Added model compatibility for OpenAI and Azure endpoints. Added some Bedrock models, now compatible with thinking models

Added deduplication with LLM functionality. Minor package updates. Updated installation documentation.

Added stop strings, optimised llama-cpp-python inference for streaming

Added possibility of adding examples quickly to the input files

Allowed possibility to run all analysis steps in one click

Enhanced app functionality by adding new logging variables, refining file input options, and updating prompts for better user experience. Updated Dockerfile for improved environment setup and adjusted requirements for compatibility. Removed unnecessary print statements and added error handling in data loading functions.

Minor fixes for Gemini, model calls. Updated Dockerfile for non-GPU systems

GPT-OSS 20b should now work correctly

Added cost code logging functionality. More customised logging output, can now save logs to DynamoDB.

Allowed for save to xlsx file. Some package updates

You can now create structured summaries by group by changing a setting under 'I have my own list of topics'

Improved on implementation of group-based analysis. Now should be possible all the way to summarisation

Improved grouping functions

Wrapper function added to add possibility of analysis by group. Some bug fixes, package changes

Downgraded Hugging Face space llama-cpp-python requirements. Updated to new Gemini SDK. File output and overall summarisation fixes.

Fixed some issues with output folder references. Minor changes to column names, summary output

Code reorganisation to better use config files. Adapted code to use Gemma 3 as local model. Minor package updates

Package updates. Can now ask the model to only assign specified topics

Upgraded Gradio. More resilient to cases where LLM calls do not return valid markdown tables (will reattempt with different temperature). Minor fixes

Allowed for manual modification of output topic table. Did some fixes to deduplication and Excel file input. Allowed for General topic specification in zero shot topics

Changed default requirements to CPU version of llama cpp. Added Gemini Flash 2.0 to model list. Output files should contain only final files.

Added presentation of summary table outputs

Added support for using local models (specifically Gemma 2b) for topic extraction and summary. Generally improved output format safeguards.

Added more guidance in Readme. Now wipes variables on click to create or summarise topics

First commit