From c3b5d86ff0266816492b1c609bda0c3a6337dcce Mon Sep 17 00:00:00 2001
From: Chang Su <chang.s.su@oracle.com>
Date: Wed, 24 Jul 2024 22:48:07 -0700
Subject: [PATCH] [Bugfix] Fix encoding_format in
 examples/openai_embedding_client.py (#6755)

---
 examples/openai_embedding_client.py        | 13 ++++++++-----
 tests/entrypoints/openai/test_embedding.py |  1 -
 2 files changed, 8 insertions(+), 6 deletions(-)

diff --git a/examples/openai_embedding_client.py b/examples/openai_embedding_client.py
index b73360fe15a24..b4f4c7ad6beb2 100644
--- a/examples/openai_embedding_client.py
+++ b/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
diff --git a/tests/entrypoints/openai/test_embedding.py b/tests/entrypoints/openai/test_embedding.py
index 2ca0c0d63c25c..c9747339bbf15 100644
--- a/tests/entrypoints/openai/test_embedding.py
+++ b/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: