Responses API in transformers serve (#39155)

* Scaffolding

* Explicit content

* Naïve Responses API streaming implementation

* Cleanup

* Responses API (to be merged into #39155) (#39338)

* Scaffolding

* Explicit content

* Naïve Responses API streaming implementation

* Cleanup

* use openai

* validate request, including detecting unused fields

* dict indexing

* dict var access

* tmp commit (tests failing)

* add slow

* use oai output type in completions

* (little rebase errors)

* working spec?

* guard type hint

* type hints. fix state (CB can now load different models)

* type hints; fn names; error type

* add docstrings

* responses + kv cache

* metadata support; fix kv cache; error event

* add output_index and content_index

* docstrings

* add test_build_response_event

* docs/comments

* gate test requirements; terminate cb manager on model switch

* nasty type hints

* more type hints

* disable validation by default; enable force models

* todo

---------

Co-authored-by: Lysandre <hi@lysand.re>

* Slight bugfixes

* PR comments from #39338

* make fixup

---------

Co-authored-by: Joao Gante <joaofranciscocardosogante@gmail.com>
Co-authored-by: Joao Gante <joao@huggingface.co>

setup.py

@@ -137,6 +137,7 @@ _deps = [
     "onnxconverter-common",
     "onnxruntime-tools>=1.4.2",
     "onnxruntime>=1.4.0",
+    "openai",
     "opencv-python",
     "optimum-benchmark>=0.3.0",
     "optuna",
@@ -314,7 +315,7 @@ extras["hub-kernels"] = deps_list("kernels")
 
 extras["integrations"] = extras["hub-kernels"] + extras["optuna"] + extras["ray"] + extras["sigopt"]
 
-extras["serving"] = deps_list("pydantic", "uvicorn", "fastapi", "starlette") + extras["torch"]
+extras["serving"] = deps_list("openai", "pydantic", "uvicorn", "fastapi", "starlette") + extras["torch"]
 extras["audio"] = deps_list(
     "librosa",
     "pyctcdecode",