Scribd
Upload
11 views1 page

Generative AI Learning Plan & Tech Stack

The document outlines a learning plan and tech stack for Generative AI, covering foundational concepts, large language models, prompt engineering, and application development. It details the architecture layers and associated technologies, including data processing, model generation, augmentation, orchestration, user interface, storage, and infrastructure. Responsibilities are divided among three members, focusing on different layers of the tech stack.

Uploaded by

uma2512003
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
11 views1 page

Generative AI Learning Plan & Tech Stack

The document outlines a learning plan and tech stack for Generative AI, covering foundational concepts, large language models, prompt engineering, and application development. It details the architecture layers and associated technologies, including data processing, model generation, augmentation, orchestration, user interface, storage, and infrastructure. Responsibilities are divided among three members, focusing on different layers of the tech stack.

Uploaded by

uma2512003
Copyright
© All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd

Generative AI: Learning Plan and Tech Stack

Concepts of Generative AI
1. Foundations of Generative AI (Difference from Traditional AI, types of GenAI models) 2. Large
Language Models (LLMs) - GPT, Claude, LLaMA, etc. 3. Prompt Engineering (zero-shot, few-shot,
CoT) 4. Embeddings - converting text to vector form 5. Vector Databases - storing/retrieving
semantic data 6. Retrieval-Augmented Generation (RAG) 7. Frameworks like LangChain,
LlamaIndex 8. Application development (chatbots, assistants) 9. Hosting & Deployment (Streamlit,
Gradio, Hugging Face)

Layers in Gen AI Architecture and Tech Stack


Layer Purpose Tech Stack
1. Data & Embedding Process & embed documents LangChain loaders, OpenAI embeddings, Hugging Fa
2. Model (LLM) Core language model generation OpenAI GPT, Claude, LLaMA, Mistral
3. Augmentation (RAG) Fetch external knowledge LangChain RAG, FAISS, Chroma, Pinecone
4. Orchestration Connect models, tools, memory LangChain, LlamaIndex
5. Application (UI) User interface layer Streamlit, Gradio, Flask
6. Storage (Vector DB) Store embeddings FAISS, ChromaDB, Pinecone
7. Infrastructure Deploy and scale app Hugging Face Spaces, Vercel, AWS

Concept Split Among 3 Members


■ Person 1 (You): LLMs, RAG, LangChain (Layers 2, 3, 4) - Understand LLMs (GPT, Claude,
LLaMA, etc.) - Retrieval-Augmented Generation (RAG) - LangChain: Chains, Tools, Memory, RAG
integration ■ Person 2: Data Processing & Embeddings (Layer 1) - Chunking, tokenization,
embedding text data - Using OpenAI/Hugging Face to generate embeddings ■ Person 3: UI, Vector
DBs, Deployment (Layers 5, 6, 7) - Streamlit/Gradio for building apps - Vector DBs: FAISS,
Chroma, Pinecone - Deploying on Hugging Face Spaces, Vercel, AWS

You might also like