Refactor stop sequences in chat.py for improved template handling

fix minor errors and improve prompt

Add RAG generation (#19)

Add requirements.txt for synthetic dataset generator dependency, update import paths for InferenceEndpointsLLM in multiple files, and modify example deployment script to comment out HF_TOKEN.

Update version to 0.1.6, remove requirements.txt, and enhance dataset handling in pipelines. Added Gradio support and improved LLM class retrieval. Commented out HF_TOKEN in example deployment script.

add vllm deployment info

add randomisation of system prompts for generation

update deployment with API providers

fix code generation for pipeline textcat

fix openai compatability

add qwen stop sequences

update sft to chat

add system prompt rewriter for more dynamic generation SFT

add multi-label support instead of num labels

add MAX_NUM_ROWS

update logic textcat for inferring labels

Merge pull request #6 from argilla-io/feat/improve-textcat

add temperature to response generation

remove obsolete class

add label randomification perf created sample

hide evaluation, update temperature

fix examples for evaluation

add buttons

refactor package folders