Change format sent

Log to remote server in non-blocking way

Add log_to_jsonl function to data.py and remove duplicate function from utils.py

Moves logging from app.py to chill.py

Add JSONL disk file logging functionality to app.py and utils.py

Add system map and worker architecture details

Readme: Note on Mistral API used, serverless backend for reliability

Show iteration count and time used

Show scores as percentages

Count LLM request and show in UI, minor text changes

Tidying: reordering code a bit

Add Mistral API support due to my RunPod serverless system reliability issues

Add TODO for Runpod timeout handling

Docs: HuggingFace README.md metadata changes

Make Gradio app text more concise

Cache examples

Add assert in improvement_loop function to make more robust

Assert RunPod env vars are setup before trying to use them

Change return type of improvement_loop to dict in app.py

Update allow_flagging option in Gradio interface

Fix Gradio textbox with placeholder

Docs: Add local usage instructions for running the Gradio web server GUI

Clarify setup comments, remove unused global, increase max iterations

Docs: Readme update

Add JSON parsing and format output in HTML

Move constants

Clarify ChillTranslator description

Docs: Move sections around

Doc: Idea for speed improvements and intermediate results display, grouping future directions

Documentation changes

Add description to app

Add cached examples

Documentation: Add image

Documentation: Update future directions

Add HuggingFace Space demo link

Reduce max_iterations value in chill.py

Comment out llama-cpp-python installation command in Docker for HuggingFace Space

Switch to serverless worker by default (PR #2 from lukestanley/serverless_json_llm)

Revert expected serverless output metadata stripper

Documents serverless motivation and testing instructions

Avoid unneeded imports, make serverless output more sensible, removing some debugging and comments

Fix RUNPOD_ENDPOINT_ID environment variable

Add more serverless GPU endpoint setup instruction detail

Document serverless setup

Rename serverless test file, set default model to Phi 2 for test, removed jq install, and env vars that are set the same in utils.py already, ignore .cache in git

Introduces worker mode env var

Make GPU detection and llama-cpp-python re-installation conditional

Initialise global variables in improvement_loop function

Ensure N_GPU_LAYERS is int

Expose json typed LLM interface for RunPod