LLMs in Prod Blog ● Portkey

Sign in Subscribe

Latest

Partnering with F5 to Productionize Enterprise AI

Partnering with F5 to Productionize Enterprise AI

We are thrilled to announce that Portkey is partnering with F5, the creators of NGINX and global leader in multi-cloud application security & delivery, to bring enterprise AI apps to production. By integrating our AI Gateway and Observability Suite with F5 Distributed Cloud Services, we are accelerating the path to production

Expanding the AI Gateway with Google Vertex AI Integration

Expanding the AI Gateway with Google Vertex AI Integration

⭐️ Implementing FrugalGPT: Reducing LLM Costs & Improving Performance

⭐️ Implementing FrugalGPT: Reducing LLM Costs & Improving Performance

What It Means To Go To Prod

What It Means To Go To Prod

Portkey Goes Multimodal

Portkey Goes Multimodal

Understanding RAG: A Deeper Dive into the Fusion of Retrieval and Generation

Understanding RAG: A Deeper Dive into the Fusion of Retrieval and Generation

Transforming E-Commerce Search with Semantic Cache: Insights from Walmart's Journey

Transforming E-Commerce Search with Semantic Cache: Insights from Walmart's Journey

Production Guides

⭐️ Implementing FrugalGPT: Reducing LLM Costs & Improving Performance

⭐️ Implementing FrugalGPT: Reducing LLM Costs & Improving Performance

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 Improving Performance". The paper outlines strategies for more cost-effective and performant usage of large language model (LLM) APIs. A

What It Means To Go To Prod

What It Means To Go To Prod

Portkey Goes Multimodal

Portkey Goes Multimodal

Understanding RAG: A Deeper Dive into the Fusion of Retrieval and Generation

Understanding RAG: A Deeper Dive into the Fusion of Retrieval and Generation

⭐️ OpenAI Model Deprecation Guide

⭐️ OpenAI Model Deprecation Guide

Anyscale's OSS Models + Portkey's Ops Stack

Anyscale's OSS Models + Portkey's Ops Stack

⭐ Building Reliable LLM Apps: 5 Things To Know

Conversations

Transforming E-Commerce Search with Semantic Cache: Insights from Walmart's Journey

Transforming E-Commerce Search with Semantic Cache: Insights from Walmart's Journey

We recently spoke with Rohit Chatter, Chief Software Architect at Walmart, who offered profound insights into how Walmart is leveraging these technologies, particularly focusing on semantic caching and its impact on e-commerce search functions.

Unpacking Semantic Caching at Walmart

Unpacking Semantic Caching at Walmart

The Confidence Checklist for LLMs in Production

Dive into what is LLMOps

Paper Summaries

More

Mixtral of Experts - Summary

LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models - Summary

Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding - Summary

Towards Reasoning in Large Language Models: A Survey - Summary

Are We Really Making Much Progress in Text Classification? A Comparative Review - Summary

Benchmarks

More

GPT-4 is Getting Faster 🐇