langchain-ai/docs
1
0
Fork 0
mirror of https://github.com/langchain-ai/docs.git synced 2026-07-22 20:35:34 -04:00
Code Issues 490 Packages Projects Releases Wiki Activity

[GH-ISSUE #2556] [langchain]: <google gemini embedding models issues> #309

New Issue
Open
opened 2026-02-17 17:19:36 -05:00 by yindo · 1 comment
yindo commented 2026-02-17 17:19:36 -05:00
Owner
Copy Link
Copy Source

Originally created by @Jitendra708097 on GitHub (Feb 9, 2026).
Original GitHub issue: https://github.com/langchain-ai/docs/issues/2556

Type of issue

issue / bug

Language

JavaScript

Description

Google Gemini embedding model "text-embedding-004" have deprecated not available now. and the vector dimensions of another latest Gemini model is 3072 in Lang chain it mention in comment is 768 which is not working model: "gemini-embedding-001", // 768 dimensions it should be model: "gemini-embedding-001", // 3072 dimensions by default on google documentation. please documentation.

regards,
Jitendra Kumar

Originally created by @Jitendra708097 on GitHub (Feb 9, 2026). Original GitHub issue: https://github.com/langchain-ai/docs/issues/2556 ### Type of issue issue / bug ### Language JavaScript ### Description Google Gemini embedding model "text-embedding-004" have deprecated not available now. and the vector dimensions of another latest Gemini model is 3072 in Lang chain it mention in comment is 768 which is not working model: "gemini-embedding-001", // 768 dimensions it should be model: "gemini-embedding-001", // 3072 dimensions by default on google documentation. please documentation. regards, Jitendra Kumar
yindo added the langchainexternal labels 2026-02-17 17:19:36 -05:00
yindo commented 2026-02-17 17:19:36 -05:00
Author
Owner
Copy Link
Copy Source

@tar-ang-2004 commented on GitHub (Feb 15, 2026):

Heyy.....I think there are two separate issues mixed here:

1. Model availability
text-embedding-004 does appear to be deprecated upstream, so LangChain should probably stop referencing it or mark it clearly as deprecated.

2. Embedding dimension mismatch
According to the current Google documentation, gemini-embedding-001 returns 3072 dimensions by default. If LangChain is still assuming 768 anywhere in the code or examples, that would definitely break vector stores expecting the correct size.

@tar-ang-2004 commented on GitHub (Feb 15, 2026): Heyy.....I think there are two separate issues mixed here: **1. Model availability** `text-embedding-004` does appear to be deprecated upstream, so LangChain should probably stop referencing it or mark it clearly as deprecated. **2. Embedding dimension mismatch** According to the current Google documentation, `gemini-embedding-001` returns 3072 dimensions by default. If LangChain is still assuming 768 anywhere in the code or examples, that would definitely break vector stores expecting the correct size.
yindo changed title from [langchain]: <google gemini embedding models issues> to [GH-ISSUE #2556] [langchain]: <google gemini embedding models issues> 2026-06-05 17:26:12 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
bug
deepagents
docs-infra
external
external
help wanted
integration
internal
internal
javascript
js/ts
langchain
langgraph
langsmith
needs-title
pull-request
Mirrored from GitHub Pull Request
 python
reference
No Label external langchain
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: langchain-ai/docs#309
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?