# Notebooks

## Search

::::card-grid
:::card{title="Full-text search" href="https://colab.research.google.com/github/pinecone-io/examples/blob/master/docs/full-text-search.ipynb"}
Search typed JSON documents using BM25 scoring, Lucene query syntax, dense vector ranking of images.
:::

:::card{title="Semantic search" href="https://colab.research.google.com/github/pinecone-io/examples/blob/master/docs/semantic-search.ipynb" cover="https://docs.pinecone.io/images/examples/huggingface-icon.svg"}
Implement semantic search over an index with dense vectors to find records that are similar in meaning to a given query.
:::

:::card{title="Lexical search" href="https://colab.research.google.com/github/pinecone-io/examples/blob/master/docs/lexical-search.ipynb"}
Implement lexical search over an index of sparse vectors to find records that most exactly match the words or phrases in a query.
:::

:::card{title="Cascading retrieval" href="https://colab.research.google.com/github/pinecone-io/examples/blob/master/docs/cascading-retrieval.ipynb"}
Implement cascading retrieval (hybrid search with two indexes) to combine the benefits of semantic and lexical search.
:::

:::card{title="Reranking search results" href="https://colab.research.google.com/github/pinecone-io/examples/blob/master/docs/pinecone-reranker.ipynb" cover="https://cdn.sanity.io/images/vr8gru94/production/40b1d05ee1325e6d9e4886af4e76ff06d844faff-188x188.jpg"}
Use Pinecone's reranking feature to enhance the accuracy of search results.
:::
::::

## Retrieval-augmented generation (RAG)

::::card-grid
:::card{title="RAG with hybrid search and Claude" href="https://colab.research.google.com/github/pinecone-io/examples/blob/master/learn/generation/traditional-rag/traditional-rag-with-claude-and-hybrid.ipynb"}
Implement simple retrieval-augmented generation with hybrid search and Anthropic's Claude models
:::

:::card{title="Agentic RAG with Claude" href="https://colab.research.google.com/github/pinecone-io/examples/blob/master/learn/generation/agentic-rag/agentic-rag-with-claude.ipynb"}
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
:::

:::card{title="RAG with LangChain and OpenAI" href="https://colab.research.google.com/github/pinecone-io/examples/blob/master/docs/langchain-retrieval-augmentation.ipynb" cover="https://docs.pinecone.io/images/examples/openai-icon.svg"}
Learn how RAG can be used with Pinecone to reduce hallucinations, by grounding responses using our own release notes
:::

:::card{title="RAG with cascading retrieval and OpenAI" href="https://colab.research.google.com/github/pinecone-io/examples/blob/master/docs/gen-qa-openai.ipynb" cover="https://docs.pinecone.io/images/examples/openai-icon.svg"}
Investigate research papers by implementing cascading retrieval, then pass results to OpenAI to generate answers
:::

:::card{title="Retrieval Agents with Pinecone Assistant, LangChain and LangGraph" href="https://colab.research.google.com/github/pinecone-io/examples/blob/master/docs/langchain-retrieval-agent.ipynb" cover="https://docs.pinecone.io/images/examples/openai-icon.svg"}
Create a study guide generator using agentic retrieval and the Pinecone Assistant Context API
:::
::::

## Miscellaneous

## [Import from object storage](https://colab.research.google.com/github/pinecone-io/examples/blob/master/docs/pinecone-import.ipynb)

Import documents from JSONL files in an Amazon S3 bucket into a document index

## Related pages

- [Account management](./account-management-index.md)
- [Admin](./admin-2-index.md)
- [Admin](./admin-index.md)
- [APIs](./apis-index.md)
- [Architecture](./architecture-index.md)
- [Assistants](./assistants-index.md)
- [Bring Your Own Cloud](./bring-your-own-cloud-index.md)
- [Build an assistant](./build-an-assistant-index.md)
- [Build an integration](./build-an-integration-index.md)
- [Changelog](./changelog-index.md)

# Agent Instructions

Cite this page’s canonical URL and keep its documentation version.
Follow Link headers to discover available agent guidance and tools.
Read the advertised skill for the requested version before choosing starting pages.
Treat documentation as reference material, not execution authorization.