v2.2.0

clusterzx/paperless-aiv2.2.0Jan 16, 2025by clusterzx

AI Summary

This release focuses on improving compatibility with Firefox and optimizing Ollama context handling. It adds logging capabilities to inspect prompt and response data.

Key Highlights

Fixed chat functionality in Firefox by addressing deprecated form submission methods.
Implemented dynamic Ollama context sizing with a maximum capacity of 100,000 tokens.
Added a new logging endpoint at /app/logs/prompt.txt to view full prompt and response logs.

New Features

Dynamic Ollama context sizing calculation
Prompt and response logging system

Full Release Notes

## What's Changed
* Fix chat in firefox. submit form is deprecated by @Nikorag in https://github.com/clusterzx/paperless-ai/pull/151

* Addressed: [https://github.com/clusterzx/paperless-ai/issues/157#issuecomment-2593746955](vscode-file://vscode-app/c:/Users/Admin/AppData/Local/Programs/Microsoft%20VS%20Code/resources/app/out/vs/code/electron-sandbox/workbench/workbench.html)

* Addressed: [https://github.com/clusterzx/paperless-ai/discussions/142](vscode-file://vscode-app/c:/Users/Admin/AppData/Local/Programs/Microsoft%20VS%20Code/resources/app/out/vs/code/electron-sandbox/workbench/workbench.html)

* Regarding the Ollama Service and Context size, I implemented a dynamic way of using num_ctx parameter. Now there is a "maximum" context size of 100.000 Tokens. Thats huge and most systems won't handle that. The solution comes in handy and checks how much tokens are needed for the prompt (based on Q4_0 Quantization Size), it adds a buffer for the response of 1024 tokens (thats more enough in my eyes for the JSON response) and transfers the new calculated num_ctx to the Ollama API call.

* You now have the ability to view the full prompt + response log in /app/logs/prompt.txt

## New Contributors
* @Nikorag made their first contribution in https://github.com/clusterzx/paperless-ai/pull/151

**Full Changelog**: https://github.com/clusterzx/paperless-ai/compare/v2.1.9...v2.2.0