Technology
Vector databases
A specialized database designed to store, index, and query high-dimensional vector embeddings, enabling fast semantic search for Generative AI and recommendation engines.
Vector databases are mission-critical infrastructure for modern AI: they efficiently manage high-dimensional vectors, or embeddings, which are numerical representations of unstructured data like text, images, or audio. Traditional databases fail at this scale; vector databases use specialized indexing algorithms (e.g., HNSW) to perform Approximate Nearest Neighbor (ANN) searches in milliseconds. This capability is essential for Retrieval-Augmented Generation (RAG) architectures, which anchor Large Language Models (LLMs) in specific, trusted data to reduce hallucinations. Key players like Pinecone, Weaviate, and Qdrant deliver this performance, powering everything from contextual chatbots to real-time product recommendations based on conceptual similarity, not just keyword matches.
What builders pair with Vector databases
Projects using both technologies. Select a pairing to see a project.
12 more pairings
Pairing: BERT
Personalized Product Discovery with Agentic AI: Beyond Traditional Recommendation Engines
Pairing: BLOOM
Personalized Product Discovery with Agentic AI: Beyond Traditional Recommendation Engines
Pairing: GPT-3
Personalized Product Discovery with Agentic AI: Beyond Traditional Recommendation Engines
Pairing: GPT-4
Personalized Product Discovery with Agentic AI: Beyond Traditional Recommendation Engines
Pairing: Llama-2
Personalized Product Discovery with Agentic AI: Beyond Traditional Recommendation Engines
Pairing: LLMs
A context graph system that allows autonomous agents to make a reliable decision
Recent Talks & Demos
Showing 1-9 of 9