laravel-vector-search
Use when implementing semantic / vector search in Laravel 13 with PostgreSQL + pgvector. Covers schema setup, embedding workflow, and the new query builder methods (`whereVectorSimilarTo`, `selectVectorDistance`, etc.).
What this skill does
# Laravel 13 Vector Search (pgvector)
## Agent Workflow (MANDATORY)
Before ANY implementation, use `TeamCreate` to spawn 3 agents:
1. **fuse-ai-pilot:explore-codebase** - Check current DB driver (must be PostgreSQL) and existing embedding columns
2. **fuse-ai-pilot:research-expert** - Verify pgvector extension version and HNSW vs IVFFlat tradeoffs
3. **mcp__context7__query-docs** - Pull `laravel.com/docs/13.x/search` + `queries` examples
After implementation, run **fuse-ai-pilot:sniper** for validation.
---
## Overview
| Feature | Description |
|---------|-------------|
| **PostgreSQL only** | Requires `pgvector` extension; not available on MySQL/SQLite |
| **Schema helper** | `Schema::ensureVectorExtensionExists()` enables the extension |
| **Query builder** | `whereVectorSimilarTo()`, `selectVectorDistance()`, `whereVectorDistanceLessThan()`, `orderByVectorDistance()` |
| **Auto-embedding** | Pass a raw string and Laravel generates the embedding via AI SDK |
| **Cosine similarity** | Default distance; threshold via `minSimilarity` (0.0 - 1.0) |
---
## Critical Rules
1. **Use PostgreSQL** - Vector clauses ONLY work on `pgsql` connections - no fallback to MySQL/SQLite
2. **Create an HNSW index** - Without an index, queries do full table scans; > 10k rows means seconds-to-minutes latency
3. **Match dimensions exactly** - Insert-time and query-time embedding models MUST share the same dimensions
4. **Cache embeddings** - Regenerating embeddings on every request is the #1 cost driver; persist them
5. **Lock the embedding model** - Changing the model invalidates ALL stored embeddings; treat the model as a schema field
---
## Architecture
```
database/migrations/
└── XXXX_create_documents_table.php # Schema::ensureVectorExtensionExists(), vector(1536) col, HNSW index
app/Models/
└── Document.php # casts embedding to array, uses whereVectorSimilarTo
app/Ai/Services/
└── VectorSearchService.php # encapsulates query + threshold logic
```
→ See [Document-model.php.md](references/templates/Document-model.php.md) for full example
---
## Reference Guide
| Topic | Reference | When to Consult |
|-------|-----------|-----------------|
| **pgvector setup** | [pgvector-setup.md](references/pgvector-setup.md) | Migrations + index creation |
| **Embedding workflow** | [embeddings-workflow.md](references/embeddings-workflow.md) | Generating + persisting vectors |
| **Query patterns** | [queries.md](references/queries.md) | `whereVectorSimilarTo` and friends |
### Templates
| Template | When to Use |
|----------|-------------|
| [Document-model.php.md](references/templates/Document-model.php.md) | Eloquent model with vector column |
| [VectorSearchService.php.md](references/templates/VectorSearchService.php.md) | Reusable service |
---
## Quick Reference
### Migration
```php
Schema::ensureVectorExtensionExists();
Schema::create('documents', function (Blueprint $table) {
$table->id();
$table->text('content');
$table->vector('embedding', 1536);
$table->timestamps();
$table->vectorIndex('embedding', algorithm: 'hnsw');
});
```
### Query
```php
$documents = Document::query()
->whereVectorSimilarTo('embedding', 'best wineries in Napa Valley', minSimilarity: 0.4)
->limit(10)
->get();
```
→ See [VectorSearchService.php.md](references/templates/VectorSearchService.php.md) for complete example
---
## Best Practices
### DO
- Create an HNSW index BEFORE inserting bulk data - faster total ingest
- Store the embedding model name alongside the vector to detect drift
- Use `minSimilarity` 0.3-0.5 as a starting threshold; tune empirically
- Combine vector search with classic `where()` for hybrid filtering (date ranges, tenancy)
### DON'T
- Don't run vector queries without an index past a few thousand rows - it becomes a full table scan
- Don't mix embedding models in the same column - distances become meaningless
- Don't generate query embeddings inside loops - batch them via `Embeddings::for([...])`
- Don't store embeddings as JSON strings - use the native `vector` column type for index support
Related in AI Agents
skill-development
IncludedComprehensive meta-skill for creating, managing, validating, auditing, and distributing Claude Code skills and slash commands (unified in v2.1.3+). Provides skill templates, creation workflows, validation patterns, audit checklists, naming conventions, YAML frontmatter guidance, progressive disclosure examples, and best practices lookup. Use when creating new skills, validating existing skills, auditing skill quality, understanding skill architecture, needing skill templates, learning about YAML frontmatter requirements, progressive disclosure patterns, tool restrictions (allowed-tools), skill composition, skill naming conventions, troubleshooting skill activation issues, creating custom slash commands, configuring command frontmatter, using command arguments ($ARGUMENTS, $1, $2), bash execution in commands, file references in commands, command namespacing, plugin commands, MCP slash commands, Skill tool configuration, or deciding between skills vs slash commands. Delegates to docs-management skill for official documentation.
reprompter
IncludedTransform messy prompts into well-structured, effective prompts — single or multi-agent. Use when: "reprompt", "reprompt this", "clean up this prompt", "structure my prompt", rough text needing XML tags and best practices, "reprompter teams", "repromptception", "run with quality", "smart run", "smart agents", multi-agent tasks, audits, parallel work, anything going to agent teams. Don't use when: simple Q&A, pure chat, immediate execution-only tasks. See "Don't Use When" section for details. Outputs: Structured XML/Markdown prompt, quality score (before/after), optional team brief + per-agent sub-prompts, agent team output files. Success criteria: Single mode quality score ≥ 7/10; Repromptception per-agent prompt quality score 8+/10; all required sections present, actionable and specific.
adaptive-compaction
IncludedAdaptive add-on policy and recovery layer that decides WHEN to compact, prune, snapshot, or fork -- replacing fixed-percent auto-compaction across Claude Code, Codex, and MCP-capable hosts. Trigger on auto-compact timing or damage: "when should I compact", "is it safe to compact now or start a fresh session", "auto-compact fires too early/mid-task", "switching to an unrelated task but the window still has space", "context rot", "answers get worse the longer the session runs", "the agent forgot the plan or my decisions after it summarized", "add a layer on top that manages context without changing the agent", raising autoCompactWindow to give the policy room, or installing/tuning a cross-tool compaction policy or PreCompact hook -- even when "compaction" is never said but the problem is context-window pressure or post-summarization memory loss. Do NOT use to summarize a conversation, build RAG, write a summarization prompt (decides WHEN not HOW), or answer max-context-length trivia.
agent-skill-creator
IncludedCreate cross-platform agent skills from workflow descriptions. Activates when users ask to create an agent, automate a repetitive workflow, create a custom skill, or need advanced agent creation. Triggers on phrases like create agent for, automate workflow, create skill for, every day I have to, daily I need to, turn process into agent, need to automate, create a cross-platform skill, validate this skill, export this skill, migrate this skill. Supports single skills, multi-agent suites, transcript processing, template-based creation, interactive configuration, cross-platform export, and spec validation.
llm-wiki
IncludedUse when building or maintaining a persistent personal knowledge base (second brain) in Obsidian where an LLM incrementally ingests sources, updates entity/concept pages, maintains cross-references, and keeps a synthesis current. Triggers include "second brain", "Obsidian wiki", "personal knowledge management", "ingest this paper/article/book", "build a research wiki", "compound knowledge", "Memex", or whenever the user wants knowledge to accumulate across sessions instead of being re-derived by RAG on every query.
skill-master
IncludedAgent Skills authoring, evaluation, and optimization. Create, edit, validate, benchmark, and improve skills following the agentskills.io specification. Use when designing SKILL.md files, structuring skill folders (references, scripts, assets), ingesting external documentation into skills, running trigger evals, benchmarking skill quality, optimizing descriptions, or performing blind A/B comparisons. Keywords: agentskills.io, SKILL.md, skill authoring, eval, benchmark, trigger optimization.