Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-22 01:55:24 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #107] addToNamespace fails with limited dimensionality #74

New Issue
Closed
opened 2026-02-22 18:17:46 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:17:46 -05:00
Owner
Copy Link
Copy Source

Originally created by @Tdarra on GitHub (Jun 25, 2023).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/107

Trying to add seemingly small local txt files into hotdir. UI suggests that the article is a mere 360 tokens yet vector dimensionality ends up being 1536. Other than upgrading Pinecone pods, is there a workaround?

Adding new vectorized document into namespace demo Chunks created from document: 3 Inserting vectorized chunks into Pinecone. addDocumentToNamespace PineconeClient: Error calling upsert: PineconeError: Vector dimension 1536 does not match the dimension of the index 512 Failed to vectorize website-ww2.arb.ca.gov/article-_.json

Originally created by @Tdarra on GitHub (Jun 25, 2023). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/107 Trying to add seemingly small local txt files into `hotdir`. UI suggests that the article is a mere 360 tokens yet vector dimensionality ends up being 1536. Other than upgrading Pinecone pods, is there a workaround? `Adding new vectorized document into namespace demo Chunks created from document: 3 Inserting vectorized chunks into Pinecone. addDocumentToNamespace PineconeClient: Error calling upsert: PineconeError: Vector dimension 1536 does not match the dimension of the index 512 Failed to vectorize website-ww2.arb.ca.gov/article-_.json `
yindo closed this issue 2026-02-22 18:17:47 -05:00
yindo commented 2026-02-22 18:17:47 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (Jun 25, 2023):

Pinecone dimensionality is not a limiting factor and is a setting you set when you create the index. Simply create an index in Pinecone with 1536 dimensions. Token count and dimensions are not related as one is a metric for LLMs and the other is a metric for vector-space embeddings. Even a single token can be 1536 dimensions.

In your pinecone account just create a new index with 1536 dimensions so it can accept openAI embeddings and you are good! A 360 token doc will probably only amount to like <10 vectors.

@timothycarambat commented on GitHub (Jun 25, 2023): Pinecone dimensionality is not a limiting factor and is a setting you set when you create the index. Simply create an index in Pinecone with 1536 dimensions. Token count and dimensions are not related as one is a metric for LLMs and the other is a metric for vector-space embeddings. Even a single token can be 1536 dimensions. In your pinecone account just create a new index with 1536 dimensions so it can accept openAI embeddings and you are good! A 360 token doc will probably only amount to like <10 vectors.
yindo changed title from addToNamespace fails with limited dimensionality to [GH-ISSUE #107] addToNamespace fails with limited dimensionality 2026-06-05 14:33:20 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#74
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?