This project provides a ready-to-use development environment for Python projects with integrated LLM (Language Model) capabilities using Ollama. It includes a pre-configured VS Code Dev Container setup with Docker Compose, a Python 3.10 environment, and example code for interacting with Ollama models.

GitHub Documentation Agent is a Retrieval-Augmented Generation (RAG) system that transforms how developers interact with GitHub's extensive documentation. The project automatically ingests GitHub's official docs, processes them using local Ollama LLMs, and stores semantic embeddings in a PostgreSQL vector database

Rag-Chat-Bot is a Retrieval-Augmented Generation chatbot that leverages OpenAI's GPT-4 and semantic search with ChromaDB to answer user queries using your own chat data. Load chats from CSV, store embeddings, and get context-aware answers—all in a simple Python app.

Visualize word embeddings in 3D using PCA and Matplotlib. Generates embeddings with a Llama model (via Ollama), reduces them to 3D, and plots them for easy comparison. Perfect for exploring semantic relationships between words.

A Python-based language translation tool using OpenAI models via the GitHub AI endpoint. Automates translation of text and GitHub issue comments, configurable for any language pair, and easily integrates with GitHub Actions for workflow automation.

Generate OpenAI embeddings with LangChain and visualize their semantic relationships in 3D using PCA + Matplotlib.