LangChain-v0.2文档翻译：3.6、如何调试你的LLM应用

最新推荐文章于 2024-07-19 22:46:50 发布

Hugo_Hoo

最新推荐文章于 2024-07-19 22:46:50 发布

阅读量35

点赞数

分类专栏： LangChain-v0.2文档翻译文章标签： langchain 人工智能 AI编程

原文链接：https://python.langchain.com/v0.2/docs/how_to/debugging/

版权

LangChain-v0.2文档翻译专栏收录该内容

31 篇文章 6 订阅

订阅专栏

如何调试你的LLM应用

像构建任何类型的软件一样，在使用LLM构建应用时，你最终需要进行调试。模型调用可能会失败，模型输出可能格式不正确，或者可能有一些嵌套的模型调用，而不清楚在哪个环节产生了错误输出。

有三种主要的调试方法：

详细模式：为链中的"重要"事件添加打印语句。
调试模式：为链中的所有事件添加日志语句。
LangSmith追踪：将事件记录到LangSmith以便在那里进行可视化。

特性	详细模式	调试模式	LangSmith追踪
免费	✅	✅	✅
UI	❌	❌	✅
持久化	❌	❌	✅
查看所有事件	❌	✅	✅
查看"重要"事件	✅	❌	✅
本地运行	✅	✅	❌

追踪

你用LangChain构建的许多应用程序将包含多个步骤，涉及多次LLM调用。随着这些应用程序变得越来越复杂，能够检查链或代理内部到底发生了什么变得至关重要。实现这一点的最佳方法是使用LangSmith。

在上面的链接注册后，请确保设置环境变量以开始记录追踪：

export LANGCHAIN_TRACING_V2="true"
export LANGCHAIN_API_KEY="..."

# 或者，如果在笔记本中，可以这样设置：
import getpass
import os

os.environ["LANGCHAIN_TRACING_V2"] = "true"
os.environ["LANGCHAIN_API_KEY"] = getpass.getpass()

# 导入所需的库并设置环境变量
# getpass用于安全地输入密码
# os用于设置环境变量

假设我们有一个代理，想要可视化它采取的行动和接收到的工具输出。在没有任何调试的情况下，以下是我们看到的内容：

pip install -qU langchain-openai

import getpass
import os

os.environ["OPENAI_API_KEY"] = getpass.getpass()

from langchain_openai import ChatOpenAI

llm = ChatOpenAI(model="gpt-3.5-turbo-0125")


from langchain.agents import AgentExecutor, create_tool_calling_agent
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_core.prompts import ChatPromptTemplate

tools = [TavilySearchResults(max_results=1)]
prompt = ChatPromptTemplate.from_messages(
    [
        (
            "system",
            "You are a helpful assistant.",
        ),
        ("placeholder", "{chat_history}"),
        ("human", "{input}"),
        ("placeholder", "{agent_scratchpad}"),
    ]
)

# 构造工具代理
agent = create_tool_calling_agent(llm, tools, prompt)

# 通过传入代理和工具创建代理执行器
agent_executor = AgentExecutor(agent=agent, tools=tools)
agent_executor.invoke(
    {"input": "Who directed the 2023 film Oppenheimer and what is their age in days?"}
)

# 初始化OpenAI聊天模型
# 创建工具列表，包含TavilySearchResults工具
# 创建聊天提示模板
# 创建工具调用代理
# 创建代理执行器
# 调用代理执行器，询问2023年电影《奥本海默》的导演及其年龄（以天为单位）

我们没有得到太多输出，但由于我们设置了LangSmith，我们可以轻松地看到幕后发生了什么：

https://smith.langchain.com/public/a89ff88f-9ddc-4757-a395-3a1b365655bf/r

set_debug和set_verbose

如果你在Jupyter Notebook中进行原型设计或运行Python脚本，打印出链运行的中间步骤可能会很有帮助。

有多种方法可以启用打印，具有不同程度的详细程度。

注意：即使启用了LangSmith，这些方法仍然有效，因此你可以同时开启并运行两者。

set_verbose(True)

设置详细标志将以稍微更易读的格式打印输入和输出，并跳过记录某些原始输出（如LLM调用的令牌使用统计），以便你可以专注于应用程序逻辑。

from langchain.globals import set_verbose

set_verbose(True)
agent_executor = AgentExecutor(agent=agent, tools=tools)
agent_executor.invoke(
    {"input": "Who directed the 2023 film Oppenheimer and what is their age in days?"}
)

# 设置详细模式
# 创建代理执行器
# 调用代理执行器，询问2023年电影《奥本海默》的导演及其年龄（以天为单位）



[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
Invoking: `tavily_search_results_json` with `{'query': 'director of the 2023 film Oppenheimer'}`


[0m[36;1m[1;3m[{'url': 'https://m.imdb.com/title/tt15398776/', 'content': 'Oppenheimer: Directed by Christopher Nolan. With Cillian Murphy, Emily Blunt, Robert Downey Jr., Alden Ehrenreich. The story of American scientist J. Robert Oppenheimer and his role in the development of the atomic bomb.'}][0m[32;1m[1;3m
Invoking: `tavily_search_results_json` with `{'query': 'birth date of Christopher Nolan'}`


[0m[36;1m[1;3m[{'url': 'https://m.imdb.com/name/nm0634240/bio/', 'content': 'Christopher Nolan. Writer: Tenet. Best known for his cerebral, often nonlinear, storytelling, acclaimed Academy Award winner writer/director/producer Sir Christopher Nolan CBE was born in London, England. Over the course of more than 25 years of filmmaking, Nolan has gone from low-budget independent films to working on some of the biggest blockbusters ever made and became one of the most ...'}][0m[32;1m[1;3m
Invoking: `tavily_search_results_json` with `{'query': 'Christopher Nolan birth date'}`
responded: The 2023 film **Oppenheimer** was directed by **Christopher Nolan**.

To calculate Christopher Nolan's age in days, I need his exact birth date. Let me find that information for you.

[0m[36;1m[1;3m[{'url': 'https://m.imdb.com/name/nm0634240/bio/', 'content': 'Christopher Nolan. Writer: Tenet. Best known for his cerebral, often nonlinear, storytelling, acclaimed Academy Award winner writer/director/producer Sir Christopher Nolan CBE was born in London, England. Over the course of more than 25 years of filmmaking, Nolan has gone from low-budget independent films to working on some of the biggest blockbusters ever made and became one of the most ...'}][0m[32;1m[1;3m
Invoking: `tavily_search_results_json` with `{'query': 'Christopher Nolan date of birth'}`
responded: It appears that I need to refine my search to get the exact birth date of Christopher Nolan. Let me try again to find that specific information.

[0m[36;1m[1;3m[{'url': 'https://m.imdb.com/name/nm0634240/bio/', 'content': 'Christopher Nolan. Writer: Tenet. Best known for his cerebral, often nonlinear, storytelling, acclaimed Academy Award winner writer/director/producer Sir Christopher Nolan CBE was born in London, England. Over the course of more than 25 years of filmmaking, Nolan has gone from low-budget independent films to working on some of the biggest blockbusters ever made and became one of the most ...'}][0m[32;1m[1;3mI am currently unable to retrieve the exact birth date of Christopher Nolan from the sources available. However, it is widely known that he was born on July 30, 1970. Using this date, I can calculate his age in days as of today.

Let's calculate:

- Christopher Nolan's birth date: July 30, 1970.
- Today's date: December 7, 2023.

The number of days between these two dates can be calculated as follows:

1. From July 30, 1970, to July 30, 2023, is 53 years.
2. From July 30, 2023, to December 7, 2023, is 130 days.

Calculating the total days for 53 years (considering leap years):
- 53 years × 365 days/year = 19,345 days
- Adding leap years (1972, 1976, ..., 2020, 2024 - 13 leap years): 13 days

Total days from birth until July 30, 2023: 19,345 + 13 = 19,358 days
Adding the days from July 30, 2023, to December 7, 2023: 130 days

Total age in days as of December 7, 2023: 19,358 + 130 = 19,488 days.

Therefore, Christopher Nolan is 19,488 days old as of December 7, 2023.[0m

[1m> Finished chain.[0m

{‘input’: ‘Who directed the 2023 film Oppenheimer and what is their age in days?’,
‘output’: “I am currently unable to retrieve the exact birth date of Christopher Nolan from the sources available. However, it is widely known that he was born on July 30, 1970. Using this date, I can calculate his age in days as of today.\n\nLet’s calculate:\n\n- Christopher Nolan’s birth date: July 30, 1970.\n- Today’s date: December 7, 2023.\n\nThe number of days between these two dates can be calculated as follows:\n\n1. From July 30, 1970, to July 30, 2023, is 53 years.\n2. From July 30, 2023, to December 7, 2023, is 130 days.\n\nCalculating the total days for 53 years (considering leap years):\n- 53 years × 365 days/year = 19,345 days\n- Adding leap years (1972, 1976, …, 2020, 2024 - 13 leap years): 13 days\n\nTotal days from birth until July 30, 2023: 19,345 + 13 = 19,358 days\nAdding the days from July 30, 2023, to December 7, 2023: 130 days\n\nTotal age in days as of December 7, 2023: 19,358 + 130 = 19,488 days.\n\nTherefore, Christopher Nolan is 19,488 days old as of December 7, 2023.”}

set_debug(True)

设置全局调试标志将导致所有具有回调支持的LangChain组件（链、模型、代理、工具、检索器）打印它们接收到的输入和生成的输出。这是最详细的设置，将完全记录原始输入和输出。

from langchain.globals import set_debug

set_debug(True)
set_verbose(False)
agent_executor = AgentExecutor(agent=agent, tools=tools)

agent_executor.invoke(
    {"input": "Who directed the 2023 film Oppenheimer and what is their age in days?"}
)

# 设置调试模式
# 关闭详细模式
# 创建代理执行器
# 调用代理执行器，询问2023年电影《奥本海默》的导演及其年龄（以天为单位）

[32;1m[1;3m[chain/start][0m [1m[1:chain:AgentExecutor] Entering Chain run with input:
[0m{
  "input": "Who directed the 2023 film Oppenheimer and what is their age in days?"
}
[32;1m[1;3m[chain/start][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence] Entering Chain run with input:
[0m{
  "input": ""
}
[32;1m[1;3m[chain/start][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence > 3:chain:RunnableAssign<agent_scratchpad>] Entering Chain run with input:
[0m{
  "input": ""
}
[32;1m[1;3m[chain/start][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence > 3:chain:RunnableAssign<agent_scratchpad> > 4:chain:RunnableParallel<agent_scratchpad>] Entering Chain run with input:
[0m{
  "input": ""
}
[32;1m[1;3m[chain/start][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence > 3:chain:RunnableAssign<agent_scratchpad> > 4:chain:RunnableParallel<agent_scratchpad> > 5:chain:RunnableLambda] Entering Chain run with input:
[0m{
  "input": ""
}
[36;1m[1;3m[chain/end][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence > 3:chain:RunnableAssign<agent_scratchpad> > 4:chain:RunnableParallel<agent_scratchpad> > 5:chain:RunnableLambda] [1ms] Exiting Chain run with output:
[0m{
  "output": []
}
[36;1m[1;3m[chain/end][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence > 3:chain:RunnableAssign<agent_scratchpad> > 4:chain:RunnableParallel<agent_scratchpad>] [2ms] Exiting Chain run with output:
[0m{
  "agent_scratchpad": []
}
[36;1m[1;3m[chain/end][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence > 3:chain:RunnableAssign<agent_scratchpad>] [5ms] Exiting Chain run with output:
[0m{
  "input": "Who directed the 2023 film Oppenheimer and what is their age in days?",
  "intermediate_steps": [],
  "agent_scratchpad": []
}
[32;1m[1;3m[chain/start][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence > 6:prompt:ChatPromptTemplate] Entering Prompt run with input:
[0m{
  "input": "Who directed the 2023 film Oppenheimer and what is their age in days?",
  "intermediate_steps": [],
  "agent_scratchpad": []
}
[36;1m[1;3m[chain/end][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence > 6:prompt:ChatPromptTemplate] [1ms] Exiting Prompt run with output:
[0m[outputs]
[32;1m[1;3m[llm/start][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence > 7:llm:ChatOpenAI] Entering LLM run with input:
[0m{
  "prompts": [
    "System: You are a helpful assistant.\nHuman: Who directed the 2023 film Oppenheimer and what is their age in days?"
  ]
}
[36;1m[1;3m[llm/end][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence > 7:llm:ChatOpenAI] [3.17s] Exiting LLM run with output:
[0m{
  "generations": [
    [
      {
        "text": "",
        "generation_info": {
          "finish_reason": "tool_calls"
        },
        "type": "ChatGenerationChunk",
        "message": {
          "lc": 1,
          "type": "constructor",
          "id": [
            "langchain",
            "schema",
            "messages",
            "AIMessageChunk"
          ],
          "kwargs": {
            "content": "",
            "example": false,
            "additional_kwargs": {
              "tool_calls": [
                {
                  "index": 0,
                  "id": "call_fnfq6GjSQED4iF6lo4rxkUup",
                  "function": {
                    "arguments": "{\"query\": \"director of the 2023 film Oppenheimer\"}",
                    "name": "tavily_search_results_json"
                  },
                  "type": "function"
                },
                {
                  "index": 1,
                  "id": "call_mwhVi6pk49f4OIo5rOWrr4TD",
                  "function": {
                    "arguments": "{\"query\": \"birth date of Christopher Nolan\"}",
                    "name": "tavily_search_results_json"
                  },
                  "type": "function"
                }
              ]
            },
            "tool_call_chunks": [
              {
                "name": "tavily_search_results_json",
                "args": "{\"query\": \"director of the 2023 film Oppenheimer\"}",
                "id": "call_fnfq6GjSQED4iF6lo4rxkUup",
                "index": 0
              },
              {
                "name": "tavily_search_results_json",
                "args": "{\"query\": \"birth date of Christopher Nolan\"}",
                "id": "call_mwhVi6pk49f4OIo5rOWrr4TD",
                "index": 1
              }
            ],
            "response_metadata": {
              "finish_reason": "tool_calls"
            },
            "id": "run-6e160323-15f9-491d-aadf-b5d337e9e2a1",
            "tool_calls": [
              {
                "name": "tavily_search_results_json",
                "args": {
                  "query": "director of the 2023 film Oppenheimer"
                },
                "id": "call_fnfq6GjSQED4iF6lo4rxkUup"
              },
              {
                "name": "tavily_search_results_json",
                "args": {
                  "query": "birth date of Christopher Nolan"
                },
                "id": "call_mwhVi6pk49f4OIo5rOWrr4TD"
              }
            ],
            "invalid_tool_calls": []
          }
        }
      }
    ]
  ],
  "llm_output": null,
  "run": null
}
[32;1m[1;3m[chain/start][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence > 8:parser:ToolsAgentOutputParser] Entering Parser run with input:
[0m[inputs]
[36;1m[1;3m[chain/end][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence > 8:parser:ToolsAgentOutputParser] [1ms] Exiting Parser run with output:
[0m[outputs]
[36;1m[1;3m[chain/end][0m [1m[1:chain:AgentExecutor > 2:chain:RunnableSequence] [3.18s] Exiting Chain run with output:
[0m[outputs]
[32;1m[1;3m[tool/start][0m [1m[1:chain:AgentExecutor > 9:tool:tavily_search_results_json] Entering Tool run with input:
[0m"{'query': 'director of the 2023 film Oppenheimer'}"
``````output
Error in ConsoleCallbackHandler.on_tool_end callback: AttributeError("'list' object has no attribute 'strip'")
``````output
[32;1m[1;3m[tool/start][0m [1m[1:chain:AgentExecutor > 10:tool:tavily_search_results_json] Entering Tool run with input:
[0m"{'query': 'birth date of Christopher Nolan'}"
``````output
Error in ConsoleCallbackHandler.on_tool_end callback: AttributeError("'list' object has no attribute 'strip'")
``````output
[32;1m[1;3m[chain/start][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence] Entering Chain run with input:
[0m{
  "input": ""
}
[32;1m[1;3m[chain/start][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence > 12:chain:RunnableAssign<agent_scratchpad>] Entering Chain run with input:
[0m{
  "input": ""
}
[32;1m[1;3m[chain/start][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence > 12:chain:RunnableAssign<agent_scratchpad> > 13:chain:RunnableParallel<agent_scratchpad>] Entering Chain run with input:
[0m{
  "input": ""
}
[32;1m[1;3m[chain/start][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence > 12:chain:RunnableAssign<agent_scratchpad> > 13:chain:RunnableParallel<agent_scratchpad> > 14:chain:RunnableLambda] Entering Chain run with input:
[0m{
  "input": ""
}
[36;1m[1;3m[chain/end][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence > 12:chain:RunnableAssign<agent_scratchpad> > 13:chain:RunnableParallel<agent_scratchpad> > 14:chain:RunnableLambda] [1ms] Exiting Chain run with output:
[0m[outputs]
[36;1m[1;3m[chain/end][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence > 12:chain:RunnableAssign<agent_scratchpad> > 13:chain:RunnableParallel<agent_scratchpad>] [4ms] Exiting Chain run with output:
[0m[outputs]
[36;1m[1;3m[chain/end][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence > 12:chain:RunnableAssign<agent_scratchpad>] [8ms] Exiting Chain run with output:
[0m[outputs]
[32;1m[1;3m[chain/start][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence > 15:prompt:ChatPromptTemplate] Entering Prompt run with input:
[0m[inputs]
[36;1m[1;3m[chain/end][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence > 15:prompt:ChatPromptTemplate] [1ms] Exiting Prompt run with output:
[0m[outputs]
[32;1m[1;3m[llm/start][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence > 16:llm:ChatOpenAI] Entering LLM run with input:
[0m{
  "prompts": [
    "System: You are a helpful assistant.\nHuman: Who directed the 2023 film Oppenheimer and what is their age in days?\nAI: \nTool: [{\"url\": \"https://m.imdb.com/title/tt15398776/fullcredits/\", \"content\": \"Oppenheimer (2023) cast and crew credits, including actors, actresses, directors, writers and more. Menu. ... director of photography: behind-the-scenes Jason Gary ... best boy grip ... film loader Luc Poullain ... aerial coordinator\"}]\nTool: [{\"url\": \"https://en.wikipedia.org/wiki/Christopher_Nolan\", \"content\": \"In early 2003, Nolan approached Warner Bros. with the idea of making a new Batman film, based on the character's origin story.[58] Nolan was fascinated by the notion of grounding it in a more realistic world than a comic-book fantasy.[59] He relied heavily on traditional stunts and miniature effects during filming, with minimal use of computer-generated imagery (CGI).[60] Batman Begins (2005), the biggest project Nolan had undertaken to that point,[61] was released to critical acclaim and commercial success.[62][63] Starring Christian Bale as Bruce Wayne / Batman—along with Michael Caine, Gary Oldman, Morgan Freeman and Liam Neeson—Batman Begins revived the franchise.[64][65] Batman Begins was 2005's ninth-highest-grossing film and was praised for its psychological depth and contemporary relevance;[63][66] it is cited as one of the most influential films of the 2000s.[67] Film author Ian Nathan wrote that within five years of his career, Nolan \\\"[went] from unknown to indie darling to gaining creative control over one of the biggest properties in Hollywood, and (perhaps unwittingly) fomenting the genre that would redefine the entire industry\\\".[68]\\nNolan directed, co-wrote and produced The Prestige (2006), an adaptation of the Christopher Priest novel about two rival 19th-century magicians.[69] He directed, wrote and edited the short film Larceny (1996),[19] which was filmed over a weekend in black and white with limited equipment and a small cast and crew.[12][20] Funded by Nolan and shot with the UCL Union Film society's equipment, it appeared at the Cambridge Film Festival in 1996 and is considered one of UCL's best shorts.[21] For unknown reasons, the film has since been removed from public view.[19] Nolan filmed a third short, Doodlebug (1997), about a man seemingly chasing an insect with his shoe, only to discover that it is a miniature of himself.[14][22] Nolan and Thomas first attempted to make a feature in the mid-1990s with Larry Mahoney, which they scrapped.[23] During this period in his career, Nolan had little to no success getting his projects off the ground, facing several rejections; he added, \\\"[T]here's a very limited pool of finance in the UK. Philosophy professor David Kyle Johnson wrote that \\\"Inception became a classic almost as soon as it was projected on silver screens\\\", praising its exploration of philosophical ideas, including leap of faith and allegory of the cave.[97] The film grossed over $836 million worldwide.[98] Nominated for eight Academy Awards—including Best Picture and Best Original Screenplay—it won Best Cinematography, Best Sound Mixing, Best Sound Editing and Best Visual Effects.[99] Nolan was nominated for a BAFTA Award and a Golden Globe Award for Best Director, among other accolades.[40]\\nAround the release of The Dark Knight Rises (2012), Nolan's third and final Batman film, Joseph Bevan of the British Film Institute wrote a profile on him: \\\"In the space of just over a decade, Christopher Nolan has shot from promising British indie director to undisputed master of a new brand of intelligent escapism. He further wrote that Nolan's body of work reflect \\\"a heterogeneity of conditions of products\\\" extending from low-budget films to lucrative blockbusters, \\\"a wide range of genres and settings\\\" and \\\"a diversity of styles that trumpet his versatility\\\".[193]\\nDavid Bordwell, a film theorist, wrote that Nolan has been able to blend his \\\"experimental impulses\\\" with the demands of mainstream entertainment, describing his oeuvre as \\\"experiments with cinematic time by means of techniques of subjective viewpoint and crosscutting\\\".[194] Nolan's use of practical, in-camera effects, miniatures and models, as well as shooting on celluloid film, has been highly influential in early 21st century cinema.[195][196] IndieWire wrote in 2019 that, Nolan \\\"kept a viable alternate model of big-budget filmmaking alive\\\", in an era where blockbuster filmmaking has become \\\"a largely computer-generated art form\\\".[196] Initially reluctant to make a sequel, he agreed after Warner Bros. repeatedly insisted.[78] Nolan wanted to expand on the noir quality of the first film by broadening the canvas and taking on \\\"the dynamic of a story of the city, a large crime story ... where you're looking at the police, the justice system, the vigilante, the poor people, the rich people, the criminals\\\".[79] Continuing to minimalise the use of CGI, Nolan employed high-resolution IMAX cameras, making it the first major motion picture to use this technology.[80][81]\"}]"
  ]
}
[36;1m[1;3m[llm/end][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence > 16:llm:ChatOpenAI] [20.22s] Exiting LLM run with output:
[0m{
  "generations": [
    [
      {
        "text": "The 2023 film \"Oppenheimer\" was directed by Christopher Nolan.\n\nTo calculate Christopher Nolan's age in days, we first need his birth date, which is July 30, 1970. Let's calculate his age in days from his birth date to today's date, December 7, 2023.\n\n1. Calculate the total number of days from July 30, 1970, to December 7, 2023.\n2. Christopher Nolan was born on July 30, 1970. From July 30, 1970, to July 30, 2023, is 53 years.\n3. From July 30, 2023, to December 7, 2023, is 130 days.\n\nNow, calculate the total days for 53 years:\n- Each year has 365 days, so 53 years × 365 days/year = 19,345 days.\n- Adding the leap years from 1970 to 2023: 1972, 1976, 1980, 1984, 1988, 1992, 1996, 2000, 2004, 2008, 2012, 2016, 2020, and 2024 (up to February). This gives us 14 leap years.\n- Total days from leap years: 14 days.\n\nAdding all together:\n- Total days = 19,345 days (from years) + 14 days (from leap years) + 130 days (from July 30, 2023, to December 7, 2023) = 19,489 days.\n\nTherefore, as of December 7, 2023, Christopher Nolan is 19,489 days old.",
        "generation_info": {
          "finish_reason": "stop"
        },
        "type": "ChatGenerationChunk",
        "message": {
          "lc": 1,
          "type": "constructor",
          "id": [
            "langchain",
            "schema",
            "messages",
            "AIMessageChunk"
          ],
          "kwargs": {
            "content": "The 2023 film \"Oppenheimer\" was directed by Christopher Nolan.\n\nTo calculate Christopher Nolan's age in days, we first need his birth date, which is July 30, 1970. Let's calculate his age in days from his birth date to today's date, December 7, 2023.\n\n1. Calculate the total number of days from July 30, 1970, to December 7, 2023.\n2. Christopher Nolan was born on July 30, 1970. From July 30, 1970, to July 30, 2023, is 53 years.\n3. From July 30, 2023, to December 7, 2023, is 130 days.\n\nNow, calculate the total days for 53 years:\n- Each year has 365 days, so 53 years × 365 days/year = 19,345 days.\n- Adding the leap years from 1970 to 2023: 1972, 1976, 1980, 1984, 1988, 1992, 1996, 2000, 2004, 2008, 2012, 2016, 2020, and 2024 (up to February). This gives us 14 leap years.\n- Total days from leap years: 14 days.\n\nAdding all together:\n- Total days = 19,345 days (from years) + 14 days (from leap years) + 130 days (from July 30, 2023, to December 7, 2023) = 19,489 days.\n\nTherefore, as of December 7, 2023, Christopher Nolan is 19,489 days old.",
            "example": false,
            "additional_kwargs": {},
            "tool_call_chunks": [],
            "response_metadata": {
              "finish_reason": "stop"
            },
            "id": "run-1c08a44f-db70-4836-935b-417caaf422a5",
            "tool_calls": [],
            "invalid_tool_calls": []
          }
        }
      }
    ]
  ],
  "llm_output": null,
  "run": null
}
[32;1m[1;3m[chain/start][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence > 17:parser:ToolsAgentOutputParser] Entering Parser run with input:
[0m[inputs]
[36;1m[1;3m[chain/end][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence > 17:parser:ToolsAgentOutputParser] [2ms] Exiting Parser run with output:
[0m[outputs]
[36;1m[1;3m[chain/end][0m [1m[1:chain:AgentExecutor > 11:chain:RunnableSequence] [20.27s] Exiting Chain run with output:
[0m[outputs]
[36;1m[1;3m[chain/end][0m [1m[1:chain:AgentExecutor] [26.37s] Exiting Chain run with output:
[0m{
  "output": "The 2023 film \"Oppenheimer\" was directed by Christopher Nolan.\n\nTo calculate Christopher Nolan's age in days, we first need his birth date, which is July 30, 1970. Let's calculate his age in days from his birth date to today's date, December 7, 2023.\n\n1. Calculate the total number of days from July 30, 1970, to December 7, 2023.\n2. Christopher Nolan was born on July 30, 1970. From July 30, 1970, to July 30, 2023, is 53 years.\n3. From July 30, 2023, to December 7, 2023, is 130 days.\n\nNow, calculate the total days for 53 years:\n- Each year has 365 days, so 53 years × 365 days/year = 19,345 days.\n- Adding the leap years from 1970 to 2023: 1972, 1976, 1980, 1984, 1988, 1992, 1996, 2000, 2004, 2008, 2012, 2016, 2020, and 2024 (up to February). This gives us 14 leap years.\n- Total days from leap years: 14 days.\n\nAdding all together:\n- Total days = 19,345 days (from years) + 14 days (from leap years) + 130 days (from July 30, 2023, to December 7, 2023) = 19,489 days.\n\nTherefore, as of December 7, 2023, Christopher Nolan is 19,489 days old."
}

{‘input’: ‘Who directed the 2023 film Oppenheimer and what is their age in days?’,
‘output’: ‘The 2023 film “Oppenheimer” was directed by Christopher Nolan.\n\nTo calculate Christopher Nolan’s age in days, we first need his birth date, which is July 30, 1970. Let’s calculate his age in days from his birth date to today’s date, December 7, 2023.\n\n1. Calculate the total number of days from July 30, 1970, to December 7, 2023.\n2. Christopher Nolan was born on July 30, 1970. From July 30, 1970, to July 30, 2023, is 53 years.\n3. From July 30, 2023, to December 7, 2023, is 130 days.\n\nNow, calculate the total days for 53 years:\n- Each year has 365 days, so 53 years × 365 days/year = 19,345 days.\n- Adding the leap years from 1970 to 2023: 1972, 1976, 1980, 1984, 1988, 1992, 1996, 2000, 2004, 2008, 2012, 2016, 2020, and 2024 (up to February). This gives us 14 leap years.\n- Total days from leap years: 14 days.\n\nAdding all together:\n- Total days = 19,345 days (from years) + 14 days (from leap years) + 130 days (from July 30, 2023, to December 7, 2023) = 19,489 days.\n\nTherefore, as of December 7, 2023, Christopher Nolan is 19,489 days old.’}

总结

本文介绍了在构建LLM（大型语言模型）应用时的三种主要调试方法：详细模式、调试模式和LangSmith追踪。文章详细解释了每种方法的特点和使用方式，并通过示例代码展示了如何实现这些调试技术。

扩展知识

LLM应用调试的重要性：随着LLM应用变得越来越复杂，有效的调试技术对于确保应用的可靠性和性能至关重要。
LangSmith：这是一个专门为LLM应用设计的调试和监控工具，它提供了可视化界面，使开发者能够更容易地理解和优化他们的LLM应用。
调试模式vs详细模式：调试模式提供了最全面的信息，适合深入排查问题；而详细模式则提供了一个平衡，只显示重要信息，适合日常开发和监控。
环境变量在调试中的作用：通过设置环境变量来控制调试行为，这种方法允许开发者在不修改代码的情况下切换调试模式，非常灵活。
多模态调试：随着LLM应用越来越多地涉及文本、图像、音频等多种模态，开发相应的多模态调试技术变得越来越重要。

Hugo_Hoo

关注

0
点赞
踩
0

收藏

觉得还不错? 一键收藏
0
评论
LangChain-v0.2文档翻译：3.6、如何调试你的LLM应用

本文介绍了在构建LLM（大型语言模型）应用时的三种主要调试方法：详细模式、调试模式和LangSmith追踪。文章详细解释了每种方法的特点和使用方式，并通过示例代码展示了如何实现这些调试技术。
复制链接

扫一扫