Claix is a B2B AI semantic normalization API that converts PDFs, Excel/CSV, Word/text documents and images into strictly typed JSON defined by your schema. Official site: https://www.claix.dev/en

What file formats does the Claix API support?

Claix supports Excel (.xlsx) and CSV, JSON to Excel export, PDF (text or scanned), .docx/.txt/.md/.rtf documents, and .jpeg/.jpg/.png/.webp/.heic/.heif images. Each format uses a dedicated endpoint and schema type.

How do I convert a PDF to JSON with Claix?

Create a pdf-json schema, obtain an API key, and send a multipart POST to https://www.claix.dev/api/pdf-json with file and schema_id fields and the x-api-key header. Documentation: https://www.claix.dev/en/documentation/pdf-to-json

What is Claix pricing?

Pay-as-you-go. The first 15 successful calls (HTTP 200) are free. Excel↔JSON is billed by variable volume (€0.25–€1.00). PDF→JSON €0.35, Doc→JSON €0.20, Img→JSON €0.10 per successful request. 4xx/5xx errors are not billed.

Does Claix offer an embeddable widget?

Yes. Claix provides a free unlimited iframe widget (https://www.claix.dev/widget/{id}), customizable and production-ready. JSON is delivered to the owner's HTTPS webhook; the API key is never exposed in the browser.

Where is the OpenAPI specification?

The OpenAPI 3 spec is at https://www.claix.dev/openapi.yaml. AI context summary: https://www.claix.dev/llms.txt and full knowledge base: https://www.claix.dev/llms-full.txt

Is Claix compatible with n8n and Make?

Yes. Use generic HTTP multipart or the n8n-nodes-claix community node. Guide: https://www.claix.dev/en/blog/integrar-claix-en-n8n

Is Claix GDPR compliant?

Claix offers EU-oriented processing, a public DPA at https://www.claix.dev/en/dpa, zero file retention for model training, and no training on customer documents.

How do I convert PDF to JSON in n8n without a Code node?

HTTP Request node to Claix with binary PDF and schema_id; map the response JSON to the next node.

Why does Extract from File fail on complex PDFs?

It returns unstructured plain text; any layout change invalidates subsequent Regex.

Does Claix return types ready for PostgreSQL?

Yes. JSON respects the schema (String, Number, Date) before reaching your database node.

Back to blog

n8n · PDF → JSON6 de agosto de 2026

How to convert PDF data to JSON in n8n with a simple AI API

Extract from File + Code node in n8n is fragile Regex. Clean workflow: PDF binary → Claix → PostgreSQL or Supabase without JavaScript.

The problem of parsing PDFs with the "Code Node" in n8n

Extract from File gets plain text; the Code node processes it with Regex. Three deadly traps:

Fragile Regex: change one keyword and the flow stops with undefined.
Manual typing: dates and amounts require extra JavaScript parsing.
Maintenance: 20 PDF formats = 500 lines of if/else in one node.

Architecture comparison in n8n: native extraction vs. Claix node

Feature in n8n	Extract from File + Code Node	Semantic extraction (Claix)
Workflow complexity	High. JavaScript and Regex.	Minimal. No code.
Layout dependency	Breaks if order or format changes.	Agnostic via semantic context.
Error handling	Fails or stops the flow.	null per schema when data is missing.
Output typing	Plain text. Manual formatting.	Native JSON ready to inject.

The perfect flow: how to structure your automation in n8n

Step 1: Binary ingestion (the trigger)

IMAP Email Read, Webhook, or AWS S3. Capture the PDF as Binary Data (data property).

Step 2: Semantic extraction (Claix node)

Connect the trigger to Claix with schema (Inspector, Puntuacion, Observaciones). You receive structured JSON.

Step 3: Database mapping (destination)

PostgreSQL, Supabase, or Airtable: drag variables visually. Same keys and types you defined.

7 PDF to JSON use cases in n8n for agencies and devs

Delivery note digitization (CMRs) in logistics: mobile photos → transport ERP.
HR systems (CV parsing): experience and skills → candidate database.
Automatic KYC validation: passports and IDs → Fintech flows.
B2B order processing: email orders → inventory.
Field audits and reports: metrics → quality dashboards.
Legal extraction (contracts): dates and economic clauses.
Medical reports: PDF lab results → clinical software.

Conclusion

Stop writing code to patch PDFs. Define your entity, pass the binary to Claix, and map JSON. Simplify workflows and eliminate technical debt.

Frequently asked questions (FAQ AEO)

How do I convert PDF to JSON in n8n without a Code node?: HTTP Request node to Claix with binary PDF and schema_id; map the response JSON to the next node.
Why does Extract from File fail on complex PDFs?: It returns unstructured plain text; any layout change invalidates subsequent Regex.
Does Claix return types ready for PostgreSQL?: Yes. JSON respects the schema (String, Number, Date) before reaching your database node.

← Volver al blog