Make embeddings computing async and add support for batching. #267
Conversation
This file contains 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
Pouyanpi
added a commit
to Pouyanpi/NeMo-Guardrails
that referenced
this pull request
Feb 7, 2024
Updated the BasicEmbeddingsIndex to use a more flexible cache configuration setup. We replaced the bool flag and the CacheEmbeddings instance with a single unified `cache_config` parameter that can accept either a dictionary or an EmbeddingsCacheConfig instance for enhanced configurability. Additionally, the `_get_embeddings` method is now an asynchronous function to allow for non-blocking I/O operations per NVIDIA#267.
Pouyanpi
added a commit
to Pouyanpi/NeMo-Guardrails
that referenced
this pull request
Feb 7, 2024
Enhanced the EmbeddingsIndex class by adding a 'cache_config' attribute for customizable cache management. Also, updated the '_get_embeddings' method to be asynchronous per NVIDIA#267.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Enable batching when computing the embeddings. Initial tests show a 3x throughput increase.