chore: import upstream snapshot with attribution

2026-07-13 12:38:16 +08:00
commit 94057c3d3e
7152 changed files with 2120455 additions and 0 deletions
@@ -0,0 +1,83 @@
+"""
+Usage:
+export ORCAROUTER_API_KEY=sk-orca-******
+python3 orcarouter_example_chat.py
+"""
+
+import os
+
+import sglang as sgl
+
+
+@sgl.function
+def multi_turn_question(s, question_1, question_2):
+    s += sgl.system("You are a helpful assistant.")
+    s += sgl.user(question_1)
+    s += sgl.assistant(sgl.gen("answer_1", max_tokens=256))
+    s += sgl.user(question_2)
+    s += sgl.assistant(sgl.gen("answer_2", max_tokens=256))
+
+
+def single():
+    state = multi_turn_question.run(
+        question_1="What is the capital of the United States?",
+        question_2="List two local attractions.",
+    )
+
+    for m in state.messages():
+        print(m["role"], ":", m["content"])
+
+    print("\n-- answer_1 --\n", state["answer_1"])
+
+
+def stream():
+    state = multi_turn_question.run(
+        question_1="What is the capital of the United States?",
+        question_2="List two local attractions.",
+        stream=True,
+    )
+
+    for out in state.text_iter():
+        print(out, end="", flush=True)
+    print()
+
+
+def batch():
+    states = multi_turn_question.run_batch(
+        [
+            {
+                "question_1": "What is the capital of the United States?",
+                "question_2": "List two local attractions.",
+            },
+            {
+                "question_1": "What is the capital of France?",
+                "question_2": "What is the population of this city?",
+            },
+        ]
+    )
+
+    for s in states:
+        print(s.messages())
+
+
+if __name__ == "__main__":
+    # "orcarouter/auto" routes each request to a suitable model.
+    # See the full model list at https://www.orcarouter.ai/models
+    backend = sgl.OpenAI(
+        model_name="orcarouter/auto",
+        base_url="https://api.orcarouter.ai/v1",
+        api_key=os.environ.get("ORCAROUTER_API_KEY"),
+    )
+    sgl.set_default_backend(backend)
+
+    # Run a single request
+    print("\n========== single ==========\n")
+    single()
+
+    # Stream output
+    print("\n========== stream ==========\n")
+    stream()
+
+    # Run a batch of requests
+    print("\n========== batch ==========\n")
+    batch()