Description
Build an AI Agent From Scratch in Python (No LangChain) is a course on using Python without relying on high-level agent frameworks like LangChain, published by Udemy Online Academy. This course is a hands-on program that teaches developers how to create intelligent AI agents using pure Python without relying on high-level agent frameworks like LangChain. Designed for Python developers, AI enthusiasts, and software engineers, this course focuses on understanding the core building blocks behind modern AI agents by implementing them from the ground up. Students learn how to integrate large language models (LLMs), manage notifications and context, implement memory, make tool calls, interact with APIs, and build standalone workflows using custom Python code.
You build your own agent framework from scratch, one concept at a time, and finish it by understanding every line of it – and you’ll be able to read LangChain, CrewAI or AutoGen like an open book. This course is recommended for working developers who use LLM but treat agents like magic and want to master the basics. By the end of this course, you’ll be able to use Python’s full potential in building intelligent AI agents.
What you will learn in Build an AI Agent From Scratch in Python (No LangChain):
- Give an agent tools from scratch: parse tool calls, dispatch them and manage an illusory tool without crashing.
- Implement working, episodic and semantic memory – and write cosine similarity and top-k retrieval yourself from scratch.
- Build a rationale for the agent with ReAct, reflection and tree-of-thoughts and direct each task to the appropriate strategy.
- Coordinate multiple agents with a delegation constraint, evaluate them (success rate, cost, regression) and make them robust for production with constraints, event logging and guardrails.
- And …
Course specifications
Publisher: Udemy
Instructors: Abhijoy Sarkar
Language: English
Level: Intermediate
Number of Lessons: 49
Duration: 1 hours and 41 minutes
Course topics
Build an AI Agent From Scratch in Python (No LangChain) Prerequisites
Solid Python: functions, classes, and dicts. You’ve called an LLM API at least once.
An API key for any OpenAI-compatible or Anthropic model (a few dollars of usage covers the labs).
No machine-learning math required — the one bit (a dot product) is taught from scratch. No LangChain, no vector DB.
Pictures
Build an AI Agent From Scratch in Python (No LangChain) introduction video
Installation guide
After Extract, watch with your favorite Player.
Subtitle: None
Quality: 1080p
Downloadly link
Rapidgator link
File password (s): www.downloadly.ir
Size
809 MB
