Document infrastructure for AI products
Turn PDFs, scans, slides, spreadsheets, and images into clean Markdown plus structured JSON your search, RAG, automation, and AI products can actually use.
20 documents free · deterministic parsing · 200 MB · no card requiredFlattened text loses the tables, reading order, page boundaries, and confidence signals your application needs. DocParse preserves useful structure from ingestion onward.
DocParse sits between the files your customers already have and the product experience you want to ship.
Preserve headings, tables, page references, and reading order before chunking and embedding.
Outcome → better retrieval contextAccept the document formats users bring without building and operating a parser zoo yourself.
Outcome → ship document features soonerNormalize uploaded files before classification, review, extraction, routing, or human approval.
Outcome → one reliable intake layerTurn mixed-format repositories into consistent, traceable artifacts for indexing and migration.
Outcome → searchable structure at scaleFidelity without one expensive default
Digital PDFs take a deterministic text-layer path. Scans and complex layouts can use OCR or layout vision. Office files keep their native structure. You get one API and a traceable route decision.
The free Trial validates deterministic parsing first. Image, Fast AI, and Layout-aware processing are enabled only for approved paid workspaces.
Use inline parsing for normal files or jobs, queues, retries, cancellation, and webhooks for slower work.
Inspect routes, job events, warnings, parser versions, manifests, and tenant-scoped artifacts.
External OCR is explicit and tenant-controlled. URL imports and webhooks can be restricted by host.
Send a file to one authenticated endpoint and receive clean Markdown plus layout-aware DocIR JSON. Start inline, then move the same integration to async jobs and webhooks as volume grows.
Open a free workspace, name the key for your backend, and copy the secret once.
Upload multipart or raw binary, or import a permitted HTTPS URL.
Read result.markdown for RAG and result.document when layout, blocks, and provenance matter.
# Keep the key in your backend environment
export DOCPARSE_API_KEY="your_key"
# Parse now and save the complete response
curl -X POST "https://docparse.genedai.me/v1/parse?wait=true" \
-H "Authorization: Bearer $DOCPARSE_API_KEY" \
-F "file=@document.pdf" \
-F "mode=both" \
-o result.json
# Send Markdown to retrieval; keep DocIR for structure
jq -r '.result.markdown' result.json > document.md
jq '.result.document' result.json > document.docir.jsonAdd ?wait=true for normal files and receive the job, Markdown, DocIR, and manifest together.
Remove ?wait=true, then poll the result link or receive a terminal webhook.
Use scoped keys, quotas, idempotency, cancellation, artifact purge, and tenant-specific URL policies.
Commercial controls are part of the service boundary: keys, quotas, idempotency, retention, and auditability live beside the parser.
Hashed API keys, explicit scopes, revocation, monthly quotas, and concurrent job admission.
Idempotency keys, retries, dead-letter handling, cancellation, purge, and signed webhooks.
Original clean-room parsing code, permissive dependencies, and Apache-2.0 project licensing.
05 / Learn before you integrate
Outputs, routes, lifecycle, access, cost, and retention in one product system.
Explore product →Architectures for RAG, AI agents, knowledge bases, search, and automation.
Choose a use case →Direct comparisons, best-tool maps, and migration alternatives grounded in official documentation.
Engineering guides for Markdown, DocIR, routing, evaluation, RAG, and security.
Read engineering guides →Start with 20 text-based documents and prove the deterministic output against your own files before you redesign the pipeline around it.
20 documents · 200 MB
Deterministic parsing · no payment card