4
[Feature Request] Logging for AI/LLM usage
Source: paperless-ngx/paperless-ngx#13740 · opened by @DennisGaida
Description
I just tried out the newish AI features for automatically suggesting tags, correspondants etc. - works very well!
However AI generation takes some time and there is not really any progress bar next to the spinner. I checked the paperless logs and there was zero logs about the AI feature. There was no log entry, that I have activated the AI feature and there was no INFO-level entry for the particular document I wanted LLM usage.
I would expect that when clicking the AI suggestion button, I would see a INFO-level log entry saying "Requesting AI suggestions for document ID 1234" and maybe even the answer (or that would be debug level?).
Right now all my log shows is the tasks feature, task X executing, scheduler executing etc.
Since the LLM/AI feature is depending on the backend provider (or myself when selfhosting), I would very much like to see the status of this external call in the logs.
Other
_No response_
I just tried out the newish AI features for automatically suggesting tags, correspondants etc. - works very well!
However AI generation takes some time and there is not really any progress bar next to the spinner. I checked the paperless logs and there was zero logs about the AI feature. There was no log entry, that I have activated the AI feature and there was no INFO-level entry for the particular document I wanted LLM usage.
I would expect that when clicking the AI suggestion button, I would see a INFO-level log entry saying "Requesting AI suggestions for document ID 1234" and maybe even the answer (or that would be debug level?).
Right now all my log shows is the tasks feature, task X executing, scheduler executing etc.
Since the LLM/AI feature is depending on the backend provider (or myself when selfhosting), I would very much like to see the status of this external call in the logs.
Other
_No response_
No pledges yet. Be the first to back this.
Comments
Similar requests
[Feature Request] Different keys for LLM vs. LLM embeddings
6 votes · 0 comments
[Feature Request] Add detailed debug logging for RAG/LLM requests
2 votes · 0 comments
[Feature Request] AI Suggestions Cache
6 votes · 0 comments
[Feature Request] Allow overriding the embeddings encoding_format for OpenAI-compatible LLM providers
4 votes · 0 comments
Add support for Ollama's think: false parameter for AI suggestions
1 vote · 0 comments
No comments yet.