AI Agents Development in Python (LangGraph):

AI & Machine Learning
Job 13 of 13
A collection of AI agents built in Python using the LangGraph framework — ranging from simple state graphs to a full RAG (Retrieval-Augmented Generation) system that answers questions based on a PDF document.

What's implemented:
• Stateful agent graphs — nodes, edges, conditional routing, and loops
• Conversational chatbots with full memory and conversation logging
• ReAct agent — reasons and calls tools in a think→act→think loop
• Document assistant — an interactive agent that creates, edits, and saves text files via tool calling
• RAG system — loads a PDF, splits it into chunks, embeds them with HuggingFace, stores vectors in ChromaDB, and answers questions grounded in the source with citations (temperature=0 to minimize hallucination)

Tech stack:
Python 3.12 · LangGraph · LangChain · Groq (LLaMA 3.3 70B, GPT-OSS 120B) · ChromaDB · HuggingFace Embeddings

These projects demonstrate hands-on experience with agentic AI workflows: tool calling, multi-step reasoning, memory management, and retrieval-augmented generation. Available for freelance work on AI agents, chatbots, and RAG systems.

Github:https://github.com/yura2787/LangGraph


#Python #AI #LangGraph #LangChain #RAG #Chatbot #LLM #AIAgents #MachineLearning #VectorDatabase #Automation