Skip to content

Fix QdrantClient Document import issue and improve text processing fo… #311

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
Tim-nocode wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix QdrantClient Document import issue and improve text processing fo… #311

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
25 changes: 18 additions & 7 deletions knowledge_storm/utils.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -166,7 +166,7 @@ def create_or_update_vector_store(
embedding_model: str = "BAAI/bge-m3",
device: str = "mps",
):
from qdrant_client import Document
from qdrant_client.models import PointStruct # switch to new version of library

"""
Takes a CSV file and adds each row in the CSV file to the Qdrant collection.
Expand Down Expand Up @@ -239,7 +239,7 @@ def create_or_update_vector_store(
# read the csv file
import pandas as pd

df = pd.read_csv(file_path)
df = pd.read_csv(file_path, sep="|", encoding="utf-8") # in example separator is "|"
# check that content column exists and url column exists
if content_column not in df.columns:
raise ValueError(
Expand All @@ -249,18 +249,29 @@ def create_or_update_vector_store(
raise ValueError(f"URL column {url_column} not found in the csv file.")

documents = [
Document(
page_content=row[content_column],
metadata={
PointStruct(
id=index,
vector=[],
payload={
"content": row[content_column],
"title": row.get(title_column, ""),
"url": row[url_column],
"description": row.get(desc_column, ""),
},
)
for row in df.to_dict(orient="records")
for index, row in enumerate(df.to_dict(orient="records"))
]

# split the documents
from langchain.schema import Document as LangchainDocument
documents_langchain = [
LangchainDocument(
page_content=doc.payload["content"],
metadata=doc.payload
)
for doc in documents
]

from langchain_text_splitters import RecursiveCharacterTextSplitter

text_splitter = RecursiveCharacterTextSplitter(
Expand All @@ -282,7 +293,7 @@ def create_or_update_vector_store(
"",
],
)
split_documents = text_splitter.split_documents(documents)
split_documents = text_splitter.split_documents(documents_langchain)

# update and save the vector store
num_batches = (len(split_documents) + batch_size - 1) // batch_size
Expand Down