Repository Issue Activity (beta)

#128 Feature Suggestion - schema based output

#430 test: Add missing test coverage for chunking module edge cases

#334 Bug / unexpected behavior: char_interval wrong for non-ASCII text when using certain providers in v1.1.1

#184 Proposal: Add Docling Integration for End-to-End Document Extraction

#475 Feature Request: Token Usage Tracking (or model metadata?) Support

#116 Support for Ollama gpt-oss:20b

#309 Batch API support for OpenAI provider

#59 Schema constraints for OpenAI not supported

#413 Bug: Returnning an empty string issue

#445 additional_context parameter not work

#463 docs: Sources for Benchmark Claims

#417 Feature Request: Add MiniMax model support

#240 langextract chunking does not recover from 503 error "The model is overloaded"

#30 Add conda recipe

#446 Performance: prompt building duplicates full few-shot preamble per prompt, causing O(batch_length × preamble_size) peak memory

#401 Bug: progress_bar resource leak — not closed on exception in save_annotated_documents and download_text_from_url

#389 Bug: `_IssueKind` is private/unexported but used in public `ValidationIssue.issue_kind` field

#437 Schema drift handling: missing *_attributes is another manifestation of the same issue as #428

#188 Performance for markdown extracted from large pdfs

#197 Debug messages about "No clean start index found and Fuzzy Aligning" when processing Vietnamese text

#386 Performance: Replace difflib with RapidFuzz for fuzzy alignment and add interval tree for merge

#428 OpenAILanguageModel with DeepSeek occasionally emits malformed attribute key (e.g. "emotion_attributes:") causing resolver ValueError

#427 OpenAILanguageModel with DeepSeek occasionally emits malformed attribute key (e.g. "emotion_attributes:") causing resolver ValueError

#293 uv as default in docs

#361 Fix: Ollama Docker healthcheck fails due to missing curl