彗星

在本指南中，我们将演示如何使用Comet跟踪您的Langchain实验、评估指标和LLM会话。

示例项目： Comet与LangChain

安装Comet和依赖项

import sys
{sys.executable} -m spacy download en_core_web_sm

初始化Comet并设置您的凭据

您可以在此处获取您的Comet API密钥，或在初始化Comet后单击链接

import comet_ml

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

设置OpenAI和SerpAPI凭据

您需要一个OpenAI API密钥和一个SerpAPI API密钥来运行以下示例

import os

os.environ["OPENAI_API_KEY"] = "..."
# os.environ["OPENAI_ORGANIZATION"] = "..."
os.environ["SERPAPI_API_KEY"] = "..."

场景1：仅使用LLM

from datetime import datetime

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

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

场景2：在链中使用LLM

from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler
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"],
)
callbacks = [StdOutCallbackHandler(), comet_callback]
llm = OpenAI(temperature=0.9, callbacks=callbacks)

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, callbacks=callbacks)

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

场景3：使用带有工具的代理

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

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

tools = load_tools(["serpapi", "llm-math"], llm=llm, callbacks=callbacks)
agent = initialize_agent(
    tools,
    llm,
    agent="zero-shot-react-description",
    callbacks=callbacks,
    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)

场景4：使用自定义评估指标

CometCallbackManager还允许您定义和使用自定义评估指标来评估模型生成的输出质量。让我们看看这是如何工作的。

在下面的代码片段中，我们将使用ROUGE指标来评估生成的摘要的质量。

%pip install rouge-score

from rouge_score import rouge_scorer

from langchain.callbacks import CometCallbackHandler, StdOutCallbackHandler
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,
)
callbacks = [StdOutCallbackHandler(), comet_callback]
llm = OpenAI(temperature=0.9)

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

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.
                 """
    }
]
print(synopsis_chain.apply(test_prompts, callbacks=callbacks))
comet_callback.flush_tracker(synopsis_chain, finish=True)