Skip to content
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 Qdrant vector store and Recursive url for documents #7807

Closed
wants to merge 1 commit into from

Conversation

kesslerdev
Copy link

This PR add support for Qdrant Vector Store with same features of others.
Also adds the Recursive url document loader

@CLAassistant
Copy link

CLAassistant commented Nov 24, 2023

CLA assistant check
All committers have signed the CLA.

@n8n-assistant n8n-assistant bot added the community Authored by a community member label Nov 24, 2023
@OlegIvaniv OlegIvaniv self-assigned this Nov 29, 2023
Copy link
Contributor

@OlegIvaniv OlegIvaniv left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thanks for the PR! I've left a few comments

Comment on lines +27 to +33
{
displayName: 'Is Auto Embedded',
name: 'isAutoEmbedded',
type: 'boolean',
default: true,
description: 'Whether to automatically embed documents when they are added',
},
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This property isn't used anywhere in the code

}),
};

QdrantVectorStore.fromDocuments(documents, embeddings, qdrantConfig) as Promise<VectorStore>;
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We've recently did some changes to improve handling of these vector store operations. Could you please merge in latest ai-beta and implement similar error handling as we have for VectorStoreSupabase or VectorStorePinecone? I'm also wondering if we should add an option to create a collection if it's missing. WDYT?

Comment on lines +2 to +13
import {
NodeConnectionType,
type IExecuteFunctions,
type INodeType,
type INodeTypeDescription,
type SupplyData,
} from 'n8n-workflow';
import { RecursiveUrlLoader } from 'langchain/document_loaders/web/recursive_url';
import type { CharacterTextSplitter } from 'langchain/text_splitter';
import { compile } from 'html-to-text';
import { logWrapper } from '../../../utils/logWrapper';
import { getConnectionHintNoticeField } from '../../../utils/sharedFields';
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Could you please extract this node from this PR? We're having an ongoing discussion about document loaders so this one will have to wait a bit before getting merged.

@janober janober deleted the branch n8n-io:ai-beta November 29, 2023 11:14
@janober janober closed this Nov 29, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
community Authored by a community member
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants