The goal of this group is to help you navigate the complex and rapidly evolving world of data science and artificial intelligence. This is your hub to stay up-to-date on the latest trends, learn specialized skills to turn raw data into valuable insights, connect with a community of like-minded individuals, and ultimately, become a Data Alchemist. Together, let's decode the language of data and shape a future where knowledge and community illuminate our way. Rules - Don't sell anything here or use Data Alchemy as any kind of funnel - We delete low effort community posts, and posts with poor English. Proofread your post first. - Help us make the posts high quality. If you see a low quality post, then click on the 3 dots on the post and "Report To Admins". Start by checking out these links - Classroom - Introduction - Roadmap - Contribution Be Aware of Scammers - Please be aware that this is a public group. Unfortunately, some people abuse the Skool platform to send DMs or post comments to trick people. This is the internet, so always do your own due diligence. Never automatically trust someone here on the Skool platform other than @Dave Ebbelaar's official account. To kick things off, please comment below, introducing yourself. Let us know: 1. Your name and where you're from 2. What project(s) you're currently focused on See you in the comments!

If you're like me, and you don't know Javascript, HTML or CSS, but still want to build chat applications, then I've got an exciting new video for you. This week, I explore how you can build a ChatGPT clone using only Python. We accomplish this by using the Streamlit library, which you easily install via pip. Streamlit recently added chat modules that let you spin up simple chat interfaces in minutes. The library is perfect for GenAI demos, small projects, or data upload GUIs for RAG applications. Go check out the video and leave a like! 🙏🏻

Hello everyone, I've had an exciting couple of weeks immersing myself in the world of AI and delving into the OpenAI API. Amidst extensive study, contemplation, and personal project work, I've encountered a question that I'd like some insights on. Recognizing the significance of ReAct as a prompt engineering technique, particularly in the success of Langchain and LlamaIndex, I've recently dedicated time to a deep dive into the ReAct pattern. This involved studying its underlying theory and attempting to construct a comprehensive mental model. However, I find myself grappling with a challenge. While I can appreciate the potential benefits of ReAct in a broad domain, such as its popularity in implementing RAG for generic Q&A, I struggle to envision its utility in a custom domain. Let me illustrate with an example. Imagine I've developed an AI/Agent system tailored for a small law practice. This system, built on gpt-4, excels at online customer service (RAG) through a web chatbot, handles appointment scheduling, conducts Q&A on legal documents (RAG) within an intranet, and possesses capabilities to summarize and review legal documents on the same platform. This comprehensive suite of functionalities fulfills the law firm's requirements, resulting in increased productivity, enhanced customer satisfaction (via the chatbot), and a more informed, successful legal team (Q&A). All of this is achieved using OpenAI APIs, vector databases, and various other tools, without the involvement of Langchain or LlamaIndex. In this scenario, despite the evident successes of the system, I struggle to identify a suitable application for ReAct as a prompting technique. Can anyone shed light on this for me?

Hi all, today I have finally decided to look again into the buzzword of prompt engineering (PE). There is lots of videos around about role-playing, describing the context, setting the temperature, but also about fancy stuff like CoT, ToT, React, graphs of thoughts, or system prompts and context windows. A lot of different things that have very little to do with each other. And afai-see no resource that looks at it comprehensively (well, this may be the closest one: https://learnprompting.org/docs/intro) I have thought about it, here are my ideas. So let me suggest this structure. Very early and crude but helps me at least a bit with "sense-making". I am calling the groups by the most relevant user group 1. PE as writing effective user prompts (zero shot, or input-output) (Common User) 2. PE as using a lot of advanced techniques to solve more complex or logical problems (few shot, CoT, ToT, React, ...) (Researcher) 3. PE as a programming tool to give context to the LLM and to write mini-applications (with the system prompt and variables) (Developer) On 1) Perfect user prompt This is a skill to be learned by everyone. Just like using google. It is mostly about being concise and descriptive. Imo this video gives an excellent explanation: Master the Perfect ChatGPT Prompt Formula (in just 8 minutes)! On 2) Advanced (user) prompting techniques Here we are talking about tools to help LLM crack more complex problems. Some of them may not be necessary any more with GPT4-Turbo and advanced models. It is about getting a solution step-by-step, decomposing the problem, trying out different solutions, have a LLM brainstorm an idea, and agentic behavior of engaging in a thinking-acting loop. This stuff I have not seen used much in "real life". But this is just an impression seeing the examples and watching YT. AutoGPT uses ReAct apparently. For many of the things if you like to understand or implement in detail you have to read the papers of the researchers.

Ever caught yourself enthusiastically sharing your grand plans, only to realize later that they remained just that – plans? It turns out, discussing our goals might not be as effective as we think, unless it's with a genuine accountability partner. Let's dive into why action often speaks louder than words. Over time, I've come to understand that aspirations are personal journeys. While ambition is commendable, what truly sets us apart is our ability to translate those dreams into reality, quietly and steadily. Rather than broadcasting your intentions, try a different tack. Give yourself the gift of action without an audience. Picture the satisfaction of achieving a personal milestone, without the need for external validation. By keeping our ambitions close to our chests, we minimize the "Intention-Behavior Gap" – that space between knowing and doing. Avoiding the trap of "Social Reality," we allow our actions to speak volumes. Remember, the most meaningful achievements often unfold in silence. I was reading @Aziz Amari's blog and came accross a post that really resonated with me. Here is his post: https://blog.azizamari.tn/talk_less Happy learning to everyone!