John Berryman’s Post

This is a summary of current API pricing from OpenAI, Anthropic (Claude), and the new Mistral API. All prices are in USD (cents); Mistral pricing is converted using today's exchange rate. Decimals in prices are fractions of a penny. These models vary greatly in terms of context and capabilities, but there are use cases for every model listed. They are all worth a look. For more information, here are the official pricing pages for each of the three platforms: OpenAI / ChatGPT: https://openai.com/pricing Anthropic / Claude: https://lnkd.in/e8sK9JkP Mistral: https://lnkd.in/ermV-NtP

If you don't understand the schema below and hear the words GPT4, RAG, LLM all the time. Let me explain you in 2 mins (Biz friendly) ▶️ 1️⃣ The user ask a question 2️⃣ The RAG (Retrieval Augmented Generation) application retrieves the correct documents to answer the question 3️⃣ This documents are sent as context to the LLM GPT 3.5/4 from OpenAI or Mistral AI All of this is made very easy thanks to LangChain (Harrison Chase) & Supabase (Paul Copplestone) ! And if you want to try out Quivr (YC W24) to test the power of chatting with your documents -> Link in comments Leave a comment if you have any questions or you'd like the full size document !

A detailed intro into LangChain, its various constructs and how to use LangChain to access LLMs provided by OpenAI.

OpenAI goes multi-modal with a super low latency LLM (1 trillion paramaters+) with GPT-4o. They're really taking it to zuck and his scorched earth approach with open-source Llama3 that can be run locally. Things are getting real interesting real quick. TechCrunch article in the comments section.

🤐 Here, openai model compares the summary of the given scientific paper with its references' titles, it tries to identify similarities and a reason for each decision. #langchain #extraction #tagging

Check out this fascinating LLM model leveraging LangChain and OpenAI, featuring a cutting-edge Similarity Search engine. Utilizing this advanced technology, I've experimented with embedding Q&A pairs from a General Knowledge PDF file through queries. Please comment

This blog shows you how to set up LLM observability using OpenTelemetry for managed LLMs, like OpenAI to collect, debug, and optimize your application in production.

This blog shows you how to set up LLM observability using OpenTelemetry for managed LLMs, like OpenAI to collect, debug, and optimize your application in production.

This blog shows you how to set up LLM observability using OpenTelemetry for managed LLMs, like OpenAI to collect, debug, and optimize your application in production.

This blog shows you how to set up LLM observability using OpenTelemetry for managed LLMs, like OpenAI to collect, debug, and optimize your application in production.