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

Support batching for multi-input embeddings #169

Open
adubovik opened this issue Nov 4, 2024 · 0 comments · May be fixed by #193
Open

Support batching for multi-input embeddings #169

adubovik opened this issue Nov 4, 2024 · 0 comments · May be fixed by #193

Comments

@adubovik
Copy link
Collaborator

adubovik commented Nov 4, 2024

ai-dial-adapter-bedrock/aidial_adapter_bedrock/embedding/amazon/titan_image.py

Lines 161 to 168 in 1785193

# NOTE: Amazon Titan doesn't support batched inputs
# TODO: create multiple tasks
async for sub_request in get_requests(self.storage, request):
embedding, text_tokens = await call_embedding_model(
self.client,
self.model,
create_titan_request(sub_request, request.dimensions),
)

follow the same pattern as in vertexai instead:

https://github.com/epam/ai-dial-adapter-vertexai/blob/7e0dc16165cf5ec9438ac41bfd02e647cc47c18f/aidial_adapter_vertexai/embedding/multi_modal.py#L199-L208
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
AI DIAL
Status: No status
Milestone
No milestone
Development

Successfully merging a pull request may close this issue.

feat: supported batching for Titan text and image embeddings epam/ai-dial-adapter-bedrock
1 participant
@adubovik