%pip install langfuse 'smolagents[telemetry]' openinference-instrumentation-smolagents datasets 'smolagents[gradio]' gradio --upgrade

import os
# Get keys for your project from the project settings page: https://cloud.langfuse.com
os.environ["LANGFUSE_PUBLIC_KEY"] = "pk-lf-..." 
os.environ["LANGFUSE_SECRET_KEY"] = "sk-lf-..." 
os.environ["LANGFUSE_HOST"] = "https://cloud.langfuse.com" # 🇪🇺 EU region
# os.environ["LANGFUSE_HOST"] = "https://us.cloud.langfuse.com" # 🇺🇸 US region

# Set your Hugging Face and other tokens/secrets as environment variable
os.environ["HF_TOKEN"] = "hf_..." 

from langfuse import get_client
 
langfuse = get_client()
 
# Verify connection
if langfuse.auth_check():
    print("Langfuse client is authenticated and ready!")
else:
    print("Authentication failed. Please check your credentials and host.")

from openinference.instrumentation.smolagents import SmolagentsInstrumentor
 
SmolagentsInstrumentor().instrument()

from smolagents import InferenceClientModel, CodeAgent

# Create a simple agent to test instrumentation
agent = CodeAgent(
    tools=[],
    model=InferenceClientModel()
)

agent.run("1+1=")

from smolagents import (CodeAgent, DuckDuckGoSearchTool, InferenceClientModel)

search_tool = DuckDuckGoSearchTool()
agent = CodeAgent(tools=[search_tool], model=InferenceClientModel())

agent.run("How many Rubik's Cubes could you fit inside the Notre Dame Cathedral?")

from smolagents import (CodeAgent, DuckDuckGoSearchTool, InferenceClientModel)

search_tool = DuckDuckGoSearchTool()
agent = CodeAgent(
    tools=[search_tool],
    model=InferenceClientModel()
)

with langfuse.start_as_current_span(
    name="Smolagent-Trace",
    ) as span:
    
    # Run your application here
    response = agent.run("What is the capital of Germany?")
 
    # Pass additional attributes to the span
    span.update_trace(
        input="What is the capital of Germany?",
        output=response,
        user_id="smolagent-user-123",
        session_id="smolagent-session-123456789",
        tags=["city-question", "testing-agents"],
        metadata={"email": "user@langfuse.com"},
        )
 
# Flush events in short-lived applications
langfuse.flush()

import gradio as gr
from smolagents import (CodeAgent, InferenceClientModel)
from langfuse import get_client

langfuse = get_client()

model = InferenceClientModel()
agent = CodeAgent(tools=[], model=model, add_base_tools=True)

trace_id = None

def respond(prompt, history):
    with langfuse.start_as_current_span(
        name="Smolagent-Trace"):
        
        # Run your application here
        output = agent.run(prompt)

        global trace_id
        trace_id = langfuse.get_current_trace_id()

    history.append({"role": "assistant", "content": str(output)})
    return history

def handle_like(data: gr.LikeData):
    # For demonstration, we map user feedback to a 1 (like) or 0 (dislike)
    if data.liked:
        langfuse.create_score(
            value=1,
            name="user-feedback",
            trace_id=trace_id
        )
    else:
        langfuse.create_score(
            value=0,
            name="user-feedback",
            trace_id=trace_id
        )

with gr.Blocks() as demo:
    chatbot = gr.Chatbot(label="Chat", type="messages")
    prompt_box = gr.Textbox(placeholder="Type your message...", label="Your message")

    # When the user presses 'Enter' on the prompt, we run 'respond'
    prompt_box.submit(
        fn=respond,
        inputs=[prompt_box, chatbot],
        outputs=chatbot
    )

    # When the user clicks a 'like' button on a message, we run 'handle_like'
    chatbot.like(handle_like, None, None)

demo.launch()

# Example: Checking if the agent’s output is toxic or not.
from smolagents import (CodeAgent, DuckDuckGoSearchTool, InferenceClientModel)

search_tool = DuckDuckGoSearchTool()
agent = CodeAgent(tools=[search_tool], model=InferenceClientModel())

agent.run("Can eating carrots improve your vision?")

import pandas as pd
from datasets import load_dataset

# Fetch GSM8K from Hugging Face
dataset = load_dataset("openai/gsm8k", 'main', split='train')
df = pd.DataFrame(dataset)
print("First few rows of GSM8K dataset:")
print(df.head())

from langfuse import get_client
langfuse = get_client()

langfuse_dataset_name = "gsm8k_dataset_huggingface"

# Create a dataset in Langfuse
langfuse.create_dataset(
    name=langfuse_dataset_name,
    description="GSM8K benchmark dataset uploaded from Huggingface",
    metadata={
        "date": "2025-03-10", 
        "type": "benchmark"
    }
)

for idx, row in df.iterrows():
    langfuse.create_dataset_item(
        dataset_name=langfuse_dataset_name,
        input={"text": row["question"]},
        expected_output={"text": row["answer"]},
        metadata={"source_index": idx}
    )
    if idx >= 9: # Upload only the first 10 items for demonstration
        break

from opentelemetry.trace import format_trace_id
from smolagents import (CodeAgent, InferenceClientModel, LiteLLMModel)
from langfuse import get_client
 
langfuse = get_client()


# Example: using InferenceClientModel or LiteLLMModel to access openai, anthropic, gemini, etc. models:
model = InferenceClientModel()

agent = CodeAgent(
    tools=[],
    model=model,
    add_base_tools=True
)

dataset_name = "gsm8k_dataset_huggingface"
current_run_name = "smolagent-notebook-run-01" # Identifies this specific evaluation run
 
# Assume 'run_smolagent' is your instrumented application function
def run_smolagent(question):
    with langfuse.start_as_current_generation(name="qna-llm-call") as generation:
        # Simulate LLM call
        result = agent.run(question)
 
        # Update the trace with the input and output
        generation.update_trace(
            input= question,
            output=result,
        )
 
        return result
 
dataset = langfuse.get_dataset(name=dataset_name) # Fetch your pre-populated dataset
 
for item in dataset.items:
 
    # Use the item.run() context manager
    with item.run(
        run_name=current_run_name,
        run_metadata={"model_provider": "Hugging Face", "temperature_setting": 0.7},
        run_description="Evaluation run for GSM8K dataset"
    ) as root_span: # root_span is the root span of the new trace for this item and run.
        # All subsequent langfuse operations within this block are part of this trace.
 
        # Call your application logic
        generated_answer = run_smolagent(question=item.input["text"])
 
        print(item.input)