lennartpollvogt/ollama-instructor

Python library for the instruction and reliable validation of structured outputs (JSON) of Large Language Models (LLMs) with Ollama and Pydantic. -> Deterministic work with LLMs.

33
/ 100
Emerging

This project helps developers working with Large Language Models (LLMs) running on Ollama to get reliable, structured data out of them. You input natural language prompts and define the desired JSON output structure using Pydantic, and the tool ensures the LLM's response matches that exact format. It's ideal for engineers building applications that need to predictably parse information from LLM interactions.

No commits in the last 6 months.

Use this if you are a developer integrating Ollama-based LLMs into applications and need to guarantee their outputs are always valid, structured JSON.

Not ideal if you are a non-technical end-user or are working with LLMs through a user interface that doesn't require direct code-level interaction.

LLM-development API-integration data-validation software-engineering AI-application-development
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 6 / 25

How are scores calculated?

Stars

77

Forks

3

Language

Python

License

MIT

Last pushed

Aug 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/lennartpollvogt/ollama-instructor"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.