update getting started guide and add llm gateway and prompt gateway samples (#330)

model_server/app/main.py

@@ -220,6 +220,12 @@ async def hallucination(req: HallucinationRequest, res: Response):
     if "messages" in req.parameters:
         req.parameters.pop("messages")
 
+    if not req.parameters or len(req.parameters) == 0:
+        return {
+            "params_scores": {},
+            "model": req.model,
+        }
+
     candidate_labels = {f"{k} is {v}": k for k, v in req.parameters.items()}
 
     predictions = classifier(

model_server/pyproject.toml

@@ -29,7 +29,7 @@ openai = "1.50.2"
 tf-keras = "*"
 onnx = "1.17.0"
 onnxruntime = "1.19.2"
-httpx = "*"
+httpx = "0.27.2" # https://community.openai.com/t/typeerror-asyncclient-init-got-an-unexpected-keyword-argument-proxies/1040287
 pytest-asyncio = "*"
 pytest = "*"
 opentelemetry-api = "^1.28.0"