📘

Prerequisites

1. ✨ Create a Workspace Set up your environment in the HrFlow.ai portal.
2. 🔑 Get your API Key Retrieve your API_KEY from the settings.
3. 🧠 Activate Profile Embedding API Ensure the embedding service is enabled for your plan.

The Embedding API generates SOTA, HR-native, and cross-lingual vectors for Profiles to power similarity search, retrieval, clustering, and HR-grade ML. Unlike generic LLM vectors, these encoders are pretrained on 1.2B hiring decisions to capture career trajectories and hiring signals beyond simple keyword overlap.

This endpoint allows you to vectorize profiles by providing either raw data objects or references to profiles already indexed in your sources. Results are deterministic: the same inputs will consistently return the same vectors.

1. How to get a Profile Object

Since this endpoint requires structured data, you can obtain a valid HrFlow.ai Profile Object through two primary methods:

• Manual Construction: Build the object programmatically by following our Profile Object 📖 The Profile Object Specification. This allows you to map data from your own internal database or CRM.
• Automated Parsing: Convert a raw resume or CV file into a structured Profile Object using our Parsing API (e.g. 🧠 Parse a Resume in a Source) This is the most efficient way to transform unstructured documents into "HR-ready" data for vectorization.

2. Available Algorithms

Choose the right algorithm key based on your use case, data type, and precision needs.

2. Request headers