Posts

Vector database -- for best search

  Popular Vector Databases (Pick Your Flavor) Name Type Best For Weaviate Open-source Feature-rich, self-hosted Pinecone Managed (cloud) Easy, no ops, pricey Milvus Open-source Massive scale, complex Qdrant Open-source (Rust) Fast, lightweight pgvector Postgres extension Simple, use your existing DB Hot take : For more than 1 million items, just use PostgreSQL + pgvector . No need for a fancy vector DB yet.

detailed text about AI agents

 https://simsbrainstew.in/blog/AiAgents

Voice AI Agents -

 https://vapi.ai/pricing

Google Knowledge Graph

 Google's Knowledge Graph

Google Knowledge Graph Search API

  Google Knowledge Graph Search API

Static, Hierarchical Knowledge (Ontology/Knowledge Graph): -- to split AI as sections - fixed data definitions and meanings

 Static, Hierarchical Knowledge (Ontology/Knowledge Graph):

RAG - Retrieval Augmented Generation - AI or DNN with understanding of new data

  Retrieval Augmented Generation (RAG):  This is a popular technique where a large language model (your "common DNN") doesn't just generate answers from its internal training data. Instead, it first  retrieves  relevant information from external knowledge bases (like your structured classifications or vector databases of new news) and then uses that retrieved information to formulate its answer. This makes the LLM more accurate, up-to-date, and less prone to "hallucinations."