google/langextract

View on GitHub

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

Stars: 38.6k
Forks: 2.7k
Open beginner issues: 0
Indexed issues: 77
Avg merge: 3d 15h
Merged PRs (30d): 3

Dominant language: Python
License: Apache-2.0
Last GitHub push: Sep 13, 2026
Latest indexed: Sep 16, 2026
Contributing guide: Contributing guide
Code of conduct: Code of conduct
Beginner labels: No beginner labels indexed

Open All

77 open issues indexed

Gemini 2.0 Flash and 2.5 Flash structured output value repetition and missing fields Open

google/langextract#1 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
BUG: Failed to parse content from a large file (ResolverParsingError) Open

more details required

google/langextract#4 · 6 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Difference between Gemini Extraction Open

question

google/langextract#20 · 5 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Support DSPy Open

discussion

google/langextract#33 · 0 comments · 6 reactions · 0 assignees · Indexed Sep 16, 2026
feat: Add delay/retry between requests for .extract Open

google/langextract#50 · 1 comment · 4 reactions · 0 assignees · Indexed Sep 16, 2026
Where is llms.txt file? Open

google/langextract#55 · 0 comments · 2 reactions · 0 assignees · Indexed Sep 16, 2026
The code is breaking with French Text Open

bug

google/langextract#63 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
feat: Add max_tokens support to .extract(...) Open

google/langextract#72 · 1 comment · 1 reaction · 0 assignees · Indexed Sep 16, 2026
tyscript / js port Open

discussion

google/langextract#78 · 6 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Can timeout be added for LLM call Open

google/langextract#82 · 2 comments · 1 reaction · 0 assignees · Indexed Sep 16, 2026
Bug: Critical Security Vulnerabilities and Bugs in Ollama API Integration Open

google/langextract#89 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
How to ensure reliability Open

google/langextract#95 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Plugin support for custom LLM providers now available Open

alternative-llm

google/langextract#99 · 35 comments · 16 reactions · 0 assignees · Indexed Sep 16, 2026
Clickable Entity Selector in Visualizations Open

google/langextract#103 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
The langextract tool takes too long to locate the original content. Would it be possible to add a parameter to provide two options: one with original content localization and one without, so that it only extracts the content? Open

google/langextract#105 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Add `config` and `model` parameters to `extract()` Open

enhancement

google/langextract#106 · 4 comments · 2 reactions · 0 assignees · Indexed Sep 16, 2026
[feature request] Add support/ template for llama.cpp compatible API endpoint. Open

google/langextract#109 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
This code causes langextract to hang Open

google/langextract#112 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Support multiple doc formats Open

enhancement

google/langextract#115 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Does it support extracting structured information from the results recognized by OCR Open

google/langextract#121 · 2 comments · 1 reaction · 0 assignees · Indexed Sep 16, 2026
Feature suggestion Open

google/langextract#124 · 0 comments · 3 reactions · 0 assignees · Indexed Sep 16, 2026
Chinese Support ? Open

google/langextract#125 · 4 comments · 2 reactions · 0 assignees · Indexed Sep 16, 2026
Example code reports that the model is overloaded Open

google/langextract#126 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
json.decoder.JSONDecodeError: Unterminated string starting at Open

google/langextract#127 · 4 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Russian text Unicode error Open

google/langextract#139 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
LangExtract Integration Challenges (Gemini SSL & Ollama API Key) Open

google/langextract#145 · 1 comment · 1 reaction · 0 assignees · Indexed Sep 16, 2026
AWS Bedrock Support (langextract-bedrock) Open

plugin

google/langextract#148 · 3 comments · 1 reaction · 0 assignees · Indexed Sep 16, 2026
Incorrect Extraction Alignment Open

google/langextract#151 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Request: Token Count on Gemini (all) APIs Open

enhancement

google/langextract#155 · 3 comments · 5 reactions · 0 assignees · Indexed Sep 16, 2026
How to "Extract aligned spans from a Question and an Answer"? Open

discussion

google/langextract#168 · 2 comments · 1 reaction · 0 assignees · Indexed Sep 16, 2026
Data Extraction from Markdown with Tables Open

discussion

google/langextract#169 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Is it able to work on large PDF files? Open

enhancement

google/langextract#178 · 2 comments · 2 reactions · 0 assignees · Indexed Sep 16, 2026
Proposal: Add Docling Integration for End-to-End Document Extraction Open

discussion

google/langextract#184 · 9 comments · 20 reactions · 0 assignees · Indexed Sep 16, 2026
LangExtract QoS for TPM Quotas Open

enhancement

google/langextract#185 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Provider LiteLLM Integration and Discussion Thread Open

discussion plugin

google/langextract#187 · 0 comments · 1 reaction · 0 assignees · Indexed Sep 16, 2026
llama-cpp-python support (langextract-llamacpp) Open

plugin

google/langextract#199 · 2 comments · 2 reactions · 0 assignees · Indexed Sep 16, 2026
When extracting content from contract texts, we have extracted a lot of irrelevant content. How should we handle this. Open

google/langextract#200 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Question: Does Langextract work better on full documents or chunks? Open

discussion

google/langextract#206 · 2 comments · 8 reactions · 0 assignees · Indexed Sep 16, 2026
Question how can i use runpod serverless api into langextract Open

google/langextract#208 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Robustness: Library fails on LLM outputs containing CJK Radicals and malformed JSON Open

google/langextract#222 · 1 comment · 2 reactions · 0 assignees · Indexed Sep 16, 2026
how to support Ali DashScope API Open

google/langextract#228 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Cohere models Open

google/langextract#229 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Browser may display garbled text when <meta charset> is not specified Open

google/langextract#234 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
vllm support (langextract-vllm) Open

plugin

google/langextract#236 · 1 comment · 12 reactions · 0 assignees · Indexed Sep 16, 2026
ExampleData creeping into final result Open

discussion

google/langextract#243 · 3 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Fuzzy Alignment Threshold Setting not Working Open

google/langextract#245 · 0 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
potential exposure of local path and identity of the user Open

google/langextract#249 · 1 comment · 0 reactions · 0 assignees · Indexed Sep 16, 2026
langextract.resolver.ResolverParsingError: Failed to parse JSON content: Expecting value: line 1 column 1 (char 0) Open

google/langextract#258 · 7 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026
Feature Request: Support multimodal extraction (text + image) Open

discussion

google/langextract#270 · 3 comments · 10 reactions · 0 assignees · Indexed Sep 16, 2026
Long `ExampleData` causes `extract` to hang on `_fuzzy_align_extraction` Open

discussion

google/langextract#277 · 2 comments · 0 reactions · 0 assignees · Indexed Sep 16, 2026

google/langextract

Get new issues in your inbox