langextract · Issues· 125 open
Open on GitHubLocally synced open issues (discussions stay on GitHub)
- #527
Bug: Gemini batch path returns empty success on a safety-blocked or refused response
Updated Sep 8, 2026 - #308
The fragmentation issue when extracting documents containing HTML tables
Updated Sep 7, 2026 - #532
Batch path nests tools inside generationConfig, producing an invalid batch request
Updated Aug 24, 2026 - #529
extract(temperature=...) is silently ignored when config= or model= is passed
Updated Aug 23, 2026 - #184
Proposal: Add Docling Integration for End-to-End Document Extraction
discussionUpdated Aug 21, 2026 - #121
Does it support extracting structured information from the results recognized by OCR
Updated Aug 21, 2026 - #524
OrcaRouter provider plugin (langextract-provider-orcarouter)
Updated Aug 20, 2026 - #522
Request: Built-in Anthropic (Claude) and xAI (Grok) providers
Updated Aug 20, 2026 - #358
Challenges extracting structured data from large Brazilian fund regulation PDFs (230K+ chars, 22 entity types)
Updated Aug 20, 2026 - #518
Bug: UnicodeEncodeError in create_provider_plugin.py on Windows (cp1252 console)
Updated Aug 18, 2026 - #446
Performance: prompt building duplicates full few-shot preamble per prompt, causing O(batch_length × preamble_size) peak memory
Updated Jul 28, 2026 - #505
Generated provider schema cannot be instantiated with --with-schema
Updated Jul 25, 2026 - #475
Feature Request: Token Usage Tracking (or model metadata?) Support
Updated Jul 25, 2026 - #425
Inference cost
Updated Jul 25, 2026 - #155
Request: Token Count on Gemini (all) APIs
enhancementUpdated Jul 25, 2026