Add Azure OpenAI Content Filter Streaming Support #340
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
rasharab
commented
May 28, 2024
| @@ -19,7 +18,17 @@ public data class ChatChunk( | |||
| /** | |||
| * The generated chat message. | |||
| */ | |||
| @SerialName("delta") public val delta: ChatDelta, | |||
| @SerialName("delta") public val delta: ChatDelta? = null, | |||
There was a problem hiding this comment.
Delta must be nullable for content filtering.
Azure enforces content filtering on all completion requests. To reduce the overhead of content filtering, they’ve added asychronous mode, which basically outputs specialized bodies at the end of streaming output. https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cpython-new#annotation-message The basic structure is this: data: {"choices":[{"content_filter_offsets":{"check_offset":33188,"start_offset":33188,"end_offset":33546},"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"finish_reason":null,"index":0}],"created":0,"id":"","model":"","object":""}
rasharab
force-pushed
the
AddAzureContentFilterSupport
branch
from
0deb69a to
5883420
Compare
rasharab
changed the title
aallam
approved these changes
Jun 17, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
ISSUE: #339
Azure enforces content filtering on all completion requests.
To reduce the overhead of content filtering, they’ve added asychronous mode, which basically outputs specialized bodies at the end of streaming output.
https://learn.microsoft.com/en-us/azure/ai-services/openai/concepts/content-filter?tabs=warning%2Cpython-new#annotation-message
The basic structure is this while streaming:
{"choices":[{"content_filter_offsets":{"check_offset":33188,"start_offset":33188,"end_offset":33546},"content_filter_results":{"hate":{"filtered":false,"severity":"safe"},"self_harm":{"filtered":false,"severity":"safe"},"sexual":{"filtered":false,"severity":"safe"},"violence":{"filtered":false,"severity":"safe"}},"finish_reason":null,"index":0}],"created":0,"id":"","model":"","object":""}
This is related to #300, but that PR has a bug with the streaming case.
TESTING: