data/process_csvs_store.py

import pandas as pd
import time
import os
from buster.documents_manager import DeepLakeDocumentsManager

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

df1 = pd.read_csv("./data/llm_course.csv")
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")
df7 = pd.read_csv("./data/activeloop.csv")
df8 = pd.read_csv("./data/langchain_docs.csv")

print(len(df1), len(df2), len(df3), len(df4), len(df5), len(df6), len(df7), len(df8))

dataset_path = f"hub://{DEEPLAKE_ORG}/{DEEPLAKE_DATASET}"

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

dm.batch_add(
    df=df1,
    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=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,
)

dm.batch_add(
    df=df8,
    batch_size=3000,
    min_time_interval=60,
    num_workers=32,
    csv_embeddings_filename="embeddings.csv",
    csv_errors_filename="tmp.csv",
    csv_overwrite=False,
)