This issue has been created

There are 2 updates.

LLM AI Integration

/

Open

Add support for embedding model prompt prefixes

View issue · Add comment

Issue created

Paul Pantiru created this issue on 01/Aug/24 18:45

Summary:	Add support for embedding model prompt prefixes
Issue Type:	New Feature
Affects Versions:	0.5.3
Assignee:	Unassigned
Created:	01/Aug/24 18:45
Priority:	Major
Reporter:	Paul Pantiru
Description:	Some language like https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1 and https://huggingface.co/nomic-ai/nomic-embed-text-v1.5 Require special prompt prefixes for use cases like RAG to work better, so we need two more fields in the model configuration for injecting these prefixes: one for index and one for query.

2 updates

Changes by Paul Pantiru on 01/Aug/24 18:45

Description:	Some language embedding models like https://huggingface.co/mixedbread-ai/mxbai-embed-large-v1 and https://huggingface.co/nomic-ai/nomic-embed-text-v1.5 Require special prompt prefixes for use cases like RAG to work better, so we need two more fields in the model configuration for injecting these prefixes: one for index and one for query.
Assignee:	Paul Pantiru

This message was sent by Atlassian Jira (v9.3.0#930000-sha1:287aeb6)

If image attachments aren't displayed, see this article.