---
title: "Kavya (@portkey-km) | Hashnode"
description: "Portkey AI. Read the latest articles by Kavya on Hashnode."
url: "https://hashnode.com/@portkey-km"
---

@portkey-km

# Kavya

@portkey-km · Joined October 2024

Portkey AI

### [⭐ Reducing LLM Costs & Latency with Semantic Cache](https://portkey-llm-elo-rating.hashnode.dev/reducing-llm-costs-latency-with-semantic-cache?utm_source=hashnode&utm_medium=feed)

Implementing semantic cache from scratch for production use cases. Vrushank Vyas Jul 11, 20235 min Image credits: Our future AI overlords. (No, seriously, Stability AI) Latency and Cost are significant hurdles for developers building on top of Large...

5 min read · [portkey-llm-elo-rating.hashnode.dev](https://portkey-llm-elo-rating.hashnode.dev/reducing-llm-costs-latency-with-semantic-cache?utm_source=hashnode&utm_medium=feed)

[Oct 14, 2024](https://hashnode.com/posts/reducing-llm-costs-latency-with-semantic-cache/670cdc7afc355e1a289ca7b0)

### [⭐️ Implementing FrugalGPT: Reducing LLM Costs & Improving Performance](https://portkey-llm-elo-rating.hashnode.dev/implementing-frugalgpt-reducing-llm-costs-improving-performance?utm_source=hashnode&utm_medium=feed)

Rohit Agarwal, Ayush Garg Apr 22, 2024∙12 min FrugalGPT is a framework proposed by Lingjiao Chen, Matei Zaharia, and James Zou from Stanford University in their 2023 paper "FrugalGPT: How to Use Large Language Models While Reducing Cost and Improvin...

14 min read · [portkey-llm-elo-rating.hashnode.dev](https://portkey-llm-elo-rating.hashnode.dev/implementing-frugalgpt-reducing-llm-costs-improving-performance?utm_source=hashnode&utm_medium=feed)

[Oct 14, 2024](https://hashnode.com/posts/implementing-frugalgpt-reducing-llm-costs-improving-performance/670cd752724022d2e35f8e76)

### [⭐️ Decoding OpenAI Evals](https://portkey-llm-elo-rating.hashnode.dev/decoding-openai-evals?utm_source=hashnode&utm_medium=feed)

Learn how to use the eval framework to evaluate models & prompts to optimise LLM systems for the best outputs. Rohit Agarwal May 10, 2023 ∙ 9 min Conversation on Twitter There's been a lot of buzz around model evaluations since OpenAI open-sourced t...

11 min read · [portkey-llm-elo-rating.hashnode.dev](https://portkey-llm-elo-rating.hashnode.dev/decoding-openai-evals?utm_source=hashnode&utm_medium=feed)

[Oct 14, 2024](https://hashnode.com/posts/decoding-openai-evals/670cd08b31d3f38e16ae7ebc)

### [⭐️ OpenAI Model Deprecation Guide](https://portkey-llm-elo-rating.hashnode.dev/openai-model-deprecation-guide?utm_source=hashnode&utm_medium=feed)

Vrushank Vyas Jan 2, 2024 ∙ 2 min In two days (i.e. Jan 4), OpenAI will retire 33 models, including GPT-3 (text-davinci-003) and various others. This is OpenAI's biggest model deprecation so far. Here's what you need to know: GPT-3 Model Retirement...

2 min read · [portkey-llm-elo-rating.hashnode.dev](https://portkey-llm-elo-rating.hashnode.dev/openai-model-deprecation-guide?utm_source=hashnode&utm_medium=feed)

[Oct 14, 2024](https://hashnode.com/posts/openai-model-deprecation-guide/670ccd417d9a71bc7b91fefb)

### [⭐️ Ranking LLMs with Elo Ratings](https://portkey-llm-elo-rating.hashnode.dev/ranking-llms-with-elo-ratings?utm_source=hashnode&utm_medium=feed)

Choosing an LLM from 50+ models available today is hard. We explore Elo ratings as a method to objectively rank and pick the best performers for our use case. Rohit Agarwal Apr 18, 20236 min Photo by Joshua Golde / Unsplash Large language models (LL...

7 min read · [portkey-llm-elo-rating.hashnode.dev](https://portkey-llm-elo-rating.hashnode.dev/ranking-llms-with-elo-ratings?utm_source=hashnode&utm_medium=feed)

[Oct 14, 2024](https://hashnode.com/posts/ranking-llms-with-elo-ratings/670cc2239a6d48174faaccd8)
