Player One – Prompt Engineering Toolkit
LLM experimentation platform for designing, testing, and optimizing prompts.
LLM experimentation platform for designing, testing, and optimizing prompts.
Comprehensive toolkit for researchers working with LLMs. Features prompt chaining, semantic search with FAISS, BLEU/perplexity evaluation, and multi-turn chat support.
Frontend: Streamlit
LLM: OpenAI
GPT-3.5/4
Framework: LangChain
Vector DB:
FAISS
Metrics: BLEU, Perplexity