Skip to main content

​
Prerequisites

ComponentVersionNotes
PHP^8.3The application targets PHP 8.3+.
Laravel^13.0Framework.
ComposerlatestPHP dependency manager.
Node.js20+Builds the React SPA + Vite assets.
PostgreSQL≥ 15With the pgvector extension.
Sanctum^4.2Ships with the app; powers SPA + token auth.
SQLite is used only for the automated test suite (the vector(N) columns swap to JSON text via the test migrations). Production and development run on PostgreSQL + pgvector.

​
1. Install dependencies

git clone https://github.com/lopadova/AskMyDocs.git
cd AskMyDocs
composer install
npm install && npm run build
cp .env.example .env
php artisan key:generate

​
2. Provision PostgreSQL + pgvector

pgvector must exist in the target database before migrating: 
CREATE DATABASE askmydocs;
\c askmydocs
CREATE EXTENSION IF NOT EXISTS vector;
Then point .env at it: 
DB_CONNECTION=pgsql
DB_HOST=127.0.0.1
DB_PORT=5432
DB_DATABASE=askmydocs
DB_USERNAME=postgres
DB_PASSWORD=secret

​
3. Choose AI providers

Chat and embeddings are configured separately — Anthropic, for example, has no embeddings endpoint, so you pair it with an embeddings-capable provider. 
AI_PROVIDER=openai            # chat: openai | anthropic | gemini | openrouter | regolo
AI_EMBEDDINGS_PROVIDER=openai # embeddings: openai | openrouter | gemini | regolo
OPENAI_API_KEY=sk-...
When AI_PROVIDER=anthropic and AI_EMBEDDINGS_PROVIDER is empty, AskMyDocs auto-selects the first embeddings-capable provider with a configured key in a dimension-safety-first order (openai → openrouter → regolo → gemini), so a deployment never silently corrupts ingest writes with a mismatched dimension. See AI providers for the full matrix.

​
4. Migrate

php artisan migrate

​
  1. Embedding dimensions

The embedding dimension is part of the schema contract. The stock vector(N) columns are sized for 1536 dimensions (openai/text-embedding-3-small, the default, which also matches OpenRouter’s default embeddings model). Choosing a different-dimension model — e.g. qwen/qwen3-embedding-4b at 2560 dims — requires all three of:
  1. migrating the vector(N) columns to the new dimension,
  2. flushing embedding_cache,
  3. re-indexing the corpus (re-ingest).
Mixing dimensions silently corrupts retrieval. Pick the embeddings model before your first ingest.

​
6. Run it

php artisan serve          # http://localhost:8000
php artisan queue:work     # processes IngestDocumentJob + canonical indexing
Open /app for the SPA (chat + admin), or hit the JSON API directly. Create your first admin user with the role seeder / auth:grant command (see Admin panel).

​
Scheduler

Several rotations run on the Laravel scheduler (bootstrap/app.php). Enable the system cron entry so they fire: 
* * * * * cd /path/to/AskMyDocs && php artisan schedule:run >> /dev/null 2>&1
Time (UTC)CommandPurpose
03:10kb:prune-embedding-cacheLRU cache rotation
03:20chat-log:prunechat-log retention
03:30kb:prune-deletedhard-delete expired soft-deletes
03:40kb:rebuild-graphcanonical graph rebuild
All commands accept --days=N and --project= overrides; 0 disables the corresponding rotation.

​
Next steps

Quickstart

Ingest and ask your first question.

Configuration reference

Every env knob, grouped by subsystem.