MTEB Retrieve

Overview

This skill provides guidance for text embedding retrieval tasks that involve encoding documents and queries using embedding models, computing similarity scores, and retrieving or ranking documents based on semantic similarity.

Workflow

Step 1: Inspect and Parse Data

Before writing any code, carefully inspect the raw data format:

1. Read the data file and examine actual line contents
2. Identify formatting artifacts such as:
   • Line number prefixes (e.g., 1→, 2→, 1., 1:)
   • Whitespace or tab characters
   • Quote characters or escape sequences
   • Header rows or metadata
3. Design parsing logic that strips all non-content artifacts