google/langextract
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization. observed · 2026-10-15
Health v2 · maintenance only
85/100
- Activity 99
- Release rhythm 98
- Longevity 33
How is this computed?
round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-10-21. Adoption (stars, forks) is never an input.
- gap_med: 12
- age_days: 469
- days_rel: 12
- days_push: 6
- n_releases_24m: 20
Adoption not part of the score
38953 stars · 2718 forks observed · 2026-10-15
What it is AI-extracted, prompt v1, taxonomy v1, 2026-09-28, confidence 0.97
LangExtract is a Python library that uses large language models to extract structured information from unstructured text. It provides precise source grounding for each extracted value and interactive visualisation of the results.
Use cases
- Extract medication lists from clinical notes into a structured format
- Convert free‑form resumes into JSON objects with standardized fields
- Parse legal contracts to identify parties, dates, and obligations
- Transform product reviews into sentiment‑tagged data tables
- Structure radiology reports for downstream analytics
When to choose
- You need high‑precision grounding of extracted values back to the original text
- Your workflow relies on LLMs (e.g., Gemini, OpenAI, Ollama) for information extraction
- You want a Python‑native solution with easy integration into data pipelines
When to avoid
- You require extraction without any reliance on external language models
- Performance is critical on extremely large corpora and you need a compiled solution
- Your environment does not support Python or the required LLM APIs
Facets
library · maturity active
parser llm-inference nlp artificial-intelligence data-science python windows structured-extraction grounded-extraction gemini openai ollama natural-language-processing linux macos
3 sources
- readme: https://github.com/google/langextract · fetched 2026-10-15 · a5025496853a
- homepage: https://pypi.org/project/langextract/ · fetched 2026-09-14 · 298451854ac8
- registry_pypi: https://pypi.org/pypi/langextract/json · fetched 2026-09-14 · cc18a47df198
Member repositories
| Repository | Role | Health v2 |
|---|---|---|
| google/langextract | main | 85 |
For agents
markdown · JSON · MCP: product_card(name="google/langextract")
Data as of 2026-10-19T08:05:51.212177+00:00 · Report a problem