[Bugfix]: Use float32 for base64 embedding (#7855)

Signed-off-by: Hollow Man <hollowman@opensuse.org>
This commit is contained in:
ℍ𝕠𝕝𝕝𝕠𝕨 𝕄𝕒𝕟
2024-08-26 03:16:38 +00:00
committed by GitHub
parent 1856aff4d6
commit 0b769992ec
3 changed files with 13 additions and 3 deletions
-1
View File
@@ -19,7 +19,6 @@ responses = client.embeddings.create(
"The best thing about vLLM is that it supports many different models"
],
model=model,
encoding_format="float",
)
for data in responses.data: