Vedcraft
599 FOLLOWERS
A place for software architects to learn, grow & share knowledge in architecture, design, code & technology trends like Cloud, DevOps, Microservices.
Vedcraft
1M ago
#1 – Google’s launch of Gemini & Gemini 1.5
Google launched Gemini 1.5 on Feb 15, 2024, which transcends all other models with a 128K token window with the capability to support up to 1 million tokens per context window.
Gemini 1.5 use-cases: Research over a very large amount of data processing by LLM including 1 hour of video, 11 hours of audio, codebases with over 30,000 lines of code or over 700,000 words
Google launched Gemini models (Ultra, Pro, and Nano) in Dec 2023. Gemini Ultra outperformed MMLU (massive multitask language understanding), which uses 50+ subject areas.
Google Gemin ..read more
Vedcraft
1M ago
Table of Contents
[Open][Close]
Introduction
Open Source LLMs
#1 – Llama 2
#2 – Falcon
#3 – BLOOM
#4 – MPT-30B and MPT-7B
#5 – Mistral 7B
Conclusion
References
Introduction
Large Language Models (LLMs) do not need any introduction with the rise of its massive adoption in the industry. Most enterprises have either adopted or planning to adopt an LLM to build Generative AI-based enterprise applications supporting a variety of business use cases.
While there are many closed-source options available such as – OpenAI’s GPT-3.5 or GPT-4, Google’s Gemini, etc., Open source LLMs have start ..read more
Vedcraft
3M ago
Since its inception in 2015, the CNCF community has evolved as a global community supporting open source, and vendor-neutral cloud-native technologies. The North American KubeCon + CloudNativeCon 2023 event in Chicago (Nov. 6 to 9) consisted of 80+ different sessions across 10+ tracks covering the broader spectrum of the Cloud-native landscape.
While I have attended KubeCon multiple times, this has been my first in-person attendance. This article shares key takeaways based on my observations based on sessions I attended at KubeCon + CloudNativeCon.
#1 — It is the place for ..read more
Vedcraft
6M ago
Amazon Bedrock, which was announced in April 2023, has drawn a lot of attention from businesses looking to leverage their existing AWS architecture for building Generative AI applications. Amazon announced the General Availability (GA) of Bedrock on September 28 — a service that offers a choice of Generative AI models from Amazon and third-party providers through an API-based interface.
With the current market landscape (high demand for leveraging GAI for building innovative business capabilities) and increasing competitive offerings (Azure’s OpenAI partnership & ..read more
Vedcraft
7M ago
Meta released Code Llama, a large language model (LLM) that can use text prompts to generate and discuss code, on August 24, 2023. It has been built on Llama 2 as a foundational model and is free for research and commercial use. Click here to read the news annoucment published by Meta.
The below visualization depicts the foundational building block of Llama 2, and an approach to build your own custom model on top of it:
Key deliverables/artifacts, which can be accessed by following links below:
GitHub Repository for Code LLama
Request Access to Download Code LLama
Research Paper on Code Lla ..read more
Vedcraft
8M ago
HashiCorp announced on August 10, 2023, that they are adopting Business Source License from Mozilla Public License v2.0 (MPL 2.0). Click here to read the announcement and they have also published a FAQ page.
This will require additional consideration if you are using their key product offerings – Terraform, Packer, Vault, Boundary, Consul, Nomad, Waypoint, and Vagrant.
Source: https://www.hashicorp.com/blog/categories/products-technology
This has raised many questions in the Open source community, particularly because of the limitations as part of the BSL license:
BSL is an alternative ..read more
Vedcraft
8M ago
Microsoft Ignite 2023, a conference aimed at expanding the partner ecosystem, just came to a close. Key announcements have been summarized below:
Enabling AI transformation through partner programs to build solutions for their clients has been the theme of the conference:
Microsoft is expanding its partnership with Meta by launching Llama 2 on Azure and Windows.Launched Bing Chat Enterprise and Microsoft 365 Copilot for Enterprise Customers — the concept of Copilot is not limited to GitHub, the foundational building block has been extended to other products. Bing Chat Enterprise enables o ..read more
Vedcraft
8M ago
Stack Overflow, which is the largest question-and-answer website for developers and technologists serving the community for 10+ years. The below statistics indicate the popularity of the platform in the developer community:
Their CEO, Prashanth Chandrasekar, has recently shared the roadmap for the integration of Generative AI into the public platform (Stack Overflow for Teams). Launched as Overflow AI, the suite of capabilities will provide the following key benefits to the community:
Enhanced search for Stack Overflow for Teams: With features such as search and question asking with instant ..read more
Vedcraft
9M ago
Facebook Twitter LinkedIn Email
Table of Contents
[Open][Close]
What is React?
An Overview of AI
Writing React Code with AI
Using AI in React Component
Examples of AI Development with React
AI Models and LLM Platforms/Tools
How to Use React for AI Development?
Conclusion
Related Articles
Today, Artificial Intelligence (AI) has become a buzzword. The global AI market size is likely to reach two trillion USD by 2030. Almost all industries around the globe are leveraging it.
AI is also relevant for web application development. Wondering how? Well, you can ..read more
Vedcraft
9M ago
Facebook Twitter LinkedIn Email
With the rise of OpenAI’s ChatGPT, there is a huge momentum to experiment, ideate, and create innovative solutions unleashing the power of ChatGPT. This blog’s focus is to explore the currently available possibilities to customize OpenAI’s ChatGPT as per your enterprise’s requirements.
Table of Contents
[Open][Close]
# 1 — Static & Dynamic Prompt Engineering
#2 — Embedding Your Data with Retrieval Augmented Generation (RAG)
#3 — Fine-tuned Model with Your Enterprise Data
#4 — Extend the functionality with ChatGPT Plugins
#1 — Static & Dynam ..read more