feat(embeddings): Support task type in VertexAI embeddings models #151
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
VertexAI embeddings models released in August support a new "task type" parameter that indicates the kind of task the embeddings is going to be used for, this helps the model produce better quality embeddings. If you are using a model that supports it, LangChain.dart will use 'RETRIEVAL_DOCUMENT' when embedding a document and 'RETRIEVAL_QUERY' when embedding a query.
davidmigloz
added a commit
that referenced
this pull request
Sep 5, 2023
VertexAI embeddings models released in August support a new "task type" parameter that indicates the kind of task the embeddings is going to be used for, this helps the model produce better quality embeddings. If you are using a model that supports it, LangChain.dart will use 'RETRIEVAL_DOCUMENT' when embedding a document and 'RETRIEVAL_QUERY' when embedding a query.
KennethKnudsen97
pushed a commit
to KennethKnudsen97/langchain_dart
that referenced
this pull request
Sep 29, 2023
…z#151) VertexAI embeddings models released in August support a new "task type" parameter that indicates the kind of task the embeddings is going to be used for, this helps the model produce better quality embeddings. If you are using a model that supports it, LangChain.dart will use 'RETRIEVAL_DOCUMENT' when embedding a document and 'RETRIEVAL_QUERY' when embedding a query.
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Outdated suggestions cannot be applied.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.
VertexAI embeddings models released in August support a new "task type" parameter that indicates the kind of task the embeddings is going to be used for, this helps the model produce better quality embeddings.
If you are using a model that supports it, LangChain.dart will use 'RETRIEVAL_DOCUMENT' when embedding a document and 'RETRIEVAL_QUERY' when embedding a query.
Docs:
https://cloud.google.com/vertex-ai/docs/generative-ai/embeddings/get-text-embeddings#api_changes_to_models_released_in_or_after_august_2023