Introducing RAG CLI 🧑‍💻🔎 - a dead-simple command-line tool that allows you to RAG literally any file on your local machine. Index any files including glob patterns, such as `$ llamaindex-cli rag --files "./docs/**/*.rst”` To search simply do `$ llamaindex-cli rag --question "What is LlamaIndex?”` Built with our IngestionPipeline... and QueryPipeline abstractions that allow efficient, performant data indexing and retrieval. Also built with Chroma. That’s not all! 💡Want to use local models like ollama? 💡Want to bake in advanced ingestion and retrieval techniques? The guide also shows you how to customize the logic for your own needs! Blog post: Docs:show more

just a word of caution: this can be expensive if you don't know how big are your files in terms of tokens. It does sends data to @OpenAI with the blog's default configuration.

Which embedding model it is using?

@ahmed_abdullahx ada-002, but you can customize it to use any model!

@ollama From the name "llamaindex" it would seem your default model would be at least llama or open weights based but instead the default is openAI based. Any reason for that? Do the open models do very poorly?

@TheAICoder This is easiest way to index and "ask" local files.

🛠️ The RAG CLI tool looks like a game-changer for developers! Easy indexing means quicker access and better productivity. Could you share more on how it handles large file systems? #DevTools #CommandLineMagic

🤯

@memdotai mem it

@llama_index Saved! Here's the compiled thread: