Langchain笔记1之loader

本文记录学习笔记，后面有新的bug和实践会不断更新～

Loader 加载器

1.文件夹 DirectoryLoader、
2.Azure 存储 AzureBlobStorageContainerLoader
3.CSV文件 CSVLoader
        ......

还有多种可看官网

实战之PDF---参考以下网址

How to load PDFs | 🦜️🔗 LangChain

1.基本loader以及嵌入大模型

%pip install -qU pypdf

# pdf文件加载器
# 返回Document对象的迭代器
from langchain_community.document_loaders import PyPDFLoader

loader = PyPDFLoader(file_path)
pages = []
async for page in loader.alazy_load():
    pages.append(page)

print(f"{pages[0].metadata}\n")
print(pages[0].page_content)



# 使用OpenAI嵌入，首先需要配置openai-key
from langchain_core.vectorstores import InMemoryVectorStore
from langchain_openai import OpenAIEmbeddings

vector_store = InMemoryVectorStore.from_documents(pages, OpenAIEmbeddings())
docs = vector_store.similarity_search("What is LayoutParser?", k=2)
for doc in docs:
    print(f'Page {doc.metadata["page"]}: {doc.page_content[:300]}\n')

2. 对pdf进行精细化处理，有时候需要更精细的文本分割（例如，分成不同的段落、标题、表格或其他结构）或需要从图像中提取文本

%pip install -qU langchain-unstructured

#key
import getpass
import os

if "UNSTRUCTURED_API_KEY" not in os.environ:
    os.environ["UNSTRUCTURED_API_KEY"] = getpass.getpass("Unstructured API Key:")


# 非结构化加载器
from langchain_unstructured import UnstructuredLoader

loader = UnstructuredLoader(
    file_path=file_path,
    strategy="hi_res",
    partition_via_api=True,
    coordinates=True,
)
docs = []
for doc in loader.lazy_load():
    docs.append(doc)

加载的每个Document都代表一个结构，如标题、段落或表格。

#识别并提取一个表格

import fitz
import matplotlib.patches as patches
import matplotlib.pyplot as plt
from PIL import Image

#画框
def plot_pdf_with_boxes(pdf_page, segments):

    # 坐标
    pix = pdf_page.get_pixmap()
    pil_image = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)

    fig, ax = plt.subplots(1, figsize=(10, 10))
    ax.imshow(pil_image)
    categories = set()

    # 标题、图像、图表对应框的不同颜色
    category_to_color = {
        "Title": "orchid",
        "Image": "forestgreen",
        "Table": "tomato",
    }
    for segment in segments:
        points = segment["coordinates"]["points"]
        layout_width = segment["coordinates"]["layout_width"]
        layout_height = segment["coordinates"]["layout_height"]
        scaled_points = [
            (x * pix.width / layout_width, y * pix.height / layout_height)
            for x, y in points
        ]
        box_color = category_to_color.get(segment["category"], "deepskyblue")
        categories.add(segment["category"])
        rect = patches.Polygon(
            scaled_points, linewidth=1, edgecolor=box_color, facecolor="none"
        )
        ax.add_patch(rect)

    # Make legend
    legend_handles = [patches.Patch(color="deepskyblue", label="Text")]

    for category in ["Title", "Image", "Table"]:
        if category in categories:
            legend_handles.append(
                patches.Patch(color=category_to_color[category], label=category)
            )
    ax.axis("off")
    ax.legend(handles=legend_handles, loc="upper right")
    plt.tight_layout()
    plt.show()

# 划分pdf的图像、标题、文档数据
def render_page(doc_list: list, page_number: int, print_text=True) -> None:
    pdf_page = fitz.open(file_path).load_page(page_number - 1)
    page_docs = [
        doc for doc in doc_list if doc.metadata.get("page_number") == page_number
    ]
    segments = [doc.metadata for doc in page_docs]
    plot_pdf_with_boxes(pdf_page, segments)
    if print_text:
        for doc in page_docs:
            print(f"{doc.page_content}\n")

具体各类数据解析，后续再更～

模型应用的数据处理

%pip install -qU PyMuPDF pillow langchain-openai

import base64
import io

import fitz
from PIL import Image
from langchain_openai import ChatOpenAI
from IPython.display import Image as IPImage
from IPython.display import display
from langchain_core.messages import HumanMessage


def pdf_page_to_base64(pdf_path: str, page_number: int):
    pdf_document = fitz.open(pdf_path)
    page = pdf_document.load_page(page_number - 1)  # input is one-indexed
    pix = page.get_pixmap()
    img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)

    buffer = io.BytesIO()
    img.save(buffer, format="PNG")

    return base64.b64encode(buffer.getvalue()).decode("utf-8")



base64_image = pdf_page_to_base64(file_path, 11)
display(IPImage(data=base64.b64decode(base64_image)))


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


query = "What is the name of the first step in the pipeline?"

message = HumanMessage(
    content=[
        {"type": "text", "text": query},
        {
            "type": "image_url",
            "image_url": {"url": f"data:image/jpeg;base64,{base64_image}"},
        },
    ],
)
response = llm.invoke([message])
print(response.content)

先更到这，后续会持续学习持续更新哒～