Skip to content
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.

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

Update Cody faq page. #897

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open
Changes from all commits
Commits
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
15 changes: 15 additions & 0 deletions docs/cody/faq.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -137,6 +137,21 @@ cody chat --model '$name_of_the_model' -m 'Hi Cody!'

For example, to use Claude 3.5 Sonnet, you'd pass the following command in your terminal, `cody chat --model 'claude-3.5-sonnet' -m 'Hi Cody!'

### Can I configure custom context windows for API-only access?

Yes, it's possible to configure a custom context window exclusively for programmatic access via the API. To achieve this you need to use the custom [model configuration](https://sourcegraph.com/docs/cody/enterprise/model-configuration#model-overrides) and set the "capabilities" list as empty in the model configuration.

Here's an example config

"contextWindow": {
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can we please enclose this under code blocks?

"contextWindow": {
        // Specifies the maximum number of tokens for the contextual data in the prompt (e.g., question, relevant snippets)
        "maxInputTokens": 45000,
        // Specifies the maximum number of tokens allowed in the response
        "maxOutputTokens": 8000
      },
      // Set the "capabilities" list as empty to ensure the model is not available on Cody Web or IDEs
      "capabilities": [],

// Specifies the maximum number of tokens for the contextual data in the prompt (e.g., question, relevant snippets)
"maxInputTokens": 45000,
// Specifies the maximum number of tokens allowed in the response
"maxOutputTokens": 8000
},
// Set the "capabilities" list as empty to ensure the model is not available on Cody Web or IDEs
"capabilities": [],

## OpenAI o1

### What are OpenAI o1 best practices?
Expand Down
Loading