feat(perplexity): deprecate chat completions helpers - #7069
Draft
andrewmadson-pplx wants to merge 4 commits into
Draft
feat(perplexity): deprecate chat completions helpers#7069andrewmadson-pplx wants to merge 4 commits into
andrewmadson-pplx wants to merge 4 commits into
Conversation
|
|
This file contains hidden or 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
The Python integrations
perplexity.LLMandopenai.LLM.with_perplexity()still use Sonar Chat Completions. Users need an actionable migration path to the existingperplexity.responses.LLMAgent API client before Sonar is retired.The OpenAI helper also defaults to
llama-3.1-sonar-small-128k-chat, which is no longer served, so its zero-configuration path fails before users can migrate.What changed
DeprecationWarnings from both Python Chat Completions entry points.openai.LLM.with_perplexity()to a workingsonar-prodefault and replace its retired model type literals with current Sonar model IDs.sonar-protoperplexity/sonar.Behavior and scope
This is a soft deprecation: existing explicit Chat Completions configurations continue to construct, while callers receive a standard Python deprecation warning with the replacement API. Zero-configuration
with_perplexity()callers temporarily regain a supported Sonar default and receive the same migration warning.The generated pdoc output renders both directives as deprecation callouts. The native Responses client remains unchanged: it defaults to
perplexity/sonar, selects HTTP athttps://api.perplexity.ai/v1/, readsPERPLEXITY_API_KEY, and sets the LiveKit attribution header.Coordinated Node change: livekit/agents-js#2392.
Coordinated Perplexity guide: ppl-ai/api-docs#807.
Tracking: Sonar to Agent migration, API-3590, and API-3389.