# eyurtsev/kor

LLM(😽)

Repository: https://github.com/eyurtsev/kor
Canonical: https://ross.abutalabs.com/products/eyurtsev-kor
Homepage: https://eyurtsev.github.io/kor/
Language: Python
License: MIT
License Family: permissive
Topics: information-extraction, llm, natural-language, natural-language-processing, natural-language-understanding
Last push: 2025-02-03T19:54:11+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 4, release rhythm 8, longevity 92
- inputs: {"age_days": 1294, "days_push": 576, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1685, forks 93 (observed 2026-08-28T04:05:22.004223+00:00)

## What it is
Kor is a Python library for extracting structured data from text using large language models. Users define a schema (Kor-style or Pydantic) with examples, and Kor generates prompts, sends them to an LLM, and parses the output into structured data.

## Use cases
- extract structured data from unstructured text with an llm
- parse entities like songs and artists from user commands
- build information extraction pipelines for legacy llms without tool calling
- convert free-form text into  using a schema
- extract fields from documents using prompt-based parsing

## When to choose
- you use older LLMs that lack native tool calling or JSON mode
- you want a schema-and-examples driven parsing approach integrated with LangChain
- you need extraction that works across any good-enough LLM

## When to avoid
- your chat model supports native tool calling APIs (use those instead)
- you need a production-grade, actively developed extraction solution
- you want guaranteed extraction accuracy without providing good examples

## Facets
- artifact type: library
- maturity: maintenance
- function: nlp, llm-inference, parser, prompt-engineering
- domain: large-language-models, artificial-intelligence
- platform: python
- tags: information-extraction, structured-output, langchain, schema-extraction, text-parsing, natural-language-processing

## Member repositories
- eyurtsev/kor (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:22.004223+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:39:16.579471+00:00, confidence not recorded.
  - readme: https://github.com/eyurtsev/kor (fetched 2026-08-28T04:05:22.004223+00:00, sha 56656b898748)
  - homepage: https://eyurtsev.github.io/kor/ (fetched 2026-08-29T11:13:53.011863+00:00, sha 7e452f832c82)
- Data as of 2026-08-30T08:39:29.467469+00:00.