Pinecone Courses

Building the Future with LLMs, LangChain, & Pinecone

1 rating

Explore the future of AI with LLMs, LangChain, and Pinecone. Learn to build powerful applications using cutting-edge tools and techniques in this comprehensive workshop led by industry experts.

• YouTube
• 59 minutes
• Self-Paced
• Free Video

Pinecone Vector Database - Building Knowledgeable AI

1 rating

Discover vector databases for AI, explore Pinecone's features, and learn implementation through a live demo to enhance your AI projects with efficient data management.

• YouTube
• 56 minutes
• Self-Paced
• Free Video

Pinecone Vector Database - Build Knowledgeable AI

Discover vector databases' advantages, explore Pinecone's innovative features, and watch a live demo on getting started with its powerful search capabilities.

• YouTube
• 38 minutes
• Self-Paced
• Free Video

The Magic of Multilingual Search with Pinecone Serverless and Inference

Explore multilingual search using Pinecone Serverless and Inference. Learn about embedding models, vector search basics, and practical applications through a language learning demo and expert insights.

• YouTube
• 54 minutes
• Self-Paced
• Free Video

Optimizing Query Performance with Pinecone's Rerank API and Fleak

Explore reranking, Pinecone's Embed and Rerank APIs, and see a live demo using Fleak to enhance query results and improve search performance.

• YouTube
• 51 minutes
• Self-Paced
• Free Video

The Future of Multi-Modal Search

Explore multi-modal search through a "Shop the Look" app, using Pinecone serverless and Google's Multimodal Embedding Model. Learn to build advanced search applications.

• YouTube
• 1 hour 2 minutes
• Self-Paced
• Free Video

PDFs for AI Masterclass - Handling PDFs and Data for AI and RAG Applications

Master handling PDFs and data for AI and RAG applications, exploring techniques and best practices in this comprehensive masterclass.

• YouTube
• 1 hour 1 minute
• Self-Paced
• Free Video

Mastering Video AI with TwelveLabs and Pinecone

Discover how to build contextual advertising and recommendation applications by combining TwelveLabs' video embedding models with Pinecone's vector database.

• YouTube
• 55 minutes
• Self-Paced
• Free Video

Introduction to Cascading Retrieval - Boosting RAG and Search Precision

Master cascading retrieval techniques to enhance RAG systems and search precision, combining dense, sparse, and reranking methods for up to 48% better performance in unified search pipelines.

• YouTube
• 49 minutes
• Self-Paced
• Free Video

Building Real-Time RAG Applications with Pinecone, Databricks, and Fivetran

Discover how to build efficient real-time RAG applications by integrating Pinecone, Databricks, and Fivetran in a streamlined data pipeline architecture.

• YouTube
• 1 hour 6 minutes
• Self-Paced
• Free Video

Secure Your RAG Pipelines with Fine-Grained Authorization Using SpiceDB

Discover how to implement fine-grained authorization in RAG pipelines using Relationship-based Access Control (ReBAC) with SpiceDB to ensure users access only authorized data.

• YouTube
• 54 minutes
• Self-Paced
• Free Video

Build RAG Workflows in Minutes with Pinecone and n8n

Discover how to build RAG workflows effortlessly using Pinecone's new Assistant node for n8n, with live demos and real-world use cases from industry experts.

• YouTube
• 58 minutes
• Self-Paced
• Free Video

Pinecone Demo - AI-Powered Search and Recommendation App

Discover how to build an AI-powered search and recommendation app using Pinecone, Groq, and Nuxt.js with vector search, hybrid retrieval, reranking, and RAG pipelines.

• YouTube
• 1 hour 21 minutes
• Self-Paced
• Free Video

Why RAG Remains Essential for Modern AI

Discover why retrieval-augmented generation stays vital for AI apps in 2025, covering context management, agent grounding, and hands-on RAG implementation with Pinecone.

• YouTube
• 54 minutes
• Self-Paced
• Free Video

Using Pinecone's MCP Server with Claude Code and Cursor

Discover how to integrate Pinecone's MCP server into IDEs like Cursor and Claude Code for enhanced vector database development workflows.

• YouTube
• 55 minutes
• Self-Paced
• Free Video