Add markdown docs

.gitignore

@@ -3,7 +3,6 @@
 /.idea/
 /.pytype/
 /build/
-/docs/api
 *.egg-info
 .DS_Store
 __pycache__

docs/api/google/generativeai.md

@@ -0,0 +1,138 @@
+description: Google AI Python SDK
+
+<div itemscope itemtype="http://developers.google.com/ReferenceObject">
+<meta itemprop="name" content="google.generativeai" />
+<meta itemprop="path" content="Stable" />
+<meta itemprop="property" content="__version__"/>
+<meta itemprop="property" content="annotations"/>
+</div>
+
+# Module: google.generativeai
+
+<!-- Insert buttons and diff -->
+
+<table class="tfo-notebook-buttons tfo-api nocontent" align="left">
+<td>
+  <a target="_blank" href="https://github.com/google/generative-ai-python/blob/master/google/generativeai/__init__.py">
+    <img src="https://www.tensorflow.org/images/GitHub-Mark-32px.png" />
+    View source on GitHub
+  </a>
+</td>
+</table>
+
+
+
+Google AI Python SDK
+
+
+
+## Setup
+
+```posix-terminal
+pip install google-generativeai
+```
+
+## GenerativeModel
+
+Use `genai.GenerativeModel` to access the API:
+
+```
+import google.generativeai as genai
+import os
+
+genai.configure(api_key=os.environ['API_KEY'])
+
+model = genai.GenerativeModel(model_name='gemini-1.5-flash')
+response = model.generate_content('Teach me about how an LLM works')
+
+print(response.text)
+```
+
+See the [python quickstart](https://ai.google.dev/tutorials/python_quickstart) for more details.
+
+## Modules
+
+[`protos`](../google/generativeai/protos.md) module: This module provides low level access to the ProtoBuffer "Message" classes used by the API.
+
+[`types`](../google/generativeai/types.md) module: A collection of type definitions used throughout the library.
+
+## Classes
+
+[`class ChatSession`](../google/generativeai/ChatSession.md): Contains an ongoing conversation with the model.
+
+[`class GenerationConfig`](../google/generativeai/types/GenerationConfig.md): A simple dataclass used to configure the generation parameters of <a href="../google/generativeai/GenerativeModel.md#generate_content"><code>GenerativeModel.generate_content</code></a>.
+
+[`class GenerativeModel`](../google/generativeai/GenerativeModel.md): The `genai.GenerativeModel` class wraps default parameters for calls to <a href="../google/generativeai/GenerativeModel.md#generate_content"><code>GenerativeModel.generate_content</code></a>, <a href="../google/generativeai/GenerativeModel.md#count_tokens"><code>GenerativeModel.count_tokens</code></a>, and <a href="../google/generativeai/GenerativeModel.md#start_chat"><code>GenerativeModel.start_chat</code></a>.
+
+## Functions
+
+[`chat(...)`](../google/generativeai/chat.md): Calls the API to initiate a chat with a model using provided parameters
+
+[`chat_async(...)`](../google/generativeai/chat_async.md): Calls the API to initiate a chat with a model using provided parameters
+
+[`configure(...)`](../google/generativeai/configure.md): Captures default client configuration.
+
+[`count_message_tokens(...)`](../google/generativeai/count_message_tokens.md): Calls the API to calculate the number of tokens used in the prompt.
+
+[`count_text_tokens(...)`](../google/generativeai/count_text_tokens.md): Calls the API to count the number of tokens in the text prompt.
+
+[`create_tuned_model(...)`](../google/generativeai/create_tuned_model.md): Calls the API to initiate a tuning process that optimizes a model for specific data, returning an operation object to track and manage the tuning progress.
+
+[`delete_file(...)`](../google/generativeai/delete_file.md): Calls the API to permanently delete a specified file using a supported file service.
+
+[`delete_tuned_model(...)`](../google/generativeai/delete_tuned_model.md): Calls the API to delete a specified tuned model
+
+[`embed_content(...)`](../google/generativeai/embed_content.md): Calls the API to create embeddings for content passed in.
+
+[`embed_content_async(...)`](../google/generativeai/embed_content_async.md): Calls the API to create async embeddings for content passed in.
+
+[`generate_embeddings(...)`](../google/generativeai/generate_embeddings.md): Calls the API to create an embedding for the text passed in.
+
+[`generate_text(...)`](../google/generativeai/generate_text.md): Calls the API to generate text based on the provided prompt.
+
+[`get_base_model(...)`](../google/generativeai/get_base_model.md): Calls the API to fetch a base model by name.
+
+[`get_file(...)`](../google/generativeai/get_file.md): Calls the API to retrieve a specified file using a supported file service.
+
+[`get_model(...)`](../google/generativeai/get_model.md): Calls the API to fetch a model by name.
+
+[`get_operation(...)`](../google/generativeai/get_operation.md): Calls the API to get a specific operation
+
+[`get_tuned_model(...)`](../google/generativeai/get_tuned_model.md): Calls the API to fetch a tuned model by name.
+
+[`list_files(...)`](../google/generativeai/list_files.md): Calls the API to list files using a supported file service.
+
+[`list_models(...)`](../google/generativeai/list_models.md): Calls the API to list all available models.
+
+[`list_operations(...)`](../google/generativeai/list_operations.md): Calls the API to list all operations
+
+[`list_tuned_models(...)`](../google/generativeai/list_tuned_models.md): Calls the API to list all tuned models.
+
+[`update_tuned_model(...)`](../google/generativeai/update_tuned_model.md): Calls the API to push updates to a specified tuned model where only certain attributes are updatable.
+
+[`upload_file(...)`](../google/generativeai/upload_file.md): Calls the API to upload a file using a supported file service.
+
+
+
+<!-- Tabular view -->
+ <table class="responsive fixed orange">
+<colgroup><col width="214px"><col></colgroup>
+<tr><th colspan="2"><h2 class="add-link">Other Members</h2></th></tr>
+
+<tr>
+<td>
+__version__<a id="__version__"></a>
+</td>
+<td>
+`'0.7.2'`
+</td>
+</tr><tr>
+<td>
+annotations<a id="annotations"></a>
+</td>
+<td>
+Instance of `__future__._Feature`
+</td>
+</tr>
+</table>
+

docs/api/google/generativeai/ChatSession.md

@@ -0,0 +1,222 @@
+description: Contains an ongoing conversation with the model.
+
+<div itemscope itemtype="http://developers.google.com/ReferenceObject">
+<meta itemprop="name" content="google.generativeai.ChatSession" />
+<meta itemprop="path" content="Stable" />
+<meta itemprop="property" content="__init__"/>
+<meta itemprop="property" content="rewind"/>
+<meta itemprop="property" content="send_message"/>
+<meta itemprop="property" content="send_message_async"/>
+</div>
+
+# google.generativeai.ChatSession
+
+<!-- Insert buttons and diff -->
+
+<table class="tfo-notebook-buttons tfo-api nocontent" align="left">
+<td>
+  <a target="_blank" href="https://github.com/google/generative-ai-python/blob/master/google/generativeai/generative_models.py#L481-L875">
+    <img src="https://www.tensorflow.org/images/GitHub-Mark-32px.png" />
+    View source on GitHub
+  </a>
+</td>
+</table>
+
+
+
+Contains an ongoing conversation with the model.
+
+<pre class="devsite-click-to-copy prettyprint lang-py tfo-signature-link">
+<code>google.generativeai.ChatSession(
+    model: GenerativeModel,
+    history: (Iterable[content_types.StrictContentType] | None) = None,
+    enable_automatic_function_calling: bool = False
+)
+</code></pre>
+
+
+
+<!-- Placeholder for "Used in" -->
+
+```
+>>> model = genai.GenerativeModel('models/gemini-pro')
+>>> chat = model.start_chat()
+>>> response = chat.send_message("Hello")
+>>> print(response.text)
+>>> response = chat.send_message("Hello again")
+>>> print(response.text)
+>>> response = chat.send_message(...
+```
+
+This `ChatSession` object collects the messages sent and received, in its
+<a href="../../google/generativeai/ChatSession.md#history"><code>ChatSession.history</code></a> attribute.
+
+<!-- Tabular view -->
+ <table class="responsive fixed orange">
+<colgroup><col width="214px"><col></colgroup>
+<tr><th colspan="2"><h2 class="add-link">Arguments</h2></th></tr>
+
+<tr>
+<td>
+`model`<a id="model"></a>
+</td>
+<td>
+The model to use in the chat.
+</td>
+</tr><tr>
+<td>
+`history`<a id="history"></a>
+</td>
+<td>
+A chat history to initialize the object with.
+</td>
+</tr>
+</table>
+
+
+
+
+
+<!-- Tabular view -->
+ <table class="responsive fixed orange">
+<colgroup><col width="214px"><col></colgroup>
+<tr><th colspan="2"><h2 class="add-link">Attributes</h2></th></tr>
+
+<tr>
+<td>
+`history`<a id="history"></a>
+</td>
+<td>
+The chat history.
+</td>
+</tr><tr>
+<td>
+`last`<a id="last"></a>
+</td>
+<td>
+returns the last received `genai.GenerateContentResponse`
+</td>
+</tr>
+</table>
+
+
+
+## Methods
+
+<h3 id="rewind"><code>rewind</code></h3>
+
+<a target="_blank" class="external" href="https://github.com/google/generative-ai-python/blob/master/google/generativeai/generative_models.py#L785-L794">View source</a>
+
+<pre class="devsite-click-to-copy prettyprint lang-py tfo-signature-link">
+<code>rewind() -> tuple[protos.Content, protos.Content]
+</code></pre>
+
+Removes the last request/response pair from the chat history.
+
+
+<h3 id="send_message"><code>send_message</code></h3>
+
+<a target="_blank" class="external" href="https://github.com/google/generative-ai-python/blob/master/google/generativeai/generative_models.py#L512-L604">View source</a>
+
+<pre class="devsite-click-to-copy prettyprint lang-py tfo-signature-link">
+<code>send_message(
+    content: content_types.ContentType,
+    *,
+    generation_config: generation_types.GenerationConfigType = None,
+    safety_settings: safety_types.SafetySettingOptions = None,
+    stream: bool = False,
+    tools: (content_types.FunctionLibraryType | None) = None,
+    tool_config: (content_types.ToolConfigType | None) = None,
+    request_options: (helper_types.RequestOptionsType | None) = None
+) -> generation_types.GenerateContentResponse
+</code></pre>
+
+Sends the conversation history with the added message and returns the model's response.
+
+Appends the request and response to the conversation history.
+
+```
+>>> model = genai.GenerativeModel('models/gemini-pro')
+>>> chat = model.start_chat()
+>>> response = chat.send_message("Hello")
+>>> print(response.text)
+"Hello! How can I assist you today?"
+>>> len(chat.history)
+2
+```
+
+Call it with `stream=True` to receive response chunks as they are generated:
+
+```
+>>> chat = model.start_chat()
+>>> response = chat.send_message("Explain quantum physics", stream=True)
+>>> for chunk in response:
+...   print(chunk.text, end='')
+```
+
+Once iteration over chunks is complete, the `response` and `ChatSession` are in states identical to the
+`stream=False` case. Some properties are not available until iteration is complete.
+
+Like <a href="../../google/generativeai/GenerativeModel.md#generate_content"><code>GenerativeModel.generate_content</code></a> this method lets you override the model's `generation_config` and
+`safety_settings`.
+
+<!-- Tabular view -->
+ <table class="responsive fixed orange">
+<colgroup><col width="214px"><col></colgroup>
+<tr><th colspan="2">Arguments</th></tr>
+
+<tr>
+<td>
+`content`
+</td>
+<td>
+The message contents.
+</td>
+</tr><tr>
+<td>
+`generation_config`
+</td>
+<td>
+Overrides for the model's generation config.
+</td>
+</tr><tr>
+<td>
+`safety_settings`
+</td>
+<td>
+Overrides for the model's safety settings.
+</td>
+</tr><tr>
+<td>
+`stream`
+</td>
+<td>
+If True, yield response chunks as they are generated.
+</td>
+</tr>
+</table>
+
+
+
+<h3 id="send_message_async"><code>send_message_async</code></h3>
+
+<a target="_blank" class="external" href="https://github.com/google/generative-ai-python/blob/master/google/generativeai/generative_models.py#L671-L733">View source</a>
+
+<pre class="devsite-click-to-copy prettyprint lang-py tfo-signature-link">
+<code>send_message_async(
+    content,
+    *,
+    generation_config=None,
+    safety_settings=None,
+    stream=False,
+    tools=None,
+    tool_config=None,
+    request_options=None
+)
+</code></pre>
+
+The async version of <a href="../../google/generativeai/ChatSession.md#send_message"><code>ChatSession.send_message</code></a>.
+
+
+
+