nlp

Practical guide to building an AI portfolio from the Linux terminal: set up Python/Bash tooling, train a reproducible scikit-learn baseline on Wine data, automate with scripts and Makefile, add MLflow experiment tracking, and ship a CLI predictor. Includes commands, artifacts (models/metrics), optional cron runs, and README tips to showcase end-to-end, MLOps-aware skills in interviews.

Learn how to convert messy PDFs, scans, and forms into private, queryable knowledge on Linux with a reproducible Bash pipeline: OCR/normalize with ocrmypdf, extract and convert to Markdown with poppler+pandoc, chunk to JSONL, enrich via local Ollama LLMs, then index and search fast with SQLite FTS5—complete with install commands, practical scripts, tips, and an end-to-end one-liner.

Build AI‑powered customer support entirely from Bash using curl, jq, and sqlite3 with any OpenAI‑compatible API: create a SQLite ticket store, redact PII, classify intent/priority for triage, summarize threads with sentiment, draft compliant replies via a style guide (human‑in‑the‑loop), and safely auto‑respond to FAQs. The toolkit is portable, auditable, privacy‑aware, and vendor‑flexible, with tips for rate limits, retries, guardrails, and scheduling.

Guide to automating high-quality, Conventional Commit–style messages from Bash using a Git prepare-commit-msg hook, powered by OpenAI (cloud) or Ollama (local). Covers Linux setup via apt/dnf/zypper, optional aicommits CLI, prompt tuning, guardrails, and human-in-the-loop review—boosting consistency, speeding reviews/releases, and preserving commit hygiene.

A practical guide to building a lightweight, hackable Linux AI assistant in Bash that runs in your terminal, maintains brief context, and uses either OpenAI (cloud) or Ollama (local). It covers installing dependencies (apt/dnf/zypper), a minimal curl+jq assistant, adding voice output/input via OpenAI TTS/Whisper, workflow integrations (aliases, piping), safety practices, real‑world examples, and privacy/cost trade‑offs.

Practical, privacy-first guide to turning noisy Linux logs into concise, actionable summaries with AI. Collect, filter, redact, and chunk data; summarise locally with Ollama or via OpenAI; consolidate and automate with cron. Provides Bash scripts, required tools, real-world triage/capacity/disk examples, and guardrails on redaction, verification, compliance, and iterating prompts.

Supercharge your Linux command line with AI: install curl, jq, pipx, and the model‑agnostic llm CLI (plus OpenAI or local Ollama) to keep workflows in Bash while getting smart log summaries, bulk line classification, reliable JSON from free text, and drafted sed/awk one‑liners; or use a pure curl+jq function—guided by privacy‑first, strict‑output, jq‑validated, chunked, versioned‑prompt practices.