Rank candidates by real semantic similarity
Want to know which of several texts best matches a query? This tool fetches real embeddings for your query and every candidate using your own API key, then ranks the candidates by cosine similarity so you can see exactly how a semantic search would order them — scores and all.
How embedding similarity works
An embedding model turns a piece of text into a vector — a list of numbers that captures its meaning. Two texts that mean similar things end up with vectors pointing in similar directions. Cosine similarity measures the angle between two vectors:
similarity = (A · B) / (‖A‖ × ‖B‖)The result ranges from -1 to 1; for typical text embeddings it sits between roughly 0 and 1, where higher means more related. Because it uses the angle and not the magnitude, cosine similarity compares meaning rather than length.
This is the exact operation behind semantic search and RAG retrieval: embed the query, embed each chunk, and return the highest-scoring matches.
Tips for using the scores
- Compare scores, not absolutes. A score of 0.45 might be the best match in one set and a poor one in another — what matters is the ranking.
- Use the large model when you need finer separation between close candidates; use the small model to save cost at volume.
- Keep candidates focused. Embedding a whole document dilutes its meaning; embed the specific passages you actually want to retrieve.
- Watch for ties. If everything scores similarly, your candidates may be too uniform, or the query too vague to discriminate between them.