Csaba Toth - senior software engineer, remote team lead, public speaker, tech meetup enthusiast

I use daily:
I work using:
I also use:
I am also proficient:
Learning about:

Generative AI and other Hackathon projects and wins

Eco Trivia Quiz Application (with chat agent on the side): Eco Trivia is a web / mobile game about climate change. Apathy and information overload prevent people getting involved with climate action. I gathered Google Developer Student Club (GDSC) Fresno members Zheng Wei Ng and Ran Hao Wong to create a quiz game about sustainability. We were exploring how far we can go with low-code / no-code tools:
- We used Agent Builder for the LLM and RAG back-end: Eco Trivia Agent Builder agent with JSON structured response and examples
- We were exploring special features such as JSON responses from the agent
- We used Flutter Flow for the front-end: Flutter Flow source code export
- We also used Flare no-code animations
- Our work reused experiences from the SDG (Sustainable Development Goals) agent, also glue code to connect the front-end and the back-end
- We also integrated a chat agent as a side feature, so the user can have free conversation besides the quiz game
- 2nd place at the GenAI Gemini Hackathon issued by Issued by Google Developer Community (GDC)
Eco Oracle Chat Agent: A no-code / low-code agent specialized in Sustainable Development Goals via RAG (Retrieval Augmented Generation). It uses the Google Cloud Platforms Agent Builder offerings which are Generative AI successor to DialogFlow CX conversational agents, and it offers no code "playbooks" (or behavior scripts), managed RAG, function calls and powered by Google Gemini under the hood.
LLM Knowledge agent with RAG Fusion: Using Cohere chat, document guided and web connector guided agents, Weaviate services and LangChain, I implemented a RAG Fusion solution with a Streamlit UI. I also experimented with Cohere's Command R large language model.
- 4th (finalist top 5) at the Cohere Coral Hackathon
QBRAG (QnA Boosted RAG) Knowledge LLM agent on Vectara platform: A company's knowledge bases often times don't answer the wide variety of questions a user could come up with. A Customer Support system ideally could answer specific (but wide variety) questions about the company's systems and knowledge (example: "How can I enter Cash Flow in ThruThink?"). But sometimes the user asks generic questions, such as "What is Cash Flow?" which could be sourced from the mind of a giant LLM model and / or the internet. My submission is essentially synthetic data enrichment of the knowledge base by reusing generated question and answers. To help and boost the performance by leveraging Question and Answer generation techniques - normally used for fine tuning but in this case - for knowledge base augmentation / indexing enrichment. The generated questions could support specific user queries potentially better matching than a "non focused" indexed generic knowledge base.
- As part of the effort I contributed to the https://github.com/nestordemeure/question_extractor open source project which offers semantic markdown knowledge base chunking.
- Tech used: Vectara (embedding, vector database, ranking, etc.), AnyScale (LLM hosting, fine tuning), and React for front-end.
- Winner of the Customer Support category of "RAG: LLMs with your data Summary" hackathon
GeMMAA (Generative Mulkti Modal Augmented Reality Art) application by AIWeavers for Multi Modal hackathon by Weaviate at AIx Innovation Summit. Team repository: https://github.com/AIWeavers/GeMMAA. An AR mobile application which can generate 3D art from a text prompt and also music from a text prompt with the option of minting an NFT from the artwork. We use 8thwall for the front-end, NFTPort for NFT minting, GCP cloud functions for back-end, Meshy for 3D model generation, Meta's music generator, and most importantly Weaviate's multi-model embedding to allow search and organization of the artwork. The team:
- Avi Rao (https://www.linkedin.com/in/avi-nav-rao-39a567205/) front-end main role for the hackathon and AR/VR + blockchain, NFT, crypto, web3 specialist
- Yvonne Fang (https://www.linkedin.com/in/yvonne-fang-679892153/) front-end main role for the hackathon and also AR/VR, Gen AI art and web3 specialist
- Andrew Savala (https://www.linkedin.com/in/redswimmer/) back-end role for the hackathon, but also full stack engineer and AI/ML specialist
- Quinton Mills (https://www.linkedin.com/in/quinton-mills/) front-end role for the hackathon, also UX design and many competencies
- Myself: back-end, GCP functions, team organization
- Winner of the Multi Modal hackathon by Weaviate at AIx Innovation Summit and ODSC West 2023 data science conference
Knowledge LLM agent with RAG utilizing low-code / no-code cnvrg LLMaaS platform: At the time of the project (Intel Innovation Bridge hackathon @ Intel Innovation 2023) cnvrg's LLMaaS (LLM as a service) by Intel was in alpha stage. The LLMaaS service provided a no code environment to fine tune and customize agent solutions with ease. Due to the development stage of this novel product I could use two toy datasets to fine tune an LLM, and I applied RAG (Retrieval Augmented Generation) with the help of a PineCone vector database, using ChatGPT's embeddings API. I also got familiar with GRadio and similar front-ends. Due to confidentiality the materials I can share are limited.
- Winner of the Intel Innovation Bridge hackathon's LLM category @ Intel Innovation 2023
Gen AI Rock Star Challenge: Song "Xeon Fury" of the band "Nerdcore Annihilation". Participants were tasked with generating a poster or album cover for an imaginary rock band, along with generating the lyrics of an imaginary song for said band. We were provided with a Gaudi2 accelerated deep learning AWS EC2 instance equipped with a Runway 1.5 text-to-image stable diffusion model, and also a Vicuna 7-based LLM model. We increased the steps of the stable diffusion model from 10 to 50 to conclude with much better images. The EC2 box was inaccessible for a while, and in the meantime, we experimented with some other LLM models for lyrics, such as ChatGPT and PaLM, as well as the officially accessible Runway Gen 1. We used the LLM to get the band name (Nerdcore Annihilation) and the song name (Xeon Fury) as well. The stable diffusion model couldn't feature text on the image precisely, so we used Runway's web-accessible edit feature to add an old school Intel Inside logo and modify the center image of the front cover. The back cover was purely generated by the Gaudi2 instance (notice how the wafer is a pastry wafer and not a chip wafer). We adjusted the prompt many times. I used my geek knowledge to provide desired keywords for the lyrics: MMX, AVX, AVX2, AVX512, AMX, Xeon Phi, Gaudi 2, Optimum Habana, 288-core Xeon (freshly announced). We mixed the best parts of the various tries together to create a hilarious final set of lyrics.
- Winner of Intel GenAI Rock Star Challenge @ Intel Innovation 2023
Multi Modal Generative AI Travel blog helper app: An app indexes pictures taken during travel trips or everyday experiences. With the power of multi modal embedding models and vector databases it is able to categorize them, describe them and help document the experiences. The back-end uses Chooch for image to text tasks and Google Cloud Platform for everything else such as asset management, search, summarization and RAG. The front-end is written in Kotlin and uses Compose UI by Kevin Moore GDE. The project management, iteration on ideation, user interviews, feasibility, presentation of our work was done by Yiru and Coco He.
CSU Fresno Recycling Trashcan locations - Outdoor Augmented Reality Map leveraging Geospatial API and Terrain Anchors to guide students to recycling trashcans
- AR mobile app source code repository
- 360 photo + video VR companion website and source code.
- Winner of Honorable Mention category at the Google Maps Platform Hackathon, individual project website.
CSU Fresno Tree Walk - Outdoor Augmented Reality Map leveraging Geospatial API and Terrain Anchors to guide visitors along the Tree Walk, boost engagement gamification as well as advanced Generative AI method: segmentation for vritual vatering
- AR mobile app source code repository
- 360 photo + video VR companion website and source code.
AMP personal website - Google Registry Website Competition Winner
- source code repository
- Google Registry Website Competition Winner
Deal-O-Round - Flutter based reimplementation of a PlayN-based multi-platform (Android / iOS / web) game
- source code repository
- companion website with web demo
- 3rd place at 59 Days of Code 2014 hackathon

mrcsabatoth Goto Github PK

Csaba Toth - senior software engineer, remote team lead, public speaker, tech meetup enthusiast

Generative AI and other Hackathon projects and wins

More projects worth mentioning:

Blog Posts

Csaba Toth's Projects

Recommend Projects

Recommend Topics

Recommend Org