Readers

from agno.knowledge.reader.pdf_reader import PDFReader

reader = PDFReader(chunk=True, chunk_size=5000)
documents = reader.read("company_handbook.pdf")

# Output structure
Document(
    content="The extracted text...",
    id="unique_id",
    name="document_name",
    meta_data={"page": 1, "source": "handbook.pdf"},
)

from agno.knowledge.knowledge import Knowledge
from agno.knowledge.reader.pdf_reader import PDFReader

knowledge = Knowledge(vector_db=vector_db)

# Use custom reader configuration
reader = PDFReader(chunk_size=3000, split_on_pages=True)
knowledge.insert(path="documents/", reader=reader)

from agno.knowledge.reader.reader_factory import ReaderFactory

# By file extension
reader = ReaderFactory.get_reader_for_extension(".pdf")  # PDFReader
reader = ReaderFactory.get_reader_for_extension(".csv")  # CSVReader

# By URL
reader = ReaderFactory.get_reader_for_url("https://youtube.com/watch?v=...")  # YouTubeReader

reader = PDFReader(
    chunk=True,           # Enable chunking (default: True)
    chunk_size=5000,      # Characters per chunk
)

# PDF with encryption and OCR
reader = PDFReader(
    password="secret",
    read_images=True,     # OCR for images
    split_on_pages=True,  # One document per page
)

# CSV with custom encoding
reader = CSVReader(
    encoding="latin-1",
)

# Text with encoding override
reader = TextReader(
    encoding="utf-8",
)

documents = reader.read(
    "file.pdf",
    name="custom_document_name",  # Override default naming
    password="runtime_password",  # Password at read time
)

import asyncio

# Single file
documents = await reader.async_read("file.pdf")

# Batch processing
tasks = [reader.async_read(file) for file in files]
all_documents = await asyncio.gather(*tasks)

from agno.knowledge.chunking.semantic_chunking import SemanticChunking

reader = PDFReader(
    chunk=True,
    chunking_strategy=SemanticChunking(),
)

reader = WebsiteReader(allowed_hosts=["docs.agno.com"])

documents = reader.read("corrupted.pdf")
if not documents:
    print("Failed to read file, check logs for details")