google/langextract
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
About the project
A Python library for extracting structured information from unstructured text using LLMs, with precise source grounding and interactive visualization.
Useful for
- Extract characters, emotions, and relationships from literary text using few-shot examples
- Structure clinical notes or medical reports into a defined schema
- Review extraction results in an interactive HTML with source-text highlighting
README summarized by DeepSeek V4.1 Flash. Details may be inaccurate.
Why it’s trending
- 65 stars so far today, about 112 expected by the end of the day. The usual pace is 9 per day, so that's 12× as much.
- Over the last two days the pace is 13× that of the previous week and a half.
- The spike has held for 2 days in a row — not a one-off blip.
- GitHub Trending Python today: #11, +154 stars.
Stars per day
Bars are daily stars, the line is the usual pace. Red marks spike days.
Numbers
- Total stars
- 38,839
- Today
- 65 · ≈ 112 by evening
- Forks
- 2,716
- Issues and pull requests
- 494
- Watchers
- 171
- Language
- Python
- License
- Apache-2.0
- Latest release
- v1.7.0 · September 13, 2026
- Created
- July 8, 2025
- Last push
- September 21, 2026
Star trust
Growth looks organic: forks and discussion are in line with active projects, and stars arrive unevenly, the way people give them.
These are heuristics, not a verdict: we judge by the repository’s behavior, not by a list of stargazers.
Spotted in
- September 25, 2026GitHub Trending Python today: #10, +154 stars
Share
README badge
Paste it into your README — the badge shows the current magnitude and links to this page.
[](https://gitnova.dev/en/r/google/langextract)Similar by description
-
1.5
JunMa11/MedJev
A tool for extracting structured clinical variables from free-text medical notes: it turns notes into table-ready data, running locally on a single consumer GPU without sending data outside.
-
1.9
fastino-ai/GLiNER2
A family of schema-conditioned encoder models for information extraction: NER, text classification, structured record extraction, relations, and span attributes. Runs locally on CPU without a GPU.