Python

Project Snapshot Run conversational AI experiments entirely on your laptop. This prototype couples a Hugging Face pipeline with GPU-aware guardrails so teams can iterate without depending on hosted endpoints. Business Context Targets labs and compliance-sensitive teams that need to validate chatbots without sending data to third-party clouds. Provides a repeatable launchpad for onboarding collaborators who work across Linux, macOS, and Windows. Core Capabilities Local BlenderBot inference driven by the facebook/blenderbot-400M-distill checkpoint via the transformers text-to-text pipeline. Notebook/script parity maintained with a Jupytext pair (basic_chat.ipynb ⇄ basic_chat.py) so edits stay synchronized across IDEs and browsers. GPU-friendly bootstrap that sets PYTORCH_CUDA_ALLOC_CONF and clears CUDA caches to squeeze models onto 2 GB cards while still offering CPU fallback. Environment diagnostics through gpu_ts.py and pt-cuda-ts, confirming PyTorch/CUDA availability before allocating large tensors. Conda-lock reproducibility with environment.yml, multi-platform lock files, and Makefile targets (make expenv, make updenv) that keep dependencies in sync. Implementation Notes Ships with concise setup steps for installing the right PyTorch build, transformers, accelerate, and sentencepiece. Encourages tight VRAM management by demonstrating how to toggle precision or device maps inside the pipeline. MIT-licensed and structured so larger checkpoints or UI wrappers (Gradio, Streamlit) can be swapped in later. My Role I packaged the notebook workflow, scripted the GPU health checks, and automated environment locking to make local LLM prototyping dependable for teammates. ...

Project Snapshot High-volume data collectors often get blocked when Tor exit nodes appear on ban lists. This toolkit automates circuit hopping, preserving throughput without compromising anonymity. Business Context Ideal for research and compliance teams that rely on Tor to gather insights from restricted networks. Prevents stalled scraping jobs by detecting unresponsive or blacklisted circuits and rotating before requests fail. Core Capabilities Multi-circuit orchestration that spins up concurrent Tor connections for parallel requests. Circuit health monitoring to flag banned endpoints and trigger renewals instantly. Lightweight thumbnail generator guideline for showcasing Tor utilization in dashboards or portfolios. Designed as a personal library foundation that can be embedded into larger scraping pipelines. Implementation Notes Python-based helper utilities with clear extension points for queue managers or custom proxies. Emphasizes clean separation between Tor control signals and business logic to simplify auditing. MIT-licensed, enabling teams to extend safeguards or integrate alternative anonymity networks. My Role I distilled recurring automation needs into reusable primitives, focusing on resilient networking patterns and developer-friendly abstractions. ...