save_embeddings.py

import json
import numpy as np
import openai
import os

openai.api_key = os.getenv("OPENAI_API_KEY")
CHUNKS_PATH = "data/chunks.json"
EMBEDDINGS_PATH = "data/embeddings.npy"
EMBEDDING_MODEL = "text-embedding-ada-002"

with open(CHUNKS_PATH, "r", encoding="utf-8") as f:
    chunks = json.load(f)

def get_embedding(text):
    resp = openai.Embedding.create(input=text, model=EMBEDDING_MODEL)
    return np.array(resp['data'][0]['embedding'], dtype=np.float32)

embeddings = []
for i, chunk in enumerate(chunks):
    print(f"Embedding {i+1}/{len(chunks)}")
    try:
        emb = get_embedding(chunk["text"])
        embeddings.append(emb)
    except Exception as e:
        print(f"Ошибка для чанка {i}: {e}")
        embeddings.append(np.zeros(1536, dtype=np.float32))  # или нужная размерность

np.save(EMBEDDINGS_PATH, np.stack(embeddings))
print("Готово! Эмбеддинги сохранены в", EMBEDDINGS_PATH)