feat: replace CrewAI with direct Groq call — 10x faster

fix: use llama-3.1-8b-instant correct model ID

fix: use llama-4-scout highest free tier TPM

fix: use smaller model for free tier

fix: update groq model name

fix: flexible BaseTool import in app.py

fix: remove crewai_tools completely

feat: switch to Groq LLaMA 3 free API

feat: add NeuralDocs agentic RAG app