Semantic search

Implement semantic search with Pinecone in minutes over a simple translation dataset
Pinecone Integrated InferenceHugging Face Datasetsllama-text-embed-v2

Reranking search results

Use Pinecone's reranking feature to enhance the accuracy of search results.
Pinecone Inferencebge-reranker-v2-m3

​
Retrieval-augmented generation (RAG)

RAG with hybrid search and Claude

Implement simple retrieval-augmented generation with hybrid search and Anthropic's Claude models
claude-3-5-haiku-latestllama-text-embed-v2pinecone-sparse-english-v0Dense IndexesSparse IndexesHybrid Search

Agentic RAG with Claude

Build an agentic RAG pipeline that uses tools to retrieve data from web search and Pinecone semantic search, then generates responses using Anthropic's Claude models
claude-3-5-haiku-latestllama-text-embed-v2Dense IndexesTool use

RAG with LangChain and OpenAI

Learn how RAG can be used with Pinecone to reduce hallucinations, by grounding responses using our own release notes
gpt-4o-minitext-embedding-3-smallOpenAILangChain

RAG with cascading retrieval and OpenAI

Investigate research papers by implementing cascading retrieval, then pass results to OpenAI to generate answers
gpt-4o-minillama-text-embed-v2pinecone-sparse-english-v0Dense IndexesSparse IndexesCascading Retrieval

Retrieval Agents with Pinecone Assistant, LangChain and LangGraph

Create a study guide generator using agentic retrieval and the Pinecone Assistant Context API
gpt-4o-minigpt-4.1LangChainLangGraphAgentic RetrievalStructured Generation

​
Miscellaneous

Import from object storage

Import records from Parquet files in Amazon S3 bucket into a serverless index.
Amazon S3