![translation](https://cdn.durumis.com/common/trans.png)
This is an AI translated post.
Mr. Know-All – 2023.7
- Writing language: Korean
- •
-
Base country: All countries
- •
- Information Technology
Select Language
Summarized by durumis AI
- The first issue of "Mr. Know-All," a monthly AI magazine in July 2023, summarizes news related to generative AI, including Claude 2, using embedding services on Azure, LangChain & FastAPI, Chaining, PDF Preview, and LlamaIndex.
- Claude 2 is a powerful new llm developed by Anthropic, which is independent of OpenAI, and is said to be a good alternative to OpenAI.
- It also introduces how to use LlamaIndex to embed personal data, and a discussion on generative AI hosted by Dr. Shanapacki, showcasing the diverse possibilities of generative AI.
I think 2023 can be considered the era of AI, more specifically, generative AI. It would not be an exaggeration to say that it was opened by OpenAI Chat-GPT.
There is a constant stream of new news, and related YouTube videos are added.
So I tried to organize and share them every day, but it was not easy, so I will do it monthly.
I am launching the AI monthly magazine "Mr. Know-All".
[Mr. Know-All Issue #1 – July 2023]
Claude 2 – a powerful new llm has come out. From Anthropic, founded by people who left OpenAI independently. It can be a great alternative to OpenAI.
It explains how to use embedding services in Azure to find meaningful information from unstructured documents. Since ms invested in openai, azure, which is providing ai services, should be closely watched.
LangChain & FastAPI – Privater, custom ChatBot with JWT Authentication
It's in German. Just refer to the GitHub repository.
What Is Chaining? | Langchain
Chaining – the core concept of Langchain. It's a chain, as the name suggests. LLM chain.
There are 3 types of chains – simple sequential, multiple input, multiple output.
I need to look at the PDF Preview part.
Chat with your Data using LlamaIndex and OpenAI GPT-3 Collab Python Demo
LlamaIndex is used to embed personal data.
LlamaIndex is a “data framework” to help you build LLM apps. You should not just think of LlamaIndex as a simple indexing library, but you should take a closer look at it.
It is about 2 hours long. Below is a summary using the OpenAI API and translated by DeepL.
Dr. Shanapaki hosts a discussion on generative AI, the major platform shift since the mid-90s. We will discuss how to build the next generation of Salesforce for Shopify through generative AI, Asian experience, architecture, and how to use machine learning with real-time and historical data. We will also discuss data engineering, vector search embedding, prompt engineering and testing, prompt search and reasoning, and how to maximize performance from vectors. We will also discuss the importance of providing feedback loops for AI to learn and adapt to changing language and concepts, and the need for human oversight to understand how to detect and prevent hallucinations.