test.py

from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI
import os
from dotenv import load_dotenv

# Load the .env file
load_dotenv()

# Retrieve HF_TOKEN from the environment variables
hf_token = os.getenv("HF_TOKEN")
gemini_api_key = os.getenv("GEMINI_API_KEY");


model = LiteLLMModel(
    model_id="gemini/gemini-2.5-flash",
    temperature=0.2
)

agent = CodeAgent(
    tools=[query_market_asset], 
    model=model,
    max_steps=5
)

llm = HuggingFaceInferenceAPI(
    model_name="Qwen/Qwen2.5-Coder-32B-Instruct",
    temperature=0.7,
    max_tokens=100,
    token=hf_token,
    provider="auto"
)

response = llm.complete("Hello, how are you?")
print(response)
# I am good, how can I help you today?