litellm

mirror of https://github.com/BerriAI/litellm.git synced 2026-11-13 08:52:02 +00:00

History

Kerry Lu e3b32534dc feat(replicate): add video generation, image generation and text to speech through the predictions API (#51360 ) * feat(replicate): add video generation, image generation and text to speech through the predictions API * fix(replicate): surface poll HTTP errors, keep deployment ssl_verify and native speech input, flatten outputs without recursion Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(replicate): keep model family mapping for deployments and versions, preserve video id on status, poll until terminal status Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(replicate): validate output downloads and poll origin, bind retrieval to the requested model, flatten image extra_body, keep speech input authoritative, use the async image path Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(replicate): keep the audited prompt authoritative over image extra_body Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(replicate): cover extra_body.prompt not replacing the audited prompt Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(replicate): honor the request ssl_verify when polling and downloading speech output Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(replicate): build the video usage into VideoObject instead of assigning it afterwards Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(replicate): keep the inspected video prompt authoritative over native extra_body prompt Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * feat(replicate): bill native image dimensions and token-metered speech output Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(replicate): bound output downloads, accept both token metric spellings and build speech usage at construction Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(http_handler): walk bounded-download redirects iteratively Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(replicate): reject dot and empty model path segments and keep the bounded redirect walk annotated Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(http_handler): drop the unused rebind suppression Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(http_handler): put the rebind suppression on the redirect hop binding Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * fix(replicate): run pinned versions through the model's own versions endpoint Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>		2026-11-12 08:44:50 -08:00
..
chat	chore(typing): clear 670 basedpyright Any errors by validating provider payloads at the boundary (#45388 )	2026-10-13 15:35:23 -07:00
image_generation	feat(replicate): add video generation, image generation and text to speech through the predictions API (#51360 )	2026-11-12 08:44:50 -08:00
text_to_speech	feat(replicate): add video generation, image generation and text to speech through the predictions API (#51360 )	2026-11-12 08:44:50 -08:00
videos	feat(replicate): add video generation, image generation and text to speech through the predictions API (#51360 )	2026-11-12 08:44:50 -08:00
__init__.py	refactor(types): replace Any with proven types in 137 files (#44478 )	2026-10-05 11:01:45 -07:00