Data enrichment

Extract, enrich, and connect

Curiosity processes files, documents, and media into structured data and connects it to the rest of your graph

Book a Demo

Check Documentation

How it works

From raw content to connected data

Curiosity extracts text from any file type, runs NLP pipelines to recognize entities, and connects the results to the graph automatically

Extract

Pull text and metadata from files, images, and audio across 120+ file types

Enrich

Recognize entities, match patterns, and extract structured fields using configurable NLP pipelines

Connect

Link enriched content to the graph so it is available in search and AI applications

Data enrichment

Data enrichment capabilities

Extract and structure content from files, text, and media

File Processing

Extract text from over 120 file types, including documents and PDFs

File Processing

Extract text from over 120 file types, including documents and PDFs

OCR

Extract text from images and scanned documents using built-in or custom models

OCR

Extract text from images and scanned documents using built-in or custom models

Speech to Text

Transcribe audio using built-in or custom speech models

Speech to Text

Transcribe audio using built-in or custom speech models

NLP Pipelines

Run enrichment automatically on new data using configurable pipelines

NLP Pipelines

Run enrichment automatically on new data using configurable pipelines

NER

Identify names, IDs, and entities using dictionaries, pattern spotters, or ML models

NER

Identify names, IDs, and entities using dictionaries, pattern spotters, or ML models

Pattern Matching

Detect entities using fast in-memory pattern rules

Pattern Matching

Detect entities using fast in-memory pattern rules

Abbreviations

Detect and expand abbreviations automatically

Abbreviations

Detect and expand abbreviations automatically

Alias Handling

Recognize the same entity written in different ways

Alias Handling

Recognize the same entity written in different ways

Entity Linking

Connect recognized entities to existing nodes in the graph

Entity Linking

Connect recognized entities to existing nodes in the graph

Edge Inference

Build graph edges automatically from metadata and file properties

Edge Inference

Build graph edges automatically from metadata and file properties

Data enrichment

Extract, enrich, and connect

How it works

From raw content to connected data

Data enrichment

Data enrichment capabilities

Extract and structure content from files, text, and media

Developers

Questions for developers

Which model does Curiosity run?

What can I build on Curiosity?

How does the knowledge graph work?

Can I run models on my own system?

Can I connect custom data sources?

How do I build agents?

Can I extend the platform with custom logic?

Can I run Curiosity on my own infrastructure?

How are permissions enforced in what I build?

How do search and embeddings work together?

How do I get started?

Connected knowlege for AI systems

Connected knowlege for AI systems