Large language models (LLMs) are emerging as a transformative technology, enabling developers to build applications that they previously could not. We have used Cohere.ai developed models to create a web application using stramlit library for many known script generations like movie script, song lyrics, story generation, poem generation, blog post generation In our current situation we offer a unique platform for creative expression with three distinct functions: writing poems, stories, and posts. It provides users with a convenient and user-friendly interface to unleash their imagination and bring their creative ideas to life. ​

Cohere Hackathon

This project offers a unique platform for creative expression with three distinct functions: writing poems, stories, and posts. It provides users with a convenient and user-friendly interface to unleash their imagination and their creative ideas to life. 

Neural Ninjas

BlogGPT

Dissection labs and complex anatomical models can be overwhelming. What if you could simply upload a picture or screenshot of a specific body part and get instant, personalized guidance?  This is where our innovative AI anatomy tutor comes in!

Leveraging the power of Vectra AI's object recognition, our app analyzes your uploaded image (png format) to pinpoint the exact anatomical structure. Our friendly AI chatbot then takes over, providing clear explanations, detailed text descriptions, and relevant high-quality diagrams to enhance your understanding.

This interactive learning tool caters to all students, from beginners overwhelmed by terminology to advanced learners seeking deeper insights.  No more flipping through textbooks or struggling with confusing terminology.  Our AI tutor personalizes the learning experience, making anatomy engaging and accessible for everyone!

This AI tutor uses Vectra tech to identify them & explains with text & diagrams. Learn anatomy the future way!

The Code Brakers

RAG-as-a-service API-driven generative AI platform.

Vectara

Automating data synthesis, advancing data privacy

Tonic.ai

Unstructured IO

Discover the power of Together AI and empower AI innovation together!

Together AI

GPT-3.5 stands for Generative Pre-trained Transformer and is fine-tuned version of GPT-3. It is an autoregressive language model that uses deep learning to produce human-like text. There are many models in GPT-3.5 family as gpt-3.5-turbo or gpt-3.5-turbo.

GPT-3.5

OpenAI is an AI research and deployment company

OpenAI

Explore Gemini, Google DeepMind's most advanced AI model, blending multimodality and high efficiency.

Gemini AI

Discover Alphabet Inc.'s gem: Google LLC! A global multi-tech marvel offering internet-focused services – search engines, online ads, cloud prowess, software savvy, and hardware innovation.

Google

Tutor Mentor

Chat with your PDF is the standard RAG 101 example.
In this hack, we demonstrate an example of Chat with your code base. 
Problem:

Imagine you are trying to contribute to a new code base (a github repository) for a beginner task.
Knowing which file to change, where to make the change can be time consuming.
This is NOT about CODE COMPLETION. 

This a semantic code search application deployable locally and works from a terminal.
Business impact:
Developers would have enhanced productivity and be willing to buy this RAG application
Code completion tools do not tell where to make the changes on an existing code base.


There are lots of chat with your PDF examples. There are not enough chat-with-your-code examples

llama buddy

LlamaIndex connects data sources to large language models, providing tools to ingest, index, and query data for building powerful AI apps augmented by your knowledge.

LlamaIndex

During this Hackathon, we delved into the feasibility of rapidly developing web-based businesses primarily powered by Vectara-supported agents. This innovative approach not only provides the flexibility to integrate Human-in-the-Loop systems but also supports continuous training opportunities.

Our exploratory findings demonstrate that such a business model can significantly enhance operational efficiency and adaptability. By leveraging dynamic structures and automation, there is a marked reduction in reliance on manual processes and personnel. Moreover, this model promotes a comprehensive and transparent view of business operations, optimizing resource management and improving overall performance.

Although this Hackathon served as an initial investigation into the feasibility of the Vectara solution-without full only conceptual implementation-our prior experience with Vectara Rag gave us confidence in the soundness of this approach. We stand on the brink of a transformative era in data management and business operations. The continued exploration and development of these technologies will be crucial in realizing their full potential. 

As we move forward, it is clear that much work remains, yet the path ahead is promising and ripe with opportunities for innovation.

In this Hackathon, we explore the practicality of swiftly establishing web-based enterprises fully staffed by Vectara-supported agents, with the option to incorporate Human-in-the-Loop and offer ongoing training.


Navigator

Large language models (LLMs) have transformed the way we approach machine learning and artificial intelligence. These models are incredibly powerful, but their true potential lies in their ability to work in harmony with other sources of data and computation. This library has been developed to assist developers in building applications that combine LLMs with other technologies, allowing them to create truly intelligent and innovative products.

LangChain

Langchain

MedMind is revolutionizing access to medical knowledge. This AI chatbot acts as your personal health assistant, providing:
Instant answers to your medical questions: MedMind draws on a curated knowledge base to address your health concerns with accuracy and clarity.
Research summaries at your fingertips: Dive into the latest research without getting lost in jargon. MedMind summarizes relevant PubMed articles, making complex science accessible.
Safe and reliable web searches: Explore further with confidence. MedMind utilizes Google Search API to provide secure and pertinent web results.
MedMind’s Potential and Economic Value:
Empowering patients: MedMind equips individuals to take control of their health by understanding their conditions and making informed decisions.
Easing the burden on healthcare systems: By providing reliable self-service tools, MedMind can alleviate pressure on doctors and medical resources.
Improving health literacy: Making medical knowledge accessible to everyone promotes preventative care and healthier communities.
Revolutionizing medical research: MedMind can accelerate research by efficiently analyzing data and identifying trends, leading to faster discoveries and breakthroughs.
MedMind is more than just a chatbot – it’s the future of healthcare information.

MedMind: Your AI-powered partner for navigating the world of health information. Ask any medical question, get instant answers and insightful research summaries, and explore reliable web resources – all through a simple chat interface.

MedMind

Code: https://github.com/sprites20/Anthroid-AI
Using together.ai to host the LLM serverless, Vectara for querying the documents, LLamaIndex for text embeddings (or LLM), and unstructured.io cleaning and translating the HTML or maybe even formatting the prompts. 

Uses Google Search API or Azure Bing Search service API to query the search engine, returns links, and sends to Vectara for indexing and querying, (perhaps more options in the future). For now, it uses only Vectara but will implement the LLamaindex soon.

Shall also use the Meta's Graph API to gather posts, not only from search engines but social media apps like Facebook for the latest news about a topic using its query engine and more content not only from websites but from actual people in real-time. (WIP)

It is also capable of choosing, retrieving code, and running code. With a built-in Python interpreter; the exec() function, that can also run other languages via bindings like jnius (Java), Cython/CPython (C/C++), C# DLLs, and whatever binding in the Python library there is. Even OpenGL for 3D rendering for true multimodality, OpenCV for RTSP streaming, image processing, and computer vision, matplotlib for mathematical visualizations, or even a custom web browser like Chrome and Edge that can also run JS evaluate to execute JS code for websites.

A cross-platform native app, that in the future should be able to run on most operating systems, not only on PC but also for mobile phones like Android and Ios. 

An attempt to utilize every partner organization's products to create AI agents.

AnthroidAI

One of the best AI labs in the world. By using the Cohere platform we are able to use one of the best and most powerful language models for our own! There are many tutorials, including our own one, that show how to use Cohere.

Cohere

Cohere is a Canadian startup that provides natural language processing models that help companies improve human-machine interactions

BlogGPT

Tutor Mentor

llama buddy

Navigator

MedMind

Search Engine Powered AI Agent and more

Tutor Mentor

llama buddy

Navigator

MedMind

Search Engine Powered AI Agent and more