Closed
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
This pull request introduces a GPU-accelerated embedding microservice and a fast QA retrieval engine, enabling efficient semantic search for question answering. The main changes include adding a Dockerized FastAPI service for generating embeddings using a SentenceTransformer model on NVIDIA GPUs, and a Python module that leverages this service alongside a FAISS index for high-speed QA retrieval.
Embedding microservice (Dockerized FastAPI application):
embedding_server.py, a FastAPI server that loads theintfloat/e5-small-v2SentenceTransformer model onto GPU, exposes/embed,/embed_fast,/embed_batch, and/healthendpoints, and supports both JSON and base64-encoded embedding responses for optimal performance.Dockerfileto build the embedding service on top of NVIDIA's PyTorch container, installs dependencies, downloads the model, and sets up the server to run on port 8100.docker-compose.ymlfile to orchestrate the embedding service with GPU support, ensuring it runs with NVIDIA runtime and exposes the necessary port.QA retrieval engine:
qa_engine.py, a Python module that loads a FAISS index and QA data, queries the embedding microservice for vector representations, and returns the best-matching answer with latency and similarity metrics. Includes a test harness for quick validation.