Tracking Large Language Models (LLM) with MLflow : A Complete Guide

pip install mlflow>=2.8.1
pip install openai
pip install chromadb==0.4.15
pip install langchain==0.0.348
pip install tiktoken
pip install 'mlflow[genai]'
pip install databricks-sdk --upgrade

import mlflow
import chromadb

print(f"MLflow version: {mlflow.__version__}")
print(f"ChromaDB version: {chromadb.__version__}")

import mlflow
import openai

def query_llm(prompt, max_tokens=100):
    response = openai.Completion.create(
        engine="text-davinci-002",
        prompt=prompt,
        max_tokens=max_tokens
    )
    return response.choices[0].text.strip()

with mlflow.start_run():
    prompt = "Explain the concept of machine learning in simple terms."
    
    # Log parameters
    mlflow.log_param("model", "text-davinci-002")
    mlflow.log_param("max_tokens", 100)
    
    # Query the LLM and log the result
    result = query_llm(prompt)
    mlflow.log_metric("response_length", len(result))
    
    # Log the prompt and response
    mlflow.log_table("prompt_responses", {"prompt": [prompt], "response": [result]})
    
    print(f"Response: {result}")

import mlflow
from mlflow.deployments import get_deploy_client

# Initialize the deployment client
client = get_deploy_client("databricks")

# Define the endpoint configuration
endpoint_name = "llm-endpoint"
endpoint_config = {
    "served_entities": [{
        "name": "gpt-model",
        "external_model": {
            "name": "gpt-3.5-turbo",
            "provider": "openai",
            "task": "llm/v1/completions",
            "openai_config": {
                "openai_api_type": "azure",
                "openai_api_key": "{{secrets/scope/openai_api_key}}",
                "openai_api_base": "{{secrets/scope/openai_api_base}}",
                "openai_deployment_name": "gpt-35-turbo",
                "openai_api_version": "2023-05-15",
            },
        },
    }],
}

# Create the endpoint
client.create_endpoint(name=endpoint_name, config=endpoint_config)

<div class="relative flex flex-col rounded-lg">

response = client.predict(
endpoint=endpoint_name,
inputs={"prompt": "Explain the concept of neural networks briefly.","max_tokens": 100,},)

print(response)

This will send a prompt to our deployed model and return the generated response.

Evaluating LLMs with MLflow

Evaluation is crucial for understanding the performance and behavior of your LLMs. MLflow provides comprehensive tools for evaluating LLMs, including both built-in and custom metrics.

Preparing Your LLM for Evaluation

To evaluate your LLM with mlflow.evaluate(), your model needs to be in one of these forms:

1. An mlflow.pyfunc.PyFuncModel instance or a URI pointing to a logged MLflow model.
2. A Python function that takes string inputs and outputs a single string.
3. An MLflow Deployments endpoint URI.
4. Set model=None and include model outputs in the evaluation data.

Let’s look at an example using a logged MLflow model:

import mlflow
import openai

with mlflow.start_run():
    system_prompt = "Answer the following question concisely."
    logged_model_info = mlflow.openai.log_model(
        model="gpt-3.5-turbo",
        task=openai.chat.completions,
        artifact_path="model",
        messages=[
            {"role": "system", "content": system_prompt},
            {"role": "user", "content": "{question}"},
        ],
    )

# Prepare evaluation data
eval_data = pd.DataFrame({
    "question": ["What is machine learning?", "Explain neural networks."],
    "ground_truth": [
        "Machine learning is a subset of AI that enables systems to learn and improve from experience without explicit programming.",
        "Neural networks are computing systems inspired by biological neural networks, consisting of interconnected nodes that process and transmit information."
    ]
})

# Evaluate the model
results = mlflow.evaluate(
    logged_model_info.model_uri,
    eval_data,
    targets="ground_truth",
    model_type="question-answering",
)

print(f"Evaluation metrics: {results.metrics}")

This example logs an OpenAI model, prepares evaluation data, and then evaluates the model using MLflow’s built-in metrics for question-answering tasks.

Custom Evaluation Metrics

MLflow allows you to define custom metrics for LLM evaluation. Here’s an example of creating a custom metric for evaluating the professionalism of responses:

from mlflow.metrics.genai import EvaluationExample, make_genai_metric

professionalism = make_genai_metric(
    name="professionalism",
    definition="Measure of formal and appropriate communication style.",
    grading_prompt=(
        "Score the professionalism of the answer on a scale of 0-4:\n"
        "0: Extremely casual or inappropriate\n"
        "1: Casual but respectful\n"
        "2: Moderately formal\n"
        "3: Professional and appropriate\n"
        "4: Highly formal and expertly crafted"
    ),
    examples=[
        EvaluationExample(
            input="What is MLflow?",
            output="MLflow is like your friendly neighborhood toolkit for managing ML projects. It's super cool!",
            score=1,
            justification="The response is casual and uses informal language."
        ),
        EvaluationExample(
            input="What is MLflow?",
            output="MLflow is an open-source platform for the machine learning lifecycle, including experimentation, reproducibility, and deployment.",
            score=4,
            justification="The response is formal, concise, and professionally worded."
        )
    ],
    model="openai:/gpt-3.5-turbo-16k",
    parameters={"temperature": 0.0},
    aggregations=["mean", "variance"],
    greater_is_better=True,
)

# Use the custom metric in evaluation
results = mlflow.evaluate(
    logged_model_info.model_uri,
    eval_data,
    targets="ground_truth",
    model_type="question-answering",
    extra_metrics=[professionalism]
)

print(f"Professionalism score: {results.metrics['professionalism_mean']}")

This custom metric uses GPT-3.5-turbo to score the professionalism of responses, demonstrating how you can leverage LLMs themselves for evaluation.

Advanced LLM Evaluation Techniques

As LLMs become more sophisticated, so do the techniques for evaluating them. Let’s explore some advanced evaluation methods using MLflow.

Retrieval-Augmented Generation (RAG) Evaluation

RAG systems combine the power of retrieval-based and generative models. Evaluating RAG systems requires assessing both the retrieval and generation components. Here’s how you can set up a RAG system and evaluate it using MLflow:

from langchain.document_loaders import WebBaseLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.chains import RetrievalQA
from langchain.llms import OpenAI

# Load and preprocess documents
loader = WebBaseLoader(["https://mlflow.org/docs/latest/index.html"])
documents = loader.load()
text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=0)
texts = text_splitter.split_documents(documents)

# Create vector store
embeddings = OpenAIEmbeddings()
vectorstore = Chroma.from_documents(texts, embeddings)

# Create RAG chain
llm = OpenAI(temperature=0)
qa_chain = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=vectorstore.as_retriever(),
    return_source_documents=True
)

# Evaluation function
def evaluate_rag(question):
    result = qa_chain({"query": question})
    return result["result"], [doc.page_content for doc in result["source_documents"]]

# Prepare evaluation data
eval_questions = [
    "What is MLflow?",
    "How does MLflow handle experiment tracking?",
    "What are the main components of MLflow?"
]

# Evaluate using MLflow
with mlflow.start_run():
    for question in eval_questions:
        answer, sources = evaluate_rag(question)
        
        mlflow.log_param(f"question", question)
        mlflow.log_metric("num_sources", len(sources))
        mlflow.log_text(answer, f"answer_{question}.txt")
        
        for i, source in enumerate(sources):
            mlflow.log_text(source, f"source_{question}_{i}.txt")

    # Log custom metrics
    mlflow.log_metric("avg_sources_per_question", sum(len(evaluate_rag(q)[1]) for q in eval_questions) / len(eval_questions))