LangChain Integration

pip install langchain-docling

from langchain_docling import DoclingLoader

# Load a document
loader = DoclingLoader(file_path="document.pdf")
documents = loader.load()

# Use in your LangChain pipeline
for doc in documents:
    print(doc.page_content)
    print(doc.metadata)

from langchain_docling import DoclingLoader
from docling.document_converter import DocumentConverter
from docling.datamodel.pipeline_options import PipelineOptions

# Configure Docling options
pipeline_options = PipelineOptions()
pipeline_options.do_ocr = True
pipeline_options.do_table_structure = True

# Create loader with custom options
loader = DoclingLoader(
    file_path="document.pdf",
    pipeline_options=pipeline_options
)

documents = loader.load()

from langchain_docling import DoclingLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.vectorstores import FAISS
from langchain_openai import OpenAIEmbeddings

# Load documents
loader = DoclingLoader(file_path="document.pdf")
documents = loader.load()

# Split documents
text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000,
    chunk_overlap=200
)
splits = text_splitter.split_documents(documents)

# Create vector store
embeddings = OpenAIEmbeddings()
vectorstore = FAISS.from_documents(splits, embeddings)

# Query
retriever = vectorstore.as_retriever()
results = retriever.get_relevant_documents("What is the main topic?")