Skip to content

Update document_processing.py #1

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
karandomguy wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Update document_processing.py #1

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
9 changes: 1 addition & 8 deletions document_processing.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,11 +5,6 @@
import re
import pandas as pd
from sentence_transformers import SentenceTransformer
import chromadb
from dotenv import load_dotenv
import requests
from bs4 import BeautifulSoup
import time

load_dotenv()

Expand Down Expand Up @@ -65,8 +60,6 @@ def load_documents(self, filename: str = "medical_documents.json") -> List[Dict[

def save_documents(self, documents: List[Dict[str, Any]], filename: str = "medical_documents.json"):
"""Save documents to JSON file"""
os.makedirs(self.data_dir, exist_ok=True)
filepath = os.path.join(self.data_dir, filename)
with open(filepath, 'w') as f:
json.dump(documents, f, indent=2)
print(f"Saved {len(documents)} documents to {filepath}")
Expand Down Expand Up @@ -244,4 +237,4 @@ def run_pipeline(self, json_file=None, urls=None):
medical_urls = []

count = processor.run_pipeline(urls=medical_urls)
print(f"Successfully processed documents into {count} chunks in the vector database")
print(f"Successfully processed documents into {count} chunks in the vector database")