v1.15.4
📦 instructorView on GitHub →
🐛 7 fixes🔧 1 symbols
Summary
Instructor 1.15.4 is a patch release consolidating fixes for runtime model preparation, streamed JSON extraction, image handling, and CLI fine-tuning operations.
🐛 Bug Fixes
- Fixed v2 response-model preparation so list and primitive response models are normalized before provider handler dispatch, resolving crashes like AttributeError: type object 'list' has no attribute 'model_json_schema' for list[Model] and scalar response models.
- Fixed streamed JSON extraction to preserve backticks inside JSON string values instead of interpreting them as markdown fence delimiters.
- Fixed Image.autodetect() to accept raw JPEG, PNG, GIF, and WebP bytes, while raising clear errors for unsupported image inputs.
- Added regression coverage for the existing Gemini empty-message path.
- Fixed list[BaseModel] simple-type detection so model lists route through iterable handling instead of scalar wrapping.
- Fixed CLI fine-tuning job creation from local files to pass the uploaded validation file ID to OpenAI instead of the local validation file path.
- Refreshed the CLI fine-tuning default model string in code and docs.