post https://api.adept-id.com/extract-skills/v3
Given multiple blocks of text, returns a list of professional and technical skills.
Use this endpoint to extract lists of skills from blocks of text (e.g., text from a resume, job description, syllabus). The endpoint accepts batches (a list of blocks of text containing one or more phrases or sentences each) and returns categorized lists of normalized (recognized by AdeptID’s search and match endpoints) skills for each batch.
This endpoint succeeds Extract Skills, introducing batch submission, and separating languages from skills and certifications in the response body.
Additional Notes:
- Enabling this service: This is a value-added service and is not available by default. To access this service, please contact your AdeptID Partner Success team.
- Skill Normalization vs. Skill Extraction: This endpoint works best when passed blocks of text, each containing one or more phrases or sentences. If the input is an already-extracted list of raw skills (i.e., as seen in raw text from resumes, job descriptions, etc.), this endpoint will perform poorly; instead, use Normalize Skills or Normalize Skills Batch.
- Document Parsing vs. Skill Normalization: This endpoint does not parse additional entities (e.g., contact information, education) from a resume or job posting; this should be done via Parse Resume or Parse Job.
- Supporting Models: AdeptID uses proprietary and third-party models to extract raw skills from a block of text and normalize those skills to a specific skills taxonomy. The below graphic depicts the difference between Extract Skills Batch and Normalize Skills Batch.
extract-skills-batch does both extraction and normalization, while normalize-skills-batch does only normalization.