Merge pull request #53 from seanpedrick-case/dev

Minor prompt improvements. Bedrock client and keys should now be correctly passed to validation function

Created wrapper summarisation function so revised summaries will be correctly created by group. Fixed output logs for summarisation tasks. Fixed some structured summary prompt issues. Minor prompt adjustments

Merge pull request #52 from seanpedrick-case/dev

Minor fixes for structured summary outputs and prompt optimisation

Improved creation of missing_df in wrapper functions

Validation processes can now be run independent from available logging data

Correctly passed validation and summary custom instructions to functions. Updated table check for when reference numbers aren't correctly defined from LLM call

Added topic validation and llm deduplication functionality. Now checks for input token count before LLM calls.

Merge pull request #51 from seanpedrick-case/dev

Update version number for 0.3.1

Merge pull request #50 from seanpedrick-case/dev

Corrected OpenAI API usage

Merge pull request #49 from seanpedrick-case/dev

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

Merge pull request #48 from seanpedrick-case/dev

Changed config defaults to enable successful app run without local model inference on first run

Merge pull request #47 from seanpedrick-case/dev

Minor changes to readme repo references and conda environment

Updated pyproject.toml file with requirements from requirements_no_local.txt

Merge pull request #46 from seanpedrick-case/dev

Reverted requirements files to previous direct wheel links

Updated git clone reference

Merge pull request #45 from seanpedrick-case/dev

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

Merge pull request #44 from seanpedrick-case/dev

Enhanced user interface and documentation for topic extraction tool. Updated file input labels for clarity, improved README instructions, and refined progress tracking in API calls. Added time tracking for LLM calls in output files.

Added examples for structured summaries and groups. Adapted functions for structured summaries. Simplified front tab GUI

Merge pull request #43 from seanpedrick-case/dev

Optimised prompts. Updated Gradio. Added example for zero shot topics. Added support for Granite 4 local model

No longer str capitalize summaries

Merge pull request #42 from seanpedrick-case/dev

Corrected blank KV_QUANT_LEVEL values. Removed erroneous extract topics output

Corrected KV quant value when not specified (set to None)

Merge pull request #40 from seanpedrick-case/dev

Corrected KV quantisation definition in config. Moved examples to top of screen under intro.

Merge pull request #39 from seanpedrick-case/dev

Generally improved inference for low vram systems, unsloth usage improvements, updated packages, switched default local model to Qwen 3 4b

Merge pull request #38 from seanpedrick-case/dev

Upload example xlsx files with repo

Merge pull request #37 from seanpedrick-case/dev

Updated output logging files. Updated examples and readme. Minor prompt adjustments and package updates

Corrected reasoning setting

Revised intro and readme. Reasoning suffix setting simplified. All in one xlsx returns correct tables.

Position of usage logs input corrected

tracking model state through all_in_one_function

Corrected usage of stop strings, streaming

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

Trying out inference with unsloth vs transformers

Merge pull request #36 from seanpedrick-case/dev