Replace rank_features for sparse_vector field type in ELSER examples #74
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
joemcelroy
reviewed
Oct 9, 2023
| @@ -10,7 +10,7 @@ | |||
| "\n", | |||
| "This workbook demonstrates similiarity search using [SparseVectorRetrievalStrategy](https://api.python.langchain.com/en/latest/vectorstores/langchain.vectorstores.elasticsearch.SparseRetrievalStrategy.html#langchain.vectorstores.elasticsearch.SparseRetrievalStrategy) (ELSER). First, we split the documents into chunks using `langchain` and then index into elasticsearch through [`ElasticsearchStore.from_documents`](https://api.python.langchain.com/en/latest/vectorstores/langchain.vectorstores.elasticsearch.ElasticsearchStore.html#langchain.vectorstores.elasticsearch.ElasticsearchStore.from_documents). \n", | |||
| "\n", | |||
| "The [SparseVectorRetrievalStrategy](https://api.python.langchain.com/en/latest/vectorstores/langchain.vectorstores.elasticsearch.SparseRetrievalStrategy.html#langchain.vectorstores.elasticsearch.SparseRetrievalStrategy) converts each document into tokens and would be stored in `vector` field with datatype `rank_features`. Hence, the inference is handled within elasticsearch.\n", | |||
| "The [SparseVectorRetrievalStrategy](https://api.python.langchain.com/en/latest/vectorstores/langchain.vectorstores.elasticsearch.SparseRetrievalStrategy.html#langchain.vectorstores.elasticsearch.SparseRetrievalStrategy) converts each document into tokens and would be stored in `vector` field with datatype `sparse_vector`. Hence, the inference is handled within elasticsearch.\n", | |||
There was a problem hiding this comment.
langchain will likely continue to use rank_features, due to the the challenge of handling both scenarios with pre / post version of 8.11.0
There was a problem hiding this comment.
That makes sense as of now, but sparse_vector will likely evolve separately in the future. The sooner we start documenting this, the better.
Should we then include both field types in this description?
|
closing this as now the ELSER notebooks have been updated to use |
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.
Now that
sparse_vectorhas been re-introduced, we should change Elastic labs notebooks to change references torank_featurestosparse_vector