Skip to content

Fix EmbeddingService blocking event loop by offloading encode to thread #262

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
dolliecoder wants to merge 1 commit into
base: main
Choose a base branch
from
+11 −2
Open

Fix EmbeddingService blocking event loop by offloading encode to thread #262

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
13 changes: 11 additions & 2 deletions backend/app/services/embedding_service/service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
import asyncio
import logging
import config
from typing import List, Dict, Any, Optional
Expand Down Expand Up @@ -66,6 +67,10 @@ def llm(self) -> ChatGoogleGenerativeAI:
raise
return self._llm


def _encode_sync(self, *args, **kwargs):
return self.model.encode(*args, **kwargs)

async def get_embedding(self, text: str) -> List[float]:
"""Generate embedding for a single text input"""
try:
Expand All @@ -74,12 +79,14 @@ async def get_embedding(self, text: str) -> List[float]:
text = [text]

# Generate embeddings
embeddings = self.model.encode(
embeddings = await asyncio.to_thread(
self._encode_sync,
text,
convert_to_tensor=True,
show_progress_bar=False
)


# Convert to standard Python list and return
embedding_list = embeddings[0].cpu().tolist()
logger.debug(f"Generated embedding with dimension: {len(embedding_list)}")
Expand All @@ -92,13 +99,15 @@ async def get_embeddings(self, texts: List[str]) -> List[List[float]]:
"""Generate embeddings for multiple text inputs in batches"""
try:
# Generate embeddings
embeddings = self.model.encode(
embeddings = await asyncio.to_thread(
self._encode_sync,
texts,
convert_to_tensor=True,
batch_size=MAX_BATCH_SIZE,
show_progress_bar=len(texts) > 10
)


# Convert to standard Python list
embedding_list = embeddings.cpu().tolist()
logger.info(f"Generated {len(embedding_list)} embeddings")
Expand Down