Tavily 提取集成

使用 LangChain Python 与 Tavily 提取工具集成。

Tavily 是专为 AI 智能体（LLM）构建的搜索引擎，能够快速提供实时、准确、事实性的结果。Tavily 提供一个 Extract 端点，可用于从一个或多个 URL 中提取内容。

概述

集成细节

类名	包名	可序列化	JS 支持	版本
@[TavilyExtract]	@[langchain-tavily]	✅	✅

工具特性

返回工件	原生异步	返回数据	定价
❌	✅	原始内容和图片	每月 1,000 个免费信用额度

设置

集成位于 langchain-tavily 包中。

pip install -qU langchain-tavily

凭证

我们还需要设置 Tavily API 密钥。您可以通过访问 此网站 并创建账户来获取 API 密钥。

import getpass
import os

if not os.environ.get("TAVILY_API_KEY"):
    os.environ["TAVILY_API_KEY"] = getpass.getpass("Tavily API key:\n")

实例化

该工具在实例化期间接受各种参数：

• extract_depth (可选, str): 提取深度，可以是 “basic” 或 “advanced”。默认为 “basic”。
• include_images (可选, bool): 是否在提取中包含图片。默认为 False。

有关可用参数的全面概述，请参阅 Tavily Extract API 文档

from langchain_tavily import TavilyExtract

tool = TavilyExtract(
    extract_depth="basic",
    include_images=False,
)

调用

使用参数直接调用

Tavily 提取工具在调用期间接受以下参数：

• urls (必需): 要从中提取内容的 URL 列表。
• extract_depth 和 include_images 也可以在调用期间设置

注意：可选参数可用于智能体动态设置，如果您在实例化期间设置了一个参数，然后在调用工具时使用不同的值，该工具将使用您在调用期间传递的值。

tool.invoke({"urls": ["https://en.wikipedia.org/wiki/Lionel_Messi"]})

{'results': [{'url': 'https://en.wikipedia.org/wiki/Lionel_Messi',
   'raw_content': 'Lionel Messi - Wikipedia\nJump to content\nMain menu\nMain menu\nmove to sidebar hide\nNavigation\n\nMain page\nContents\nCurrent events\nRandom article\nAbout Wikipedia\nContact us\n\nContribute\n\nHelp\nLearn to edit\nCommunity portal\nRecent changes\nUpload file\nSpecial pages\n\n  \nSearch\nSearch\nAppearance\n\nDonate\nCreate account\nLog in\n\nPersonal tools\n\nDonate\nCreate account\nLog in\n\nPages for logged out editors learn more\n\nContributions\nTalk\n\nContents\nm... (truncated) ',
   'images': []}],
 'failed_results': [],
 'response_time': 0.02}

使用 ToolCall 调用

我们也可以使用模型生成的 ToolCall 调用该工具，此时将返回一个 ToolMessage：

# This is usually generated by a model, but we'll create a tool call directly for demo purposes.
model_generated_tool_call = {
    "args": {"urls": ["https://en.wikipedia.org/wiki/Lionel_Messi"]},
    "id": "1",
    "name": "tavily",
    "type": "tool_call",
}
tool_msg = tool.invoke(model_generated_tool_call)

# The content is a JSON string of results
print(tool_msg.content[:400])

{"results": [{"url": "https://en.wikipedia.org/wiki/Lionel_Messi", "raw_content": "Lionel Messi - Wikipedia\nJump to content\nMain menu\nMain menu\nmove to sidebar hide\nNavigation\n\nMain page\nContents\nCurrent events\nRandom article\nAbout Wikipedia\nContact us\n\nContribute\n\nHelp\nLearn to edit\nCommunity portal\nRecent changes\nUpload file\nSpecial pages\n\n  \nSearch\nSearch\nAppearance\n\

在智能体中使用

我们可以通过将工具绑定到智能体执行器来直接使用我们的工具。这使智能体能够动态设置 Tavily 搜索工具的可用参数。

if not os.environ.get("OPENAI_API_KEY"):
    os.environ["OPENAI_API_KEY"] = getpass.getpass("OPENAI_API_KEY:\n")

from langchain.chat_models import init_chat_model

model = init_chat_model(model="gpt-5.5", model_provider="openai", temperature=0)

from langchain_tavily import TavilyExtract
from langchain.agents import create_agent


tavily_extract_tool = TavilyExtract()

agent = create_agent(model, [tavily_extract_tool])

user_input = "['https://en.wikipedia.org/wiki/Albert_Einstein','https://en.wikipedia.org/wiki/Theoretical_physics']"

stream = agent.stream_events({"messages": user_input}, version="v3")
for snapshot in stream.values:
    snapshot["messages"][-1].pretty_print()

================================ Human Message =================================

['https://en.wikipedia.org/wiki/Albert_Einstein','https://en.wikipedia.org/wiki/Theoretical_physics']
================================== Ai Message ==================================
Tool Calls:
  tavily_extract (call_BAK906Cpy8fDZttwqYTMdkKp)
 Call ID: call_BAK906Cpy8fDZttwqYTMdkKp
  Args:
    urls: ['https://en.wikipedia.org/wiki/Albert_Einstein']
    extract_depth: advanced
    include_images: False
  tavily_extract (call_4NFRB92QpiI5jnCTGr76dgMX)
 Call ID: call_4NFRB92QpiI5jnCTGr76dgMX
  Args:
    urls: ['https://en.wikipedia.org/wiki/Theoretical_physics']
    extract_depth: advanced
    include_images: False
================================= Tool Message =================================
Name: tavily_extract

{"results": [{"url": "https://en.wikipedia.org/wiki/Theoretical_physics", "raw_content": "Published Time: 2003-09-21T15:11:11Z\nTheoretical physics - Wikipedia\nJump to content\nMain menu\nMain menu\nmove to sidebar hide\nNavigation\n\nMain page\nContents\nCurrent events\nRandom article\nAbout Wikipedia\nContact us\n\nContribute\n\nHelp\nLearn to edit\nCommunity portal\nRecent changes\nUpload file\nSpecial pages\n\n  \nSearch\nSearch\nAppearance\n\nDonate\nCreate account\nLog in\n\nPersonal tools\n\nDonate\nCreate account\nLog in\n\nPages for logged out editors learn more\n\nContributions\nTalk\n\nContents\nmove to sidebar hide\n\n(Top)\n\n1 Overview\n\n\n2 History\n\n\n3 Mainstream theories... (truncated) ...", "images": []}], "failed_results": [], "response_time": 0.01}
================================== Ai Message ==================================

Here is a summary of the content from the Wikipedia pages on Albert Einstein and Theoretical Physics:

### Albert Einstein
Albert Einstein was a German-born theoretical physicist renowned for developing the theory of relativity, which revolutionized our understanding of space, time, and energy. His mass-energy equivalence formula, E=mc², is one of the most famous equations in physics. Einstein received the 1921 Nobel Prize in Physics for his explanation of the photoelectric effect, which was pivotal in establishing quantum theory.

Einstein's early life was marked by a deep interest in mathematics and physics, leading him to study at the Swiss Federal Polytechnic in Zurich. He worked at the Swiss Patent Office while developing his theories. His "miracle year" in 1905 saw the publication of four groundbreaking papers, including those on special relativity and the photoelectric effect.

Throughout his career, Einstein made significant contributions to statistical mechanics, quantum theory, and cosmology. He was a vocal advocate for civil rights and pacifism, and he played a role in alerting the U.S. to the potential of nuclear weapons during World War II. Einstein spent his later years at the Institute for Advanced Study in Princeton, New Jersey, where he continued to work on a unified field theory until his death in 1955.

### Theoretical Physics
Theoretical physics is a branch of physics that uses mathematical models and abstractions to explain and predict natural phenomena. It contrasts with experimental physics, which uses empirical methods to test these theories. Theoretical physics has been instrumental in developing major scientific theories, such as relativity and quantum mechanics.

The field involves creating models to describe physical events and is judged by how well these models predict empirical observations. Theoretical physics has a rich history, dating back to ancient philosophers and evolving significantly during the Scientific Revolution with figures like Galileo and Newton.

Modern theoretical physics seeks to unify existing theories and explore new concepts, often using advanced mathematics. It includes mainstream theories like the Big Bang, chaos theory, and quantum mechanics, as well as proposed and fringe theories that are still under investigation. Thought experiments, such as Schrödinger's cat, play a crucial role in theoretical physics by exploring scenarios that are not easily tested in reality.

Both pages highlight the interplay between theory and experimentation in advancing our understanding of the universe, with Einstein's work serving as a prime example of theoretical physics' impact.

---

API 参考

有关 Tavily Extract API 功能和配置的详细文档，请前往 API 参考：docs.tavily.com/documentation/api-reference/endpoint/extract

---

官方原文：src/oss/python/integrations/tools/tavily_extract.mdx · 非官方翻译，译文由 AI 生成，以英文原文为准。