Skip to content

Commit a6dccd9

Browse files
shilpakancharlashilpakancharla
committed
Revert "Delete certain markdown files, update other mds"
This reverts commit dca0b1f.
1 parent d6ef4e0 commit a6dccd9

File tree

4 files changed

+570
-2
lines changed

4 files changed

+570
-2
lines changed

‎docs/api/google/generativeai/chat.md

Lines changed: 198 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,198 @@
1+
description: Calls the API to initiate a chat with a model using provided parameters
2+
3+
<div itemscope itemtype="http://developers.google.com/ReferenceObject">
4+
<meta itemprop="name" content="google.generativeai.chat" />
5+
<meta itemprop="path" content="Stable" />
6+
</div>
7+
8+
# google.generativeai.chat
9+
10+
<!-- Insert buttons and diff -->
11+
12+
<table class="tfo-notebook-buttons tfo-api nocontent" align="left">
13+
<td>
14+
<a target="_blank" href="https://github.com/google/generative-ai-python/blob/master/google/generativeai/discuss.py#L312-L408">
15+
<img src="https://www.tensorflow.org/images/GitHub-Mark-32px.png" />
16+
View source on GitHub
17+
</a>
18+
</td>
19+
</table>
20+
21+
22+
23+
Calls the API to initiate a chat with a model using provided parameters
24+
25+
26+
<pre class="devsite-click-to-copy prettyprint lang-py tfo-signature-link">
27+
<code>google.generativeai.chat(
28+
*,
29+
model: (model_types.AnyModelNameOptions | None) = &#x27;models/chat-bison-001&#x27;,
30+
context: (str | None) = None,
31+
examples: (discuss_types.ExamplesOptions | None) = None,
32+
messages: (discuss_types.MessagesOptions | None) = None,
33+
temperature: (float | None) = None,
34+
candidate_count: (int | None) = None,
35+
top_p: (float | None) = None,
36+
top_k: (float | None) = None,
37+
prompt: (discuss_types.MessagePromptOptions | None) = None,
38+
client: (glm.DiscussServiceClient | None) = None,
39+
request_options: (helper_types.RequestOptionsType | None) = None
40+
) -> discuss_types.ChatResponse
41+
</code></pre>
42+
43+
44+
45+
<!-- Placeholder for "Used in" -->
46+
47+
48+
<!-- Tabular view -->
49+
<table class="responsive fixed orange">
50+
<colgroup><col width="214px"><col></colgroup>
51+
<tr><th colspan="2"><h2 class="add-link">Args</h2></th></tr>
52+
53+
<tr>
54+
<td>
55+
`model`<a id="model"></a>
56+
</td>
57+
<td>
58+
Which model to call, as a string or a <a href="../../google/generativeai/types/Model.md"><code>types.Model</code></a>.
59+
</td>
60+
</tr><tr>
61+
<td>
62+
`context`<a id="context"></a>
63+
</td>
64+
<td>
65+
Text that should be provided to the model first, to ground the response.
66+
67+
If not empty, this `context` will be given to the model first before the
68+
`examples` and `messages`.
69+
70+
This field can be a description of your prompt to the model to help provide
71+
context and guide the responses.
72+
73+
Examples:
74+
75+
* "Translate the phrase from English to French."
76+
* "Given a statement, classify the sentiment as happy, sad or neutral."
77+
78+
Anything included in this field will take precedence over history in `messages`
79+
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>.
80+
</td>
81+
</tr><tr>
82+
<td>
83+
`examples`<a id="examples"></a>
84+
</td>
85+
<td>
86+
Examples of what the model should generate.
87+
88+
This includes both the user input and the response that the model should
89+
emulate.
90+
91+
These `examples` are treated identically to conversation messages except
92+
that they take precedence over the history in `messages`:
93+
If the total input size exceeds the model's `input_token_limit` the input
94+
will be truncated. Items will be dropped from `messages` before `examples`
95+
</td>
96+
</tr><tr>
97+
<td>
98+
`messages`<a id="messages"></a>
99+
</td>
100+
<td>
101+
A snapshot of the conversation history sorted chronologically.
102+
103+
Turns alternate between two authors.
104+
105+
If the total input size exceeds the model's `input_token_limit` the input
106+
will be truncated: The oldest items will be dropped from `messages`.
107+
</td>
108+
</tr><tr>
109+
<td>
110+
`temperature`<a id="temperature"></a>
111+
</td>
112+
<td>
113+
Controls the randomness of the output. Must be positive.
114+
115+
Typical values are in the range: `[0.0,1.0]`. Higher values produce a
116+
more random and varied response. A temperature of zero will be deterministic.
117+
</td>
118+
</tr><tr>
119+
<td>
120+
`candidate_count`<a id="candidate_count"></a>
121+
</td>
122+
<td>
123+
The **maximum** number of generated response messages to return.
124+
125+
This value must be between `[1, 8]`, inclusive. If unset, this
126+
will default to `1`.
127+
128+
Note: Only unique candidates are returned. Higher temperatures are more
129+
likely to produce unique candidates. Setting `temperature=0.0` will always
130+
return 1 candidate regardless of the `candidate_count`.
131+
</td>
132+
</tr><tr>
133+
<td>
134+
`top_k`<a id="top_k"></a>
135+
</td>
136+
<td>
137+
The API uses combined [nucleus](https://arxiv.org/abs/1904.09751) and
138+
top-k sampling.
139+
140+
`top_k` sets the maximum number of tokens to sample from on each step.
141+
</td>
142+
</tr><tr>
143+
<td>
144+
`top_p`<a id="top_p"></a>
145+
</td>
146+
<td>
147+
The API uses combined [nucleus](https://arxiv.org/abs/1904.09751) and
148+
top-k sampling.
149+
150+
`top_p` configures the nucleus sampling. It sets the maximum cumulative
151+
probability of tokens to sample from.
152+
153+
For example, if the sorted probabilities are
154+
`[0.5, 0.2, 0.1, 0.1, 0.05, 0.05]` a `top_p` of `0.8` will sample
155+
as `[0.625, 0.25, 0.125, 0, 0, 0]`.
156+
157+
Typical values are in the `[0.9, 1.0]` range.
158+
</td>
159+
</tr><tr>
160+
<td>
161+
`prompt`<a id="prompt"></a>
162+
</td>
163+
<td>
164+
You may pass a <a href="../../google/generativeai/types/MessagePromptOptions.md"><code>types.MessagePromptOptions</code></a> **instead** of a
165+
setting `context`/`examples`/`messages`, but not both.
166+
</td>
167+
</tr><tr>
168+
<td>
169+
`client`<a id="client"></a>
170+
</td>
171+
<td>
172+
If you're not relying on the default client, you pass a
173+
`glm.DiscussServiceClient` instead.
174+
</td>
175+
</tr><tr>
176+
<td>
177+
`request_options`<a id="request_options"></a>
178+
</td>
179+
<td>
180+
Options for the request.
181+
</td>
182+
</tr>
183+
</table>
184+
185+
186+
187+
<!-- Tabular view -->
188+
<table class="responsive fixed orange">
189+
<colgroup><col width="214px"><col></colgroup>
190+
<tr><th colspan="2"><h2 class="add-link">Returns</h2></th></tr>
191+
<tr class="alt">
192+
<td colspan="2">
193+
A <a href="../../google/generativeai/types/ChatResponse.md"><code>types.ChatResponse</code></a> containing the model's reply.
194+
</td>
195+
</tr>
196+
197+
</table>
198+

‎docs/api/google/generativeai/chat_async.md

Lines changed: 198 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,198 @@
1+
description: Calls the API to initiate a chat with a model using provided parameters
2+
3+
<div itemscope itemtype="http://developers.google.com/ReferenceObject">
4+
<meta itemprop="name" content="google.generativeai.chat_async" />
5+
<meta itemprop="path" content="Stable" />
6+
</div>
7+
8+
# google.generativeai.chat_async
9+
10+
<!-- Insert buttons and diff -->
11+
12+
<table class="tfo-notebook-buttons tfo-api nocontent" align="left">
13+
<td>
14+
<a target="_blank" href="https://github.com/google/generative-ai-python/blob/master/google/generativeai/discuss.py#L411-L441">
15+
<img src="https://www.tensorflow.org/images/GitHub-Mark-32px.png" />
16+
View source on GitHub
17+
</a>
18+
</td>
19+
</table>
20+
21+
22+
23+
Calls the API to initiate a chat with a model using provided parameters
24+
25+
26+
<pre class="devsite-click-to-copy prettyprint lang-py tfo-signature-link">
27+
<code>google.generativeai.chat_async(
28+
*,
29+
model=&#x27;models/chat-bison-001&#x27;,
30+
context=None,
31+
examples=None,
32+
messages=None,
33+
temperature=None,
34+
candidate_count=None,
35+
top_p=None,
36+
top_k=None,
37+
prompt=None,
38+
client=None,
39+
request_options=None
40+
)
41+
</code></pre>
42+
43+
44+
45+
<!-- Placeholder for "Used in" -->
46+
47+
48+
<!-- Tabular view -->
49+
<table class="responsive fixed orange">
50+
<colgroup><col width="214px"><col></colgroup>
51+
<tr><th colspan="2"><h2 class="add-link">Args</h2></th></tr>
52+
53+
<tr>
54+
<td>
55+
`model`<a id="model"></a>
56+
</td>
57+
<td>
58+
Which model to call, as a string or a <a href="../../google/generativeai/types/Model.md"><code>types.Model</code></a>.
59+
</td>
60+
</tr><tr>
61+
<td>
62+
`context`<a id="context"></a>
63+
</td>
64+
<td>
65+
Text that should be provided to the model first, to ground the response.
66+
67+
If not empty, this `context` will be given to the model first before the
68+
`examples` and `messages`.
69+
70+
This field can be a description of your prompt to the model to help provide
71+
context and guide the responses.
72+
73+
Examples:
74+
75+
* "Translate the phrase from English to French."
76+
* "Given a statement, classify the sentiment as happy, sad or neutral."
77+
78+
Anything included in this field will take precedence over history in `messages`
79+
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>.
80+
</td>
81+
</tr><tr>
82+
<td>
83+
`examples`<a id="examples"></a>
84+
</td>
85+
<td>
86+
Examples of what the model should generate.
87+
88+
This includes both the user input and the response that the model should
89+
emulate.
90+
91+
These `examples` are treated identically to conversation messages except
92+
that they take precedence over the history in `messages`:
93+
If the total input size exceeds the model's `input_token_limit` the input
94+
will be truncated. Items will be dropped from `messages` before `examples`
95+
</td>
96+
</tr><tr>
97+
<td>
98+
`messages`<a id="messages"></a>
99+
</td>
100+
<td>
101+
A snapshot of the conversation history sorted chronologically.
102+
103+
Turns alternate between two authors.
104+
105+
If the total input size exceeds the model's `input_token_limit` the input
106+
will be truncated: The oldest items will be dropped from `messages`.
107+
</td>
108+
</tr><tr>
109+
<td>
110+
`temperature`<a id="temperature"></a>
111+
</td>
112+
<td>
113+
Controls the randomness of the output. Must be positive.
114+
115+
Typical values are in the range: `[0.0,1.0]`. Higher values produce a
116+
more random and varied response. A temperature of zero will be deterministic.
117+
</td>
118+
</tr><tr>
119+
<td>
120+
`candidate_count`<a id="candidate_count"></a>
121+
</td>
122+
<td>
123+
The **maximum** number of generated response messages to return.
124+
125+
This value must be between `[1, 8]`, inclusive. If unset, this
126+
will default to `1`.
127+
128+
Note: Only unique candidates are returned. Higher temperatures are more
129+
likely to produce unique candidates. Setting `temperature=0.0` will always
130+
return 1 candidate regardless of the `candidate_count`.
131+
</td>
132+
</tr><tr>
133+
<td>
134+
`top_k`<a id="top_k"></a>
135+
</td>
136+
<td>
137+
The API uses combined [nucleus](https://arxiv.org/abs/1904.09751) and
138+
top-k sampling.
139+
140+
`top_k` sets the maximum number of tokens to sample from on each step.
141+
</td>
142+
</tr><tr>
143+
<td>
144+
`top_p`<a id="top_p"></a>
145+
</td>
146+
<td>
147+
The API uses combined [nucleus](https://arxiv.org/abs/1904.09751) and
148+
top-k sampling.
149+
150+
`top_p` configures the nucleus sampling. It sets the maximum cumulative
151+
probability of tokens to sample from.
152+
153+
For example, if the sorted probabilities are
154+
`[0.5, 0.2, 0.1, 0.1, 0.05, 0.05]` a `top_p` of `0.8` will sample
155+
as `[0.625, 0.25, 0.125, 0, 0, 0]`.
156+
157+
Typical values are in the `[0.9, 1.0]` range.
158+
</td>
159+
</tr><tr>
160+
<td>
161+
`prompt`<a id="prompt"></a>
162+
</td>
163+
<td>
164+
You may pass a <a href="../../google/generativeai/types/MessagePromptOptions.md"><code>types.MessagePromptOptions</code></a> **instead** of a
165+
setting `context`/`examples`/`messages`, but not both.
166+
</td>
167+
</tr><tr>
168+
<td>
169+
`client`<a id="client"></a>
170+
</td>
171+
<td>
172+
If you're not relying on the default client, you pass a
173+
`glm.DiscussServiceClient` instead.
174+
</td>
175+
</tr><tr>
176+
<td>
177+
`request_options`<a id="request_options"></a>
178+
</td>
179+
<td>
180+
Options for the request.
181+
</td>
182+
</tr>
183+
</table>
184+
185+
186+
187+
<!-- Tabular view -->
188+
<table class="responsive fixed orange">
189+
<colgroup><col width="214px"><col></colgroup>
190+
<tr><th colspan="2"><h2 class="add-link">Returns</h2></th></tr>
191+
<tr class="alt">
192+
<td colspan="2">
193+
A <a href="../../google/generativeai/types/ChatResponse.md"><code>types.ChatResponse</code></a> containing the model's reply.
194+
</td>
195+
</tr>
196+
197+
</table>
198+

0 commit comments

Comments
 (0)