Skip to content

fix: use URL-based hash as Pinecone vector ID to prevent silent data loss (#174) #176

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
ahmedk20 wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: use URL-based hash as Pinecone vector ID to prevent silent data loss (#174) #176

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
7 changes: 6 additions & 1 deletion db_update/Update.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
import sys
import os
import hashlib
from dotenv import dotenv_values
from pinecone import Pinecone, ServerlessSpec
sys.path.append(os.path.abspath(os.path.join(os.path.dirname(__file__), '..')))
Expand Down Expand Up @@ -100,9 +101,13 @@ def update_database(overwrite=(len(sys.argv) > 1 and sys.argv[1] == '--overwrite
values = [float(emb_array[i]) for i in indices]
sparse_vector = {"indices": indices, "values": values}

# Use a URL-based hash as the Pinecone vector ID.
# guaranteed unique per article since URLs are already deduplicated.
vector_id = hashlib.md5(url.encode()).hexdigest()

# Construct record exactly as per Pinecone documentation
record = {
"id": str(article.get("id", "")),
"id": vector_id,
"values": dense_vector,
"sparse_values": sparse_vector,
"metadata": {
Expand Down