[GH-ISSUE #2533] Setting Query vector Size #27242

Open
opened 2026-04-22 04:24:35 -05:00 by GiteaMirror · 0 comments
Owner

Originally created by @stealthier-ai on GitHub (Feb 16, 2024).
Original GitHub issue: https://github.com/ollama/ollama/issues/2533

I used Ollama Embeddings through langchain with one of the models to embed a large number of documents. The LLM I am using is a multi-lingual model and has already been tested on a significant document set in solely English. When I query the vector store through LanceDB I receive the error "ValueError: Query vector size 8192 does not match index column size 384." I am using the exact same embedding model but now he query vector is 8192. How do I set the vector size to make it match the index column size with Ollama embedding?

Originally created by @stealthier-ai on GitHub (Feb 16, 2024). Original GitHub issue: https://github.com/ollama/ollama/issues/2533 I used Ollama Embeddings through langchain with one of the models to embed a large number of documents. The LLM I am using is a multi-lingual model and has already been tested on a significant document set in solely English. When I query the vector store through LanceDB I receive the error "ValueError: Query vector size 8192 does not match index column size 384." I am using the exact same embedding model but now he query vector is 8192. How do I set the vector size to make it match the index column size with Ollama embedding?
GiteaMirror added the question label 2026-04-22 04:24:35 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#27242