How ashishpatel26/ollama-playground works
Project type and purpose
• This is an open-source monorepo of AI demonstration tools built with Ollama’s local LLMs.
• Each subdirectory under the root is a standalone Python demo (e.g., “chat-with-pdf”, “video-summarization”, “image-search”, etc.) that ingests a specific data type, runs preprocessing, invokes an Ollama model, and produces an output.
File structure
• Top-level: .gitignore, README.md, then one folder per demo.
• Each demo folder contains:
• A README describing purpose and usage
• A Python script (e.g., ai_scraper.py, video_summary.py)
• A requirements.txt for dependencies
• A data folder (e.g., pdfs/, images/, videos/, audios/)
• No central “backend” or “frontend”—this is purely a toolkit of CLI/Python scripts.
README for additional insights
• The root README simply lists the demos built with Ollama’s models.