Skip to content

Add clarification around deepseek model #979

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
merged 1 commit into from
Feb 13, 2025
Merged

Add clarification around deepseek model #979

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
2 changes: 2 additions & 0 deletions docs/cody/capabilities/supported-models.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,4 +43,6 @@ Cody uses a set of models for autocomplete which are suited for the low latency

<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>

Read here for [Ollama setup instructions](https://sourcegraph.com/docs/cody/clients/install-vscode#supported-local-ollama-models-with-cody). For information on context token limits, see our [documentation here](/cody/core-concepts/token-limits).
8 changes: 8 additions & 0 deletions docs/cody/faq.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -100,6 +100,14 @@ Cody does not support embeddings on Cody PLG and Cody Enterprise because we have

Leveraging Sourcegraph Search allowed us to deliver these enhancements.

## LLM Data Sharing and Retention

### Is any of my data sent to DeepSeek?

Our autocomplete features uses the open source DeepSeek-Coder-V2 model, which is hosted by Fireworks.ai in a secure single-tenant environment located in the USA. No customer chat or autocomplete data - such as chat messages, or context such as code snippets or configuration - is stored by Fireworks.ai.

Sourcegraph does not use models hosted by DeepSeek (the company), and does not send any data to the same.

## Third party dependencies

### What is the default `sourcegraph` provider for completions?
Expand Down