AI RAG with LlamaIndex, Local Embedding, and Ollama Llama 3.1 8bIn this post, I cover using LlamaIndex LlamaParse in auto mode to parse a PDF page containing a table, using a Hugging Face local embedding…3d ago3d ago
Using LlamaIndex Part 1 — OpenAII have started to experiment with LlamaIndex for use in Retrieval Augmented Generation (RAG) document parsing and indexing. My results…Jan 4Jan 4
Agents Craft Hackathon and Inspiration BlockWhen you want to do a hackathon but am missing the perfect idea.Nov 4, 2024Nov 4, 2024
VSCode and Debugging Python in Virtual EnvironmentsThis post is really for me more than anyone else. I will be able to come back here and find it. If it helps you as well, then great.Nov 1, 2024Nov 1, 2024
CrewAI, Simple Enough but It Once Made 100 API Calls Instead of 1I continued my experimentation with CrewAI this weekend. To see the code, take a look at the following repo and path: Starter CrewAI Series…Oct 28, 2024Oct 28, 2024
In the day or two after I wrote this, LM Studio released a new version that is headless (don't need…Oct 23, 2024Oct 23, 2024
Using LM Studio and CrewAI with LlamaI was recently experimenting with CrewAI, but in one experiment I wanted to use a local LLM hosted by LM Studio. Why LMStudio? Well……Oct 21, 20241Oct 21, 20241
AI “its got legs”This last week I spoke with two folks on AI intersection within their work and how their work intersects with one another. One was a CPO…Oct 13, 2024Oct 13, 2024
Sometimes It’s All About The ChunkingAs I continue my study and experimentation with coding up AI solutions, and especially, at the moment, with Retrieval-Augmented Generation…Oct 8, 2024Oct 8, 2024
Google’s NotebookLM, RAG and Then SomeI played around just a little bit with Google’s NotebookLM. It’s a Retrieval-Augmented Generation (RAG) tool. One thing it does is convert…Oct 1, 2024Oct 1, 2024