Community Picks·2yThe State of Data Engineering 2024
The 2024 State of Data Engineering report discusses the influence of GenAI on software infrastructure, the expansion of product offerings due to the economic downturn, and the impact of open table formats and their catalogs in the data lake industry. It also highlights the importance of data version control and observability in AI/ML systems.
Medium·2yHow to Build RAG Applications with Pinecone Serverless, OpenAI, Langchain and Python
Learn how to build RAG applications using Pinecone Serverless, OpenAI, Langchain, and Python. Discover why Pinecone is a preferred vector database, and follow a step-by-step guide on building RAG apps. Upsert data to the vector database and query it to retrieve relevant information.
AI in Plain English·2yYour guide to Vector Databases
This post provides a guide to understanding Vector Databases, including their definition, functionality, and applications. It also highlights the features of a good Vector Database and offers best practices for choosing the right one. The post includes a list of over 80 Vector Databases for AI projects.
Towards AI·2yWhat are Vector Databases?
Vector databases are designed specifically for storing vector embeddings and enhance operations such as semantic search, recommendation engines, and advanced AI/ML processes. They leverage similarity metrics for data retrieval and offer benefits like scalability, flexibility, ultra-low latency, high performance, and optimized storage and memory.
Substack·2yUnderstanding How Vector Databases Work!
Vector databases are used for recommender engines to find similar items using approximate nearest-neighbor search. They can be indexed using algorithms like Product Quantization, Locality-sensitive hashing, and Hierarchical Navigable Small World. Euclidean distance, dot product, and cosine similarity are common measures for comparing vectors. Vector databases also offer database operations, metadata and filtering capabilities, and scalability.