6
[Feature Request] Different keys for LLM vs. LLM embeddings
Source: paperless-ngx/paperless-ngx#13275 · opened by @dpeuscher
Description
The current configuration for LLM and LLM embeddings do support different endpoints but not different auth keys. It would be great if I could mix between LLM via some api that does offer embeddings and for example openai for embeddings.
Other
Tested with Paperless-NGX Version 3.0.2
The current configuration for LLM and LLM embeddings do support different endpoints but not different auth keys. It would be great if I could mix between LLM via some api that does offer embeddings and for example openai for embeddings.
Other
Tested with Paperless-NGX Version 3.0.2
No pledges yet. Be the first to back this.
Comments
Similar requests
[Feature Request] Allow overriding the embeddings encoding_format for OpenAI-compatible LLM providers
4 votes · 0 comments
Allow AI classification strategy to be selected independently of embeddings
1 vote · 0 comments
[Feature Request] make "test connection" button for LLM endpoints /add 2nd backend provider for LLMs
1 vote · 0 comments
[Feature Request] Exclude Inbox documents as reference examples for AI metadata suggestions while keeping full RAG indexing
1 vote · 0 comments
[Feature Request] Logging for AI/LLM usage
4 votes · 0 comments
No comments yet.