Corrected Gemma model prompt format, made prompts in general ask for more detail. Wording changes.

Updated Dockerfile so it actually works. Modified config file to include/exclude models and change relevant options as needed. Fixed thumbs up/down feedback.

Removed other references to boto3 client

Removed obligatory bedrock load in from app

Refocused app for working with Document Redaction guide. Added Gemma 3 1b as base model. Various UI and config improvements

Initial compatibility tested for use with Gemini and AWS Bedrock APIs

Returned to bge-base embeddings for now. Improved UI a little

Updated packages, functions, fixed a couple of bugs

Updated packages, models, preparing for use with AWS (in background)

Changed 'large' model to Phi 3 Mini gguf 128k. Added requirements file for cpu. Put prompts in separate file.

CPU Flan inference is crashing, so trying to revert to previous package versions that worked

Removed reference to ctransformers

Upgraded gradio and packages to latest. Switched Ctransformers with Llama.cpp Python

Minor dependency updates, increased max allowable layers for GPU

Added temperature slider, more stringent checks for document relevance

Added slider for changing number of passages out

Improved prompting for csv/excel files

Added csv/Excel file support

Put sources behind accordion, minor change to model params. Gitignore update

Build fail when gpu_layers > 0, so will set to 0 at start and modify in app.

Made GPU layer bar invisible. Changed default GPU layers when CUDA available

Upgraded large model to Mistral OpenOrca 7B Q4. More checks for empty questions.

Changed embedding model, added reference to chat model on front page

Improved advanced model prompt, added stop generation button. context prompt improvements

Stop generation button. Better model load. Trying one source that's longer.

gpu_layers should now update correctly. Added code for creating distribution.

Hopefully fixed Orca load cuda error. Loads in Orca on app load. Later gradio version installed.

Added working like buttons. Added model choice. Modified requirements txt

Cleaned up code a bit, added user icons, thumbs up/down

Added support for Mistral Orca

Attempt to switch to Orca Mini GGUF

Tidied up intro text

Disabled chat memory as I think it is not needed for most user queries (max_memory_length = 0)

Changed theme, example set now disappears upon new file load

Adapted code to keep newly-loaded vectorstores within local user state

Added reference to source on app. Minor text changes.

Updated web ingest. Added some warnings to intro text

Added to intro, temp disabled web page load, address pdf load issue

Remove ctransformers model load (not needed yet). Used faster keyword model

Added nltk wordnet download to chatfuncs

Changed app space image, removed unnecessary files

Init repo