mirror of
https://git.datalinker.icu/vllm-project/vllm.git
synced 2025-12-09 04:45:01 +08:00
71b1c8b667
Signed-off-by: Yeshwanth Surya <yeshsurya@gmail.com> Signed-off-by: Yeshwanth N <yeshsurya@gmail.com> Signed-off-by: yeshsurya <yeshsurya@gmail.com>
52 lines
1.4 KiB
Python
52 lines
1.4 KiB
Python
# SPDX-License-Identifier: Apache-2.0
|
|
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
|
|
|
from argparse import Namespace
|
|
|
|
from vllm import LLM, EngineArgs
|
|
from vllm.utils.argparse_utils import FlexibleArgumentParser
|
|
|
|
|
|
def parse_args():
|
|
parser = FlexibleArgumentParser()
|
|
parser = EngineArgs.add_cli_args(parser)
|
|
# Set example specific arguments
|
|
parser.set_defaults(
|
|
model="intfloat/e5-small",
|
|
runner="pooling",
|
|
enforce_eager=True,
|
|
)
|
|
return parser.parse_args()
|
|
|
|
|
|
def main(args: Namespace):
|
|
# Sample prompts.
|
|
prompts = [
|
|
"Hello, my name is",
|
|
"The president of the United States is",
|
|
"The capital of France is",
|
|
"The future of AI is",
|
|
]
|
|
|
|
# Create an LLM.
|
|
# You should pass runner="pooling" for embedding models
|
|
llm = LLM(**vars(args))
|
|
|
|
# Generate embedding. The output is a list of EmbeddingRequestOutputs.
|
|
outputs = llm.embed(prompts)
|
|
|
|
# Print the outputs.
|
|
print("\nGenerated Outputs:\n" + "-" * 60)
|
|
for prompt, output in zip(prompts, outputs):
|
|
embeds = output.outputs.embedding
|
|
embeds_trimmed = (
|
|
(str(embeds[:16])[:-1] + ", ...]") if len(embeds) > 16 else embeds
|
|
)
|
|
print(f"Prompt: {prompt!r} \nEmbeddings: {embeds_trimmed} (size={len(embeds)})")
|
|
print("-" * 60)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
args = parse_args()
|
|
main(args)
|