Anthropic Cookbook

Provides production-ready Jupyter notebooks (.ipynb files) that demonstrate Claude API capabilities with runnable code cells organized by feature domain. Each notebook is structured as a self-contained example with setup, execution, and output cells that developers can copy and adapt, backed by a machine-readable registry.yaml catalog system for programmatic discovery and automated validation of notebook metadata and API usage patterns.

Implements a YAML-based registry system (registry.yaml) that serves as a machine-readable catalog of all cookbook entries with standardized metadata fields including author, category, model compatibility, dependencies, and validation status. This enables programmatic discovery, filtering, and automated validation workflows that ensure examples remain functional and correctly use the Claude API across updates.

Provides CI/CD infrastructure for validating cookbook notebooks including automated testing, API usage validation, dependency checking, and metadata verification. The validation system uses scripts (validate_notebooks.py) and GitHub Actions workflows to ensure notebooks remain executable, use current API patterns, and maintain consistent metadata in registry.yaml. Enables continuous quality assurance as Claude API evolves.

Provides structured contribution guidelines and tooling for submitting new cookbook examples, including PR templates, author registration, metadata requirements, and validation checks. The system uses registry.yaml entries and authors.yaml for tracking contributors, enforces consistent notebook structure, and automates validation of new submissions through GitHub Actions before merge.

Provides executable notebook templates demonstrating Claude's tool-use capabilities including function calling, schema-based tool definition, multi-turn tool interactions, and memory management for agents. Templates show how to define tool schemas, handle tool responses, implement error handling, and maintain conversation context across multiple tool invocations using the Anthropic API's native tool-calling interface.

Provides executable templates for building RAG systems with Claude, covering basic RAG pipelines, vector database integrations (Pinecone, Weaviate, Chroma), embedding generation, semantic search, and advanced patterns using LlamaIndex. Templates demonstrate how to chunk documents, generate embeddings, store vectors, retrieve relevant context, and augment Claude prompts with retrieved information to enable knowledge-grounded responses.

Demonstrates Anthropic's prompt caching feature through executable examples showing how to structure prompts with cache control tokens, measure cache hit rates, optimize for cache efficiency, and calculate cost savings. Templates show practical patterns for caching system prompts, large context blocks, and repeated query patterns to reduce API costs and latency for Claude API calls.

Demonstrates Anthropic's Batch API for processing multiple Claude requests asynchronously with cost savings and higher rate limits. Templates show how to structure batch requests, submit them to the Batch API, poll for completion, retrieve results, and handle partial failures. Includes patterns for cost optimization, request formatting, and result aggregation for large-scale processing workflows.

Provides executable templates for Claude's vision capabilities including image analysis, OCR, visual question answering, and image-based reasoning. Templates demonstrate how to encode images (base64, URLs), structure vision prompts, interpret Claude's image analysis responses, and combine vision with other capabilities like tool use or RAG for multimodal applications.

Provides templates for implementing content moderation using Claude, including classification of harmful content, safety filtering, policy violation detection, and moderation workflow patterns. Templates demonstrate how to structure moderation prompts, interpret Claude's safety assessments, implement multi-stage filtering, and integrate moderation into application workflows.

Provides templates for generating embeddings using Anthropic's embedding API and implementing semantic search, similarity matching, and clustering. Templates demonstrate how to generate embeddings for documents or queries, compute similarity scores, implement approximate nearest neighbor search, and integrate embeddings into RAG or recommendation systems.

Provides templates for managing multi-turn conversations with Claude, including conversation history management, context window optimization, token counting, and state persistence. Templates demonstrate how to structure conversation messages, maintain context across turns, implement conversation memory, and handle context length limits for long conversations.