jxnl/instructor: openai function calls for humans

openai function calls for humans

Get reliable JSON from any LLM. Built on Pydantic for validation, type safety, and IDE support. import instructor from pydantic import BaseModel # Define what you want class User(BaseModel): name: str age: int # Extract it from natural language client = instructor.from_provider("openai/gpt-4o-mini") user = client.chat.completions.create( response_model=User, messages=[{"role": "user", "content": "John is 25 years old"}], ) print(user) # User(name='John', age=25) That's it. No JSON parsing, no error handling, no retries. Just define a model and get structured data. Use Instructor for…

saved by

• Eric Chang

related reading

• GitHub - guidance-ai/guidance: A guidance language for controlling large language models.github.com
• GitHub - deepset-ai/haystack: Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing, memory, and generation. Built for scalable agents, RAG, multimodal applications, semantic search, and conversational systems.github.com
• LLM Evaluation doesn't need to be complicatedphilschmid.de
• GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4.github.com
• Cookbookcookbook.openai.com
• GitHub - rasbt/LLMs-from-scratch: Implement a ChatGPT-like LLM in PyTorch from scratch, step by stepgithub.com
• Building Effective AI Agents \ Anthropicanthropic.com
• Prompt engineering | OpenAI APIplatform.openai.com
• LangChain Tutorial in Python - Crash Course - Python Engineerpython-engineer.com
• Introductions - Jason Liujxnl.co
• The Problem With LangChain | Max Woolf's Blogminimaxir.com
• Text Classification with OpenAI and Pydantic - Instructorpython.useinstructor.com