hokusai/bulkgen/providers
Konstantin Fickel 61f30a8bb1
All checks were successful
Continuous Integration / Build Package (push) Successful in 31s
Continuous Integration / Lint, Check & Test (push) Successful in 50s
fix: don't pass response_format to gpt-image-* models
gpt-image-* models return b64_json by default and reject the
response_format parameter with a 400 error. Only pass it for
DALL-E models which default to url.
2026-02-15 14:47:52 +01:00
..
__init__.py feat: add OpenAI as provider for text and image generation 2026-02-15 13:48:06 +01:00
bfl.py refactor: replace blackforest package with custom async BFL client 2026-02-14 16:44:36 +01:00
blackforest.py refactor: move model definitions into providers and extract resolve module 2026-02-15 11:03:57 +01:00
mistral.py refactor: move model definitions into providers and extract resolve module 2026-02-15 11:03:57 +01:00
models.py refactor: move model definitions into providers and extract resolve module 2026-02-15 11:03:57 +01:00
openai_image.py fix: don't pass response_format to gpt-image-* models 2026-02-15 14:47:52 +01:00
openai_text.py feat: add GPT-5 generation models to OpenAI providers 2026-02-15 14:42:43 +01:00
registry.py feat: add OpenAI as provider for text and image generation 2026-02-15 13:48:06 +01:00