Run OCR and document extraction at scale
Run parallelized OCR and document-extraction jobs on the cloud.
Run document processing pipelines
Bring your models and Beam runs them.
One container per document
A 10,000-file backlog becomes a .map() call. Beam fans the work out and streams results back as they finish.
Explore docsPrivate processing
Workloads run in isolated, non-root containers, and Beam's self-hosted deployment keeps confidential documents entirely inside your VPC.
Explore docsAny OCR or vision model
Run TrOCR, layout models, vision LLMs, or any other model that runs in Python, on the GPU you pick.
Explore docsQueues for steady intake
Deploy a managed task queue that ingests documents over HTTP as they arrive and works through them on autoscaling containers.
Explore docsCallbacks per document
Get a webhook the moment each extraction lands instead of polling for results.
Explore docsCorpora on volumes
Stage large document sets on persistent volumes shared across every container in the run. Storage is not billed yet. Planned: $0.0001 per GB-hour of data stored, with no free allowance.
Explore docsBuild the pipeline in three steps
Write the per-document function
Wrap whatever your stack does to one document (OCR, layout parsing, entity extraction) in a decorator.
Fan out or enqueue
Use .map() for backlogs and one-off batches, or deploy a task queue for documents that arrive continuously.
Collect structured results
Return JSON directly, persist artifacts with Output, or receive a webhook per completed document.
# For a steady stream of documents, deploy a queue
from beam import task_queue, Output
@task_queue(
gpu="RTX4090",
callback_url="https://api.your-app.com/extracted",
)
def handler(doc_url: str):
result = extract_structured_data(doc_url)
Output(path=result).save()
$ beam deploy pipeline.py:handler
# Each upload enqueues instantly with a task ID
$ curl -X POST https://your-queue.app.beam.cloud \
-H 'Authorization: Bearer YOUR_TOKEN' \
-d '{"doc_url": "https://example.com/invoice-4821.pdf"}'Frequently asked questions
How do you handle confidential documents?
Workloads are isolated from one another and run in non-root containers. For stricter requirements, Beam offers a self-hosted product that runs entirely in your own environment, so no data leaves your VPC.
Which models can I use?
Any OCR or vision model you can run in Python, such as TrOCR, docTR, layout-aware transformers, or vision LLMs for extraction with reasoning.
How do PDFs get handled?
Use any Python library to split PDFs into page images inside the container, then run your model per page. The whole toolchain is your own code.
What about documents that arrive continuously?
Deploy the same function as a managed task queue. Every upload enqueues instantly, and containers scale with the backlog. Add a cron schedule for nightly sweeps.
How do I get results back into my system?
Return values stream back from .map() calls, files persist via Output, and callback URLs POST to your API as each document completes.
Related use cases
Fan out batch jobs across thousands of containers
Fan out batch inference and ETL across thousands of containers.
InferenceDeploy computer vision models at scale
Detection, segmentation, and classification behind managed APIs.
InferenceServe embedding models for your RAG stack
Host embedding and reranking models on your own endpoints.
Give your agents their own machines
Sign up, install the CLI, and launch a sandbox, VM, or GPU from your terminal or your coding agent.