Drag & Drop to Build AI Agents

PLUS: Open models by AI21, AI agent for software testing

AuthorAuthor

Shubham Saboo & Gargi Gupta
August 23, 2024

In partnership with

The fastest way to build AI apps

  • Writer Framework: build Python apps with drag-and-drop UI

  • API and SDKs to integrate into your codebase

  • Intuitive no-code tools for business users

Today’s top AI Highlights:

  1. Run AI agents locally with this opensource low-code AI starter kit

  2. AI21 releases state-of-the-art opensource family of models Jamba 1.5

  3. Claude now renders math equations and expressions

  4. AI video translation that clones the face and syncs lips

  5. AI agent for end-to-end software testing

& so much more!

Read time: 3 mins

Latest Developments

Running AI locally is gaining traction, but setting up the infrastructure can be a challenge. n8n has released a self-hosted AI starter kit to make the process easier and more accessible. This starter kit provides a pre-configured Docker Compose template, making it a breeze to get your AI projects up and running on your own hardware.

Key Highlights:

  1. Get started quickly - The starter kit includes a curated list of popular AI tools like Ollama, Qdrant, and PostgreSQL, pre-configured for easy integration and deployment. You can start building your AI workflows without spending weeks on setup.

  2. Build powerful AI applications - The kit combines n8n's powerful low-code platform with the flexibility of local AI tools, enabling you to create sophisticated AI agents, automate tasks, and build custom workflows for your specific needs.

  3. Gain control over data and costs - Running AI locally ensures data privacy and allows you to avoid the fluctuating costs of API calls to external models. The starter kit provides a robust foundation for building your own secure and cost-effective AI solutions.

AI21 Labs has just released the Jamba 1.5 family of open models – Jamba 1.5 Mini and Jamba 1.5 Large. These models are built on a new architecture called SSM-Transformer, which combines transformers' strengths with Mamba's efficiency, resulting in superior long-context handling, speed, and quality. The Jamba 1.5 models are available for immediate download on Hugging Face and will soon be available on popular frameworks like LangChain and LlamaIndex.

Key Highlights:

  1. Longest context window - Jamba 1.5 models boast a 256K effective context window – the longest in the market. This makes them ideal for tasks like long document summarization, analysis, and agentic and RAG workflows.

  2. Exceptional speed - Jamba 1.5 models are up to 2.5X faster on long contexts than other models in their size class.

  3. Superior quality - Jamba 1.5 Mini is the strongest open model in its size class, while Jamba 1.5 Large outperforms leading models like Llama 3.1 70B and 405B on the Arena Hard benchmark.

  4. Developer-friendly - Jamba 1.5 models natively support structured JSON output, function calling, digesting document objects, and generating citations.

Quick Bites

  1. Anthropic has added support for LaTeX rendering in Claude as a feature preview. Claude can now display mathematical equations and expressions in a consistent format.

  1. AI video creation platform D-ID has launched a new AI video translation tool that not only translates videos into other languages but also clones the speaker's voice and syncs their lip movements to the translated words.

  2. ElevenLabs has reduced prices for its Turbo AI audio models by 50%, offering new pricing plans for both self-serve and enterprise users. It has also introduced a new Business Plan with increased benefits and credits. The company has also implemented credit rollovers and usage-based billing for greater flexibility and control.

Tools of the Trade

  1. KaneAI: AI-powered software testing tool that uses natural language to generate, debug, and manage automated tests across web and mobile applications

  2. Outerport: A unified registry for foundation model weights, enabling efficient inference and deployment by offering instant hot swaps, fast cold starts, and optimized resource utilization.

  1. Scopilot: AI tool that helps you define and scope software projects faster by generating features, user stories, and clarification questions. It also assists with product discovery and specification.

  2. Awesome LLM Apps: Build awesome LLM apps using RAG to interact with data sources like GitHub, Gmail, PDFs, and YouTube videos through simple text. These apps will let you retrieve information, engage in chat, and extract insights directly from content on these platforms.

Hot Takes

  1. We won’t see superintelligence in the near-term – that’s just hype from people who don’t understand how far we actually are right now from genuine intelligence – and we don’t (at least anytime soon) have to worry about “extinction”. ~
    Gary Marcus

  2. In the short term Nvidia rules. In the long term it’s extremely vulnerable because GPUs are far from the ideal architecture for AI. ~
    Pedro Domingos

Meme of the Day

That’s all for today! See you tomorrow with more such AI-filled content.

Real-time AI Updates 🚨

⚡️ Follow me on Twitter @Saboo_Shubham for lightning-fast AI updates and never miss what’s trending!

Unwind AI - Twitter | LinkedIn | Instagram | Facebook

PS: We curate this AI newsletter every day for FREE, your support is what keeps us going. If you find value in what you read, share it with at least one (or 20) of your friends!

Reply

or to participate.