Generative AI for upskilling and learning initiatives

Master generative AI by mastering prerequisites: Python, statistics, NLP, computer vision; plus frameworks like LangChain, LlamaIndex, ChainLink, Hugging Face, and open-source model fine-tuning.

Explore the LangChain ecosystem, using Lang Smith for observability, debugging, and dashboards, build LM apps via FastAPI, and master chains, agents, retrieval, and the Lang chain expression language (LCL).

Develop a generative AI app with LangChain by ingesting US census PDFs, chunking text with a recursive splitter, building Hugging Face embeddings, and powering retrieval QA with a vector store.

Explore core Python data types—integers, floating point numbers, strings, and booleans—plus type casting and common errors, with practical examples and memory implications.

Explore practical Python lists in action: build a to-do list, manage grades and inventory, and analyze user feedback with append, remove, in-list checks, and sum, average, max, min.

Master lists in Python to organize data, perform iterations, and apply practical list operations within generative AI upskilling projects.

Explore Python tuples, an immutable, ordered collection. Create and access elements, slice, concatenate, repeat, and pack/unpack, including nested tuples and star unpacking, with count and index methods.

Explore Python operators with arithmetic, division, floor division, modulus, and exponentiation, and learn comparison and logical operators like and, or, not.

Explore real-world Python list applications, including to-do lists, student grades, inventory management, and user feedback analysis, using append, remove, and in checks to build practical data workflows.

Build a generative AI-powered LLM application by integrating arXiv, Wikipedia, and PDFs with wrappers, tools, and agents in LangChain for a multi-source Q&A experience.

Master for loops and range to generate number sequences, using start, stop, and step parameters, with nested loops and practical examples to avoid common errors.

Explore Python tuples to understand immutability, creating and converting between lists and tuples, indexing and slicing, concatenation and repetition, packing and unpacking, and nested tuples.

Map applies a function to every item in an iterable, yielding a map object. Use cases include squaring numbers, using lambda, mapping multiple iterables, and converting strings to integers.

Explore the Python standard library with practical examples of array, math, random, os, shutil, json, csv, datetime, time, and re for real-world file and data handling.

Discover how to implement custom exceptions in Python, including a generic error class and a DOB exception, with try-except handling and messages for age input validation.

Learn to build interactive data apps with streamlit by writing simple Python code, displaying data frames, charts, widgets, and file uploads.