| from sentence_transformers import SentenceTransformer, util | |
| MODELS = { | |
| "all-MiniLM-L6-v2": SentenceTransformer("all-MiniLM-L6-v2"), | |
| "multi-qa-MiniLM-L6-cos-v1": SentenceTransformer("multi-qa-MiniLM-L6-cos-v1"), | |
| "paraphrase-MiniLM-L3-v2": SentenceTransformer("paraphrase-MiniLM-L3-v2"), | |
| "all-mpnet-base-v2": SentenceTransformer("all-mpnet-base-v2"), | |
| "distilbert-base-nli-mean-tokens": SentenceTransformer("distilbert-base-nli-mean-tokens"), | |
| } | |
| def score_fit(text: str, goal: str, method: str) -> dict: | |
| results = {} | |
| for name, model in MODELS.items(): | |
| emb1 = model.encode(text, convert_to_tensor=True) | |
| emb2 = model.encode(goal, convert_to_tensor=True) | |
| cos = util.cos_sim(emb1, emb2).item() | |
| score = max(0, min(100, int((cos + 1) * 50))) | |
| results[name] = score | |
| return results | |