data/process_csvs_store.py

import pandas as pd
import time
import os
from buster.documents_manager import DeepLakeDocumentsManager
from deeplake.core.vectorstore import VectorStore
from langchain.embeddings.openai import OpenAIEmbeddings
import numpy as np

# from openai import OpenAI

DEEPLAKE_DATASET = os.getenv("DEEPLAKE_DATASET", "ai-tutor-dataset")
DEEPLAKE_ORG = os.getenv("DEEPLAKE_ORG", "towards_ai")

# df1 = pd.read_csv("./data/jobs.csv", encoding='ISO-8859-1')  # or 'latin1' or 'cp1252'
# df2 = pd.read_csv("./data/hf_transformers.csv")
# df3 = pd.read_csv("./data/langchain_course.csv")
# df4 = pd.read_csv("./data/filtered_tai_v2.csv")
# df5 = pd.read_csv("./data/wiki.csv")  # , encoding="ISO-8859-1")
# df6 = pd.read_csv("./data/openai.csv")
df1 = pd.read_csv("./advanced_rag_course.csv")

# print(len(df1), len(df2), len(df3), len(df4), len(df5), len(df6))
print(len(df1))

dataset_path = f"hub://{DEEPLAKE_ORG}/{DEEPLAKE_DATASET}"
# dataset_path = f"{DEEPLAKE_DATASET}"
# because wrong name
# df1['content'] = df1['cleaned_description']
# print(np.sum(df1.content.isna()), len(df1) )

dm = DeepLakeDocumentsManager(
    vector_store_path=dataset_path,
    overwrite=False,
    required_columns=["url", "content", "source", "title"],
)

dm.batch_add(
    df=df1,
    batch_size=3000,
    min_time_interval=60,
    num_workers=32,
    csv_overwrite=False,
)

# dm.batch_add(
#     df=df2,
#     batch_size=3000,
#     min_time_interval=60,
#     num_workers=32,
#     csv_embeddings_filename="embeddings.csv",
#     csv_errors_filename="tmp.csv",
#     csv_overwrite=False,
# )

# dm.batch_add(
#     df=df3,
#     batch_size=3000,
#     min_time_interval=60,
#     num_workers=32,
#     csv_embeddings_filename="embeddings.csv",
#     csv_errors_filename="tmp.csv",
#     csv_overwrite=False,
# )

# dm.batch_add(
#     df=df4,
#     batch_size=3000,
#     min_time_interval=60,
#     num_workers=32,
#     csv_embeddings_filename="embeddings.csv",
#     csv_errors_filename="tmp.csv",
#     csv_overwrite=False,
# )

# dm.batch_add(
#     df=df5,
#     batch_size=3000,
#     min_time_interval=60,
#     num_workers=32,
#     csv_embeddings_filename="embeddings.csv",
#     csv_errors_filename="tmp.csv",
#     csv_overwrite=False,
# )

# dm.batch_add(
#     df=df6,
#     batch_size=3000,
#     min_time_interval=60,
#     num_workers=32,
#     csv_embeddings_filename="embeddings.csv",
#     csv_overwrite=False,
#     csv_errors_filename="tmp.csv",
# )

# dm.batch_add(
#     df=df7,
#     batch_size=3000,
#     min_time_interval=60,
#     num_workers=32,
#     csv_embeddings_filename="embeddings.csv",
#     csv_errors_filename="tmp.csv",
#     csv_overwrite=False,
# )


# client = OpenAI()

# openai_embeddings = OpenAIEmbeddings()
# def get_embedding(text, model="text-embedding-ada-002"):
#     # Call to OpenAI's API to create the embedding
#     response = client.embeddings.create(input=[text], model=model)

#     # Extract the embedding data from the response
#     embedding = response.data[0].embedding

#     # Convert the ndarray to a list
#     if isinstance(embedding, np.ndarray):
#         embedding = embedding.tolist()

#     return embedding


# vs = VectorStore(
#     dataset_path,
#     runtime='compute_engine',
#     token=os.environ['ACTIVELOOP_TOKEN']
# )

# data = vs.search(query = "select * where shape(embedding)[0] == 0")

# vs.update_embedding(embedding_source_tensor = "text",
#           query = "select * where shape(embedding)[0] == 0",
#           exec_option = "compute_engine",
#           embedding_function=get_embedding)

# data2 = vs.search(query = "select * where shape(embedding)[0] == 0")