AI

Over the past two weeks, there has been a massive increase in using LLMs in an agentic manner. Specifically, projects like AutoGPT, BabyAGI, CAMEL, and Generative Agents have popped up. The LangChain community has now implemented some parts of all of those projects in the LangChain framework. While researching and implementing these projects, we’ve tried to best understand what the differences between them are and what the novel features of each are.

Chat with your CSV files with a memory chatbot🤖 | Made with Langchain🦜 and OpenAI🧠 Link

As an AI enthusiast, I’m always on the lookout for new AI-powered tools and technologies to make my life easier. Recently, I stumbled upon Chart-GPT, a game-changing tool that transforms text into beautiful charts within seconds with the help of OpenAI’s APIs. Link

Use the new GPT-4 api to build a chatGPT chatbot for multiple Large PDF files. Tech stack used includes LangChain, Pinecone, Typescript, Openai, and Next.js. LangChain is a framework that makes it easier to build scalable AI/LLM apps and chatbots. Pinecone is a vectorstore for storing embeddings and your PDF in text to later retrieve similar docs. Link

🧠 Memory Bot 🤖 — An easy up-to-date implementation of ChatGPT API, the GPT-3.5-Turbo model, with LangChain AI’s 🦜 — ConversationChain memory module with Streamlit front-end. Link

LLaMA model weights are available over the internet on various websites. This is not legal but I am sharing just a “How to — tutorial” Link

Financial professionals, investors, and hobbyists need efficient ways to access, analyze, and make sense of this data to make informed decisions. Naturally, this is why building chatbots for your data tools to analyze earnings calls, financial report PDFs, or SEC filings is all the rage now. Link

We now provide a pretrained MiniGPT-4 aligned with Vicuna-7B! The demo GPU memory consumption now can be as low as 12GB. Link

A Step-by-Step Tutorial for Building an AI Flight Recommendation Application Link

In this post, we will dive into the inner workings of ChatGPT and how it is trained. However, before we get into the specifics of ChatGPT, it’s important to first review some relevant prior works and concepts to give us a strong foundation. Once we have a solid understanding of these foundations, we can move on to exploring ChatGPT in depth. Link

Semantic/Vector search is a powerful technique that can greatly improve the accuracy and relevance of search results. Unlike traditional keyword-based search methods, semantic search uses the meaning and context of words to understand the intent behind a query and deliver more accurate results. One of the most popular tools for implementing semantic search is Elasticsearch, a highly scalable and powerful search engine that can be used to index and search large volumes of data.

This notebook is designed to let you quickly generate text with the latest StableLM models (StableLM-Alpha) using Hugging Face’s transformers library Link

In a world where technology continues to evolve at breakneck speed, it’s crucial to stay ahead of the curve and harness the power of AI to enhance your personal and professional life. Auto-GPT is an advanced AI tool that can help you do just that. Link

In this article, we’ll go through how to summarize and query multiple research papers using LangChain. Link

The common AI/ML Lifecycle consists of data collection, preparation, training, evaluation, deployment and monitoring all encompassed with an MLOps pipeline. Generative AI (GenAI) is a transformational technology that will continue its ramifications of major industry shifts in the coming months and years. Currently, in its earlier stages it has a raised a lot of hype; a distraction to fundamental shift that underlies its promise. Link