chore: update docs

PiperOrigin-RevId: 720733411

Author: sasha-gitg

docs/_sources/index.rst.txt

@@ -68,11 +68,11 @@ with text content
 .. code:: python
 
     response = client.models.generate_content(
-        model="gemini-2.0-flash-exp", contents="What is your name?"
+        model="gemini-2.0-flash-exp", contents="Why is the sky blue?"
     )
     print(response.text)
 
-with uploaded file (Google AI only)
+with uploaded file (Gemini API only)
 ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
 
 download the file in console.
@@ -85,9 +85,10 @@ python code.
 
 .. code:: python
 
-    file = client.files.upload(path='a11.text')
+    file = client.files.upload(path='a11.txt')
     response = client.models.generate_content(
-        model='gemini-2.0-flash-exp', contents=['Summarize this file', file]
+        model='gemini-2.0-flash-exp',
+        contents=['Could you summarize this file?', file]
     )
     print(response.text)
 
@@ -117,7 +118,7 @@ dictionaries. You can get the type from ``google.genai.types``.
 
     response = client.models.generate_content(
         model="gemini-2.0-flash-exp",
-        contents=types.Part.from_text("Why is the sky blue?"),
+        contents=types.Part.from_text(text="Why is the sky blue?"),
         config=types.GenerateContentConfig(
             temperature=0,
             top_p=0.95,
@@ -131,7 +132,46 @@ dictionaries. You can get the type from ``google.genai.types``.
         ),
     )
 
-    response
+    print(response.text)
+
+Thinking Model
+---------------
+
+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.
+
+.. code:: 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
+~~~~~~~~~~~~~~
+
+.. code:: 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
 ----------------
@@ -230,10 +270,10 @@ Then you will receive a function call part in the response.
     function = types.FunctionDeclaration(
         name="get_current_weather",
         description="Get the current weather in a given location",
-        parameters=types.FunctionParameters(
+        parameters=types.Schema(
             type="OBJECT",
             properties={
-                "location": types.ParameterType(
+                "location": types.Schema(
                     type="STRING",
                     description="The city and state, e.g. San Francisco, CA",
                 ),
@@ -262,10 +302,9 @@ The following example shows how to do it for a simple function invocation.
 
     user_prompt_content = types.Content(
         role="user",
-        parts=[types.Part.from_text("What is the weather like in Boston?")],
+        parts=[types.Part.from_text(text="What is the weather like in Boston?")],
     )
-    function_call_content = response.candidates[0].content
-    function_call_part = function_call_content.parts[0]
+    function_call_part = response.function_calls[0]
 
 
     try:
@@ -366,6 +405,60 @@ Schemas can be provided as Pydantic Models.
     )
     print(response.text)
 
+Enum Response Schema
+--------------------
+
+Text Response
+~~~~~~~~~~~~~
+
+You can set response_mime_type to 'text/x.enum' to return one of those enum 
+values as the response.
+
+.. code:: python
+
+    from enum import Enum
+
+    class InstrumentEnum(Enum):
+        PERCUSSION = 'Percussion'
+        STRING = 'String'
+        WOODWIND = 'Woodwind'
+        BRASS = 'Brass'
+        KEYBOARD = 'Keyboard'
+
+    response = client.models.generate_content(
+        model='gemini-2.0-flash-exp',
+        contents='What instrument plays multiple notes at once?',
+        config={
+            'response_mime_type': 'text/x.enum',
+            'response_schema': InstrumentEnum,
+        },
+    )
+    print(response.text)
+
+JSON Response
+~~~~~~~~~~~~~
+
+You can also set response_mime_type to 'application/json', the response will be 
+identical but in quotes.
+
+.. code:: python
+
+    class InstrumentEnum(Enum):
+        PERCUSSION = 'Percussion'
+        STRING = 'String'
+        WOODWIND = 'Woodwind'
+        BRASS = 'Brass'
+        KEYBOARD = 'Keyboard'
+
+    response = client.models.generate_content(
+        model='gemini-2.0-flash-exp',
+        contents='What instrument plays multiple notes at once?',
+        config={
+            'response_mime_type': 'application/json',
+            'response_schema': InstrumentEnum,
+        },
+    )
+    print(response.text)
 
 Streaming
 ---------
@@ -439,10 +532,10 @@ Streaming
 
 .. code:: python
 
-    async for response in client.aio.models.generate_content_stream(
+    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."
     ):
-        print(response.text, end="")
+        print(chunk.text, end="")
 
 Count Tokens and Compute Tokens
 -------------------------------
@@ -451,7 +544,7 @@ Count Tokens and Compute Tokens
 
     response = client.models.count_tokens(
         model="gemini-2.0-flash-exp",
-        contents="What is your name?",
+        contents="why is the sky blue?",
     )
     print(response)
 
@@ -464,7 +557,7 @@ Compute tokens is only supported in Vertex AI.
 
     response = client.models.compute_tokens(
         model="gemini-2.0-flash-exp",
-        contents="What is your name?",
+        contents="why is the sky blue?",
     )
     print(response)
 
@@ -475,7 +568,7 @@ Async
 
     response = await client.aio.models.count_tokens(
         model="gemini-2.0-flash-exp",
-        contents="What is your name?",
+        contents="why is the sky blue?",
     )
     print(response)
 
@@ -486,7 +579,7 @@ Embed Content
 
     response = client.models.embed_content(
         model="text-embedding-004",
-        contents="What is your name?",
+        contents="why is the sky blue?",
     )
     print(response)
 
@@ -495,7 +588,7 @@ Embed Content
     # multiple contents with config
     response = client.models.embed_content(
         model="text-embedding-004",
-        contents=["What is your name?", "What is your age?"],
+        contents=["why is the sky blue?", "What is your age?"],
         config=types.EmbedContentConfig(output_dimensionality=10),
     )
 
@@ -512,10 +605,10 @@ Support for generate image in Gemini Developer API is behind an allowlist
 .. code:: python
 
     # Generate Image
-    response1 = client.models.generate_image(
-        model="imagen-3.0-generate-001",
+    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",
-        config=types.GenerateImageConfig(
+        config=types.GenerateImagesConfig(
             negative_prompt="human",
             number_of_images=1,
             include_rai_reason=True,
@@ -533,7 +626,7 @@ Upscale image is only supported in Vertex AI.
 
     # Upscale the generated image from above
     response2 = client.models.upscale_image(
-        model="imagen-3.0-generate-001",
+        model="imagen-3.0-generate-002",
         image=response1.generated_images[0].image,
         upscale_factor="x2",
         config=types.UpscaleImageConfig(
@@ -621,7 +714,7 @@ Async Streaming
 .. code:: python
 
     chat = client.aio.chats.create(model="gemini-2.0-flash-exp")
-    async for chunk in chat.send_message_stream("tell me a story"):
+    async for chunk in await chat.send_message_stream("tell me a story"):
         print(chunk.text, end="")
 
 Files
@@ -720,7 +813,7 @@ Tunings
 =======
 
 ``client.tunings`` contains tuning job APIs and supports supervised fine
-tuning through ``tune`` and distillation through ``distill``
+tuning through ``tune``.
 
 Tune
 ----
@@ -789,7 +882,7 @@ Use Tuned Model
 
     response = client.models.generate_content(
         model=tuning_job.tuned_model.endpoint,
-        contents="What is your name?",
+        contents="why is the sky blue?",
     )
 
     print(response.text)
@@ -852,49 +945,6 @@ Update Tuned Model
 
     print(model)
 
-Distillation
-------------
-
-Only supported in Vertex AI. Requires allowlist.
-
-.. code:: python
-
-    distillation_job = client.tunings.distill(
-        student_model="gemma-2b-1.1-it",
-        teacher_model="gemini-1.5-pro-002",
-        training_dataset=genai.types.DistillationDataset(
-            gcs_uri="gs://cloud-samples-data/ai-platform/generative_ai/gemini-1_5/text/sft_train_data.jsonl",
-        ),
-        config=genai.types.CreateDistillationJobConfig(
-            epoch_count=1,
-            pipeline_root_directory=(
-                "gs://vertex-sdk-dev-staging-us-central1/tmp/distillation_pipeline_root"
-            ),
-        ),
-    )
-    print(distillation_job)
-
-.. code:: python
-
-    completed_states = set(
-        [
-            "JOB_STATE_SUCCEEDED",
-            "JOB_STATE_FAILED",
-            "JOB_STATE_CANCELLED",
-            "JOB_STATE_PAUSED",
-        ]
-    )
-
-    while distillation_job.state not in completed_states:
-        print(distillation_job.state)
-        distillation_job = client.tunings.get(name=distillation_job.name)
-        time.sleep(10)
-
-    print(distillation_job)
-
-.. code:: python
-
-    distillation_job
 
 List Tuning Jobs
 ----------------
@@ -976,12 +1026,12 @@ List
 
 .. code:: python
 
-    for job in client.batches.list(config=types.ListBatchJobConfig(page_size=10)):
+    for job in client.batches.list(config=types.ListBatchJobsConfig(page_size=10)):
         print(job)
 
 .. code:: python
 
-    pager = client.batches.list(config=types.ListBatchJobConfig(page_size=10))
+    pager = client.batches.list(config=types.ListBatchJobsConfig(page_size=10))
     print(pager.page_size)
     print(pager[0])
     pager.next_page()
@@ -993,14 +1043,14 @@ Async
 .. code:: python
 
     async for job in await client.aio.batches.list(
-        config=types.ListBatchJobConfig(page_size=10)
+        config=types.ListBatchJobsConfig(page_size=10)
     ):
         print(job)
 
 .. code:: python
 
     async_pager = await client.aio.batches.list(
-        config=types.ListBatchJobConfig(page_size=10)
+        config=types.ListBatchJobsConfig(page_size=10)
     )
     print(async_pager.page_size)
     print(async_pager[0])