MongoDB’s Post

Building Full-Stack RAG-based Apps with NextJS, Vercel, GPT-4o https://lnkd.in/g8nyUr6T Featuring Object Relational Mapper (ORM), SDKs, Next.js (a React-based framework created by Vercel), and CRUD (Create, Read, Update, Delete, equivalent to Post, Get, Put, Delete in RESTful APIs). Case study: AI Chatbot creation. This hands-on workshop is for developers and AI professionals, featuring case studies, on state-of-the-art technology. Recording and GitHub material will be available to registrants who cannot attend the free 60-min session. #vercel #nextJS #rag

Great updates are coming soon on what I am building on generative AI as a developer! My tech stack is - NextJS, MongoDB, Open AI APIs, Pinecone DB, Core JavaScript and Websockets for chatbot optimisations Will start fine tuning the AI models from scratch and also share my work live with the community. Lots of updates are coming soon. #GenerativeAI #code #buildinpublic #100DaysOfCode

Anthropic Claude has its own issues, which, of course, can be fixed; one of our team asked to generate code for using Anthropic API SDK in nodejs, and here is the response: Claude started to answer the prompt itself in the code 😂 (Note: Our AI usage is under beta, we create only boilerplate code with AI, our devs strictly don't have access to any client data)

This the outlook of my first search engine mobile application based on artificial intelligence built with React Native and Nodejs for the Backend with Generative Ai principles. #artificialintelligence #reactnative

Exciting Update on StudyBuddy 📚 🔍 Last week, I dived into techniques to boost #RetrievalAugmentedGeneration systems in my article, "Improving RAG AI Systems." 🤖🌐 Check it out here: https://lnkd.in/dxWCTC_t Now, let's talk about the latest StudyBuddy update! 🌟 I've implemented the Query Expansion with Multiple Queries technique to enhance StudyBuddy's accuracy in answering your questions. 💬✨ Leveraging LangChain's "MultiQueryRetriever" class and some custom prompting, I've fine-tuned the question outputs that are used for the relevant document retrieval process. 🛠️💡 Now, when you input a query, the RAG system generates three additional similar queries which when used to retrieve documents from the Pinecone vector database, create a comprehensive knowledge base for a more robust answer! 🤯🔗 Explore StudyBuddy on the public repo: https://lnkd.in/dvy9r6Yc 🚀📖 Your comments and feedback are always valued! 🙌🏽 💬 #AIInnovation #ArtificialIntelligence #StudyBuddy #OpenSourceAI

PromptVerse is a website designed to unleash the full potential of GPT by allowing users to create, share, and explore AI prompts. This project utilizes the power of Next.js for server-side rendering, MongoDB for data storage, and integrates Google authentication for a secure user experience. Features - User Authentication: Utilizes Google Auth and NextAuth for secure user authentication. - Server-Side Rendering (SSR): Leverages the full potential of Next.js SSR for optimal performance. - MongoDB Integration: Stores and retrieves user posts using MongoDB. - Community-driven Prompts: Users can create, share, and copy AI prompts for GPT. - User Pages: Each user has their own page to showcase and manage their prompts. - Search Functionality: Allows users to search for prompts using the search bar. GitHub Link: https://lnkd.in/dzn5PY_C Live Preview: https://lnkd.in/dXqkkQqs #Web_development #NEXTJS #NextJs #TailwindCss #ReactJs #ReactJS #Full_Stack

Curious about integrating LLMs into your apps? This new blog from the Go team dives into building a powerful RAG server for Q&A using Go. From the blog: "LLM-powered applications are a lot like other modern cloud-native applications: they require excellent support for REST and RPC protocols, concurrency and performance. These just so happen to be the areas where Go excels, making it a fantastic language for writing LLM-powered applications." The blog will cover examples in LangChainGo and my teams new AI framework, Firebase Genkit. https://lnkd.in/eCkw36mY

بسم الله الرحمن الرحيم 🖤 New Project ♻️ Django ChatBot with Ai Support 🤖 This is a web app integrated with various AI tools to support multiple languages spoken by users. It is a Django-based web application that allows users to submit questions and receive answers. The application leverages a database to store question-answer pairs and uses the OpenAI GPT-4 model to provide answers for new questions. Features : -Upload questions and answers from an Excel file. -Store questions and answers in a database. -Find the most similar question in the database to a user's query using fuzzy matching. -Fallback to a chatbot API for responses if no similar question is found in the database. -Handle Arabic language inputs and queries. Here is GitHub repo : https://lnkd.in/g-TM8byy Live test : https://lnkd.in/gWqGrZR6

🚀 Excited to introduce Doc Buddy! 🚀 Doc Buddy is a RAG-based application designed to enhance the way you interact with your PDF documents. With Doc Buddy, you can seamlessly engage in conversations with an AI bot about the content of your uploaded PDF files. 📄🤖 *Select between two of the most renowned names in AI, with the flexibility to choose between Google AI and Mistral AI for a tailored conversational experience. *Engage in conversations with multiple PDFs simultaneously, enhancing productivity and information retrieval. *Enjoy a fun and interactive user interface, along-side document preview for a seamless experience. Stack Used: React.js, FastAPI, Langchain, Pinecone, SupaBase. Deployed over Render: https://lnkd.in/dheFCrRR A shoutout to Yuvraj Zanwar ! Your contributions and support were absolutely invaluable—thank you for being an awesome collaborator and helping me with the bugs and UI development process. Links to repo: https://lnkd.in/d34rS9sy https://lnkd.in/dVxPQQ32 #RAG #Langchain # #ReactJS #FastAPI #Langchain #Pinecone #Supabase #GoogleAI #MistralAI #MultiPDFChat #TechnologyInnovation #DocBuddy

Introducing CodeKitten, a Google Chrome extension that uses the AI language model to explain large GitHub codebase files and individual codes. If the code is very large, you can select individual code blocks to get an explanation. I will upload the extension to the Chrome Web Store soon after making some additional improvements.