Skip to content

Solve batch size too large issue #40

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

Merged
wilsonccccc merged 1 commit into from
Jul 30, 2025
Merged

Solve batch size too large issue #40

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
57 changes: 39 additions & 18 deletions app/services/providers/openai_adapter.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,14 +4,20 @@

import aiohttp
from app.core.logger import get_logger
from app.exceptions.exceptions import ProviderAPIException, BaseInvalidRequestException
from app.exceptions import (
ProviderAPIException,
BaseInvalidRequestException,
)

from .base import ProviderAdapter

# Configure logging
logger = get_logger(name="openai_adapter")


MAX_BATCH_SIZE = 2048


class OpenAIAdapter(ProviderAdapter):
"""Adapter for OpenAI API"""

Expand Down Expand Up @@ -256,21 +262,36 @@ async def process_embeddings(
url = f"{base_url or self._base_url}/{endpoint}"
query_params = query_params or {}

async with (
aiohttp.ClientSession() as session,
session.post(
url, headers=headers, json=payload, params=query_params
) as response,
):
if response.status != HTTPStatus.OK:
error_text = await response.text()
logger.error(
f"Embeddings API error for {self.provider_name}: {error_text}"
)
raise ProviderAPIException(
provider_name=self.provider_name,
error_code=response.status,
error_message=error_text,
)
all_embeddings = []
for i in range(0, len(payload["input"]), MAX_BATCH_SIZE):
batch_payload = payload.copy()
batch_payload["input"] = payload["input"][i : i + MAX_BATCH_SIZE]

return await response.json()
async with (
aiohttp.ClientSession() as session,
session.post(
url, headers=headers, json=batch_payload, params=query_params
) as response,
):
if response.status != HTTPStatus.OK:
error_text = await response.text()
logger.error(
f"Embeddings API error for {self.provider_name}: {error_text}"
)
raise ProviderAPIException(
provider_name=self.provider_name,
error_code=response.status,
error_message=error_text,
)

response_json = await response.json()
all_embeddings.extend(response_json["data"])

# Combine the results into a single response
final_response = {
"object": "list",
"data": all_embeddings,
"model": response_json["model"],
"usage": response_json["usage"],
}
return final_response
Loading