彗星 Comet#
在本指南中,我们将演示如何使用Comet (opens in a new tab)跟踪您的Langchain实验、评估指标和LLM会话。
(opens in a new tab) 示例项目:使用LangChain的Comet (opens in a new tab)
安装Comet和依赖项#
%pip install comet_ml langchain openai google-search-results spacy textstat pandas
import sys
!{sys.executable} -m spacy download en_core_web_sm
初始化Comet并设置您的凭据#
你可以在这里获取你的Comet API密钥 (opens in a new tab),或者在初始化Comet后单击链接
import comet_ml
comet_ml.init(project_name="comet-example-langchain")
设置OpenAI和SerpAPI凭证#
运行以下示例需要一个OpenAI API密钥 (opens in a new tab)和一个SerpAPI API密钥 (opens in a new tab)
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)
Scenario 4: Using Custom Evaluation Metrics#
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。让我们看看它是如何工作的。
在下面的代码片段中,我们将使用 ROUGE 指标来评估输入提示的生成摘要的质量。
%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)