Production-ready database schema patterns for AI applications including chat/conversation schemas, RAG document storage with pgvector, multi-tenant organization models, user management, and AI usage tracking. Use when building AI applications, creating database schemas, setting up chat systems, implementing RAG, designing multi-tenant databases, or when user mentions supabase schemas, chat database, RAG storage, pgvector, embeddings, conversation history, or AI application database.
Limited to specific tools
Additional assets for this skill
This skill is limited to using the following tools:
README.mdexamples/complete-ai-app-schema.mdexamples/indexing-strategy.mdexamples/migration-guide.mdscripts/apply-migration.shscripts/generate-schema.shscripts/seed-data.shscripts/validate-schema.shtemplates/ai-usage-tracking-schema.sqltemplates/chat-schema.sqltemplates/migration-template.sqltemplates/multi-tenant-schema.sqltemplates/rag-schema.sqltemplates/user-management-schema.sqlProduction-ready PostgreSQL/Supabase database schemas optimized for AI applications including chat systems, RAG (Retrieval-Augmented Generation), multi-tenancy, and usage tracking.
Ask the user which schema pattern they need:
Use the generation script:
cd /home/vanman2025/Projects/ai-dev-marketplace/plugins/supabase/skills/schema-patterns
./scripts/generate-schema.sh <pattern-type> <output-file>
Pattern types: chat, rag, multi-tenant, user-management, ai-usage, complete
Before applying, validate the generated schema:
./scripts/validate-schema.sh <schema-file>
This checks for:
Apply the schema to your Supabase project:
./scripts/apply-migration.sh <schema-file> <migration-name>
This creates a timestamped migration file and validates before applying.
For development, generate realistic test data:
./scripts/seed-data.sh <pattern-type>
chat-schema.sql: Complete chat/conversation system with users, conversations, messages, participantsrag-schema.sql: RAG document storage with chunks, embeddings (pgvector), and similarity searchmulti-tenant-schema.sql: Organization-based multi-tenancy with orgs, teams, members, rolesuser-management-schema.sql: Extended user profiles, metadata, preferencesai-usage-tracking-schema.sql: Token usage, API costs, rate limiting, usage analyticsmigration-template.sql: Boilerplate migration structure with version trackingindexes-template.sql: Performance optimization index patternsrls-policies-template.sql: Row Level Security policy patternsAll RAG schemas include:
Organization-based isolation:
Optimized for real-time messaging:
See the examples directory for:
complete-ai-app-schema.md: Full schema combining all patternsmigration-guide.md: Schema evolution and versioningindexing-strategy.md: Performance optimization guide./scripts/generate-schema.sh chat schema.sql
./scripts/validate-schema.sh schema.sql
./scripts/apply-migration.sh schema.sql "initial-chat-schema"
./scripts/seed-data.sh chat
./scripts/generate-schema.sh rag schema.sql
./scripts/validate-schema.sh schema.sql
./scripts/apply-migration.sh schema.sql "add-rag-storage"
./scripts/seed-data.sh rag
./scripts/generate-schema.sh complete schema.sql
./scripts/validate-schema.sh schema.sql
./scripts/apply-migration.sh schema.sql "complete-ai-platform"
pgvector not found: Enable the vector extension in Supabase dashboard (Database > Extensions)
RLS blocks queries: Check RLS policies or temporarily disable for testing (not recommended for production)
Slow similarity search: Ensure HNSW index is created on vector columns with proper operator class
Migration conflicts: Check migration version ordering and resolve conflicts manually
Skill Location: /home/vanman2025/Projects/ai-dev-marketplace/plugins/supabase/skills/schema-patterns/ Version: 1.0.0