-
Notifications
You must be signed in to change notification settings - Fork 16.2k
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
langchain_community: Checking text property first in neo4j to avoid duplicate nodes #17381
Conversation
The latest updates on your projects. Learn more about Vercel for Git ↗︎ 1 Ignored Deployment
|
Merging on long text properties is expensive and not good. If you want, you can change the id calculation by using a cheap hash function |
…ps with parent or child nodes
All you need to do is to change this one line: https://github.com/langchain-ai/langchain/blob/master/libs/community/langchain_community/vectorstores/neo4j_vector.py#L429 No need to introduce new params or anything |
@tomasonjo This diff now also handles creation of relationships to parent and child nodes. |
Not really, this is way too specific and not general to be merged in |
@tomasonjo This does not break any existing functionality but allow the ability to create relationships with other exiting nodes while creating new docs. No worries, I reverted my changes to just introduce text hash as ids |
believe this was resolved in #18846, let me know if i'm missing something! |
Checking text property first in neo4j to avoid duplicate nodes
@dev2049
@vowelparrot