Skip to content

Commit 52aec0f

Browse files
hubwritersophiethekingthispaulmyarb
authored
Add Copilot docs for the Gemini 2.0 Flash model (#54076)
Co-authored-by: Sophie <[email protected]> Co-authored-by: Paul Loeb <[email protected]> Co-authored-by: Melanie Yarbrough <[email protected]>
1 parent f867504 commit 52aec0f

26 files changed

+270
-99
lines changed
46.8 KB
Loading

Diff for: content/code-security/code-scanning/managing-code-scanning-alerts/responsible-use-autofix-code-scanning.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -22,7 +22,7 @@ redirect_from:
2222

2323
{% data reusables.rai.code-scanning.copilot-autofix-note %}
2424

25-
{% data variables.product.prodname_copilot_autofix_short %} generates potential fixes that are relevant to the existing source code and translates the description and location of an alert into code changes that may fix the alert. {% data variables.product.prodname_copilot_autofix_short %} uses internal {% data variables.product.prodname_copilot %} APIs interfacing with the large language model GPT-4o from OpenAI, which has sufficient generative capabilities to produce both suggested fixes in code and explanatory text for those fixes.
25+
{% data variables.product.prodname_copilot_autofix_short %} generates potential fixes that are relevant to the existing source code and translates the description and location of an alert into code changes that may fix the alert. {% data variables.product.prodname_copilot_autofix_short %} uses internal {% data variables.product.prodname_copilot %} APIs interfacing with the large language model GPT 4o from OpenAI, which has sufficient generative capabilities to produce both suggested fixes in code and explanatory text for those fixes.
2626

2727
{% data variables.product.prodname_copilot_autofix_short %} is allowed by default and enabled for every repository using {% data variables.product.prodname_codeql %}, but you can choose to opt out and disable {% data variables.product.prodname_copilot_autofix_short %}. To learn how to disable {% data variables.product.prodname_copilot_autofix_short %} at the enterprise, organization and repository levels, see [AUTOTITLE](/code-security/code-scanning/managing-code-scanning-alerts/disabling-autofix-for-code-scanning).
2828

Diff for: content/copilot/managing-copilot/managing-copilot-as-an-individual-subscriber/about-github-copilot-free.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -26,7 +26,7 @@ topics:
2626
* {% data variables.product.prodname_copilot_edits_vscode_short %} to make changes across multiple files (**only in {% data variables.product.prodname_vscode %} and {% data variables.product.prodname_vs %}**)
2727
* {% data variables.product.prodname_copilot_chat_short %} in {% data variables.product.prodname_vscode %}, {% data variables.product.prodname_vs %}, JetBrains IDEs, and {% data variables.product.prodname_dotcom_the_website %}
2828
* Block suggestions matching public code
29-
* Access to {% data variables.copilot.copilot_claude_sonnet %} models
29+
* Access to the {% data variables.copilot.copilot_claude_sonnet %} and {% data variables.copilot.copilot_gemini_flash %} models
3030
* Access to {% data variables.product.prodname_copilot_extensions_short %} in {% data variables.product.prodname_vscode %}, {% data variables.product.prodname_vs %}, JetBrains IDEs, {% data variables.product.prodname_dotcom_the_website %}, and {% data variables.product.prodname_mobile %}
3131

3232
## What are the limitations of {% data variables.product.prodname_copilot_free_short %}?

Diff for: content/copilot/managing-copilot/managing-copilot-as-an-individual-subscriber/managing-copilot-policies-as-an-individual-subscriber.md

+6-3
Original file line numberDiff line numberDiff line change
@@ -38,12 +38,15 @@ You can choose whether your prompts and {% data variables.product.prodname_copil
3838
{% data reusables.user-settings.copilot-settings %}
3939
1. To allow or prevent {% data variables.product.prodname_dotcom %} using your data, select or deselect **Allow {% data variables.product.prodname_dotcom %} to use my code snippets from the code editor for product improvements**.
4040

41-
## Enabling or disabling {% data variables.copilot.copilot_claude_sonnet %}
41+
## Enabling or disabling alternative AI models
4242

43-
You can choose whether to allow use of Anthropic's {% data variables.copilot.copilot_claude_sonnet %} model as an alternative to {% data variables.product.prodname_copilot_short %}'s default model. For more information, see [AUTOTITLE](/copilot/using-github-copilot/using-claude-sonnet-in-github-copilot).
43+
You can choose whether to allow the following AI models to be used as an alternative to {% data variables.product.prodname_copilot_short %}'s default model.
44+
45+
* {% data variables.copilot.copilot_claude_sonnet %} - see [AUTOTITLE](/copilot/using-github-copilot/ai-models/using-claude-sonnet-in-github-copilot)
46+
* {% data variables.copilot.copilot_gemini_flash %} - see [AUTOTITLE](/copilot/using-github-copilot/ai-models/using-gemini-flash-in-github-copilot)
4447

4548
{% data reusables.user-settings.copilot-settings %}
46-
1. To the right of **Anthropic {% data variables.copilot.copilot_claude_sonnet %} in {% data variables.product.prodname_copilot_short %}**, select the dropdown menu, then click **Enabled** or **Disabled**.
49+
1. To the right of the model name, select the dropdown menu, then click **Enabled** or **Disabled**.
4750

4851
## Enabling or disabling web search for {% data variables.product.prodname_copilot_chat %}
4952

Diff for: content/copilot/managing-copilot/managing-copilot-for-your-enterprise/managing-policies-and-features-for-copilot-in-your-enterprise.md

+9-18
Original file line numberDiff line numberDiff line change
@@ -33,8 +33,7 @@ You can configure any of the following policies for your enterprise:
3333
* [{% data variables.product.prodname_copilot_extensions %}](#github-copilot-extensions)
3434
* [Suggestions matching public code](#suggestions-matching-public-code)
3535
* [Give {% data variables.product.prodname_copilot_short %} access to Bing](#give-copilot-access-to-bing)
36-
* [{% data variables.product.prodname_copilot_short %} access to {% data variables.copilot.copilot_claude_sonnet %}](#copilot-access-to-claude-35-sonnet)
37-
* [{% data variables.product.prodname_copilot_short %} access to the o1 and o3 families of models](#copilot-access-to-the-o1-and-o3-families-of-models)
36+
* [{% data variables.product.prodname_copilot_short %} access to alternative AI models](#copilot-access-to-alternative-ai-models)
3837

3938
### {% data variables.product.prodname_copilot_short %} in {% data variables.product.prodname_dotcom_the_website %}
4039

@@ -75,25 +74,17 @@ You can chat with {% data variables.product.prodname_copilot %} in your IDE to g
7574
7675
{% data variables.product.prodname_copilot_chat %} can use Bing to provide enhanced responses by searching the internet for information related to a question. Bing search is particularly helpful when discussing new technologies or highly specific subjects.
7776

78-
### {% data variables.product.prodname_copilot_short %} access to {% data variables.copilot.copilot_claude_sonnet %}
77+
### {% data variables.product.prodname_copilot_short %} access to alternative AI models
7978

80-
{% data reusables.copilot.claude-sonnet-preview-note %}
79+
> [!NOTE] The following models are currently in {% data variables.release-phases.public_preview %} as AI models for {% data variables.product.prodname_copilot %}, and are subject to change. The [AUTOTITLE](/free-pro-team@latest/site-policy/github-terms/github-pre-release-license-terms) apply to your use of these products.
8180
82-
By default, {% data variables.product.prodname_copilot_chat_short %} uses the `GPT 4o` model. If you grant access to **Anthropic {% data variables.copilot.copilot_claude_sonnet %} in {% data variables.product.prodname_copilot_short %}**, members of your enterprise can choose to use this model rather than the default `GPT 4o` model. See [AUTOTITLE](/copilot/using-github-copilot/using-claude-sonnet-in-github-copilot).
81+
By default, {% data variables.product.prodname_copilot_chat_short %} uses the GPT 4o model. If you grant access to the alternative models, members of your enterprise can choose to use these models rather than the default GPT 4o model. The available alternative models are:
8382

84-
### {% data variables.product.prodname_copilot_short %} access to the o1 and o3 families of models
85-
86-
{% data reusables.models.o1-models-preview-note %}
87-
88-
By default, {% data variables.product.prodname_copilot_chat_short %} uses the `GPT 4o` model. If you grant access to the o1 or o3 models, members of your enterprise can select to use these models rather than the default `GPT 4o` model.
89-
90-
The o1 family of models includes the following models:
91-
92-
* `o1`/`o1-preview`: These models are focused on advanced reasoning and solving complex problems, in particular in math and science. They respond more slowly than the `gpt-4o` model. Each member of your enterprise can make 10 requests to each of these models per day.
93-
94-
The o3 family of models includes one model:
95-
96-
* `o3-mini`: This is the next generation of reasoning models, following from `o1` and `o1-mini`. The `o3-mini` model outperforms `o1` on coding benchmarks with response times that are comparable to `o1-mini`, providing improved quality at nearly the same latency. It is best suited for code generation and small context operations. Each member of your enterprise can make 50 requests to this model every 12 hours.
83+
* **{% data variables.copilot.copilot_claude_sonnet %}**. See [AUTOTITLE](/copilot/using-github-copilot/ai-models/using-claude-sonnet-in-github-copilot).
84+
* **{% data variables.copilot.copilot_gemini_flash %}**. See [AUTOTITLE](/copilot/using-github-copilot/ai-models/using-gemini-flash-in-github-copilot).
85+
* **OpenAI's o1 and o3 models**
86+
* **o1**: This model is focused on advanced reasoning and solving complex problems, in particular in math and science. It responds more slowly than the GPT 4o model. Each member of your enterprise can make 10 requests to this model per day.
87+
* **o3-mini**: This is the next generation of reasoning models, following from o1 and o1-mini. The o3-mini model outperforms o1 on coding benchmarks with response times that are comparable to o1-mini, providing improved quality at nearly the same latency. It is best suited for code generation and small context operations. Each member of your enterprise can make 50 requests to this model every 12 hours.
9788

9889
### {% data variables.product.prodname_copilot_short %} Metrics API access
9990

Diff for: content/copilot/managing-copilot/managing-github-copilot-in-your-organization/managing-policies-for-copilot-in-your-organization.md

+3-2
Original file line numberDiff line numberDiff line change
@@ -32,8 +32,9 @@ Organization owners can set policies to govern how {% data variables.product.pro
3232
* {% data variables.product.prodname_copilot_cli_short %} and {% data variables.product.prodname_windows_terminal %}
3333
* Suggestions matching public code
3434
* Access to alternative models for {% data variables.product.prodname_copilot_short %}
35-
* Anthropic {% data variables.copilot.copilot_claude_sonnet %} in Copilot
36-
* OpenAI o1 and o3 models in Copilot
35+
* Anthropic {% data variables.copilot.copilot_claude_sonnet %} in {% data variables.product.prodname_copilot_short %}
36+
* Google {% data variables.copilot.copilot_gemini_flash %} in {% data variables.product.prodname_copilot_short %}
37+
* OpenAI o1 and o3 models in {% data variables.product.prodname_copilot_short %}
3738

3839
The policy settings selected by an organization owner determine the behavior of {% data variables.product.prodname_copilot %} for all organization members that have been granted access to {% data variables.product.prodname_copilot_short %} through the organization.
3940

Diff for: content/copilot/troubleshooting-github-copilot/troubleshooting-common-issues-with-github-copilot.md

+1-1
Original file line numberDiff line numberDiff line change
@@ -64,7 +64,7 @@ For more information, see the [{% data variables.product.prodname_copilot_cli_sh
6464

6565
This error suggests that you have exceeded the rate limit for {% data variables.product.prodname_copilot_short %} requests. {% data variables.product.github %} uses rate limits to ensure everyone has fair access to the {% data variables.product.prodname_copilot_short %} service and to protect against abuse.
6666

67-
Most people see rate limiting for preview models, like OpenAI’s o1 and o1-mini, which are rate-limited due to limited capacity.
67+
Most people see rate limiting for preview models, like OpenAI’s o1 and o3-mini, which are rate-limited due to limited capacity.
6868

6969
Service-level request rate limits ensure high service quality for all {% data variables.product.prodname_copilot_short %} users and should not affect typical or even deeply engaged {% data variables.product.prodname_copilot_short %} usage. We are aware of some use cases that are affected by it. {% data variables.product.github %} is iterating on {% data variables.product.prodname_copilot_short %}’s rate-limiting heuristics to ensure it doesn’t block legitimate use cases.
7070

Original file line numberDiff line numberDiff line change
@@ -0,0 +1,90 @@
1+
---
2+
title: Changing the AI model for Copilot Chat
3+
shortTitle: 'Change the AI model'
4+
intro: 'Learn how to change the default LLM for {% data variables.product.prodname_copilot_chat_short %} to a different model.'
5+
versions:
6+
feature: copilot
7+
topics:
8+
- Copilot
9+
---
10+
11+
By default, {% data variables.product.prodname_copilot_chat_short %} uses OpenAI's GPT 4o large language model. This is a highly proficient model that performs well for text generation tasks, such as summarization and knowledge-based chat. The model is also capable of reasoning, solving complex math problems and coding.
12+
13+
However, you are not limited to using this model. You can choose from a selection of other models, each with its own particular strengths. You may have a favorite model that you like to use, or you might prefer to use a particular model for inquiring about a specific subject.
14+
15+
{% data variables.product.prodname_copilot_short %} allows you to change the model during a chat and have the alternative model used to generate responses to your prompts.
16+
17+
{% webui %}
18+
19+
> [!NOTE]
20+
> * Multiple model support in {% data variables.product.prodname_copilot_chat_short %} is in {% data variables.release-phases.public_preview %} and is subject to change.
21+
> * You can only use an alternative AI model in the immersive view of {% data variables.product.prodname_copilot_chat_short %}. This is the full-page version of {% data variables.product.prodname_copilot_chat_short %} that's displayed at [https://github.com/copilot](https://github.com/copilot). The {% data variables.product.prodname_copilot_chat_short %} panel always uses the default model.
22+
23+
## AI models for {% data variables.product.prodname_copilot_chat_short %}
24+
25+
{% data reusables.copilot.copilot-chat-models-list %}
26+
27+
### Limitations of AI models for {% data variables.product.prodname_copilot_chat_short %}
28+
29+
* If you want to use the skills listed in the table above{% ifversion ghec %}, or knowledge bases{% endif %}, on the {% data variables.product.github %} website, only the GPT 4o, {% data variables.copilot.copilot_claude_sonnet %}, and {% data variables.copilot.copilot_gemini_flash %} models are supported.
30+
* Experimental pre-release versions of the models may not interact with all filters correctly, including the duplication detection filter.
31+
32+
## Changing your AI model
33+
34+
These instructions are for {% data variables.product.prodname_copilot_short %} on the {% data variables.product.github %} website. For {% data variables.product.prodname_vs %} or {% data variables.product.prodname_vscode_shortname %}, click the appropriate tab at the top of this page.
35+
36+
{% data reusables.copilot.model-picker-enable-o1-models %}
37+
38+
> [!NOTE] If you use {% data variables.product.prodname_copilot_extensions_short %}, they may override the model you select.
39+
40+
1. In the top right of any page on {% data variables.product.github %}, click the down arrow beside the **{% octicon "copilot" aria-hidden="true" %}** icon and click **Immersive** in the dropdown menu.
41+
42+
![Screenshot of the 'Immersive' button, highlighted with a dark orange outline.](/assets/images/help/copilot/copilot-immersive-button.png)
43+
44+
1. At the top of the immersive view, select the **CURRENT-MODEL** {% octicon "chevron-down" aria-hidden="true" %} dropdown menu, then click the AI model of your choice.
45+
46+
{% endwebui %}
47+
48+
{% vscode %}
49+
50+
> [!NOTE] Multiple model support in {% data variables.product.prodname_copilot_chat_short %} is in {% data variables.release-phases.public_preview %} and is subject to change.
51+
52+
## AI models for {% data variables.product.prodname_copilot_chat_short %}
53+
54+
{% data reusables.copilot.copilot-chat-models-list %}
55+
56+
## Changing your AI model
57+
58+
These instructions are for {% data variables.product.prodname_vscode_shortname %}. For {% data variables.product.prodname_vs %} or for {% data variables.product.prodname_copilot_short %} on the {% data variables.product.github %} website, click the appropriate tab at the top of this page.
59+
60+
{% data reusables.copilot.model-picker-enable-o1-models %}
61+
62+
{% data reusables.copilot.chat-model-limitations-ide %}
63+
64+
{% data reusables.copilot.open-chat-vs-code %}
65+
1. In the bottom right of the chat view, select the **CURRENT-MODEL** {% octicon "chevron-down" aria-hidden="true" %} dropdown menu, then click the AI model of your choice.
66+
67+
{% endvscode %}
68+
69+
{% visualstudio %}
70+
71+
> [!NOTE] Multiple model support in {% data variables.product.prodname_copilot_chat_short %} is in {% data variables.release-phases.public_preview %} and is subject to change.
72+
73+
## AI models for {% data variables.product.prodname_copilot_chat_short %}
74+
75+
{% data reusables.copilot.copilot-chat-models-list-visual-studio %}
76+
77+
## Changing your AI model
78+
79+
These instructions are for {% data variables.product.prodname_vs %}. For {% data variables.product.prodname_vscode_shortname %} or for {% data variables.product.prodname_copilot_short %} on the {% data variables.product.github %} website, click the appropriate tab at the top of this page.
80+
81+
To use multi-model {% data variables.product.prodname_copilot_chat_short %}, you must use {% data variables.product.prodname_vs %} 2022 version 17.12 or later. See the [{% data variables.product.prodname_vs %} downloads page](https://visualstudio.microsoft.com/downloads/).
82+
83+
{% data reusables.copilot.model-picker-enable-o1-models %}
84+
85+
{% data reusables.copilot.chat-model-limitations-ide %}
86+
87+
1. In the {% data variables.product.prodname_vs %} menu bar, click **View**, then click **{% data variables.product.prodname_copilot_chat %}**.
88+
1. In the bottom right of the chat view, select the **CURRENT-MODEL** {% octicon "triangle-down" aria-hidden="true" %} dropdown menu, then click the AI model of your choice.
89+
90+
{% endvisualstudio %}
+13
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,13 @@
1+
---
2+
title: AI models for Copilot Chat
3+
shortTitle: AI models
4+
intro: "Learn how to use alternative large language models for {% data variables.product.prodname_copilot_chat %}."
5+
versions:
6+
feature: copilot
7+
topics:
8+
- Copilot
9+
children:
10+
- /changing-the-ai-model-for-copilot-chat
11+
- /using-claude-sonnet-in-github-copilot
12+
- /using-gemini-flash-in-github-copilot
13+
---

0 commit comments

Comments
 (0)