#faiss

[ follow ]
#vector-search #rag #embeddings #approximate-nearest-neighbor #indexing #high-dimensional-data #langchain #mysql
Python
fromPyImageSearch
2 days ago

Vector Search Using Ollama for Retrieval-Augmented Generation (RAG) - PyImageSearch

Retrieval-Augmented Generation (RAG) augments LLMs with retrieved context from vector search (FAISS) to produce accurate, up-to-date, evidence-grounded responses.
fromPyImageSearch
1 week ago

Vector Search with FAISS: Approximate Nearest Neighbor (ANN) Explained - PyImageSearch

In the previous lesson, you learned how to turn text into embeddings - compact, high-dimensional vectors that capture semantic meaning. By computing cosine similarity between these vectors, you could find which sentences or paragraphs were most alike. That worked beautifully for a small handcrafted corpus of 30-40 paragraphs. But what if your dataset grows to millions of documents or billions of image embeddings? Suddenly, your brute-force search breaks down - and that's where Approximate Nearest Neighbor (ANN) methods come to the rescue.
Python
fromHackernoon
6 years ago

How I Super-Charged My LangChain-MySQL Agent: Part 2 | HackerNoon

Contextualizing database schemas into a vector format reduces the complexity for LLM-based retrieval while simultaneously addressing the common rate limit issues with OpenAI APIs.
Artificial intelligence
[ Load more ]