Monitoring en ligne

!pip install streamlit pandas plotly weave

PROJECT_NAME = "wandb-smle/weave-cookboook-demo"
python
import weave

MODEL_NAMES = [
    # nom du modèle, coût du prompt, coût de la complétion
    ("gpt-4o-2024-05-13", 0.03, 0.06),
    ("gpt-4o-mini-2024-07-18", 0.03, 0.06),
    ("gemini/gemini-1.5-flash", 0.00025, 0.0005),
    ("gpt-4o-mini", 0.03, 0.06),
    ("gpt-4-turbo", 0.03, 0.06),
    ("claude-3-haiku-20240307", 0.01, 0.03),
    ("gpt-4o", 0.03, 0.06),
]

def init_weave_client(project_name):
    try:
        client = weave.init(project_name)
        for model, prompt_cost, completion_cost in MODEL_NAMES:
            client.add_cost(
                llm_id=model,
                prompt_token_cost=prompt_cost,
                completion_token_cost=completion_cost,
            )
    except Exception as e:
        print(f"Failed to initialize Weave client for project '{project_name}': {e}")
        return None
    else:
        return client

client = init_weave_client(PROJECT_NAME)

import itertools
from datetime import datetime, timedelta

import pandas as pd

def fetch_calls(client, project_id, start_time, trace_roots_only, limit):
    filter_params = {
        "project_id": project_id,
        "filter": {"started_at": start_time, "trace_roots_only": trace_roots_only},
        "expand_columns": ["inputs.example", "inputs.model"],
        "sort_by": [{"field": "started_at", "direction": "desc"}],
        "include_costs": True,
        "include_feedback": True,
    }
    try:
        calls_stream = client.server.calls_query_stream(filter_params)
        calls = list(
            itertools.islice(calls_stream, limit)
        )  # limiter le nombre d'appels à récupérer si trop nombreux
        print(f"Fetched {len(calls)} calls.")
    except Exception as e:
        print(f"Error fetching calls: {e}")
        return []
    else:
        return calls

calls = fetch_calls(client, PROJECT_NAME, datetime.now() - timedelta(days=1), True, 100)
python
# les données brutes sont une liste d'objets Call
pd.DataFrame([call.dict() for call in calls]).head(3)

import json
from datetime import datetime

import pandas as pd

def process_calls(calls):
    records = []
    for call in calls:
        feedback = call.summary.get("weave", {}).get("feedback", [])
        thumbs_up = sum(
            1
            for item in feedback
            if isinstance(item, dict) and item.get("payload", {}).get("emoji") == "👍"
        )
        thumbs_down = sum(
            1
            for item in feedback
            if isinstance(item, dict) and item.get("payload", {}).get("emoji") == "👎"
        )
        latency = call.summary.get("weave", {}).get("latency_ms", 0)

        records.append(
            {
                "Call ID": call.id,
                "Trace ID": call.trace_id,  # ID unique de la trace, utilisable pour la récupérer
                "Display Name": call.display_name,  # nom facultatif que vous pouvez définir dans l'interface utilisateur ou par programmation
                "Latency (ms)": latency,
                "Thumbs Up": thumbs_up,
                "Thumbs Down": thumbs_down,
                "Started At": pd.to_datetime(getattr(call, "started_at", datetime.min)),
                "Inputs": json.dumps(call.inputs, default=str),
                "Outputs": json.dumps(call.output, default=str),
            }
        )
    return pd.DataFrame(records)
python
df_calls = process_calls(calls)
df_calls.head(3)

# Utiliser l'API de coût pour obtenir les coûts
costs = client.query_costs()
df_costs = pd.DataFrame([cost.dict() for cost in costs])
df_costs["total_cost"] = (
    df_costs["prompt_token_cost"] + df_costs["completion_token_cost"]
)

# afficher uniquement la première ligne pour chaque llm_id unique
df_costs

import plotly.express as px
import plotly.graph_objects as go

def plot_feedback_pie_chart(thumbs_up, thumbs_down):
    fig = go.Figure(
        data=[
            go.Pie(
                labels=["Thumbs Up", "Thumbs Down"],
                values=[thumbs_up, thumbs_down],
                marker={"colors": ["#66b3ff", "#ff9999"]},
                hole=0.3,
            )
        ]
    )
    fig.update_traces(textinfo="percent+label", hoverinfo="label+percent")
    fig.update_layout(showlegend=False, title="Feedback Summary")
    return fig

def plot_model_cost_distribution(df):
    fig = px.bar(
        df,
        x="llm_id",
        y="total_cost",
        color="llm_id",
        title="Cost Distribution by Model",
    )
    fig.update_layout(xaxis_title="Model", yaxis_title="Cost (USD)")
    return fig

# Voir le code source pour tous les graphiques
python
plot_feedback_pie_chart(df_calls["Thumbs Up"].sum(), df_calls["Thumbs Down"].sum())
python
plot_model_cost_distribution(df_costs)