The #1 Goal of #Pinecone’s Developer Experience | Tej Chilukuri on Vector Search #nytechweek

Pinecone for Startups at NY Tech Week #pinecone #startups #ai #NYTECHWEEK

Evolving Pinecone's architecture w/ CTO Ram Sriharsha #knowledge #ai #serverlessarchitecture

Mixing and Matching Rerankers and Embedding Models #pinecone #cohere #rag

How Latency Works with Rerankers in Search #rerank #pinecone #cohere #searchengine

How Rerankers Work #pinecone #rag #vectordatabase

Handling Tokens with Sparse Models #rag #vectorsearch #pinecone

Query Embeddings vs Passage Embeddings #pinecone #rag #llms

Cascading Retrieval vs Hybrid Search #pinecone #llms #ai

Why RAG can reduce hallucinations #pinecone #rag #ai

Testing AI applications #pinecone #inkeep #rag

Question to Question Semantic Search #pinecone #rag #inkeep

What is Multi-hop retrieval? #pinecone #rag #unblocked

Using Metadata in RAG Systems #pinecone #rag #shortwave

Namespaces make semantic search faster #pinecone

What does a complex retrieval pipeline look like, and why?

Tackle hallucinations with simple prompts and tests #rag

Shortwave's New Feature from Hallucinations #pinecone #shortwave #rag

Five New Things about Pinecone Assistant #rag #pinecone #chatbots

Understanding Namespaces in Pinecone Serverless #shorts #ai #database

Vector databases like Pinecone are powerful because they allow application developers to build #ai

Why attaching metadata to vectors is such a powerful pattern #ai #database