[Bugfix] Fix encoding_format in examples/openai_embedding_client.py (v…

…llm-project#6755)

examples/openai_embedding_client.py

@@ -13,11 +13,14 @@
 models = client.models.list()
 model = models.data[0].id
 
-responses = client.embeddings.create(input=[
-    "Hello my name is",
-    "The best thing about vLLM is that it supports many different models"
-],
-                                     model=model)
+responses = client.embeddings.create(
+    input=[
+        "Hello my name is",
+        "The best thing about vLLM is that it supports many different models"
+    ],
+    model=model,
+    encoding_format="float",
+)
 
 for data in responses.data:
     print(data.embedding)  # list of float of len 4096

tests/entrypoints/openai/test_embedding.py

@@ -18,7 +18,6 @@ def embedding_server():
         "--enforce-eager",
         "--max-model-len",
         "8192",
-        "--enforce-eager",
     ]
 
     with RemoteOpenAIServer(EMBEDDING_MODEL_NAME, args) as remote_server: