Spaces:
Sleeping
Sleeping
File size: 1,878 Bytes
2c612d2 |
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 |
import ast
import logging
import os
import pandas as pd
from dotenv import load_dotenv
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import SupabaseVectorStore
from supabase.client import create_client
logging.basicConfig(level=logging.INFO)
logger = logging.getLogger(__name__)
class SupabaseConnector:
def __init__(self):
load_dotenv()
self.supabase = create_client(
os.environ.get("SUPABASE_URL"), os.environ.get("SUPABASE_SERVICE_KEY")
)
self.embeddings = HuggingFaceEmbeddings(
model_name="sentence-transformers/all-mpnet-base-v2"
)
self.vector_store = SupabaseVectorStore(
client=self.supabase,
embedding=self.embeddings,
table_name="documents",
query_name="match_documents_langchain",
)
def upload_csv(self, file_path: str, batch_size: int = 100):
"""
Upload documents from supabase_docs.csv to Supabase vector store.
Only 'content' and parsed 'metadata' are used.
"""
df = pd.read_csv(file_path)
logger.info(f"Loaded {len(df)} records from {file_path}")
# Parse metadata column from string to dict
df["metadata"] = df["metadata"].apply(
lambda x: ast.literal_eval(x) if isinstance(x, str) else {}
)
for i in range(0, len(df), batch_size):
batch = df.iloc[i : i + batch_size]
texts = batch["content"].tolist()
metadatas = batch["metadata"].tolist()
self.vector_store.add_texts(texts=texts, metadatas=metadatas)
logger.info(f"Uploaded batch {i//batch_size + 1}")
logger.info("CSV upload completed.")
if __name__ == "__main__":
connector = SupabaseConnector()
connector.upload_csv("supabase_docs.csv")
|