Skip to content

Faster Smart Apply updates #1107

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
MaedahBatool merged 2 commits into from
Apr 30, 2025
Merged

Faster Smart Apply updates #1107

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
408cbdd
Faster Smart Apply updates
MaedahBatool Apr 29, 2025
4f21961
Add feedback from team
MaedahBatool Apr 29, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions docs/cody/capabilities/chat.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,6 +74,12 @@ Smart Apply also supports the executing of commands in the terminal. When you as

![smart-apply](https://storage.googleapis.com/sourcegraph-assets/Docs/smart-apply-2025.png)

### Model used for Smart Apply

To ensure low latency, Cody uses a more targeted Qwen 2.5 Coder model for Smart Apply. This model improves the responsiveness of the Smart Apply feature in both VS Code and JetBrains while preserving edit quality. Users on Cody Free, Pro, Enterprise Starter, and Enterprise plans get this default Qwen 2.5 Coder model for Smart Apply suggestions.

Enterprise users not using Cody Gateway get a Claude Sonnet-based model for Smart Apply.

## Chat history

Cody keeps a history of your chat sessions. You can view it by clicking the **History** button in the chat panel. You can **Export** it to a JSON file for later use or click the **Delete all** button to clear the chat history.
Expand Down
47 changes: 27 additions & 20 deletions docs/cody/capabilities/supported-models.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,20 +6,20 @@ Cody supports a variety of cutting-edge large language models for use in chat an

<Callout type="note">Newer versions of Sourcegraph Enterprise, starting from v5.6, it will be even easier to add support for new models and providers, see [Model Configuration](/cody/enterprise/model-configuration) for more information.</Callout>

| **Provider** | **Model** | **Free** | **Pro** | **Enterprise** | | | | |
| :------------ | :-------------------------------------------------------------------------------------------------------------------------------------------- | :----------- | :----------- | :------------- | --- | --- | --- | --- |
| OpenAI | [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo#:~:text=TRAINING%20DATA-,gpt%2D4%2D0125%2Dpreview,-New%20GPT%2D4) | - | ✅ | ✅ | | | | |
| OpenAI | [GPT-4o](https://platform.openai.com/docs/models#gpt-4o) | - | ✅ | ✅ | | | | |
| OpenAI | [GPT-4o-mini](https://platform.openai.com/docs/models#gpt-4o-mini) | ✅ | ✅ | ✅ | | | | |
| OpenAI | [o3-mini-medium](https://openai.com/index/openai-o3-mini/) (experimental) | ✅ | ✅ | ✅ | | | | |
| OpenAI | [o3-mini-high](https://openai.com/index/openai-o3-mini/) (experimental) | - | - | ✅ | | | | |
| OpenAI | [o1](https://platform.openai.com/docs/models#o1) | - | ✅ | ✅ | | | | |
| Anthropic | [Claude 3.5 Haiku](https://docs.anthropic.com/claude/docs/models-overview#model-comparison) | ✅ | ✅ | ✅ | | | | |
| Anthropic | [Claude 3.5 Sonnet](https://docs.anthropic.com/claude/docs/models-overview#model-comparison) | ✅ | ✅ | ✅ | | | | |
| Anthropic | [Claude 3.7 Sonnet](https://docs.anthropic.com/claude/docs/models-overview#model-comparison) | - | ✅ | ✅ | | | | |
| Google | [Gemini 1.5 Pro](https://deepmind.google/technologies/gemini/pro/) | ✅ | ✅ | ✅ (beta) | | | | |
| Google | [Gemini 2.0 Flash](https://deepmind.google/technologies/gemini/flash/) | ✅ | ✅ | ✅ | | | | |
| Google | [Gemini 2.0 Flash-Lite Preview](https://deepmind.google/technologies/gemini/flash/) (experimental) | ✅ | ✅ | ✅ | | | | |
| **Provider** | **Model** | **Free** | **Pro** | **Enterprise** | | | | |
Comment thread
MaedahBatool marked this conversation as resolved.
| :----------- | :-------------------------------------------------------------------------------------------------------------------------------------------- | :------- | :------ | :------------- | --- | --- | --- | --- |
| OpenAI | [GPT-4 Turbo](https://platform.openai.com/docs/models/gpt-4-and-gpt-4-turbo#:~:text=TRAINING%20DATA-,gpt%2D4%2D0125%2Dpreview,-New%20GPT%2D4) | - | ✅ | ✅ | | | | |
| OpenAI | [GPT-4o](https://platform.openai.com/docs/models#gpt-4o) | - | ✅ | ✅ | | | | |
| OpenAI | [GPT-4o-mini](https://platform.openai.com/docs/models#gpt-4o-mini) | ✅ | ✅ | ✅ | | | | |
| OpenAI | [o3-mini-medium](https://openai.com/index/openai-o3-mini/) (experimental) | ✅ | ✅ | ✅ | | | | |
| OpenAI | [o3-mini-high](https://openai.com/index/openai-o3-mini/) (experimental) | - | - | ✅ | | | | |
| OpenAI | [o1](https://platform.openai.com/docs/models#o1) | - | ✅ | ✅ | | | | |
| Anthropic | [Claude 3.5 Haiku](https://docs.anthropic.com/claude/docs/models-overview#model-comparison) | ✅ | ✅ | ✅ | | | | |
| Anthropic | [Claude 3.5 Sonnet](https://docs.anthropic.com/claude/docs/models-overview#model-comparison) | ✅ | ✅ | ✅ | | | | |
| Anthropic | [Claude 3.7 Sonnet](https://docs.anthropic.com/claude/docs/models-overview#model-comparison) | - | ✅ | ✅ | | | | |
| Google | [Gemini 1.5 Pro](https://deepmind.google/technologies/gemini/pro/) | ✅ | ✅ | ✅ (beta) | | | | |
| Google | [Gemini 2.0 Flash](https://deepmind.google/technologies/gemini/flash/) | ✅ | ✅ | ✅ | | | | |
| Google | [Gemini 2.0 Flash-Lite Preview](https://deepmind.google/technologies/gemini/flash/) (experimental) | ✅ | ✅ | ✅ | | | | |

<Callout type="note">To use Claude 3 Sonnet models with Cody Enterprise, make sure you've upgraded your Sourcegraph instance to the latest version. </Callout>

Expand All @@ -39,13 +39,20 @@ In addition, Sourcegraph Enterprise customers using GCP Vertex (Google Cloud Pla

Cody uses a set of models for autocomplete which are suited for the low latency use case.

| **Provider** | **Model** | **Free** | **Pro** | **Enterprise** | | | | |
| :-------------------- | :---------------------------------------------------------------------------------------- | :------- | :------ | :------------- | --- | --- | --- | --- |
| Fireworks.ai | [DeepSeek-Coder-V2](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct) | ✅ | ✅ | ✅ | | | | |
| Fireworks.ai | [StarCoder](https://arxiv.org/abs/2305.06161) | - | - | ✅ | | | | |
| Anthropic | [claude Instant](https://docs.anthropic.com/claude/docs/models-overview#model-comparison) | - | - | ✅ | | | | |
| | | | | | | | | |
| **Provider** | **Model** | **Free** | **Pro** | **Enterprise** | | | | |
| :----------- | :---------------------------------------------------------------------------------------- | :------- | :------ | :------------- | --- | --- | --- | --- |
| Fireworks.ai | [DeepSeek-Coder-V2](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Lite-Instruct) | ✅ | ✅ | ✅ | | | | |
| Anthropic | [claude Instant](https://docs.anthropic.com/claude/docs/models-overview#model-comparison) | - | - | ✅ | | | | |
| | | | | | | | | |

<Callout type="note">The default autocomplete model for Cody Free, Pro and Enterprise users is DeepSeek-Coder-V2.</Callout>

<Callout type="note">The DeepSeek model used by Sourcegraph is hosted by Fireworks.ai, and is hosted as a single-tenant service in a US-based data center. For more information see our [Cody FAQ](https://sourcegraph.com/docs/cody/faq#is-any-of-my-data-sent-to-deepseek).</Callout>

## Smart Apply

| **Provider** | **Model** | **Free** | **Pro** | **Enterprise** | | | | | | |
| :----------- | :------------- | :------- | :------ | :------------- | --- | --- | --- | --- | --- | --- |
| Fireworks.ai | Qwen 2.5 Coder | ✅ | ✅ | ✅ | | | | | | |

<Callout type="note">Enterprise users not using Cody Gateway get a Claude Sonnet-based model for Smart Apply.</Callout>