vLLM Embedder

from agno.knowledge.embedder.vllm import VLLMEmbedder

# Local mode: vLLM loads the model in-process
embedder = VLLMEmbedder(
    id="sentence-transformers/all-MiniLM-L6-v2",
    dimensions=384,
    enforce_eager=True,
    vllm_kwargs={
        "disable_sliding_window": True,
        "max_model_len": 256,
    },
)
embedding = embedder.get_embedding("The quick brown fox jumps over the lazy dog.")

print(embedding[:5])
print(len(embedding))

# Remote mode: connect to a running vLLM server
remote_embedder = VLLMEmbedder(
    id="sentence-transformers/all-MiniLM-L6-v2",
    dimensions=384,
    base_url="http://localhost:8000/v1",
    api_key="your-api-key",  # optional, also read from VLLM_API_KEY
)