-
Notifications
You must be signed in to change notification settings - Fork 13.3k
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
Add SpacyEmbeddings class #6967
Conversation
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Ignored Deployment
|
Returns: | ||
A list of embeddings, one for each document. | ||
""" | ||
return self.embed_documents(texts) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
we shouldn't use the synchronous methods here. can just raise a NotImplementedError if we don't want to implement async right now
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
I need some more explanation to understand the comment better. Can you pls share some reference design pattern or interface templates to be followed for implementing embedding integrations. @baskaryan
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
we shouldn't use the synchronous methods here. can just raise a NotImplementedError if we don't want to implement async right now
@baskaryan I have made the changes and committed.
nice! could we add an example notebook showing how to use this? probably would live in docs/extras/modules/data_connection/text_embedding/integrations |
Sure, i will get one created |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this is great - thanks!
"metadata": {}, | ||
"outputs": [], | ||
"source": [ | ||
"# Import the necessary classes\n", |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
notebooks should have a title of # Spacy
and then all other cells should NOT have #
but should be more like ## Import the ....
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
notebooks should have a title of
# Spacy
and then all other cells should NOT have#
but should be more like## Import the ....
done. Notebook updated
…e spacy embedded , updated notebook for better readability
thanks @rjarun8! |
* master: (212 commits) Add SpacyEmbeddings class (langchain-ai#6967) docs: commented out `editUrl` option (langchain-ai#6440) Remove duplicate mongodb integration doc (langchain-ai#7006) Update get_started.mdx (langchain-ai#7005) openapi chain nit (langchain-ai#7012) Fix sample in FAISS section (langchain-ai#7050) Fix typo in google_places_api.py (langchain-ai#7055) move base prompt to schema (langchain-ai#6995) added `Brave Search` document_loader (langchain-ai#6989) Add JSON Lines support to JSONLoader (langchain-ai#6913) Vectara upd2 (langchain-ai#6506) docstrings `document_loaders` 2 (langchain-ai#6890) docstrings `document_loaders` 1 (langchain-ai#6847) Added filter and delete all option to delete function in Pinecone integration, updated base VectorStore's delete function (langchain-ai#6876) bump 221 (langchain-ai#7047) Rm retriever kwargs (langchain-ai#7013) Polish reference docs (langchain-ai#7045) Support params on GoogleSearchApiWrapper (langchain-ai#6810) (langchain-ai#7014) Fix typo (langchain-ai#7023) Fix openai multi functions agent docs (langchain-ai#7028) ...
- Description: Added a new SpacyEmbeddings class for generating embeddings using the Spacy library. - Issue: Sentencebert/Bert/Spacy/Doc2vec embedding support #6952 - Dependencies: This change requires the Spacy library and the 'en_core_web_sm' Spacy model. - Tag maintainer: @dev2049 - Twitter handle: N/A This change includes a new SpacyEmbeddings class, but does not include a test or an example notebook. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>
- Description: Added a new SpacyEmbeddings class for generating embeddings using the Spacy library. - Issue: Sentencebert/Bert/Spacy/Doc2vec embedding support langchain-ai#6952 - Dependencies: This change requires the Spacy library and the 'en_core_web_sm' Spacy model. - Tag maintainer: @dev2049 - Twitter handle: N/A This change includes a new SpacyEmbeddings class, but does not include a test or an example notebook. --------- Co-authored-by: Bagatur <baskaryan@gmail.com>
This change includes a new SpacyEmbeddings class, but does not include a test or an example notebook.