-
Notifications
You must be signed in to change notification settings - Fork 18k
community[minor]: Add keybert-based link extractor #24311
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
community[minor]: Add keybert-based link extractor #24311
Conversation
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Skipped Deployment
|
Somehow this got through CI: langchain-ai#24363
Head branch was pushed to by a user without write access
LinkExtractor, | ||
) | ||
|
||
# TypeAlias is not available in Python 2.9, we can't use that or the newer `type`. |
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.
Python 3.8 is minimum
embedding_model: str = "all-MiniLM-L6-v2", | ||
extract_keywords_kwargs: Optional[Dict[str, Any]] = None, | ||
): | ||
"""Extract keywords using Keybert. |
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.
Could you add in code examples and a link to keybert docs? (Same comment as in the other PRs)
- **Description:** Add a `KeybertLinkExtractor` for graph vectorstores. This allows extracting links from keywords in a Document and linking nodes that have common keywords. - **Issue:** None - **Dependencies:** None. --------- Co-authored-by: Eugene Yurtsev <[email protected]> Co-authored-by: ccurme <[email protected]>
KeybertLinkExtractor
for graph vectorstores. This allows extracting links from keywords in a Document and linking nodes that have common keywords.