HoneyHive Cookbooks

This repository contains various cookbooks and examples for integrating different tools and services with HoneyHive for AI observability.

Available Cookbooks

Vector Databases

• Qdrant Cookbook: Integration with Qdrant vector database for RAG pipelines
• Zilliz Cookbook: Integration with Zilliz (Milvus) vector database
• ChromaDB Cookbook: Integration with ChromaDB for RAG pipelines

LLM Providers

• Mistral AI Cookbook: Integration with Mistral AI's models and API

Frameworks

• LangChain Python: Integration with LangChain in Python
• LangChain TypeScript: Integration with LangChain in TypeScript
• LlamaIndex Python: Integration with LlamaIndex in Python

Web Applications

• Next.js Quickstart: Basic Next.js integration with HoneyHive
• Next.js with Sentry: Next.js integration with both HoneyHive and Sentry

Evaluation

• Putnam Evaluation (Python): Evaluation examples using Putnam dataset
• Putnam Evaluation (Async Python): Asynchronous evaluation examples

General Tutorials

• Observability Tutorial (Python): Basic observability tutorial in Python
• Observability Tutorial (TypeScript): Basic observability tutorial in TypeScript

Getting Started

Each cookbook contains its own README with specific instructions. Generally, you'll need:

1. A HoneyHive account and API key
2. Python 3.8+ or Node.js (depending on the cookbook)
3. Any additional API keys for third-party services (e.g., OpenAI, Mistral AI)

Contributing

Feel free to contribute additional cookbooks or improvements to existing ones by submitting a pull request.

Support

For questions or issues, please contact the HoneyHive team or visit honeyhive.ai.