File size: 2,272 Bytes
dfd6145 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 |
from smolagents import (
CodeAgent,
InferenceClientModel,
LiteLLMModel,
OpenAIServerModel,
ToolCallingAgent,
TransformersModel,
tool,
)
# Choose which inference type to use!
available_inferences = ["inference_client", "transformers", "ollama", "litellm", "openai"]
chosen_inference = "inference_client"
print(f"Chose model: '{chosen_inference}'")
if chosen_inference == "inference_client":
model = InferenceClientModel(model_id="meta-llama/Llama-3.3-70B-Instruct", provider="nebius")
elif chosen_inference == "transformers":
model = TransformersModel(model_id="HuggingFaceTB/SmolLM2-1.7B-Instruct", device_map="auto", max_new_tokens=1000)
elif chosen_inference == "ollama":
model = LiteLLMModel(
model_id="ollama_chat/llama3.2",
api_base="http://localhost:11434", # replace with remote open-ai compatible server if necessary
api_key="your-api-key", # replace with API key if necessary
num_ctx=8192, # ollama default is 2048 which will often fail horribly. 8192 works for easy tasks, more is better. Check https://huggingface.co/spaces/NyxKrage/LLM-Model-VRAM-Calculator to calculate how much VRAM this will need for the selected model.
)
elif chosen_inference == "litellm":
# For anthropic: change model_id below to 'anthropic/claude-3-5-sonnet-latest'
model = LiteLLMModel(model_id="gpt-4o")
elif chosen_inference == "openai":
# For anthropic: change model_id below to 'anthropic/claude-3-5-sonnet-latest'
model = OpenAIServerModel(model_id="gpt-4o")
@tool
def get_weather(location: str, celsius: bool | None = False) -> str:
"""
Get weather in the next days at given location.
Secretly this tool does not care about the location, it hates the weather everywhere.
Args:
location: the location
celsius: the temperature
"""
return "The weather is UNGODLY with torrential rains and temperatures below -10°C"
agent = ToolCallingAgent(tools=[get_weather], model=model, verbosity_level=2)
print("ToolCallingAgent:", agent.run("What's the weather like in Paris?"))
agent = CodeAgent(tools=[get_weather], model=model, verbosity_level=2, stream_outputs=True)
print("CodeAgent:", agent.run("What's the weather like in Paris?"))
|