llama-stack-mirror/examples/agent.py
Antony Sallas 17e74251e2 updated with vllm based values
rh-pre-commit.version: 2.3.2
rh-pre-commit.check-secrets: ENABLED
2025-10-22 18:20:32 +08:00

40 lines
No EOL
1.2 KiB
Python

from llama_stack_client import LlamaStackClient
from llama_stack_client import Agent, AgentEventLogger
from rich.pretty import pprint
import uuid
client = LlamaStackClient(base_url=f"http://localhost:8321",
default_headers={
"X-Telemetry-Service": "llama-stack-agent",
"X-Telemetry-Version": "1.0.0",
})
models = client.models.list()
llm = next(m for m in models if m.model_type == "llm" and m.provider_id == "vllm")
model_id = llm.identifier
agent = Agent(client, model=model_id, instructions="You are a helpful assistant.")
s_id = agent.create_session(session_name=f"s{uuid.uuid4().hex}")
print("Non-streaming ...")
response = agent.create_turn(
messages=[{"role": "user", "content": "Who are you?"}],
session_id=s_id,
stream=False,
)
print("agent>", response.output_message.content)
print("Streaming ...")
stream = agent.create_turn(
messages=[{"role": "user", "content": "Who are you?"}], session_id=s_id, stream=True
)
for event in stream:
pprint(event)
print("Streaming with print helper...")
stream = agent.create_turn(
messages=[{"role": "user", "content": "Who are you?"}], session_id=s_id, stream=True
)
for event in AgentEventLogger().log(stream):
event.print()