Deep Hack on Generative AI 2023
2023-04-01
Bengaluru, India
who it's for
generative AI engineers, machine learning engineers, data engineers, backend engineers, frontend developers, chatbot developers
topics
Guardrails.ai rail spec; Weaviate vector database; LlamaIndex indexing pipelines; semantic search with HNSW; Cohere/Hugging Face/OpenAI embeddings; Appsmith front ends for AI stacks; audio capture to transcription pipeline; ChatGPT integration and fine-tuning JSONL; GPT-3 question generation; GPT-4 based QA evaluation
| title | author | length |
|---|---|---|
| Using Guardrails.ai for building Generative AI apps | Shreya Rajpal | 31m |
Open-source Guardrails.ai enforces structure, types and quality checks for LLM outputs using a small XML-like Rail spec that compiles into prompts, runs… | ||
| Using Weaviate for building Generative AI apps | Sebastian Witalec | 27m |
Open source vector database Weaviate stores embeddings from Cohere/Hugging Face/OpenAI, demo loads 100,000 chunked Wikipedia paragraphs into a WCS instance… | ||
| Using Appsmith for building GenerativeAI apps | Jospeh Petty, Ron Northcutt | 34m |
Appsmith builds a front end for GenerativeAI stacks by dragging widgets, wiring REST/GraphQL or Postgres queries, and running inline JavaScript; a working… | ||
| Using LlamaIndex for building Generative AI apps | Jerry J Liu | 42m |
LlamaIndex presents a concrete pipeline: 70+ data connectors to ingest files, APIs and databases, a vector store index (compatible with Pinecone, Chroma, etc.)… | ||
| Deep Hack - India's first ever ChatGPT Hackathon | Amod Malviya, Manisha Raisinghani, Sunit Singh, Toshi Prakash | 05h 50m |
150 builders compete over 24 hours, producing 43 demos; expect concrete prototypes, numbers and failures, not theory. Demos include a bot that logs in via OTP… | ||
| Farmer.CHAT - A GPT-powered, multi-lingual WhatsApp bot | Dev Aggarwal | 21m |
A WhatsApp chatbot pulls Ministry of Agriculture videos and PDFs plus Digital Green transcripts into a vector database, transcribes regional audio with… | ||
| Evaluation of QA systems built on LlamaIndex | Ravi Theja | 32m |
Builds a QA pipeline on LlamaIndex that chunks documents into nodes and wires them to LLMs; index creation and a query loop run in four lines of code… | ||
| nothing matches | ||