feat: use Chat Completions API for inline completion in OpenAI Compatible provider#117
Merged
mbektas merged 1 commit intoApr 7, 2026
Conversation
…ible provider Replace Legacy Completions API with Chat Completions API for inline completion. This enables compatibility with vLLM and other OpenAI-compatible APIs that don't support the suffix parameter. Changes: - Use chat.completions.create instead of completions.create - Add prompt engineering to handle prefix/suffix context - Add code extraction from markdown response - Add cancellation token checks
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
/v1/completions) with Chat Completions API (/v1/chat/completions) for inline completionsuffixparameter in Legacy Completions APIChanges
chat.completions.createinstead ofcompletions.create_extract_llm_generated_code()method to extract code from markdown responseMotivation
vLLM's OpenAI-compatible API does not support the
suffixparameter in the Legacy Completions API:This PR makes the OpenAI Compatible provider work with vLLM and similar services.
Testing
Tested with vLLM server providing inline completions in JupyterLab notebooks.