Skip to content

fix:updated embedding cleaning #11

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
So-Summer wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix:updated embedding cleaning #11

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
22 changes: 12 additions & 10 deletions backend/scripts/rank.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,25 +18,27 @@
"""Pre-Processing for Embedding"""

def clean_for_embedding(to_clean):
text = to_clean
# Remove special characters that don't add meaning
text = re.sub(r'[^\w\s.,;:!?()-]', ' ', text)
text = to_clean.lower()
# Remove special characters and punctuation
# text = re.sub(r'[^a-zA-Z0-9\s]', '', text)
# # Normalize the numbers
# text = re.sub(r'\d+', '#', text)
# Remove extra whitespace
text = re.sub(r'\s+', ' ', text).strip()
# Remove common filler phrases that don't add semantic value
fillers = ["click here", "read more", "learn more", "cookies", "privacy policy"]
for filler in fillers:
text = text.replace(filler, "")
# # Remove common filler phrases that don't add semantic value
# fillers = ["click here", "read more", "learn more", "cookies", "privacy policy"]
# for filler in fillers:
# text = text.replace(filler, "")

return text

# From Claude:
def extract_keywords(text, top_n=5):
# Simple keyword extraction by frequency
words = re.findall(r'\b[a-zA-Z]{3,15}\b', text.lower())
common_words = ["the", "and", "for", "this", "that", "with", "from"]
filtered = [w for w in words if w not in common_words]
return [word for word, _ in Counter(filtered).most_common(top_n)]
# common_words = ["i", "me", "my", "myself", "we", "our", "ours", "ourselves", "you", "your", "yours", "yourself", "yourselves", "he", "him", "his", "himself", "she", "her", "hers", "herself", "it", "its", "itself", "they", "them", "their", "theirs", "themselves", "what", "which", "who", "whom", "this", "that", "these", "those", "am", "is", "are", "was", "were", "be", "been", "being", "have", "has", "had", "having", "do", "does", "did", "doing", "a", "an", "the", "and", "but", "if", "or", "because", "as", "until", "while", "of", "at", "by", "for", "with", "about", "against", "between", "into", "through", "during", "before", "after", "above", "below", "to", "from", "up", "down", "in", "out", "on", "off", "over", "under", "again", "further", "then", "once", "here", "there", "when", "where", "why", "how", "all", "any", "both", "each", "few", "more", "most", "other", "some", "such", "only", "own", "same", "so", "than", "too", "very", "s", "t", "can", "will", "just", "don", "should", "now"]
# filtered = [w for w in words if w not in common_words]
return [word for word, _ in Counter(words).most_common(top_n)]

# From Claude:
def add_keywords(text):
Expand Down