Skip to content

support for serverless accounts, local vLLM execution, logging of full-text requests#63

Open
alekseys wants to merge 1 commit into
mainfrom
feature/serverless-vllm-logging
Open

support for serverless accounts, local vLLM execution, logging of full-text requests#63
alekseys wants to merge 1 commit into
mainfrom
feature/serverless-vllm-logging

Conversation

@alekseys

Copy link
Copy Markdown
Collaborator

added support for serverless accounts, local vLLM execution, logging of full-text requests

Copilot AI review requested due to automatic review settings July 12, 2026 15:37
@alekseys alekseys added the enhancement New feature or request label Jul 12, 2026

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

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

Pull request overview

This PR updates the retrieval/ingestion utilities to better support additional deployment modes (serverless Cosmos accounts and local OpenAI-compatible LLM endpoints) and to reduce noisy user-facing output in fulltext search failure cases.

Changes:

  • Add a serverless fallback when Cosmos container creation fails due to unsupported throughput settings.
  • Add support for local OpenAI-compatible endpoints (e.g., vLLM) by switching to AsyncOpenAI when the configured endpoint is localhost.
  • Replace a print(...) on fulltext query failure with logger.debug(...) to keep CLI output cleaner.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.

File Description
utils/fulltext.py Replaces user-facing print on query failure with debug logging.
dynamic_retriever.py Adds AsyncOpenAI for localhost endpoints, aiming to enable local/vLLM execution.
cosmos_db_upload.py Adds retry logic for serverless Cosmos accounts by removing throughput options on retry.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread dynamic_retriever.py
Comment on lines +468 to +472
def llm_client(self):
if not self._llm_client:
client_kwargs = {
"api_version": self._cfg["api_version"],
"azure_endpoint": self._cfg["llm_endpoint"],
endpoint = self._cfg["llm_endpoint"]
if endpoint.startswith("http://localhost") or endpoint.startswith("http://127.0.0.1"):
self._llm_client = AsyncOpenAI(
Comment thread utils/fulltext.py
except Exception as e:
print(f" [fulltext_search_single_field] query failed: {e}")
# Suppress verbose Cosmos diagnostics in user-facing output.
logger.debug("fulltext_search_single_field failed for field '%s': %s", field, type(e).__name__)
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants