Backbone AI Documentation
One API for multiple AI providers, structured data extraction, prompt management, and document conversion. Go from zero to your first extraction in under five minutes.
Quick Start
Create a project
Head to Projects in the dashboard and create a new project. Projects group your schemas and extractions.
Define a schema
Inside your project, create a schema — a standard JSON Schema describing the fields you want to extract:
{
"type": "object",
"properties": {
"name": { "type": "string" },
"email": { "type": "string", "format": "email" },
"phone": { "type": "string" }
},
"required": ["name"]
}
Commit and label
Hit Commit to lock in an immutable version. The latest label updates automatically — create custom labels like production to pin versions for consumers.
Extract
curl -X POST https://backbone.manfred-kunze.dev/api/v1/projects/{projectId}/extractions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk_your_api_key" \
-d '{
"schemaId": "your-schema-id",
"inputText": "Contact: John Doe, [email protected], 555-1234",
"model": "gpt-4o"
}'
Response:
{
"status": "COMPLETED",
"result": {
"structuredOutput": {
"name": "John Doe",
"email": "[email protected]",
"phone": "555-1234"
}
}
}
Schema in, structured data out. See the full Data Extraction docs for async processing, chunking strategies, and more.
Resources
LLM Gateway
One API, any provider. Use the OpenAI SDK you already know — Backbone routes to the right backend.
Data Extraction
Define a JSON schema, feed in any text or document, and get back validated structured output.
Document Conversion
Turn PDFs, Word docs, emails, and images into clean text ready for extraction.
Prompt Management
Version-controlled prompt templates with variables, labels, and built-in testing.