Praison AI

OCR

Extract text and markdown from PDFs and images with OCRAgent

Extract text from PDFs and images with OCRAgent — pass a URL or base64 source and get markdown-ready text back.

python
from praisonaiagents import Agent, OCRAgent

ocr = OCRAgent()
text = ocr.read("https://arxiv.org/pdf/2201.04234")
agent = Agent(name="Reader", instructions="Summarise documents clearly.")
agent.start(f"Summarise this paper:\n\n{text[:4000]}")

The user supplies a document URL; OCR extracts text and the agent summarises it.

Diagram

Document URL

OCRAgent

Extracted Text

Agent / Pipeline

Quick Start

  1. Extract text from a PDF
    python
    from praisonaiagents import Agent, OCRAgent

ocr = OCRAgent()
text = ocr.read("https://arxiv.org/pdf/2201.04234")

agent = Agent(name="Reader", instructions="Summarise documents clearly.")
summary = agent.start(f"Summarise this paper:\n\n{text[:4000]}")
  2. Configure with OCRConfig
    python
    import os
from praisonaiagents import OCRAgent, OCRConfig

config = OCRConfig(
    pages=[0, 1],
    timeout=300,
    api_key=os.getenv("MISTRAL_API_KEY"),
)

ocr = OCRAgent(ocr=config)
result = ocr.extract("https://arxiv.org/pdf/2201.04234")

for page in result.pages:
    print(f"Page {page.index}: {page.markdown[:100]}")
  3. Async extraction
    python
    import asyncio
from praisonaiagents import OCRAgent

async def main():
    ocr = OCRAgent()
    text = await ocr.aread("https://example.com/screenshot.png")
    print(text)

asyncio.run(main())

How It Works

Diagram
TextProviderOCRAgentUserTextProviderOCRAgentUserread(url) / extract(url)mistral/mistral-ocr-latestpages + markdownplain text or OCRResponse
MethodReturnsUse when
read / areadstr (markdown)You only need plain text
extract / aextractFull result with pagesYou need per-page markdown or metadata

Configuration Options

OCRAgent

Agent class reference

 OCRConfig

Configuration dataclass

OptionTypeDefaultDescription
include_image_base64boolFalseInclude base64-encoded image bytes in the result
pagesOptional[List[int]]NoneSpecific page indexes to extract (0-indexed)
image_limitOptional[int]NoneMax images to process
timeoutint600Request timeout in seconds
api_baseOptional[str]NoneOverride provider base URL
api_keyOptional[str]NoneOverride provider API key

Common Patterns

Specific pages

python
from praisonaiagents import OCRAgent

ocr = OCRAgent()
result = ocr.extract("https://example.com/large.pdf", pages=[0, 1, 2])
print(result.pages[0].markdown)

Image URL

python
from praisonaiagents import OCRAgent

ocr = OCRAgent()
text = ocr.read("https://example.com/screenshot.png")
print(text)

Batch loop

python
from praisonaiagents import OCRAgent

ocr = OCRAgent()
urls = [
    "https://example.com/doc1.pdf",
    "https://example.com/doc2.pdf",
]

for url in urls:
    print(ocr.read(url)[:500])

Async concurrency

python
import asyncio
from praisonaiagents import OCRAgent

async def extract_all(urls):
    ocr = OCRAgent()
    tasks = [ocr.aread(url) for url in urls]
    return await asyncio.gather(*tasks)

texts = asyncio.run(extract_all(["https://example.com/a.pdf", "https://example.com/b.pdf"]))

Providers

Mistral OCR

Provider setup and model options

Best Practices

Use HTTPS URLs or base64

Local file paths are not supported — upload to a reachable URL or encode as base64 before calling OCRAgent.

Extract pages selectively for large PDFs

Use pages=[0, 1, 2] via OCRConfig or method kwargs to limit cost and latency on multi-hundred-page documents.

Tune timeout for slow documents

Default timeout is 600 seconds. Lower it for quick image OCR; raise it for large scanned PDFs.

API key precedence

Pass api_key on OCRConfig, on OCRAgent(...), or set MISTRAL_API_KEY in the environment — instance config wins over env vars.

Related

Knowledge

Index extracted text for retrieval

 Toolsets

Bundle document-processing tools for agents