Mode Comparison Guide
Compare different modes available in Instructor and understand when to use each
Explore
11,453 skills indexed with the new KISS metadata standard.
Compare different modes available in Instructor and understand when to use each
No description available.
Get structured, validated data from any LLM with Instructor - the #1 library for LLM data extraction. Supports 15+ providers (OpenAI, Anthropic, Google, Ollama, DeepSeek) in 6 languages. Built on type-safe schemas with automatic retries, streaming, and nested object support.
Learn how to install Instructor and its dependencies using pip for Python 3.9+. Simple setup guide included.
Explore key resources for getting help with Instructor, including Discord, blog, concepts, cookbooks, and GitHub discussions.
A step-by-step guide to getting started with Instructor for structured outputs from LLMs
Common questions and answers about using Instructor
Join us in enhancing the Instructor library with evals, report issues, and submit pull requests on GitHub. Collaborate and contribute!
Learn how to debug Instructor applications with hooks, logging, and exception handling. Practical techniques for inspecting inputs, outputs, and retries.
Learn about the internal architecture and design decisions of the Instructor library
Explore the comprehensive API reference with details on instructors, validation, iteration, and function calls.
Internal guide for maintaining and improving Instructor documentation
.cache
site_description: The framework for programming—rather than prompting—language models.
Build collaborative AI agents, crews, and flows — production ready from day one.
info:
info:
info:
info:
dist/
This directory contains the documentation source code for LlamaIndex, available at https://docs.llamaindex.ai.
This directory is retained purely for archival purposes and is no longer updated. The examples previously found here have been moved to the newly [consolidated LangChain documentation](https://docs.langchain.com/oss/python/langgraph/overview). Please refer to the LangChain docs for the most up-to-da
settings: