import json
import sys

from deeplake.core.vectorstore import VectorStore
from openai import OpenAI

client = OpenAI()

with open("data.json", "r", encoding="cp866") as f:
    json_data = json.load(f)

CHUNK_SIZE = 1000

text = json_data["textContent"]

chunked_text = []
chunked_text = [text[i : i + CHUNK_SIZE] for i in range(0, len(text), CHUNK_SIZE)]
metadata = [json_data for i in range(len(chunked_text))]


def embedding_function(texts, model="text-embedding-ada-002"):
    if isinstance(texts, str):
        texts = [texts]

    texts = [t.replace("\n", " ") for t in texts]

    return [
        data.embedding
        for data in client.embeddings.create(input=texts, model=model).data
    ]


vector_store = VectorStore(
    path="vector_store",
)


ds = vector_store.dataset
metadatas = ds.tensors["metadata"].data()["value"]
key = "uid"
val = "1337"
if not next((d for d in metadatas if d.get(key) == val), None):
    print("not found")
else:
    print("found")


vector_store.add(
    text=chunked_text,
    embedding_function=embedding_function,
    embedding_data=chunked_text,
    metadata=metadata,
)