Spaces:
Running
Running
File size: 2,911 Bytes
0f06abd |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 |
import pandas as pd
import time
import os
from deeplake.core.vectorstore import VectorStore
from langchain.embeddings.openai import OpenAIEmbeddings
import logging
from buster.documents_manager import DeepLakeDocumentsManager
from buster.llm_utils import get_openai_embedding_constructor
# Set the logging level of `httpx` to WARNING or higher to suppress annoying INFO logs
logging.getLogger("httpx").setLevel(logging.WARNING)
openai_embedding_fn = get_openai_embedding_constructor(
client_kwargs={"max_retries": 10}
)
# 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/langchain.csv") # 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")
df7 = pd.read_csv("./data/activeloop.csv")
df8 = pd.read_csv("./data/llm_course.csv")
print(
f"Number of samples: {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,
)
dm.batch_add(
df=df1,
batch_size=3000,
min_time_interval=60,
num_workers=32,
embedding_fn=openai_embedding_fn,
csv_filename="embeddings.csv",
csv_overwrite=False,
)
dm.batch_add(
df=df2,
batch_size=3000,
min_time_interval=60,
num_workers=32,
embedding_fn=openai_embedding_fn,
csv_filename="embeddings.csv",
csv_overwrite=False,
)
dm.batch_add(
df=df3,
batch_size=3000,
min_time_interval=60,
num_workers=32,
embedding_fn=openai_embedding_fn,
csv_filename="embeddings.csv",
csv_overwrite=False,
)
dm.batch_add(
df=df4,
batch_size=3000,
min_time_interval=60,
num_workers=32,
embedding_fn=openai_embedding_fn,
csv_filename="embeddings.csv",
csv_overwrite=False,
)
dm.batch_add(
df=df5,
batch_size=3000,
min_time_interval=60,
num_workers=32,
embedding_fn=openai_embedding_fn,
csv_filename="embeddings.csv",
csv_overwrite=False,
)
dm.batch_add(
df=df6,
batch_size=3000,
min_time_interval=60,
num_workers=32,
embedding_fn=openai_embedding_fn,
csv_filename="embeddings.csv",
csv_overwrite=False,
)
dm.batch_add(
df=df7,
batch_size=3000,
min_time_interval=60,
num_workers=32,
embedding_fn=openai_embedding_fn,
csv_filename="embeddings.csv",
csv_overwrite=False,
)
dm.batch_add(
df=df8,
batch_size=3000,
min_time_interval=60,
num_workers=32,
embedding_fn=openai_embedding_fn,
csv_filename="embeddings.csv",
csv_overwrite=False,
)
|