A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 16, 20:45 UTC
[Bugfix] Fix encoding_format in examples/openai_embedding_client.py (#6755)
Chang Su committed
Jul 24, 2024 at 22:48 UTC
316a41ac1de4e6e46933cadb39b9b7af65b01abd
2 files changed
+8
-6
examples/openai_embedding_client.py
+8
-5
@@ -13,11 +13,14 @@ client = OpenAI(
13
models = client.models.list()
14
model = models.data[0].id
15
16
-responses = client.embeddings.create(input=[
17
- "Hello my name is",
18
- "The best thing about vLLM is that it supports many different models"
19
-],
20
- model=model)
16
+responses = client.embeddings.create(
17
+ input=[
18
+ "Hello my name is",
19
+ "The best thing about vLLM is that it supports many different models"
20
+ ],
21
+ model=model,
22
+ encoding_format="float",
23
+)
24
25
for data in responses.data:
26
print(data.embedding) # list of float of len 4096
tests/entrypoints/openai/test_embedding.py
-1
@@ -18,7 +18,6 @@ def embedding_server():
18
"--enforce-eager",
19
"--max-model-len",
20
"8192",
21
- "--enforce-eager",
21
]
22
23
with RemoteOpenAIServer(EMBEDDING_MODEL_NAME, args) as remote_server: