infrastructure-storage-serializatio-storagecontext-persist-fails-with-typeerror-object-46ee27c3

THEN Convert numpy arrays and other non-JSON-serializable types to native Python types before creating Document objects or before calling persist. For numpy arrays, call .tolist() on the embedding; for scalar numpy types, call .item(). In embedding models like InstructorEmbedding, modify the _embed method to convert each embedding to a Python list before returning.

# Example fix for Document creation
embedding = models.encode(text).tolist()  # Convert numpy array to list
document = Document(text, embedding=embedding)

# Example fix for InstructorEmbedding (inside _embed method)
embeddings = [emb.tolist() if hasattr(emb, 'tolist') else emb for emb in embeddings]