Nimble Extract

import getpass
import os

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

from langchain_nimble import NimbleExtractRetriever

# 基础检索器 - 需要提供要提取的 URL
retriever = NimbleExtractRetriever()

from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_openai import ChatOpenAI

# 创建 RAG 提示
prompt = ChatPromptTemplate.from_template(
    """Analyze the extracted content from the provided URLs.
Answer the question based only on the extracted content.
If you cannot answer based on the content, say so.

Content: {content}

Question: {question}

Answer:"""
)

llm = ChatOpenAI(model="gpt-4o-mini")

# 配置内容提取检索器
retriever = NimbleExtractRetriever(
    parsing_type="markdown",
    wait=3000
)


def format_docs(docs):
    return "\n\n".join(doc.page_content for doc in docs)


# 示例：从 LangChain 文档中提取并分析内容
urls = [
    "https://python.langchain.com/docs/concepts/retrievers/",
    "https://python.langchain.com/docs/concepts/tools/",
    "https://python.langchain.com/docs/tutorials/agents/"
]

# 创建一个将 URL 传递给检索器的自定义可运行对象
def get_docs(question):
    # 在实际场景中，URL 可能由前置步骤确定
    return retriever.invoke(urls)


# 构建 RAG 链
chain = (
    {
        "content": lambda _: get_docs(_) | format_docs,
        "question": RunnablePassthrough()
    }
    | prompt
    | llm
    | StrOutputParser()
)

# 对提取的内容提问
response = chain.invoke("What are the key differences between retrievers and tools in LangChain?")
print(response)

Based on the extracted LangChain documentation, here are the key differences:

**Retrievers:**
- Interface for document retrieval based on unstructured queries
- Primary use case is RAG (Retrieval Augmented Generation)
- Returns documents from various sources like vector stores
- Focuses on semantic search and information retrieval
- Core component for question-answering systems

**Tools:**
- Interface for agents to interact with external systems
- Enables actions beyond text generation (API calls, calculations, web search)
- Used by agents to extend capabilities dynamically
- Supports both synchronous and asynchronous execution
- Can be chained together for complex workflows

**Agents:**
- High-level orchestrators that use tools to accomplish tasks
- Make decisions about which tools to use and when
- Can combine multiple tools to solve complex problems
- Tutorial shows how to build agent workflows with tool integration

The documentation emphasizes that retrievers are specialized for information retrieval, while tools provide broader action capabilities for agents.

from langchain_nimble import NimbleExtractRetriever

# 针对 JavaScript 密集型文档网站优化的检索器
retriever = NimbleExtractRetriever(
    parsing_type="markdown",
    driver="vx10",  # 对复杂 SPA 使用全面驱动
    wait=5000,  # 等待最多 5 秒以完整渲染页面
    render=True,  # 启用 JavaScript 渲染
    locale="en-US",
    country="US"
)

# 从特定 LangChain 文档页面提取内容
docs = retriever.invoke([
    "https://python.langchain.com/docs/concepts/chat_models/",
    "https://python.langchain.com/docs/concepts/prompts/"
])