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.

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

feat(service): add multimodal embedder #326

Merged
merged 20 commits into from
Jul 30, 2024
Merged

feat(service): add multimodal embedder #326

merged 20 commits into from
Jul 30, 2024

Conversation

tpoisonooo
Copy link
Collaborator

@tpoisonooo tpoisonooo commented Jul 19, 2024

  1. Remove langchain, re-implement Query, Splitter, Faiss and Chunk
  • Thus we can add progress bar when build feature store, then we know how many time left
    image

  • And easily support multimodal retrieval

    For text-only gradio demo

    image

    For multimodal gradio demo

    image

  1. merge db-reject and db-response, simplify implementation
  2. simplify requirements.txt

add more example:

KE2GWWLk14

feat(feature_store): update
@tpoisonooo tpoisonooo changed the title WIP: feat(service): add multimodal embedder feat(service): add multimodal embedder Jul 30, 2024
@tpoisonooo tpoisonooo merged commit 0c4300e into main Jul 30, 2024
1 check passed
@tpoisonooo tpoisonooo deleted the image-retrieval branch August 1, 2024 11:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant