victorvargas/rony-chat-bot
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 2
rony-chat-bot/data/projects
History
Victor Hugo Vargas ab510d8b31 docs: document auto-compaction behavior in architecture guide 
Adds the §4.5 Auto-compaction section to architecture.md and
architecture.es.md describing the trigger, fallback, persistence and
the new SSE 'compaction' event so consumers know how to react.

Includes the three placeholder projects used while exercising the
feature end to end (bot-onboarding, dashboard-metricas, tienda-ropa)
so /api/reindex picks them up without further setup.
2026-07-18 00:08:37 -07:00
..
bot-onboarding.md docs: document auto-compaction behavior in architecture guide 2026-07-18 00:08:37 -07:00
dashboard-metricas.md docs: document auto-compaction behavior in architecture guide 2026-07-18 00:08:37 -07:00
example-project.es.md docs(i18n): translate all docs to English (with .es.md as Spanish alternative) 2026-06-30 13:27:00 -07:00
example-project.md docs(i18n): translate all docs to English (with .es.md as Spanish alternative) 2026-06-30 13:27:00 -07:00
README.es.md feat: bootstrap rony-chat-bot Go module 2026-07-17 00:56:06 -07:00
README.md feat: bootstrap rony-chat-bot Go module 2026-07-17 00:56:06 -07:00
tienda-ropa.md docs: document auto-compaction behavior in architecture guide 2026-07-18 00:08:37 -07:00

README.md

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

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