[Frontend] add `add_request_id` middleware (#9594)

Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>

docs/source/serving/openai_compatible_server.md

@@ -62,6 +62,32 @@ completion = client.chat.completions.create(
 )
 ```
 
+### Extra HTTP Headers
+
+Only `X-Request-Id` HTTP request header is supported for now.
+
+```python
+completion = client.chat.completions.create(
+  model="NousResearch/Meta-Llama-3-8B-Instruct",
+  messages=[
+    {"role": "user", "content": "Classify this sentiment: vLLM is wonderful!"}
+  ],
+  extra_headers={
+    "x-request-id": "sentiment-classification-00001",
+  }
+)
+print(completion._request_id)
+
+completion = client.completions.create(
+  model="NousResearch/Meta-Llama-3-8B-Instruct",
+  prompt="A robot may not injure a human being",
+  extra_headers={
+    "x-request-id": "completion-test",
+  }
+)
+print(completion._request_id)
+```
+
 ### Extra Parameters for Completions API
 
 The following [sampling parameters (click through to see documentation)](../dev/sampling_params.rst) are supported.

vllm/entrypoints/openai/api_server.py

@@ -7,6 +7,7 @@ import re
 import signal
 import socket
 import tempfile
+import uuid
 from argparse import Namespace
 from contextlib import asynccontextmanager
 from functools import partial
@@ -475,6 +476,13 @@ def build_app(args: Namespace) -> FastAPI:
                                     status_code=401)
             return await call_next(request)
 
+    @app.middleware("http")
+    async def add_request_id(request: Request, call_next):
+        request_id = request.headers.get("X-Request-Id") or uuid.uuid4().hex
+        response = await call_next(request)
+        response.headers["X-Request-Id"] = request_id
+        return response
+
     for middleware in args.middleware:
         module_path, object_name = middleware.rsplit(".", 1)
         imported = getattr(importlib.import_module(module_path), object_name)