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

[BUG] Upsert - Error: vectorsService.upsertVector - Error: TypeError: Cannot read properties of undefined (reading '0') #3113

Open
ApplicationError opened this issue Aug 29, 2024 · 6 comments
Labels
question Further information is requested

Comments

@ApplicationError
Copy link

ApplicationError commented Aug 29, 2024

Describe the bug
Error: vectorsService.upsertVector - Error: TypeError: Cannot read properties of undefined (reading '0')

I've setup a new Flowise project with the following components & configuration:

Conversational Retrieval QA Chain

  • Chat Model
    -- GroqChat (Model Name: llama-3.1-405b-reasoning)
  • Vector Store Retriever
    -- Pinecone
    --- Embeddings
    ---- VoyageAI Embeddings (Model name: voyage-2)
    --- Document
    ---- Pdf File (.pdf file)
    ---- File Loader (.txt file)
    --- Text Splitter (Chuck Size: 1000, Chunk Coverlap: 200)

Check I go to "upsert" the data to Pinecone I get that error message.
Error: vectorsService.upsertVector - Error: TypeError: Cannot read properties of undefined (reading '0')

To Reproduce
Steps to reproduce the behavior:

1.) Setup as outlined above
2.) Save project
3.) Click on green "upsert" icon
4.) Click on green "upsert" button

Expected behavior
The data from the PDF and the TXT file to be stored in the Pinecone vector store.

Setup

  • Installation: Render / Docker
  • Flowise Version: 2.0.7

Render.com Logs

error 2024-08-29 19:57:30 [ERROR]: TypeError: Cannot read properties of undefined (reading '0')
error Error: TypeError: Cannot read properties of undefined (reading '0')
info at Pinecone_VectorStores.upsert (/usr/src/packages/components/dist/nodes/vectorstores/Pinecone/Pinecone.js:80:27)
info at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
info at async buildFlow (/usr/src/packages/server/dist/utils/index.js:415:37)
info at async upsertVector (/usr/src/packages/server/dist/utils/upsertVector.js:126:32)
info at async Object.upsertVectorMiddleware (/usr/src/packages/server/dist/services/vectors/index.js:9:16)
info at async createInternalUpsert (/usr/src/packages/server/dist/controllers/vectors/index.js:28:29)
error 2024-08-29 19:57:30 [ERROR]: [server]: Error: Error: TypeError: Cannot read properties of undefined (reading '0')
error Error: Error: TypeError: Cannot read properties of undefined (reading '0')
info at buildFlow (/usr/src/packages/server/dist/utils/index.js:493:19)
info at process.processTicksAndRejections (node:internal/process/task_queues:95:5)
info at async upsertVector (/usr/src/packages/server/dist/utils/upsertVector.js:126:32)
info at async Object.upsertVectorMiddleware (/usr/src/packages/server/dist/services/vectors/index.js:9:16)
info at async createInternalUpsert (/usr/src/packages/server/dist/controllers/vectors/index.js:28:29)

2024-08-29 at 4 14 PM

@HenryHengZJ
Copy link
Contributor

If you switch to other embeddings model it should works. Seen this issue with voyage embeddings, mostly due to the rate limit

@HenryHengZJ HenryHengZJ added the question Further information is requested label Aug 29, 2024
@ApplicationError
Copy link
Author

If you switch to other embeddings model it should works. Seen this issue with voyage embeddings, mostly due to the rate limit

Thank you very much for the reply. Do you have any recommendations for embedding models that would work best?

@Vortigern-source
Copy link

I have a similar issue, Im not sure what embedding to use with groq if VoyageAI isnt working the best

@Vortigern-source
Copy link

What embeddings can be used that are free? Also are you saying that reducing the rate limit option should fix it?

@jockharkness
Copy link

If you switch to other embeddings model it should works. Seen this issue with voyage embeddings, mostly due to the rate limit

I have a similar setup (except using in-memory vector store) and the exact same error message.

I changed to OpenAI embeddings and it didn't fix the issue, still getting the same error message

@abslearn
Copy link

Same issue here. I changed to OpenAI embeddings and it didn't fix the issue, still getting the same error message

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
question Further information is requested
Projects
None yet
Development

No branches or pull requests

5 participants