Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Agentic Dashboard
This talk demonstrates building custom agentic frameworks from scratch to automatically generate dashboards by directly querying databases, highlighting function calling and tool integration.
Convert text to dashboards: A dashboard that is generated automatically using agentic frameworks that directly talks to your database.
QDash: Privacy-first, AI-powered, local data processing for browser-based dashboards.
- LangChainThe open-source framework for building and deploying reliable, data-aware Large Language Model (LLM) applications.LangChain is the essential framework for engineering LLM-powered applications: it simplifies connecting models (like GPT-4 or Claude) to external data, computation, and APIs. The platform provides a modular set of components—Chains, Agents, Tools, and Memory—allowing developers to quickly build complex workflows like Retrieval-Augmented Generation (RAG) pipelines and sophisticated conversational agents. Its Python and JavaScript libraries, combined with LangChain Expression Language (LCEL), offer a standardized interface for rapid prototyping and moving applications to production with confidence.
- OpenAI APIOpenAI API: Your direct gateway to cutting-edge AI models (GPT-4o, DALL-E 3, Whisper), enabling scalable, multimodal intelligence integration into any application.The OpenAI API provides authenticated, programmatic access to a powerful suite of generative AI models. Developers leverage REST endpoints and official libraries (Python, Node.js) to integrate capabilities like advanced text generation (GPT-4o), image creation (DALL-E 3), and speech-to-text transcription (Whisper). This platform is engineered for scale, supporting millions of daily requests for tasks from complex reasoning to real-time customer support agents, ensuring your application gets reliable, state-of-the-art intelligence.
- OpenAI Function CallingOpenAI Function Calling connects models (e.g., GPT-4) to external tools; it translates natural language requests into structured JSON objects for execution.Function Calling (now Tool Calling) enables models to interface with external systems: you define available functions using a JSON schema. When a user prompt requires external data or action (e.g., 'what's the weather in Paris?'), the model returns a structured JSON object, not a final answer. This object specifies the function name and precise arguments (e.g., `get_current_weather("Paris")`). Your application executes this call, then sends the result back to the model. This two-step conversation allows the LLM to access real-time data, run code, or trigger API actions, significantly extending its capabilities beyond its training data.
Related projects
Customer name consolidation
Dubai
Learn how to consolidate global customer names using Hybrid Search and LLMs, then explore Self/Agentic RAG for deterministic…
Microsoft Agent Framework Accelerator
Dubai
See how the Microsoft Agent Framework Accelerator uses YAML and plugins for rapid, low-code creation of multi-agent systems,…
AI Eyes
Dubai
Explore a deep learning model that transforms images into spoken captions using attention on Flickr data, providing real‑time…
SlateFront AI: A new way to learn with AI, visually.
Abu Dhabi
Learn how SlateFront uses AI to instantly turn text or sketches into accurate math and physics animations, enabling…
AI WebScraper
Abu Dhabi
Learn how to use a generative AI web scraper that takes a URL and keywords, extracts data, and…
Dr Auntie
Dubai
See a Telegram bot analyze lab reports using Gemini Vision and Groq, delivering personalized advice with a cloned…