day3/embeddings.py

from typing import List, Dict
from sentence_transformers import SentenceTransformer

_embedder = SentenceTransformer("all-MiniLM-L6-v2")

def embed_texts(texts: List[str]) -> List[List[float]]:
    # Return as Python lists of floats (Chroma-compatible)
    return _embedder.encode(texts, convert_to_numpy=True).tolist()

def create_embeddings(chunks: List[str]) -> Dict:
    vectors = embed_texts(chunks)
    return {"embeddings": vectors, "count": len(vectors)}