demo

docs/api/google/generativeai/chat_async.md

@@ -1,67 +1,27 @@
-description: Calls the API to initiate a chat with a model using provided parameters
 
-<div itemscope itemtype="http://developers.google.com/ReferenceObject">
-<meta itemprop="name" content="google.generativeai.chat_async" />
-<meta itemprop="path" content="Stable" />
-</div>
-
-# google.generativeai.chat_async
-
-<!-- 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/discuss.py#L411-L441">
-    <img src="https://www.tensorflow.org/images/GitHub-Mark-32px.png" />
-    View source on GitHub
-  </a>
-</td>
-</table>
-
-
-
-Calls the API to initiate a chat with a model using provided parameters
-
-
-<pre class="devsite-click-to-copy prettyprint lang-py tfo-signature-link">
-<code>google.generativeai.chat_async(
-    *,
-    model=&#x27;models/chat-bison-001&#x27;,
-    context=None,
-    examples=None,
-    messages=None,
-    temperature=None,
-    candidate_count=None,
-    top_p=None,
-    top_k=None,
-    prompt=None,
-    client=None,
-    request_options=None
-)
-</code></pre>
-
-
-
-<!-- Placeholder for "Used in" -->
-
-
-<!-- Tabular view -->
- <table class="responsive fixed orange">
+ <table class="responsive fixed orange">
 <colgroup><col width="214px"><col></colgroup>
 <tr><th colspan="2"><h2 class="add-link">Args</h2></th></tr>
 
 <tr>
 <td>
+
 `model`<a id="model"></a>
+
 </td>
 <td>
+
 Which model to call, as a string or a <a href="../../google/generativeai/types/Model.md"><code>types.Model</code></a>.
+
 </td>
 </tr><tr>
 <td>
+
 `context`<a id="context"></a>
+
 </td>
 <td>
+
 Text that should be provided to the model first, to ground the response.
 
 If not empty, this `context` will be given to the model first before the
@@ -77,12 +37,16 @@ Examples:
 
 Anything included in this field will take precedence over history in `messages`
 if the total input size exceeds the model's <a href="../../google/generativeai/protos/Model.md#input_token_limit"><code>Model.input_token_limit</code></a>.
+
 </td>
 </tr><tr>
 <td>
+
 `examples`<a id="examples"></a>
+
 </td>
 <td>
+
 Examples of what the model should generate.
 
 This includes both the user input and the response that the model should
@@ -92,34 +56,46 @@ These `examples` are treated identically to conversation messages except
 that they take precedence over the history in `messages`:
 If the total input size exceeds the model's `input_token_limit` the input
 will be truncated. Items will be dropped from `messages` before `examples`
+
 </td>
 </tr><tr>
 <td>
+
 `messages`<a id="messages"></a>
+
 </td>
 <td>
+
 A snapshot of the conversation history sorted chronologically.
 
 Turns alternate between two authors.
 
 If the total input size exceeds the model's `input_token_limit` the input
 will be truncated: The oldest items will be dropped from `messages`.
+
 </td>
 </tr><tr>
 <td>
+
 `temperature`<a id="temperature"></a>
+
 </td>
 <td>
+
 Controls the randomness of the output. Must be positive.
 
 Typical values are in the range: `[0.0,1.0]`. Higher values produce a
 more random and varied response. A temperature of zero will be deterministic.
+
 </td>
 </tr><tr>
 <td>
+
 `candidate_count`<a id="candidate_count"></a>
+
 </td>
 <td>
+
 The **maximum** number of generated response messages to return.
 
 This value must be between `[1, 8]`, inclusive. If unset, this
@@ -128,22 +104,30 @@ will default to `1`.
 Note: Only unique candidates are returned. Higher temperatures are more
 likely to produce unique candidates. Setting `temperature=0.0` will always
 return 1 candidate regardless of the `candidate_count`.
+
 </td>
 </tr><tr>
 <td>
+
 `top_k`<a id="top_k"></a>
+
 </td>
 <td>
+
 The API uses combined [nucleus](https://arxiv.org/abs/1904.09751) and
 top-k sampling.
 
 `top_k` sets the maximum number of tokens to sample from on each step.
+
 </td>
 </tr><tr>
 <td>
+
 `top_p`<a id="top_p"></a>
+
 </td>
 <td>
+
 The API uses combined [nucleus](https://arxiv.org/abs/1904.09751) and
 top-k sampling.
 
@@ -155,29 +139,42 @@ top-k sampling.
  as `[0.625, 0.25, 0.125, 0, 0, 0]`.
 
  Typical values are in the `[0.9, 1.0]` range.
+
 </td>
 </tr><tr>
 <td>
+
 `prompt`<a id="prompt"></a>
+
 </td>
 <td>
+
 You may pass a <a href="../../google/generativeai/types/MessagePromptOptions.md"><code>types.MessagePromptOptions</code></a> **instead** of a
 setting `context`/`examples`/`messages`, but not both.
+
 </td>
 </tr><tr>
 <td>
+
 `client`<a id="client"></a>
+
 </td>
 <td>
+
 If you're not relying on the default client, you pass a
 `glm.DiscussServiceClient` instead.
+
 </td>
 </tr><tr>
 <td>
+
 `request_options`<a id="request_options"></a>
+
 </td>
 <td>
+
 Options for the request.
+
 </td>
 </tr>
 </table>