Files API
CV parsing API
Turn resumes into clean, structured JSON in seconds — extract personal info, experience, education, skills, and more with high accuracy.
Powerful CV parsing infrastructure, ready to integrate
The Files API extracts and normalises candidate data from common file types — names, contact details, work history, education, skills, certifications, and more — returning a consistent JSON schema you can search and match against immediately.
What you can do with CV parsing
- Extract personal details, work history, education, skills, and certifications.
- Normalise job titles, skills, dates, and locations for reliable search and match.
- Support PDFs, DOCX, TXT, and scanned images with OCR where needed.
- Handle multiple languages and regional formats.
- Return clean JSON that maps to your existing candidate schema.
- Process in real time via API or batch using webhooks.
CV parsing features
- High-accuracy entity extraction with role, seniority, and tenure inference.
- Multilingual support and OCR for scanned documents.
- Configurable JSON schema with field-level confidence scores.
- Deduplication helpers and section segmentation.
- Optional PII redaction and field-level validation.
- Developer-friendly docs, SDKs, and webhook callbacks.
Why choose Ruvia?
- Built for developers: fast integration, clear docs, real support.
- Accurate and fast: production-grade parsing at scale.
- Security-first: encryption in transit and at rest, GDPR compliant.
- Enterprise-ready: scales to millions of documents per month.
- Transparent, usage-based pricing with flexible credits.
“At GoHire we process thousands of job postings every month, and fraudulent ads were becoming a real risk to both our clients and candidates. Since integrating Ruvia’s Trust API, we automatically block 98% of scam job postings before they go live. It’s seamless, highly accurate, and gives us a huge competitive edge in building trust with our customers.”
Chris Smith
Co-Founder at GoHire
Frequently asked questions
What file types are supported?
PDF, DOCX, TXT, and common image formats (PNG, JPEG, TIFF) with OCR. You can parse multiple formats with a single integration.
What does the output look like?
A consistent JSON schema including personal details, work history, education, skills, certifications, and metadata such as confidence scores and detected language.
How accurate is the parser?
Accuracy depends on document quality and language. We provide field-level confidence scores and continuous improvements driven by anonymised usage signals.
Is processing real time?
Yes — typical responses are returned in seconds. For large batches or heavy OCR, you can use webhooks for asynchronous processing.
How do you handle PII and compliance?
Data is encrypted in transit and at rest. We support GDPR/CCPA compliance, optional PII redaction, and data minimisation policies. See our security page for details.
How is this priced?
Pricing uses our credit model (e.g., 1 credit = £0.01). Each parse consumes credits based on file type and processing depth (OCR, language detection). See the pricing page for per-call credits.
Can I test before integrating?
Yes. New accounts include free trial credits and a sandbox key so you can evaluate accuracy and speed with your own documents.