Docprompt is a library for Document AI. It aims to make enterprise-level document analysis easy thanks to the zero-shot capability of large language models.
Documents and large language models
TextBlock, BoundingBox, etcUse the package manager pip to install Docprompt.
pip install docprompt
With an OCR provider
pip install "docprompt[google]
With search support
pip install "docprompt[search]"
from docprompt import load_document
# Load a document
document = load_document("path/to/my.pdf")
# Rasterize a single page using Ghostscript
page_number = 5
rastered = document.rasterize_page(page_number, dpi=120)
# Split a pdf based on a page range
document_2 = document.split(start=125, stop=130)
Coverting documents into markdown is a great way to prepare documents for downstream chunking or ingestion into a RAG system.
from docprompt import load_document_node
from docprompt.tasks.markerize import AnthropicMarkerizeProvider
document_node = load_document_node("path/to/my.pdf")
markerize_provider = AnthropicMarkerizeProvider()
markerized_document = markerize_provider.process_document_node(document_node)
Extract tables with SOTA speed and accuracy.
from docprompt import load_document_node
from docprompt.tasks.table_extraction import AnthropicTableExtractionProvider
document_node = load_document_node("path/to/my.pdf")
table_extraction_provider = AnthropicTableExtractionProvider()
extracted_tables = table_extraction_provider.process_document_node(document_node)
from docprompt import load_document, DocumentNode
from docprompt.tasks.ocr.gcp import GoogleOcrProvider
provider = GoogleOcrProvider.from_service_account_file(
project_id=my_project_id,
processor_id=my_processor_id,
service_account_file=path_to_service_file
)
document = load_document("path/to/my.pdf")
# A container holds derived data for a document, like OCR or classification results
document_node = DocumentNode.from_document(document)
provider.process_document_node(document_node) # Caches results on the document_node
document_node[0].ocr_result # Access OCR results
When a large language model returns a result, we might want to highlight that result for our users. However, language models return results as text, while what we need to show our users requires a page number and a bounding box.
After extracting text from a PDF, we can support this pattern using DocumentProvenanceLocator, which lives on a DocumentNode
from docprompt import load_document, DocumentNode
from docprompt.tasks.ocr.gcp import GoogleOcrProvider
provider = GoogleOcrProvider.from_service_account_file(
project_id=my_project_id,
processor_id=my_processor_id,
service_account_file=path_to_service_file
)
document = load_document("path/to/my.pdf")
# A container holds derived data for a document, like OCR or classification results
document_node = DocumentNode.from_document(document)
provider.process_document_node(document_node) # Caches results on the document_node
# With OCR results available, we can now instantiate a locator and search through documents.
document_node.locator.search("John Doe") # This will return a list of all terms across the document that contain "John Doe"
document_node.locator.search("Jane Doe", page_number=4) # Just return results a list of matching results from page 4
This functionality uses a combination of rtree and the Rust library tantivy, allowing you to perform thousands of searches in seconds :fire: :rocket:
FAQs
Documents and large language models.
We found that docprompt demonstrated a healthy version release cadence and project activity because the last version was released less than a year ago. It has 1 open source maintainer collaborating on the project.
Did you know?
Socket for GitHub automatically highlights issues in each pull request and monitors the health of all your open source dependencies. Discover the contents of your packages and block harmful activity before you install or update your dependencies.
Research
Security News
Malicious Go packages are impersonating popular libraries to install hidden loader malware on Linux and macOS, targeting developers with obfuscated payloads.
Security News
Bybit's $1.46B hack by North Korea's Lazarus Group pushes 2025 crypto losses to $1.6B in just two months, already surpassing all of 2024's $1.49B total.
Security News
OpenSSF has published OSPS Baseline, an initiative designed to establish a minimum set of security-related best practices for open source software projects.