langchain/docs/ecosystem/comet_tracking.ipynb

Comet

In this guide we will demonstrate how to track your Langchain Experiments, Evaluation Metrics, and LLM Sessions with Comet.

Example Project: Comet with LangChain

Install Comet and Dependencies

In [ ]:

!pip install comet_ml
!pip install langchain
!pip install openai
!pip install google-search-results

Initialize Comet and Set your Credentials

You can grab your Comet API Key here or click the link after intializing Comet

In [ ]:

import comet_ml

comet_ml.init(project_name="comet-example-langchain")

Set OpenAI and SerpAPI credentials

You will need an OpenAI API Key and a SerpAPI API Key to run the following examples

In [ ]:

import os

%env OPENAI_API_KEY="..."
%env SERPAPI_API_KEY="..."

Scenario 1: Using just an LLM

In [ ]:

from datetime import datetime

from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler
from langchain.callbacks.base import CallbackManager
from langchain.llms import OpenAI

comet_callback = CometCallbackHandler(
    project_name="comet-example-langchain",
    complexity_metrics=True,
    stream_logs=True,
    tags=["llm"],
    visualizations=["dep"],
)
manager = CallbackManager([StdOutCallbackHandler(), comet_callback])
llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)

llm_result = llm.generate(["Tell me a joke", "Tell me a poem", "Tell me a fact"] * 3)
print("LLM result", llm_result)
comet_callback.flush_tracker(llm, finish=True)

Scenario 2: Using an LLM in a Chain

In [ ]:

from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler
from langchain.callbacks.base import CallbackManager
from langchain.chains import LLMChain
from langchain.llms import OpenAI
from langchain.prompts import PromptTemplate

comet_callback = CometCallbackHandler(
    complexity_metrics=True,
    project_name="comet-example-langchain",
    stream_logs=True,
    tags=["synopsis-chain"],
)
manager = CallbackManager([StdOutCallbackHandler(), comet_callback])

llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)

template = """You are a playwright. Given the title of play, it is your job to write a synopsis for that title.
Title: {title}
Playwright: This is a synopsis for the above play:"""
prompt_template = PromptTemplate(input_variables=["title"], template=template)
synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)

test_prompts = [{"title": "Documentary about Bigfoot in Paris"}]
synopsis_chain.apply(test_prompts)
comet_callback.flush_tracker(synopsis_chain, finish=True)

Scenario 3: Using An Agent with Tools

In [ ]:

from langchain.agents import initialize_agent, load_tools
from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler
from langchain.callbacks.base import CallbackManager
from langchain.llms import OpenAI

comet_callback = CometCallbackHandler(
    project_name="comet-example-langchain",
    complexity_metrics=True,
    stream_logs=True,
    tags=["agent"],
)
manager = CallbackManager([StdOutCallbackHandler(), comet_callback])
llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)

tools = load_tools(["serpapi", "llm-math"], llm=llm, callback_manager=manager)
agent = initialize_agent(
    tools,
    llm,
    agent="zero-shot-react-description",
    callback_manager=manager,
    verbose=True,
)
agent.run(
    "Who is Leo DiCaprio's girlfriend? What is her current age raised to the 0.43 power?"
)
comet_callback.flush_tracker(agent, finish=True)

Scenario 4: Using Custom Evaluation Metrics

The CometCallbackManager also allows you to define and use Custom Evaluation Metrics to assess generated outputs from your model. Let's take a look at how this works.

In the snippet below, we will use the ROUGE metric to evaluate the quality of a generated summary of an input prompt.

In [ ]:

!pip install rouge-score

In [ ]:

from rouge_score import rouge_scorer

from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler
from langchain.callbacks.base import CallbackManager
from langchain.chains import LLMChain
from langchain.llms import OpenAI
from langchain.prompts import PromptTemplate


class Rouge:
    def __init__(self, reference):
        self.reference = reference
        self.scorer = rouge_scorer.RougeScorer(["rougeLsum"], use_stemmer=True)

    def compute_metric(self, generation, prompt_idx, gen_idx):
        prediction = generation.text
        results = self.scorer.score(target=self.reference, prediction=prediction)

        return {
            "rougeLsum_score": results["rougeLsum"].fmeasure,
            "reference": self.reference,
        }


reference = """
The tower is 324 metres (1,063 ft) tall, about the same height as an 81-storey building.
It was the first structure to reach a height of 300 metres.

It is now taller than the Chrysler Building in New York City by 5.2 metres (17 ft)
Excluding transmitters, the Eiffel Tower is the second tallest free-standing structure in France .
"""
rouge_score = Rouge(reference=reference)

template = """Given the following article, it is your job to write a summary.
Article:
{article}
Summary: This is the summary for the above article:"""
prompt_template = PromptTemplate(input_variables=["article"], template=template)

comet_callback = CometCallbackHandler(
    project_name="comet-example-langchain",
    complexity_metrics=False,
    stream_logs=True,
    tags=["custom_metrics"],
    custom_metrics=rouge_score.compute_metric,
)
manager = CallbackManager([StdOutCallbackHandler(), comet_callback])
llm = OpenAI(temperature=0.9, callback_manager=manager, verbose=True)

synopsis_chain = LLMChain(llm=llm, prompt=prompt_template, callback_manager=manager)

test_prompts = [
    {
        "article": """
                 The tower is 324 metres (1,063 ft) tall, about the same height as
                 an 81-storey building, and the tallest structure in Paris. Its base is square,
                 measuring 125 metres (410 ft) on each side.
                 During its construction, the Eiffel Tower surpassed the
                 Washington Monument to become the tallest man-made structure in the world,
                 a title it held for 41 years until the Chrysler Building
                 in New York City was finished in 1930.

                 It was the first structure to reach a height of 300 metres.
                 Due to the addition of a broadcasting aerial at the top of the tower in 1957,
                 it is now taller than the Chrysler Building by 5.2 metres (17 ft).

                 Excluding transmitters, the Eiffel Tower is the second tallest
                 free-standing structure in France after the Millau Viaduct.
                 """
    }
]
synopsis_chain.apply(test_prompts)
comet_callback.flush_tracker(synopsis_chain, finish=True)