chore: import upstream snapshot with attribution

doc/source/serve/doc_code/getting_started/model_deployment.py

@@ -0,0 +1,67 @@
+# flake8: noqa
+
+# __import_start__
+from starlette.requests import Request
+
+import ray
+from ray import serve
+
+# __import_end__
+
+# __model_start__
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+
+@serve.deployment(num_replicas=2, ray_actor_options={"num_cpus": 0.2, "num_gpus": 0})
+class Translator:
+    def __init__(self):
+        # Load model
+        self.tokenizer = AutoTokenizer.from_pretrained("t5-small")
+        self.model = AutoModelForSeq2SeqLM.from_pretrained("t5-small")
+
+    def translate(self, text: str) -> str:
+        # Run inference
+        input_ids = self.tokenizer(
+            f"translate English to French: {text}", return_tensors="pt"
+        ).input_ids
+        output_ids = self.model.generate(
+            input_ids, num_beams=4, early_stopping=True, max_length=300
+        )
+
+        # Post-process output to return only the translation text
+        translation = self.tokenizer.decode(
+            output_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=False
+        )
+
+        return translation
+
+    async def __call__(self, http_request: Request) -> str:
+        english_text: str = await http_request.json()
+        return self.translate(english_text)
+
+
+# __model_end__
+
+# __model_deploy_start__
+translator_app = Translator.bind()
+# __model_deploy_end__
+
+translator_app = Translator.options(ray_actor_options={}).bind()
+serve.run(translator_app)
+
+# __client_function_start__
+# File name: model_client.py
+import requests
+
+english_text = "Hello world!"
+
+response = requests.post("http://127.0.0.1:8000/", json=english_text)
+french_text = response.text
+
+print(french_text)
+# __client_function_end__
+
+assert french_text == "Bonjour monde!"
+
+serve.shutdown()
+ray.shutdown()

doc/source/serve/doc_code/getting_started/model_deployment_full.py

@@ -0,0 +1,53 @@
+# flake8: noqa
+
+# __deployment_full_start__
+# File name: serve_quickstart.py
+from starlette.requests import Request
+
+import ray
+from ray import serve
+
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+
+@serve.deployment(num_replicas=2, ray_actor_options={"num_cpus": 0.2, "num_gpus": 0})
+class Translator:
+    def __init__(self):
+        # Load model
+        self.tokenizer = AutoTokenizer.from_pretrained("t5-small")
+        self.model = AutoModelForSeq2SeqLM.from_pretrained("t5-small")
+
+    def translate(self, text: str) -> str:
+        # Run inference
+        input_ids = self.tokenizer(
+            f"translate English to French: {text}", return_tensors="pt"
+        ).input_ids
+        output_ids = self.model.generate(
+            input_ids, num_beams=4, early_stopping=True, max_length=300
+        )
+
+        # Post-process output to return only the translation text
+        translation = self.tokenizer.decode(
+            output_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=False
+        )
+
+        return translation
+
+    async def __call__(self, http_request: Request) -> str:
+        english_text: str = await http_request.json()
+        return self.translate(english_text)
+
+
+translator_app = Translator.bind()
+# __deployment_full_end__
+
+translator_app = Translator.options(ray_actor_options={}).bind()
+serve.run(translator_app)
+
+import requests
+
+response = requests.post("http://127.0.0.1:8000/", json="Hello world!").text
+assert response == "Bonjour monde!"
+
+serve.shutdown()
+ray.shutdown()

doc/source/serve/doc_code/getting_started/models.py

@@ -0,0 +1,83 @@
+# flake8: noqa
+
+# __start_translation_model__
+# File name: model.py
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+
+class Translator:
+    def __init__(self):
+        # Load model
+        self.tokenizer = AutoTokenizer.from_pretrained("t5-small")
+        self.model = AutoModelForSeq2SeqLM.from_pretrained("t5-small")
+
+    def translate(self, text: str) -> str:
+        # Run inference
+        input_ids = self.tokenizer(
+            f"translate English to French: {text}", return_tensors="pt"
+        ).input_ids
+        output_ids = self.model.generate(
+            input_ids, num_beams=4, early_stopping=True, max_length=300
+        )
+
+        # Post-process output to return only the translation text
+        translation = self.tokenizer.decode(
+            output_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=False
+        )
+
+        return translation
+
+
+translator = Translator()
+
+translation = translator.translate("Hello world!")
+print(translation)
+# __end_translation_model__
+
+# Test model behavior
+assert translation == "Bonjour monde!"
+
+
+# __start_summarization_model__
+# File name: summary_model.py
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+
+class Summarizer:
+    def __init__(self):
+        # Load model
+        self.tokenizer = AutoTokenizer.from_pretrained("t5-small")
+        self.model = AutoModelForSeq2SeqLM.from_pretrained("t5-small")
+
+    def summarize(self, text: str) -> str:
+        # Run inference
+        input_ids = self.tokenizer(f"summarize: {text}", return_tensors="pt").input_ids
+        output_ids = self.model.generate(
+            input_ids,
+            num_beams=4,
+            early_stopping=True,
+            length_penalty=2.0,
+            no_repeat_ngram_size=3,
+            min_length=5,
+            max_length=15,
+        )
+
+        # Post-process output to return only the summary text
+        summary = self.tokenizer.decode(
+            output_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=False
+        )
+
+        return summary
+
+
+summarizer = Summarizer()
+
+summary = summarizer.summarize(
+    "It was the best of times, it was the worst of times, it was the age "
+    "of wisdom, it was the age of foolishness, it was the epoch of belief"
+)
+print(summary)
+# __end_summarization_model__
+
+# Test model behavior
+assert summary == "it was the best of times, it was worst of times ."

doc/source/serve/doc_code/getting_started/translator.py

@@ -0,0 +1,91 @@
+# flake8: noqa
+
+# __start_graph__
+# File name: serve_quickstart_composed.py
+from starlette.requests import Request
+
+import ray
+from ray import serve
+from ray.serve.handle import DeploymentHandle
+
+from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
+
+
+@serve.deployment
+class Translator:
+    def __init__(self):
+        # Load model
+        self.tokenizer = AutoTokenizer.from_pretrained("t5-small")
+        self.model = AutoModelForSeq2SeqLM.from_pretrained("t5-small")
+
+    def translate(self, text: str) -> str:
+        # Run inference
+        input_ids = self.tokenizer(
+            f"translate English to French: {text}", return_tensors="pt"
+        ).input_ids
+        output_ids = self.model.generate(
+            input_ids, num_beams=4, early_stopping=True, max_length=300
+        )
+
+        # Post-process output to return only the translation text
+        translation = self.tokenizer.decode(
+            output_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=False
+        )
+
+        return translation
+
+
+@serve.deployment
+class Summarizer:
+    def __init__(self, translator: DeploymentHandle):
+        self.translator = translator
+
+        # Load model.
+        self.tokenizer = AutoTokenizer.from_pretrained("t5-small")
+        self.model = AutoModelForSeq2SeqLM.from_pretrained("t5-small")
+
+    def summarize(self, text: str) -> str:
+        # Run inference
+        input_ids = self.tokenizer(f"summarize: {text}", return_tensors="pt").input_ids
+        output_ids = self.model.generate(
+            input_ids, num_beams=4, early_stopping=True, max_length=15
+        )
+
+        # Post-process output to return only the summary text
+        summary = self.tokenizer.decode(
+            output_ids[0], skip_special_tokens=True, clean_up_tokenization_spaces=False
+        )
+
+        return summary
+
+    async def __call__(self, http_request: Request) -> str:
+        english_text: str = await http_request.json()
+        summary = self.summarize(english_text)
+
+        translation = await self.translator.translate.remote(summary)
+        return translation
+
+
+app = Summarizer.bind(Translator.bind())
+# __end_graph__
+
+serve.run(app)
+
+# __start_client__
+# File name: composed_client.py
+import requests
+
+english_text = (
+    "It was the best of times, it was the worst of times, it was the age "
+    "of wisdom, it was the age of foolishness, it was the epoch of belief"
+)
+response = requests.post("http://127.0.0.1:8000/", json=english_text)
+french_text = response.text
+
+print(french_text)
+# __end_client__
+
+assert french_text == "C'était le meilleur des temps, c'était le pire des temps,"
+
+serve.shutdown()
+ray.shutdown()