Victor Hugo Vargas f33708534a feat: bootstrap rony-chat-bot Go module

Initial implementation of the bot:

- cmd/chat-bot: CLI entrypoint (serve, reindex, ask, version)
- internal/agent: LLM provider client + agent runner with RAG injection
- internal/config: YAML config loader (providers, RAG, persona, server)
- internal/i18n: response-language detection (EN/ES)
- internal/persona: persona system prompt assembly from YAML
- internal/portfolio: heading-based chunker + SQLite FTS5 indexer
- internal/server: chi router with /api/chat (SSE), /api/health, /api/info,
  /api/reindex, middleware (RequestID, Logging, CORS, RateLimit)
- internal/streaming: SSE protocol helpers (start, chunk, sources, done, error)
- web/: drop-in vanilla-JS chat widget (no build, no deps) + demo + README
- bench/: reproducible driver benchmark (modernc vs mattn SQLite)
- configs/portfolio-bot.yaml: llama.cpp default provider, SQLite RAG, canine persona
- docs/architecture.md / .es.md: aligned with SQLite FTS5 + llama.cpp decisions
- data/projects/README*.md: project data documentation
- README.md / .es.md: updated for current implementation

All tests pass (go test ./...). Bot is functional end-to-end with the
configured LLM provider.

2026-07-17 00:56:06 -07:00

1.3 KiB

Raw Blame History

Portfolio Projects

Place a .md file here for each project you want the bot to be able to answer about.

File naming convention

One file per project: project-name.md
Name in kebab-case (lowercase with hyphens)
Example: rony-harness.md, rony-llm-agent.md, portfolio-astro.md

Frontmatter (optional but recommended)

---
title: "Rony Harness"
date: 2026-06
status: "active"     # active | archived | wip
tags: ["go", "ai", "cli"]
repo: "https://github.com/VictorVargas/rony-harness"
demo: "https://..."  # optional
---

# Rony Harness

AI agent harness for software development...

How they're processed

The bot scans this directory on startup
Each .md is split into chunks of ~500 characters
Chunks are stored in a local SQLite database with FTS5 (full-text search, BM25 ranking)
When someone asks a question, the top-5 most relevant chunks are matched
Those chunks are injected into the LLM context

No embedding models or external vector DBs are required — everything runs in a single SQLite file (data/portfolio.db).

Re-index

If you modify the .md files, run:

./bin/chat-bot reindex

This rebuilds the SQLite FTS5 index from scratch.

Project example

See example-project.md for a template.

1.3 KiB Raw Blame History