PHPackages hemreduru/vizier - PHPackages - PHPackages [Skip to content](#main-content)[PHPackages](/)[Directory](/)[Categories](/categories)[Trending](/trending)[Leaderboard](/leaderboard)[Changelog](/changelog)[Analyze](/analyze)[Collections](/collections)[Log in](/login)[Sign up](/register) 1. [Directory](/) 2. / 3. hemreduru/vizier ActiveLibrary hemreduru/vizier ================ Self-hosted natural language to SQL report engine. Scans your database and codebase once, builds a semantic catalog, then turns plain Turkish/English questions into safe, read-only SQL reports using cheap LLMs. v0.1.0(1mo ago)00MITPHPPHP >=8.2 Since Jul 17Pushed 1mo agoCompare [ Source](https://github.com/hemreduru/vizier)[ Packagist](https://packagist.org/packages/hemreduru/vizier)[ RSS](/packages/hemreduru-vizier/feed)WikiDiscussions main Synced 1w ago READMEChangelogDependencies (1)Versions (2)Used By (0) vizier ====== [](#vizier) Self-hosted **natural language → SQL report engine**. Scans your database *and*your codebase once, builds a semantic catalog (schema cards, a human-approved join graph, a real-cell-value dictionary, a library of proven question→SQL examples), then turns plain Turkish or English questions into safe, read-only SQL reports using cheap LLMs — local Qwen via Ollama, DeepSeek, or any OpenAI-compatible endpoint. Runs as a small **sidecar service** with its own embeddable UI, so it can be attached to *any* host app (even a legacy Laravel 5.5 / PHP 7 project) with a single ``. ``` Question ──► retrieve (relevant tables + exact values + similar examples) ──► cheap LLM generates one SELECT ──► guard (parser gate, allowlist, forced LIMIT + timeout) ──► read-only execution ──► table / chart / SQL always visible └── on SQL error: feed the error back, retry (max 2) Confirmed answers are stored as approved examples — accuracy compounds with use. ``` Why it works on your schema when benchmarks look scary ------------------------------------------------------ [](#why-it-works-on-your-schema-when-benchmarks-look-scary) Text-to-SQL benchmarks measure *unseen* schemas. This engine works on **one known schema** that it documents during the scan, seeds with every hand-written JOIN already in your codebase, and improves with every confirmed answer. No fine-tuning, no per-row embeddings, no external vector database — vectors live as BLOBs in the catalog schema and are searched in-process. Requirements ------------ [](#requirements) - PHP **8.2+** with `pdo_mysql`, `curl`, `mbstring` (the *sidecar's* PHP — the host app's PHP version is irrelevant) - A MySQL server for the catalog (a dedicated schema; it rides your existing backups) - Any OpenAI-compatible LLM endpoint (Ollama, vLLM/SGLang, OpenRouter, DeepSeek, OpenAI…) - Optional but recommended: an embedding model (e.g. `bge-m3` on Ollama). Without one, a Turkish-aware token-overlap fallback keeps everything working. Quickstart A — modern Laravel app (10+): true plug-and-play ----------------------------------------------------------- [](#quickstart-a--modern-laravel-app-10-true-plug-and-play) ``` composer require hemreduru/vizier php artisan vizier:scan # installs vz_* catalog tables + scans your DB and app/ code + LLM passes ``` Open **`/vizier`** while logged in — that's it. The service provider is auto-discovered; routes sit behind `['web', 'auth']`. Configure the LLM with two env vars (`VIZIER_LLM_URL`, optionally `VIZIER_LLM_MODEL`), publish the full config with `php artisan vendor:publish --tag=vizier-config`. > Production hardening: point `VIZIER_CONNECTION` at a connection that uses a **read-only DB user**. Out of the box Vizier uses your default connection (with a fresh read-only session + SQL guard), which is fine for trying it out. Quickstart B — any other stack (legacy Laravel, plain PHP, Node, …): sidecar ---------------------------------------------------------------------------- [](#quickstart-b--any-other-stack-legacy-laravel-plain-php-node--sidecar) ``` git clone https://github.com/hemreduru/vizier && cd vizier composer install bin/vizier setup # interactive wizard: creates DB users + grants + config, runs the full scan bin/vizier serve --port=8080 ``` `setup` asks for admin MySQL credentials **once** (never stored), creates the catalog schema and the read-only `vizier_ro` user with SELECT grants on the schemas you pick, writes `config.php` with generated passwords, scans the database and (optionally) your codebase, auto-approves high-confidence joins, and prints a ready-to-open UI link. Non-interactive: pass `--yes` with `--db-host= --admin-user= --admin-pass= --schemas= --llm-url= --code=` flags. After the scan (optional polish, both modes) -------------------------------------------- [](#after-the-scan-optional-polish-both-modes) ``` bin/vizier pair-examples --sql="SELECT class_name, definition_tr FROM registry.reports" # name harvested corpus examples from your report registry bin/vizier edges # review remaining join candidates: --approve=ID / --reject=ID bin/vizier note "Active students: spc.sp_is_active = 1" # tribal knowledge, injected into every prompt ``` The codebase harvest is the warm start: every hand-written `JOIN` in your project is a proven relationship edge, and every report query becomes an approved example once `pair-examples` names it — the flywheel starts **full**, not empty. Run --- [](#run) ``` bin/vizier ask "yazılım ofisinde aktif çalışan personel listesi" # CLI test bin/vizier serve --port=8080 # UI + API ``` Embed in any host app: ``` ``` The token is a tiny HMAC the host signs with the shared `auth.secret` — see [examples/host-issue-token.php](examples/host-issue-token.php) (PHP 5.6+ compatible, no dependencies). Dev shortcut: `bin/vizier token --user=me`. HTTP API -------- [](#http-api) MethodPathBodyNotesPOST`/api/ask``{"question": "..."}`full pipeline; returns title/chart/sql/columns/rowsPOST`/api/feedback``{"run_id": 1, "good": true}``good` feeds the example flywheelGET`/api/admin/edges?status=pending`—admin tokenPOST`/api/admin/edges``{"id": 1, "status": "approved"}`admin tokenGET/POST`/api/admin/examples`—review corpus candidatesGET`/api/health`—no authToken via `?t=` or `Authorization: Bearer`. Safety model (defense in depth) ------------------------------- [](#safety-model-defense-in-depth) 1. Prompt rules (courtesy, not control) 2. `phpmyadmin/sql-parser` gate: exactly one statement, SELECT-only 3. Catalog allowlist — only scanned, enabled tables; system schemas always denied 4. Every query wrapped: forced `LIMIT` + `MAX_EXECUTION_TIME` hint 5. PHP-side row cap + read-only session 6. **Least-privilege read-only DB user — the boundary that holds even if everything above fails** 7. Full audit log (`vz_runs`): every question, SQL, outcome, user The UI always shows the generated SQL and row count — no silent wrong answers. Tests ----- [](#tests) ``` composer test # logic + pipeline with fakes, no DB needed VIZIER_TEST_DSN="mysql:host=...;dbname=vizier_test" \ VIZIER_TEST_USER=... VIZIER_TEST_PASS=... composer test # + catalog store tier ``` Design notes ------------ [](#design-notes) - Catalog + vectors live in MySQL (BLOB + in-process cosine; ~10k vectors ≈ tens of ms). `vector_store` adapters (Qdrant) are the upgrade path, not a requirement. - One LLM config covers every provider via the OpenAI-compatible API; no SDK dependencies. - The schema excerpt sent to the model is explicitly labeled as a *partial subset* — this stops hallucinated tables. - Turkish questions are handled by keeping literals verbatim (value dictionary supplies exact cell strings) and folding/stemming on the retrieval side. MIT © Emre Duru ### Health Score 34 — LowBetter than 74% of packages Maintenance90 Actively maintained with recent releases Popularity0 Limited adoption so far Community6 Small or concentrated contributor base Maturity36 Early-stage or recently created project Bus Factor1 Top contributor holds 100% of commits — single point of failure How is this calculated?**Maintenance (25%)** — Last commit recency, latest release date, and issue-to-star ratio. Uses a 2-year decay window. **Popularity (30%)** — Total and monthly downloads, GitHub stars, and forks. Logarithmic scaling prevents top-heavy scores. **Community (15%)** — Contributors, dependents, forks, watchers, and maintainers. Measures real ecosystem engagement. **Maturity (30%)** — Project age, version count, PHP version support, and release stability. ### Release Activity Cadence Unknown Total 1 Last Release 46d ago ### Community Maintainers ![](https://avatars.githubusercontent.com/u/116385552?v=4)[Hursit Emre](/maintainers/hemreduru)[@hemreduru](https://github.com/hemreduru) --- Top Contributors [![hemreduru](https://avatars.githubusercontent.com/u/116385552?v=4)](https://github.com/hemreduru "hemreduru (4 commits)") --- Tags laravelaibusiness intelligencellmreportstext-to-sql ### Embed Badge ![Health badge](/badges/hemreduru-vizier/health.svg) ``` [![Health](https://phpackages.com/badges/hemreduru-vizier/health.svg)](https://phpackages.com/packages/hemreduru-vizier) ``` ### Alternatives [php-mcp/laravel Laravel SDK for building Model Context Protocol (MCP) servers - Seamlessly integrate MCP tools, resources, and prompts into Laravel applications 476214.2k4](/packages/php-mcp-laravel)[claude-php/claude-php-sdk-laravel Laravel integration for the Claude PHP SDK - Anthropic Claude API 5229.7k](/packages/claude-php-claude-php-sdk-laravel)[blockshiftnetwork/chat-markdown-converter Convert AI-generated Markdown to WhatsApp, Telegram, Discord, Slack and Instagram compatible formats using an Intermediate Representation (IR). 1213.5k](/packages/blockshiftnetwork-chat-markdown-converter)[alidaaer/laravel-ai-agent Give your Laravel app a brain, safely. Build AI Agents that can execute real actions in your application. 281.0k](/packages/alidaaer-laravel-ai-agent) PHPackages © 2026 [Directory](/)[Categories](/categories)[Trending](/trending)[Changelog](/changelog)[Analyze](/analyze)