LangChain 中文文档

主题

使用 Pytest/Vitest 和 LangSmith 测试 ReAct 代理

本教程将展示如何使用 LangSmith 与流行测试工具（Pytest、Vitest 和 Jest）的集成来评估您的 LLM 应用程序。我们将创建一个 ReAct 智能体，用于回答关于公开交易股票的问题，并为其编写全面的测试套件。

设置 ​

本教程使用 LangGraph 进行智能体编排，使用 OpenAI 的 GPT-4o，Tavily 进行搜索，E2B 的代码解释器，以及 Polygon 来检索股票数据，但只需稍作修改即可适配其他框架、模型和工具。Tavily、E2B 和 Polygon 均可免费注册。

安装 ​

首先，安装构建智能体所需的包：

bash
pip install -U langgraph langchain[openai] langchain-community e2b-code-interpreter
bash
yarn add @langchain/openai @langchain/community @langchain/langgraph @langchain/core @e2b/code-interpreter @polygon.io/client-js openai zod

接下来，安装测试框架：

bash
# Make sure you have langsmith>=0.3.1
pip install -U "langsmith[pytest]"
bash
yarn add -D langsmith vitest
bash
yarn add -D langsmith jest

环境变量 ​

设置以下环境变量：

bash
export LANGSMITH_TRACING=true
export LANGSMITH_API_KEY=<YOUR_LANGSMITH_API_KEY>
export OPENAI_API_KEY=<YOUR_OPENAI_API_KEY>
export TAVILY_API_KEY=<YOUR_TAVILY_API_KEY>
export E2B_API_KEY=<YOUR_E2B_API_KEY>
export POLYGON_API_KEY=<YOUR_POLYGON_API_KEY>

创建您的应用 ​

为了定义我们的 ReAct 智能体，我们将使用 LangGraph/LangGraph.js 进行编排，并使用 LangChain 处理 LLM 和工具。

定义工具 ​

首先，我们将定义智能体中要使用的工具。将会有 3 个工具：

  • 使用 Tavily 的搜索工具
  • 使用 E2B 的代码解释器工具
  • 使用 Polygon 的股票信息工具
python
from langchain_community.tools import TavilySearchResults
from e2b_code_interpreter import Sandbox
from langchain_community.tools.polygon.aggregates import PolygonAggregates
from langchain_community.utilities.polygon import PolygonAPIWrapper
from typing_extensions import Annotated, TypedDict, Optional, Literal

# Define search tool
search_tool = TavilySearchResults(
  max_results=5,
  include_raw_content=True,
)

# Define code tool
def code_tool(code: str) -> str:
  """Execute python code and return the result."""
  sbx = Sandbox()
  execution = sbx.run_code(code)

  if execution.error:
      return f"Error: {execution.error}"
  return f"Results: {execution.results}, Logs: {execution.logs}"

# Define input schema for stock ticker tool
class TickerToolInput(TypedDict):
  """Input format for the ticker tool.
    The tool will pull data in aggregate blocks (timespan_multiplier * timespan) from the from_date to the to_date
  """
  ticker: Annotated[str, ..., "The ticker symbol of the stock"]
  timespan: Annotated[Literal["minute", "hour", "day", "week", "month", "quarter", "year"], ..., "The size of the time window."]
  timespan_multiplier: Annotated[int, ..., "The multiplier for the time window"]
  from_date: Annotated[str, ..., "The date to start pulling data from, YYYY-MM-DD format - ONLY include the year month and day"]
  to_date: Annotated[str, ..., "The date to stop pulling data, YYYY-MM-DD format - ONLY include the year month and day"]

api_wrapper = PolygonAPIWrapper()
polygon_aggregate = PolygonAggregates(api_wrapper=api_wrapper)

# Define stock ticker tool
def ticker_tool(query: TickerToolInput) -> str:
  """Pull data for the ticker."""
  return polygon_aggregate.invoke(query)
typescript
import { TavilySearchResults } from "@langchain/community/tools/tavily_search";
import { Sandbox } from "@e2b/code-interpreter";
import { tool } from "@langchain/core/tools";
import { z } from "zod";
import { restClient } from "@polygon.io/client-js";

// Define search tool
const searchTool = new TavilySearchResults({
  maxResults: 5,
});

// Define code tool
const codeTool = tool(async (input) => {
  const sbx = await Sandbox.create();
  const execution = await sbx.runCode(input.code);
  if (execution.error) {
    return `Error: ${execution.error}`;
  }
  return `Results: ${execution.results}, Logs: ${execution.logs}`;
}, {
  name: "code",
  description: "Execute python code and return the result.",
  schema: z.object({
    code: z.string().describe("The python code to execute"),
  }),
});

// Define input schema for stock ticker tool
const TickerToolInputSchema = z.object({
  ticker: z.string().describe("The ticker symbol of the stock"),
  timespan: z.enum(["minute", "hour", "day", "week", "month", "quarter", "year"]).describe("The size of the time window."),
  timespan_multiplier: z.number().describe("The multiplier for the time window"),
  from_date: z
    .string()
    .describe("The date to start pulling data from, YYYY-MM-DD format - ONLY include the year, month, and day"),
  to_date: z
    .string()
    .describe("The date to stop pulling data, YYYY-MM-DD format - ONLY include the year, month, and day"),
});

const rest = restClient(process.env.POLYGON_API_KEY);

// Define stock ticker tool
const tickerTool = tool(async (query) => {
  const parsed = TickerToolInputSchema.parse(query);
  const result = await rest.stocks.aggregates(
      parsed.ticker,
      parsed.timespan_multiplier,
      parsed.timespan,
      parsed.from_date,
      parsed.to_date
  );
  return JSON.stringify(result);
}, {
  name: "ticker",
  description: "Pull data for the ticker",
  schema: TickerToolInputSchema,
});

定义智能体 ​

现在我们已经定义了所有工具，可以使用 create_agent 来创建我们的智能体。

python
from typing_extensions import Annotated, TypedDict
from langchain.agents import create_agent

class AgentOutputFormat(TypedDict):
    numeric_answer: Annotated[float | None, ..., "The numeric answer, if the user asked for one"]
    text_answer: Annotated[str | None, ..., "The text answer, if the user asked for one"]
    reasoning: Annotated[str, ..., "The reasoning behind the answer"]

agent = create_agent(
    model="gpt-4o-mini",
    tools=[code_tool, search_tool, polygon_aggregates],
    response_format=AgentOutputFormat,
    system_prompt="You are a financial expert. Respond to the users query accurately",
)
typescript
import { z } from "zod";
import { ChatOpenAI } from "@langchain/openai";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const AgentOutputFormatSchema = z.object({
  numeric_answer: z.number().optional().describe("The numeric answer, if the user asked for one"),
  text_answer: z.string().optional().describe("The text answer, if the user asked for one"),
  reasoning: z.string().describe("The reasoning behind the answer"),
})

const tools = [codeTool, searchTool, tickerTool];

const agent = createReactAgent({
  llm: new ChatOpenAI({ model: "gpt-4o" }),
  tools: tools,
  responseFormat: AgentOutputFormatSchema,
  stateModifier: "You are a financial expert. Respond to the users query accurately",
});

export default agent;

编写测试 ​

现在我们已经定义了智能体，让我们编写一些测试来确保基本功能。在本教程中，我们将测试智能体的工具调用能力是否正常工作，智能体是否知道忽略不相关的问题，以及它是否能够回答涉及使用所有工具的复杂问题。

我们首先需要设置一个测试文件，并在文件顶部添加所需的导入。

python
Create a `tests/test_agent.py` file.

from app import agent, polygon_aggregates, search_tool # import from wherever your agent is defined
import pytest
from langsmith import testing as t
typescript
Name your test file `agent.vitest.eval.ts`

import { expect } from "vitest";
import * as ls from "langsmith/vitest";
import agent from "../agent"; // import from wherever your agent is defined

// Optional, but recommended to group tests together
ls.describe("Agent Tests", () => {
  // PLACE TESTS Here
});
typescript
Name your test file `agent.jest.eval.ts`

import { expect } from "@jest/globals";
import * as ls from "langsmith/jest";
import agent from "../agent"; // import from wherever your agent is defined

// Optional, but recommended to group tests together
ls.describe("Agent Tests", () => {
  // PLACE TESTS Here
});

测试 1：处理离题问题 ​

第一个测试将是一个简单的检查，确保智能体不会在无关查询上使用工具。

python
@pytest.mark.langsmith
@pytest.mark.parametrize(
  # <-- Can still use all normal pytest markers
  "query",
  ["Hello!", "How are you doing?"],
)
def test_no_tools_on_offtopic_query(query: str) -> None:
  """Test that the agent does not use tools on offtopic queries."""
  # Log the test example
  t.log_inputs({"query": query})
  expected = []
  t.log_reference_outputs({"tool_calls": expected})
  # Call the agent's model node directly instead of running the ReACT loop.
  result = agent.nodes["agent"].invoke(
      {"messages": [{"role": "user", "content": query}]}
  )
  actual = result["messages"][0].tool_calls
  t.log_outputs({"tool_calls": actual})
  # Check that no tool calls were made.
  assert actual == expected
typescript
ls.test.each([
  { inputs: { query: "Hello!" }, expected: { numMessages: 2 } },
  { inputs: { query: "How are you doing?" }, expected: { numMessages: 2 } },
])(
  "should not use tools on offtopic query: %s",
  async ({ inputs: { query }, expected: { numMessages } }) => {
    const result = await agent.invoke({ messages: [{ role: "user", content: query }] });
    ls.logOutputs(result);

    // Check that the flow was HUMAN -> AI FINAL RESPONSE (no tools called)
    expect(result.messages).toHaveLength(numMessages);
  }
);
typescript
ls.test.each([
  { inputs: { query: "Hello!" }, expected: { numMessages: 2 } },
  { inputs: { query: "How are you doing?" }, expected: { numMessages: 2 } },
])(
  "should not use tools on offtopic query: %s",
  async ({ inputs: { query }, expected: { numMessages } }) => {
    const result = await agent.invoke({ messages: [{ role: "user", content: query }] });
    ls.logOutputs(result);

    // Check that the flow was HUMAN -> AI FINAL RESPONSE (no tools called)
    expect(result.messages).toHaveLength(numMessages);
  }
);

测试 2：简单的工具调用 ​

对于工具调用，我们将验证智能体是否使用正确的参数调用了正确的工具。

python
@pytest.mark.langsmith
def test_searches_for_correct_ticker() -> None:
  """Test that the model looks up the correct ticker on simple query."""
  # Log the test example
  query = "What is the price of Apple?"
  t.log_inputs({"query": query})
  expected = "AAPL"
  t.log_reference_outputs({"ticker": expected})
  # Call the agent's model node directly instead of running the full ReACT loop.
  result = agent.nodes["agent"].invoke(
      {"messages": [{"role": "user", "content": query}]}
  )
  tool_calls = result["messages"][0].tool_calls
  if tool_calls[0]["name"] == polygon_aggregates.name:
      actual = tool_calls[0]["args"]["ticker"]
  else:
      actual = None
  t.log_outputs({"ticker": actual})
  # Check that the right ticker was queried
  assert actual == expected
typescript
ls.test(
  "should search for correct ticker",
  {
    inputs: { query: "What is the price of Apple?" },
    expected: { numMessages: 4 },
  },
  async ({ inputs: { query }, expected: { numMessages } }) => {
    const result = await agent.invoke({
      messages: [{ role: "user", content: query }],
    });

    ls.logOutputs(result);

    // The agent should have made a single tool call to the ticker tool
    const toolCalls = (result.messages[1] as AIMessage).tool_calls || [];
    const tickerQuery = JSON.parse(toolCalls[0].function.arguments).query.ticker;
    // Check that the right ticker was queried
    expect(tickerQuery).toBe("AAPL");

    // Check that the flow was HUMAN -> AI -> TOOL -> AI FINAL RESPONSE
    expect(result.messages).toHaveLength(numMessages);
  }
);
typescript
ls.test(
  "should search for correct ticker",
  {
    inputs: { query: "What is the price of Apple?" },
    expected: { numMessages: 4 },
  },
  async ({ inputs: { query }, expected: { numMessages } }) => {
    const result = await agent.invoke({
      messages: [{ role: "user", content: query }],
    });

    ls.logOutputs(result);

    // The agent should have made a single tool call to the ticker tool
    const toolCalls = (result.messages[1] as AIMessage).tool_calls || [];
    const tickerQuery = JSON.parse(toolCalls[0].function.arguments).query.ticker;
    // Check that the right ticker was queried
    expect(tickerQuery).toBe("AAPL");

    // Check that the flow was HUMAN -> AI -> TOOL -> AI FINAL RESPONSE
    expect(result.messages).toHaveLength(numMessages);
  }
);

测试 3：复杂的工具调用 ​

有些工具调用比其他更容易测试。对于股票代码查询，我们可以断言搜索了正确的股票代码。对于编码工具，工具的输入和输出约束要少得多，并且有很多方法可以得到正确答案。在这种情况下，通过运行完整的智能体并断言它既调用了编码工具又最终得到了正确答案，来测试工具是否正确使用会更简单。

python
@pytest.mark.langsmith
def test_executes_code_when_needed() -> None:
  query = (
      "In the past year Facebook stock went up by 66.76%, "
      "Apple by 25.24%, Google by 37.11%, Amazon by 47.52%, "
      "Netflix by 78.31%. Whats the avg return in the past "
      "year of the FAANG stocks, expressed as a percentage?"
  )
  t.log_inputs({"query": query})
  expected = 50.988
  t.log_reference_outputs({"response": expected})
  # Test that the agent executes code when needed
  result = agent.invoke({"messages": [{"role": "user", "content": query}]})
  t.log_outputs({"result": result["structured_response"].get("numeric_answer")})
  # Grab all the tool calls made by the LLM
  tool_calls = [
      tc["name"]
      for msg in result["messages"]
      for tc in getattr(msg, "tool_calls", [])
  ]
  # This will log the number of steps taken by the agent, which is useful for
  # determining how efficiently the agent gets to an answer.
  t.log_feedback(key="num_steps", score=len(result["messages"]) - 1)
  # Assert that the code tool was used
  assert "code_tool" in tool_calls
  # Assert that a numeric answer was provided:
  assert result["structured_response"].get("numeric_answer") is not None
  # Assert that the answer is correct
  assert abs(result["structured_response"]["numeric_answer"] - expected) <= 0.01
typescript
ls.test(
  "should execute code when needed",
  {
    inputs: { query: "What was the average return rate for FAANG stock in 2024?" },
    expected: { answer: 53 },
  },
  async ({ inputs: { query }, expected: { answer } }) => {
    const result = await agent.invoke({
      messages: [{ role: "user", content: query }],
    });

    ls.logOutputs(result);

    // Grab all the tool calls made by the LLM
    const toolCalls = result.messages
      .filter(m => (m as AIMessage).tool_calls)
      .flatMap(m => (m as AIMessage).tool_calls?.map(tc => tc.name));
    // This will log the number of steps taken by the LLM, which we can track over time to measure performance
    ls.logFeedback({
      key: "num_steps",
      score: result.messages.length - 1, // The first message is the user message
    });
    // Assert that the tool calls include the "code_tool" function
    expect(toolCalls).toContain("code_tool");
    // Assert that the answer is within 1 of the expected answer
    expect(Math.abs(result.structured_response.numeric_answer - answer)).toBeLessThanOrEqual(1);
  }
);
typescript
ls.test(
  "should execute code when needed",
  {
    inputs: { query: "What was the average return rate for FAANG stock in 2024?" },
    expected: { answer: 53 },
  },
  async ({ inputs: { query }, expected: { answer } }) => {
    const result = await agent.invoke({
      messages: [{ role: "user", content: query }],
    });

    ls.logOutputs(result);
    // Grab all the tool calls made by the LLM
    const toolCalls = result.messages
      .filter(m => (m as AIMessage).tool_calls)
      .flatMap(m => (m as AIMessage).tool_calls?.map(tc => tc.name));
    // This will log the number of steps taken by the LLM, which we can track over time to measure performance
    ls.logFeedback({
      key: "num_steps",
      score: result.messages.length - 1, // The first message is the user message
    });
    // Assert that the tool calls include the "code_tool" function
    expect(toolCalls).toContain("code_tool");
    // Assert that the answer is within 1 of the expected answer
    expect(Math.abs(result.structured_response.numeric_answer - answer)).toBeLessThanOrEqual(1);
  }
);

测试 4：LLM 作为评判者 ​

我们将通过运行 LLM 作为评判者的评估，来确保智能体的答案基于搜索结果。为了将 LLM 作为评判者的调用与我们的智能体调用分开追踪，我们将在 Python 中使用 LangSmith 提供的 trace_feedback 上下文管理器，在 JS/TS 中使用 wrapEvaluator 函数。

python
from typing_extensions import Annotated, TypedDict
from langchain.chat_models import init_chat_model

class Grade(TypedDict):
  """Evaluate the groundedness of an answer in source documents."""
  score: Annotated[
      bool,
      ...,
      "Return True if the answer is fully grounded in the source documents, otherwise False.",
  ]

judge_llm = init_chat_model("gpt-4o").with_structured_output(Grade)

@pytest.mark.langsmith
def test_grounded_in_source_info() -> None:
  """Test that response is grounded in the tool outputs."""
  query = "How did Nvidia stock do in 2024 according to analysts?"
  t.log_inputs({"query": query})
  result = agent.invoke({"messages": [{"role": "user", "content": query}]})
  # Grab all the search calls made by the LLM
  search_results = "\n\n".join(
      msg.content
      for msg in result["messages"]
      if msg.type == "tool" and msg.name == search_tool.name
  )
  t.log_outputs(
      {
          "response": result["structured_response"].get("text_answer"),
          "search_results": search_results,
      }
  )
  # Trace the feedback LLM run separately from the agent run.
  with t.trace_feedback():
      # Instructions for the LLM judge
      instructions = (
          "Grade the following ANSWER. "
          "The ANSWER should be fully grounded in (i.e. supported by) the source DOCUMENTS. "
          "Return True if the ANSWER is fully grounded in the DOCUMENTS. "
          "Return False if the ANSWER is not grounded in the DOCUMENTS."
      )
      answer_and_docs = (
          f"ANSWER: {result['structured_response'].get('text_answer', '')}\n"
          f"DOCUMENTS:\n{search_results}"
      )
      # Run the judge LLM
      grade = judge_llm.invoke(
          [
              {"role": "system", "content": instructions},
              {"role": "user", "content": answer_and_docs},
          ]
      )
      t.log_feedback(key="groundedness", score=grade["score"])
  assert grade['score']
typescript
// THIS CODE GOES OUTSIDE THE TEST - IT IS JUST A HELPER FUNCTION
const judgeLLM = new ChatOpenAI({ model: "gpt-4o" });
const groundedEvaluator = async (params: {
  answer: string;
  referenceDocuments: string,
}) => {
  // Instructions for the LLM judge
  const instructions = [
    "Return 1 if the ANSWER is grounded in the DOCUMENTS",
    "Return 0 if the ANSWER is not grounded in the DOCUMENTS",
  ].join("\n");

  // Run the judge LLM
  const grade = await judgeLLM.invoke([
    { role: "system", content: instructions },
    { role: "user", content: `ANSWER: ${params.answer}\nDOCUMENTS: ${params.referenceDocuments}` },
  ]);
  const score = parseInt(grade.content.toString());
  return { key: "groundedness", score };
};

// THIS CODE GOES INSIDE THE TEST
ls.test(
  "grounded in the source",
  {
    inputs: { query: "How did Nvidia stock do in 2024 according to analysts?" },
  },
  async ({ inputs: { query } }) => {
    const result = await agent.invoke({
      messages: [{ role: "user", content: query }],
    });
    const wrappedEvaluator = ls.wrapEvaluator(groundedEvaluator);
    await wrappedEvaluator({
      answer: result.structuredResponse.text_answer ?? "",
      referenceDocuments: result.structuredResponse.reasoning,
    })
    ls.logOutputs(result);
  }
);
typescript
// THIS CODE GOES OUTSIDE THE TEST - IT IS JUST A HELPER FUNCTION
const judgeLLM = new ChatOpenAI({ model: "gpt-4o" });
const groundedEvaluator = async (params: {
  answer: string;
  referenceDocuments: string,
}) => {
  // Instructions for the LLM judge
  const instructions = [
    "Return 1 if the ANSWER is grounded in the DOCUMENTS",
    "Return 0 if the ANSWER is not grounded in the DOCUMENTS",
  ].join("\n");

  // Run the judge LLM
  const grade = await judgeLLM.invoke([
    { role: "system", content: instructions },
    { role: "user", content: `ANSWER: ${params.answer}\nDOCUMENTS: ${params.referenceDocuments}` },
  ]);
  const score = parseInt(grade.content.toString());
  return { key: "groundedness", score };
};

// THIS CODE GOES INSIDE THE TEST
ls.test(
  "grounded in the source",
  {
    inputs: { query: "How did Nvidia stock do in 2024 according to analysts?" },
  },
  async ({ inputs: { query } }) => {
    const result = await agent.invoke({
      messages: [{ role: "user", content: query }],
    });
    const wrappedEvaluator = ls.wrapEvaluator(groundedEvaluator);
    await wrappedEvaluator({
      answer: result.structuredResponse.text_answer ?? "",
      referenceDocuments: result.structuredResponse.reasoning,
    })
    ls.logOutputs(result);
  }
);

运行测试 ​

一旦您设置好配置文件（如果您使用 Vitest 或 Jest），就可以使用以下命令运行测试：

Vitest/Jest 的配置文件
typescript
Create a `ls.vitest.config.ts` file:

import { defineConfig } from "vitest/config";

export default defineConfig({
  test: {
    include: ["**/*.eval.?(c|m)[jt]s"],
    reporters: ["langsmith/vitest/reporter"],
    setupFiles: ["dotenv/config"],
    testTimeout: 30000,
  },
});
javascript
Create a `ls.jest.config.ts` file:

require('dotenv').config();

module.exports = {
  preset: 'ts-jest',
  testEnvironment: 'node',
  testMatch: [
    '<rootDir>/tests/jest/**/*.jest.eval.ts'
  ],
  testPathIgnorePatterns: [
    '<rootDir>/tests/vitest/.*.vitest.eval.ts$'
  ],
  reporters: ["langsmith/jest/reporter"],
  testTimeout: 30000,
};
bash
pytest --langsmith-output tests
bash
yarn vitest --config ls.vitest.config.ts
bash
yarn jest --config ls.jest.config.ts

参考代码 ​

请记得将 Vitest 和 Jest 的配置文件也添加到您的项目中。

智能体 ​

智能体代码
python
from e2b_code_interpreter import Sandbox
from langchain_community.tools import PolygonAggregates, TavilySearchResults
from langchain_community.utilities.polygon import PolygonAPIWrapper
from langchain.agents import create_agent
from typing_extensions import Annotated, TypedDict

search_tool = TavilySearchResults(
    max_results=5,
    include_raw_content=True,
)

def code_tool(code: str) -> str:
    """Execute python code and return the result."""
    sbx = Sandbox()
    execution = sbx.run_code(code)

    if execution.error:
        return f"Error: {execution.error}"
    return f"Results: {execution.results}, Logs: {execution.logs}"

polygon_aggregates = PolygonAggregates(api_wrapper=PolygonAPIWrapper())

class AgentOutputFormat(TypedDict):
    numeric_answer: Annotated[
        float | None, ..., "The numeric answer, if the user asked for one"
    ]
    text_answer: Annotated[
        str | None, ..., "The text answer, if the user asked for one"
    ]
    reasoning: Annotated[str, ..., "The reasoning behind the answer"]

agent = create_agent(
    model="gpt-4o-mini",
    tools=[code_tool, search_tool, polygon_aggregates],
    response_format=AgentOutputFormat,
    system_prompt="You are a financial expert. Respond to the users query accurately",
)
typescript
import { ChatOpenAI } from "@langchain/openai";
import { createReactAgent } from "@langchain/langgraph/prebuilt";
import { TavilySearchResults } from "@langchain/community/tools/tavily_search";
import { Sandbox } from '@e2b/code-interpreter'
import { restClient } from '@polygon.io/client-js';
import { tool } from "@langchain/core/tools";
import { z } from "zod";

const codeTool = tool(async (input) => {
    const sbx = await Sandbox.create();
    const execution = await sbx.runCode(input.code);
    if (execution.error) {
    return `Error: ${execution.error}`;
    }
    return `Results: ${execution.results}, Logs: ${execution.logs}`;
}, {
    name: "code",
    description: "Execute python code and return the result.",
    schema: z.object({
    code: z.string().describe("The python code to execute"),
    }),
});

const TickerToolInputSchema = z.object({
    ticker: z.string().describe("The ticker symbol of the stock"),
    timespan: z.enum(["minute", "hour", "day", "week", "month", "quarter", "year"]).describe("The size of the time window."),
    timespan_multiplier: z.number().describe("The multiplier for the time window"),
    from_date: z
    .string()
    .describe("The date to start pulling data from, YYYY-MM-DD format - ONLY include the year, month, and day"),
    to_date: z
    .string()
    .describe("The date to stop pulling data, YYYY-MM-DD format - ONLY include the year, month, and day"),
});

const rest = restClient(process.env.POLYGON_API_KEY);

const tickerTool = tool(async (query) => {
    const parsed = TickerToolInputSchema.parse(query);
    const result = await rest.stocks.aggregates(
    parsed.ticker,
    parsed.timespan_multiplier,
    parsed.timespan,
    parsed.from_date,
    parsed.to_date
    );
    return JSON.stringify(result);
}, {
    name: "ticker",
    description: "Pull data for the ticker",
    schema: TickerToolInputSchema,
});

const searchTool = new TavilySearchResults({
    maxResults: 5,
});

const AgentOutputFormatSchema = z.object({
    numeric_answer: z.number().optional().describe("The numeric answer, if the user asked for one"),
    text_answer: z.string().optional().describe("The text answer, if the user asked for one"),
    reasoning: z.string().describe("The reasoning behind the answer"),
})

const tools = [codeTool, searchTool, tickerTool];

const agent = createReactAgent({
    llm: new ChatOpenAI({ model: "gpt-4o" }),
    tools: tools,
    responseFormat: AgentOutputFormatSchema,
    stateModifier: "You are a financial expert. Respond to the users query accurately",
});

export default agent;

测试 ​

测试代码
python
# from app import agent, polygon_aggregates, search_tool # import from wherever your agent is defined
import pytest
from langchain.chat_models import init_chat_model
from langsmith import testing as t
from typing_extensions import Annotated, TypedDict

@pytest.mark.langsmith
@pytest.mark.parametrize(
  # <-- Can still use all normal pytest markers
  "query",
  ["Hello!", "How are you doing?"],
)
def test_no_tools_on_offtopic_query(query: str) -> None:
  """Test that the agent does not use tools on offtopic queries."""
  # Log the test example
  t.log_inputs({"query": query})
  expected = []
  t.log_reference_outputs({"tool_calls": expected})
  # Call the agent's model node directly instead of running the ReACT loop.
  result = agent.nodes["agent"].invoke(
      {"messages": [{"role": "user", "content": query}]}
  )
  actual = result["messages"][0].tool_calls
  t.log_outputs({"tool_calls": actual})
  # Check that no tool calls were made.
  assert actual == expected

@pytest.mark.langsmith
def test_searches_for_correct_ticker() -> None:
  """Test that the model looks up the correct ticker on simple query."""
  # Log the test example
  query = "What is the price of Apple?"
  t.log_inputs({"query": query})
  expected = "AAPL"
  t.log_reference_outputs({"ticker": expected})
  # Call the agent's model node directly instead of running the full ReACT loop.
  result = agent.nodes["agent"].invoke(
      {"messages": [{"role": "user", "content": query}]}
  )
  tool_calls = result["messages"][0].tool_calls
  if tool_calls[0]["name"] == polygon_aggregates.name:
      actual = tool_calls[0]["args"]["ticker"]
  else:
      actual = None
  t.log_outputs({"ticker": actual})
  # Check that the right ticker was queried
  assert actual == expected

@pytest.mark.langsmith
def test_executes_code_when_needed() -> None:
  query = (
      "In the past year Facebook stock went up by 66.76%, "
      "Apple by 25.24%, Google by 37.11%, Amazon by 47.52%, "
      "Netflix by 78.31%. Whats the avg return in the past "
      "year of the FAANG stocks, expressed as a percentage?"
  )
  t.log_inputs({"query": query})
  expected = 50.988
  t.log_reference_outputs({"response": expected})
  # Test that the agent executes code when needed
  result = agent.invoke({"messages": [{"role": "user", "content": query}]})
  t.log_outputs({"result": result["structured_response"].get("numeric_answer")})
  # Grab all the tool calls made by the LLM
  tool_calls = [
      tc["name"]
      for msg in result["messages"]
      for tc in getattr(msg, "tool_calls", [])
  ]
  # This will log the number of steps taken by the agent, which is useful for
  # determining how efficiently the agent gets to an answer.
  t.log_feedback(key="num_steps", score=len(result["messages"]) - 1)
  # Assert that the code tool was used
  assert "code_tool" in tool_calls
  # Assert that a numeric answer was provided:
  assert result["structured_response"].get("numeric_answer") is not None
  # Assert that the answer is correct
  assert abs(result["structured_response"]["numeric_answer"] - expected) <= 0.01

class Grade(TypedDict):
  """Evaluate the groundedness of an answer in source documents."""
  score: Annotated[
      bool,
      ...,
      "Return True if the answer is fully grounded in the source documents, otherwise False.",
  ]

judge_llm = init_chat_model("gpt-4o").with_structured_output(Grade)

@pytest.mark.langsmith
def test_grounded_in_source_info() -> None:
  """Test that response is grounded in the tool outputs."""
  query = "How did Nvidia stock do in 2024 according to analysts?"
  t.log_inputs({"query": query})
  result = agent.invoke({"messages": [{"role": "user", "content": query}]})
  # Grab all the search calls made by the LLM
  search_results = "\n\n".join(
      msg.content
      for msg in result["messages"]
      if msg.type == "tool" and msg.name == search_tool.name
  )
  t.log_outputs(
      {
          "response": result["structured_response"].get("text_answer"),
          "search_results": search_results,
      }
  )
  # Trace the feedback LLM run separately from the agent run.
  with t.trace_feedback():
      # Instructions for the LLM judge
      instructions = (
          "Grade the following ANSWER. "
          "The ANSWER should be fully grounded in (i.e. supported by) the source DOCUMENTS. "
          "Return True if the ANSWER is fully grounded in the DOCUMENTS. "
          "Return False if the ANSWER is not grounded in the DOCUMENTS."
      )
      answer_and_docs = (
          f"ANSWER: {result['structured_response'].get('text_answer', '')}\n"
          f"DOCUMENTS:\n{search_results}"
      )
      # Run the judge LLM
      grade = judge_llm.invoke(
          [
              {"role": "system", "content": instructions},
              {"role": "user", "content": answer_and_docs},
          ]
      )
      t.log_feedback(key="groundedness", score=grade["score"])
  assert grade["score"]
typescript
import { expect } from "vitest";
import * as ls from "langsmith/vitest";
import agent from "../agent";
import { AIMessage, ToolMessage } from "@langchain/core/messages";
import { ChatOpenAI } from "@langchain/openai";

const judgeLLM = new ChatOpenAI({ model: "gpt-4o" });

const groundedEvaluator = async (params: {
  answer: string;
  referenceDocuments: string,
}) => {
  const instructions = [
    "Return 1 if the ANSWER is grounded in the DOCUMENTS",
    "Return 0 if the ANSWER is not grounded in the DOCUMENTS",
  ].join("\n");

  const grade = await judgeLLM.invoke([
    { role: "system", content: instructions },
    { role: "user", content: `ANSWER: ${params.answer}\nDOCUMENTS: ${params.referenceDocuments}` },
  ]);
  const score = parseInt(grade.content.toString());
  return { key: "groundedness", score };
};

ls.describe("Agent Tests", () => {
  ls.test.each([
    { inputs: { query: "Hello!" }, referenceOutputs: { numMessages: 2 } },
    { inputs: { query: "How are you doing?" }, referenceOutputs: { numMessages: 2 } },
  ])(
    "should not use tools on offtopic query: %s",
    async ({ inputs: { query }, referenceOutputs: { numMessages } }) => {
      const result = await agent.invoke({
        messages: [{ role: "user", content: query }],
      });
      ls.logOutputs(result);
      expect(result.messages).toHaveLength(numMessages);
    }
  );

  ls.test(
    "should search for correct ticker",
    {
      inputs: { query: "What is the price of Apple?" },
      referenceOutputs: { numMessages: 4 },
    },
    async ({ inputs: { query }, referenceOutputs: { numMessages } }) => {
      const result = await agent.invoke({
        messages: [{ role: "user", content: query }],
      });
      const toolCalls = (result.messages[1] as AIMessage).tool_calls || [];
      const tickerQuery = toolCalls[0].args.ticker;
      ls.logOutputs(result);
      expect(tickerQuery).toBe("AAPL");
      expect(result.messages).toHaveLength(numMessages);
    }
  );

  ls.test(
    "should execute code when needed",
    {
      inputs: { query: "What was the average return rate for FAANG stock in 2024?" },
      referenceOutputs: { answer: 53 },
    },
    async ({ inputs: { query }, referenceOutputs: { answer } }) => {
      const result = await agent.invoke({
        messages: [{ role: "user", content: query }],
      });

      const toolCalls = result.messages
        .filter(m => (m as AIMessage).tool_calls)
        .flatMap(m => (m as AIMessage).tool_calls?.map(tc => tc.name));
      ls.logFeedback({
        key: "num_steps",
        score: result.messages.length - 1,
      });
      ls.logOutputs(result);
      expect(toolCalls).toContain("code_tool");
      expect(Math.abs((result.structuredResponse.numeric_answer ?? 0) - answer)).toBeLessThanOrEqual(1);
    }
  );

  ls.test(
    "grounded in the source",
    {
      inputs: { query: "How did Nvidia stock do in 2024?" },
      referenceOutputs: {},
    },
    async ({ inputs: { query }, referenceOutputs: {} }) => {
      const result = await agent.invoke({
        messages: [{ role: "user", content: query }],
      });
      const referenceDocuments = result.messages
        .filter((m): m is ToolMessage => m.name?.includes('tavily_search_results_json') ?? false)
        .map(m => m.content)
        .join('\n');
      const wrappedEvaluator = ls.wrapEvaluator(groundedEvaluator);
      await wrappedEvaluator({
        answer: result.structuredResponse.text_answer ?? "",
        referenceDocuments: referenceDocuments,
      })
      ls.logOutputs(result);
    }
  );
});
typescript
import { expect } from "@jest/globals";
import * as ls from "langsmith/jest";
import agent from "../agent";
import { AIMessage } from "@langchain/core/messages";
import { ChatOpenAI } from "@langchain/openai";

const judgeLLM = new ChatOpenAI({ model: "gpt-4o" });

const groundedEvaluator = async (params: {
  answer: string;
  referenceDocuments: string,
}) => {
  const instructions = [
    "Return 1 if the ANSWER is grounded in the DOCUMENTS",
    "Return 0 if the ANSWER is not grounded in the DOCUMENTS",
  ].join("\n");

  const grade = await judgeLLM.invoke([
    { role: "system", content: instructions },
    { role: "user", content: `ANSWER: ${params.answer}\nDOCUMENTS: ${params.referenceDocuments}` },
  ]);
  const score = parseInt(grade.content.toString());
  return { key: "groundedness", score };
};

ls.describe("Agent Tests", () => {
  ls.test.each([
    { inputs: { query: "Hello!" }, referenceOutputs: { numMessages: 2 } },
    { inputs: { query: "How are you doing?" }, referenceOutputs: { numMessages: 2 } },
  ])(
    "should not use tools on offtopic query: %s",
    async ({ inputs: { query }, referenceOutputs: { numMessages } }) => {
      const result = await agent.invoke({
        messages: [{ role: "user", content: query }],
      });
      ls.logOutputs(result);
      expect(result.messages).toHaveLength(numMessages);
    }
  );

  ls.test(
    "should search for correct ticker",
    {
      inputs: { query: "What is the price of Apple?" },
      referenceOutputs: { numMessages: 4 },
    },
    async ({ inputs: { query }, referenceOutputs: { numMessages } }) => {
      const result = await agent.invoke({
        messages: [{ role: "user", content: query }],
      });
      const toolCalls = (result.messages[1] as AIMessage).tool_calls || [];
      const tickerQuery = toolCalls[0].args.ticker;
      ls.logOutputs(result);
      expect(tickerQuery).toBe("AAPL");
      expect(result.messages).toHaveLength(numMessages);
    }
  );

  ls.test(
    "should execute code when needed",
    {
      inputs: { query: "What was the average return rate for FAANG stock in 2024?" },
      referenceOutputs: { answer: 53 },
    },
    async ({ inputs: { query }, referenceOutputs: { answer } }) => {
      const result = await agent.invoke({
        messages: [{ role: "user", content: query }],
      });
      const toolCalls = result.messages
        .filter(m => (m as AIMessage).tool_calls)
        .flatMap(m => (m as AIMessage).tool_calls?.map(tc => tc.name));
      ls.logFeedback({
        key: "num_steps",
        score: result.messages.length - 1,
      });
      ls.logOutputs(result);
      expect(toolCalls).toContain("code_tool");
      expect(Math.abs((result.structuredResponse.numeric_answer ?? 0) - answer)).toBeLessThanOrEqual(1);
    }
  );

  ls.test(
    "grounded in the source",
    {
      inputs: { query: "How did Nvidia stock do in 2024 according to analysts?" },
      referenceOutputs: {},
    },
    async ({ inputs: { query }, referenceOutputs: {} }) => {
      const result = await agent.invoke({
        messages: [{ role: "user", content: query }],
      });
      const wrappedEvaluator = ls.wrapEvaluator(groundedEvaluator);
      await wrappedEvaluator({
        answer: result.structuredResponse.text_answer ?? "",
        referenceDocuments: result.structuredResponse.reasoning,
      })
      ls.logOutputs(result);
    }
  );
});

LangChain 中文文档

Copyright © 王码码