Skip to content

Adding Teradata VectorStore support in DocumentStore #5159

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.

Sign up for GitHub

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

Jump to bottom
Open
wants to merge 7 commits into
base: main
Choose a base branch
from
Open

Adding Teradata VectorStore support in DocumentStore #5159

wants to merge 7 commits into from
+1,009 −263

Conversation

sshekhar1
Copy link

@sshekhar1 sshekhar1 commented Sep 1, 2025 •
edited
Loading

Below are the screenshots for the working demo:

  • Selecting Vector Store Provider under Upsert Chunks option:
image
  • Using Teradata Vector Store under Upsert Chunks option in Document Store:
image
  • Upsert successful into Teradata Vector Store:
image
  • Test Retrieval on Teradata Vector Store:
image
  • Teradata Vector Store node under ChatFlow:
image_721

@HenryHengZJ
Copy link
Contributor

are there any screenshots for working demo or recordings?

@sshekhar1 sshekhar1 force-pushed the Teradata_DocumentStore branch from 6729347 to 79620b4 Compare September 8, 2025 07:09
@sshekhar1
Copy link
Author

are there any screenshots for working demo or recordings?

@HenryHengZJ I have added the screenshots in the Pull Request Description as suggested. Thanks !

@HenryHengZJ
Copy link
Contributor

can you do pnpm lint-fix?

@sshekhar1
Copy link
Author

Output for pnpm lint-fix:

$ pnpm lint-fix

> [email protected] lint-fix C:\Users\ss186247\OneDrive - Teradata Corporation\Documents\FlowiseAI\flowise_repo_build\Flowise
> pnpm lint --fix


> [email protected] lint C:\Users\ss186247\OneDrive - Teradata Corporation\Documents\FlowiseAI\flowise_repo_build\Flowise
> eslint "**/*.{js,jsx,ts,tsx,json,md}" "--fix"

@sshekhar1
Copy link
Author

@HenryHengZJ can you please help review the changes and let me know if any additional changes needed ?

HenryHengZJ
HenryHengZJ reviewed Sep 30, 2025
View reviewed changes
packages/components/credentials/TeradataVectorStoreApi.credential.ts
constructor() {
this.label = 'Teradata Vector Store API Credentials'
this.name = 'teradataVectorStoreApiCredentials'
this.version = 1.0
Copy link
Contributor

Choose a reason for hiding this comment

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

can we add description on how to get these credentials? as if user is new to teradata

Copy link
Contributor

Choose a reason for hiding this comment

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

or perhaps we can create a docs page on https://github.com/FlowiseAI/FlowiseDocs and link to that

HenryHengZJ
HenryHengZJ reviewed Sep 30, 2025
View reviewed changes
packages/components/nodes/vectorstores/Teradata/Teradata.ts
import { Document } from '@langchain/core/documents'
import { ICommonObject, INode, INodeData, INodeOutputsValue, INodeParams, IndexingResult } from '../../../src/Interface'
import { Embeddings } from '@langchain/core/embeddings'
import * as teradatasql from 'teradatasql'
Copy link
Contributor

Choose a reason for hiding this comment

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

from experience, I'm little afraid of adding new database library. is there a way to achieve this via API?

that's because previously we had other integrations such as couchbase that caused failed docker build due to unsupported arm64 compatibility and such

Copy link
Contributor

Choose a reason for hiding this comment

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

plus adding new library always adds up to the total bundle size

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@HenryHengZJ HenryHengZJ HenryHengZJ left review comments

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
2 participants
@sshekhar1 @HenryHengZJ