Unify apps/simple and examples - move everything to examples

Update link to python docs

Minor fixes in PGVectorStore

Feat: add GPT4 Vision support (and file upload) to create-llama

fix: set maxTokens to 4096 so vision model is not stopping too early (seems to have a lower default than other models)

Several fixes for improving compatibility with Next.JS

Add AssemblyAI integration

Add PGVectorStore

support for claude-2.1

feat: add clip embedding to llamaindex

Added custom RAG prompt for Claude.
Supporting system message format.

add .env instructions