Future Plans

Future Plans

Vector Search for AI News

The ai_news table currently stores articles as plain PostgreSQL rows (title, URL, summary). The plan is to add vector embeddings later for semantic search capabilities.

Approach Options

Option A: pgvector on Neon (recommended)

Neon natively supports the pgvector extension. Add an embedding column to the existing table:

CREATE EXTENSION IF NOT EXISTS vector;
ALTER TABLE ai_news ADD COLUMN embedding vector(1536);

Then backfill embeddings from existing summaries using an embedding model and query by similarity:

SELECT title, summary, url
FROM ai_news
ORDER BY embedding <=> $1  -- cosine distance
LIMIT 10;

Option B: Export to dedicated vector DB

Export existing data and import into a free-tier vector database:

• Pinecone — free tier available
• Qdrant — open-source, free cloud tier
• Weaviate — open-source, free sandbox

Embedding Model Options

Model	Cost	Dimensions
OpenAI text-embedding-3-small	~$0.02/1M tokens	1536
Voyage AI	Free tier available	1024
HuggingFace transformers.js	Free (runs locally)	Varies

Potential Use Cases

• "What happened with LangChain this month?" — semantic search across historical news
• Trend detection — cluster similar articles to spot emerging topics
• Personal knowledge base — search your curated news history naturally
• Newsletter generation — weekly/monthly digest from stored articles

Other Ideas

• Weekly summary email — aggregate the week's news into a single report
• Slack integration — send digest to a Slack channel instead of/alongside Telegram
• RSS feed support — add specific AI blogs as additional sources
• Read tracking — mark articles as read/bookmarked via Telegram inline buttons