RSSAmplifier

Blog

Ihsaan's Blog

A blog from Ihsaan Patel

ihsaanp.comRSS feed ↗8 posts

Latest posts

Postgres Schema for Prompting

A query to get your postgres schema for llm prompts

Sending Webhooks with Temporal

Using temporal to deliver webhooks reliably

Building Tools for Agents

Some things I learned building an email tool for agents

Converting MS Office Files to PDFs for RAG

A quick and dirty way to include docx and xlsx files in your LLM application

Parsing Readline PDFs

Strategies for parsing redline PDFs

Efficient References with LLMs

Using marker injection can solve a lot of issues with LLM document referencing, particularly for exact text matching and token efficiency.

When is Code Generation Useful?

As LLMs get smarter and faster, is code generation necessary?

Are these two people the same? Solving entity resolution with LLMs

Figuring out whether two entities (people, places, products, etc.) are the same for data joins or de-duplication can always be a challenge, particularly when dealing with messy data with no unique identifier. LLMs provide a potentially simpler / more generalizable solution to this problem