Skip to content

Fix guardrails streaming documentation #667

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

Open
mintlify wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix guardrails streaming documentation #667

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: 1 addition & 1 deletion product/guardrails.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -601,7 +601,7 @@ This example corresponds to a `config` like:
#### Streaming Responses

<Note>
Portkey now supports hook results in streaming responses for `/chat/completions`, `/completions`, `/embeddings`, and `/messages` endpoints. This allows you to stop streaming or show redacted content if a request violates your guardrail policies, enabling clients to respect content policy guidelines in real-time.
For streaming requests, Portkey supports guardrails on the **input** (request) only—not on the streaming output. When an input guardrail runs on a streaming request, the hook results are now included in the streaming response, allowing clients to handle policy violations (e.g., stop streaming or show redacted content) in real-time.
</Note>

To receive hook results in streaming responses, you must set the `x-portkey-strict-open-ai-compliance` header to `false`.
Expand Down