Skip to content
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

Jump to bottom

fix(llamaindex): avoid batching in embeddings #353

Merged
merged 1 commit into from
Apr 26, 2024
Merged

fix(llamaindex): avoid batching in embeddings #353

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.
Jump to
Jump to file
Failed to load files.
Diff view
Diff view
5 changes: 5 additions & 0 deletions src/genai/extensions/llama_index/embeddings.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,8 @@
import asyncio
from typing import Optional

from pydantic import Field

from genai._types import ModelLike
from genai.client import Client
from genai.schema import TextEmbeddingParameters
Expand All @@ -17,6 +19,9 @@ class IBMGenAILlamaIndexEmbedding(BaseEmbedding):
model_id: str
parameters: Optional[ModelLike[TextEmbeddingParameters]] = None
execution_options: Optional[ModelLike[CreateExecutionOptions]] = None
# Batch size is set to 100000 to avoid batching in
# LlamaIndex as it is handled by the SDK itself
embed_batch_size: int = Field(default=10000, description="The batch size for embedding calls.", gt=0)

@classmethod
def class_name(cls) -> str:
Expand Down