API Documentation
Getting Started with VectorForgeAI API
Welcome to VectorForgeAI's developer documentation. This guide will help you get started with our API and understand the core concepts.
API Overview
VectorForgeAI provides a REST API that enables you to:
- Create and manage document collections
- Upload and embed documents
- Perform semantic searches across your data
- Generate LLM completions with context from your documents
- Build conversational experiences with memory
Base URL
All API requests should be sent to:
https://api.vectorforgeai.com/v1
Rate Limiting
To ensure fair usage and maintain service quality, the API enforces the following rate limit:
⚡ Rate Limit
300 requests per minute per client
If you exceed this limit, you'll receive a 429 Too Many Requests response. Please implement appropriate retry logic with exponential backoff in your applications.
OpenAPI Specification
We provide a complete OpenAPI 3.0 specification for our API, which you can use to generate client libraries, test your integration, or import into API development tools like Postman or Insomnia.
📋 API Specification
Download our OpenAPI spec to integrate with your preferred development tools:
Next Steps
Now that you've learned the basics, explore these topics to get the most out of the VectorForgeAI API:
- API Authentication - Learn more about securing your API requests
- Document Collections - Organize your data efficiently
- Vector Search - Advanced search capabilities
- Conversation API - Build chat interfaces with memory
Need Help?
If you're having trouble with the API or have questions, we're here to help!