLj5kte9UZSCLwkGhJhqp2JXlJHyNB6wC_37w4,4795
 google/genai/files.py,sha256=PB5Rh5WiLOPHcqPR1inGyhqL9PiE0BFHSL4Dz9HKtl8,39516
 google/genai/live.py,sha256=PtosiGwQ4I72HMlAhiBDrMteWCH-_RBIIww6mVHDIuc,35105
-google/genai/models.py,sha256=Cy3uyULLtqiziJdB1d0M_uq7p91LRnuSyjE6HqkTGxE,210250
+google/genai/models.py,sha256=ldNpy0DwnK72_oVfvlK9x6-YK9u_ZQ65Dra0ddnvPek,214467
 google/genai/operations.py,sha256=wWGngU4N3U2y_JteBkwqTmoNncehk2NcZgPyHaVulfI,20304
 google/genai/pagers.py,sha256=dhdKUr4KiUGHOt8OPLo51I0qXJpBU2iH4emTKC4UINI,6797
 google/genai/py.typed,sha256=RsMFoLwBkAvY05t6izop4UHZtqOPLiKp3GkIEizzmQY,40
-google/genai/tunings.py,sha256=X2dIs9v9e91bd-PwZja-BaA3kNQxwyAjt1x5fhP4Phk,47594
-google/genai/types.py,sha256=-4pDSUJm-p4hWQGXF-jaRJky62ild0YYj779T_vnyYw,380305
-google/genai/version.py,sha256=JfaQeixdUPeyGjk5Go9QAXqET7q1wsD96DuQDdI8j8E,627
-google_genai-1.14.0.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
-google_genai-1.14.0.dist-info/METADATA,sha256=Xc190vgHeoF7eELP7e1ArEFFfRp_u_cvdDH46SzCkgc,33082
-google_genai-1.14.0.dist-info/WHEEL,sha256=0CuiUZ_p9E4cD6NyLD6UG80LBXYyiSYZOKDm5lp32xk,91
-google_genai-1.14.0.dist-info/top_level.txt,sha256=_1QvSJIhFAGfxb79D6DhB7SUw2X6T4rwnz_LLrbcD3c,7
-google_genai-1.14.0.dist-info/RECORD,,
+google/genai/tunings.py,sha256=bmLGBN1EhsDvm-OpHwX3UgNPauG2FUJsq0Z327C6Tmk,49226
+google/genai/types.py,sha256=jFDra81W6-DOCXthJzjhQpbUjH-01_ZaziEWwPJBGyg,386019
+google/genai/version.py,sha256=YR-NrHLpLS5deIRlUcFzZEz8W284JQPHrAUOeUt0Q7A,627
+google_genai-1.15.0.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
+google_genai-1.15.0.dist-info/METADATA,sha256=xnydtMjKTfpQ50V0kny2Q7oRCuUULKvZoO30Gb8kEHw,35580
+google_genai-1.15.0.dist-info/WHEEL,sha256=DnLRTWE75wApRYVsjgc6wsVswC54sMSJhAEd4xhDpBk,91
+google_genai-1.15.0.dist-info/top_level.txt,sha256=_1QvSJIhFAGfxb79D6DhB7SUw2X6T4rwnz_LLrbcD3c,7
+google_genai-1.15.0.dist-info/RECORD,,

{google_genai-1.14.0.dist-info → google_genai-1.15.0.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (80.3.1)
+Generator: setuptools (80.4.0)
 Root-Is-Purelib: true
 Tag: py3-none-any