ngmi / google / langextract

google/langextract

Python 33.6k stars

A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.

✓ Synced 1h ago Share on X →
README badge: [![ngmi](https://ngmi.review/badge/google/langextract.svg)](https://ngmi.review/repo/google/langextract)
77 Merged PRs
15.7h Avg Merge Time
0m Fastest PR
21 days Slowest PR
#145 Global Speed Rank

PR Size Analysis

Lines changed (additions + deletions) vs review outcomes. Re-sync to populate data for older PRs.

PRs by size
Avg review time (hrs)
Clean approval rate (%)

Top Reviewers

#1
@aksg87
4 reviews ✓ 3 approved ↺ 1 blocked
#2 @PLPeeters
@PLPeeters
2 reviews
#3 @JamesWordie
@JamesWordie
1 reviews
#4 @MeshkatShB
@MeshkatShB
1 reviews
#5 @tonebeta
@tonebeta
1 reviews

Recent Merged PRs

# Title Author Time Reviews Blocks
#383 Refactor Github Action per b/485167538 @google-admin 2m 0 ✓
#306 feat: Add cross-chunk context awareness for coreference resolution @aksg87 3.3h 0 ✓
#302 docs: Clarify best practices for few-shot examples @aksg87 5m 0 ✓
#300 fix: Handle non-Gemini model output parsing edge cases @aksg87 6m 0 ✓
#288 chore: Bump version to 1.1.1 @aksg87 6m 0 ✓
#286 Fix: Pass project parameter correctly to storage.Client in Gemini Batch API @aksg87 43m 0 ✓
#284 refactor: Multi-language tokenizer support (Unicode & Regex) @aksg87 23m 0 ✓
#282 chore: enforce dotenv override, warn on key conflict, and refactor fa… @aksg87 3.2h 0 ✓
#280 fix: Apply autoformatting and add pre-commit to dev dependencies @aksg87 12m 0 ✓
#279 feat: Add Vertex AI Batch API support with real-time fallback @aksg87 16.7h 0 ✓
#276 fix: streamline annotation layer with lazy streaming @aksg87 47m 0 ✓
#272 Add tokenization performance benchmark with multi-language support @aksg87 1.3h 0 ✓
#273 Fix: Resolve pylint naming convention warnings in provider modules @aksg87 32m 0 ✓
#261 Fix: Enable suppress_parse_errors parameter in resolver_params @aksg87 4m 0 ✓
#250 Add Outlines to the list of community providers @RobinPicard 3 days 0 ✓
#248 Internal: Strengthen CI/CD security for fork PR validation @aksg87 8m 0 ✓
#244 Add vLLM community provider information to the plugin registry @wuli666 18m 0 ✓
#239 feat: Add FormatHandler and schema validation framework @aksg87 19m 0 ✓
#223 docs: Fix broken community support link in issue template @gerritcloete 2 days 0 ✓
#227 feat: Add show_progress parameter for independent progress bar control @aksg87 6m 0 ✓