Topic deduplication/merging now separated from summarisation. Gradio upgrade

Added spaces to requirements for cpu run and AWS run.

Moved spaces GPU calls back to main functions as otherwise it doesn't seem to work correctly

Trying to move calls to @spaces.GPU to specific gemma calls to use the local model more efficiently

Added presentation of summary table outputs

Corrected line in upload_file_to_s3 function that was causing issues

Refactor app.py and related modules for improved topic extraction and summarization. Updated UI prompts for clarity, enhanced file upload functionality, and added error handling in AWS file uploads. Introduced new functions for converting response text to markdown tables, creating general topics from subtopics, and improved overall code structure for better maintainability.

Updated intro and readme to link to datasets

Enhanced local model support by adding model loading functionality in chatfuncs.py and updating llm_api_call.py to utilize local models for topic extraction and summarization. Improved model path handling and ensured compatibility with GPU configurations.

Refactored call_llama_cpp_model function to include model parameter in chatfuncs.py and updated import statements in llm_api_call.py to reflect this change.

Moved model load to chatfuncs submodule to hopefully avoid gpu run issues

Corrected references to extra-index-url in requirements/Dockerfile

Adding some compatibility with Zero GPU spaces

Corrected prompt. Now runs Haiku correctly

Updated Dockerfile with packages needed to compile Python wheels (for llama-cpp-python)

Can now specify root path for app with an environment variable

Changed readme sdk back to gradio, updated intro text

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

Allowed for server port, queue size, and file size to be specified by environment variables

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

Capitalise zero shot topics on input

Added rapidfuzz to requirements

Updated sdk option in README to 'gradio'

First commit