# graphile-llm
LLM integration plugin for PostGraphile v5 — server-side text-to-vector embedding, resolve-time vector injection, and RAG (Retrieval-Augmented Generation) for pgvector columns using `@agentic-kit/ollama`.
## Table of contents
- [Installation](#installation)
- [Usage](#usage)
- [Features](#features)
- [Plugins](#plugins)
- [Configuration](#configuration)
- [RAG queries](#rag-queries)
- [License](#license)
## Installation
```bash
npm install graphile-llm
```
## Usage
```typescript
import { GraphileLlmPreset } from 'graphile-llm';
const preset = {
extends: [
GraphileLlmPreset({
defaultEmbedder: {
provider: 'ollama',
model: 'nomic-embed-text',
baseUrl: 'http://localhost:11434',
},
}),
],
};
```
The preset bundles all plugins listed below. You can also import each plugin individually (`createLlmModulePlugin`, `createLlmTextSearchPlugin`, `createLlmTextMutationPlugin`, `createLlmRagPlugin`) if you prefer a-la-carte.
## Features
- **Text-based vector search** — adds `text: String` field to `VectorNearbyInput`; clients pass natural language instead of raw float vectors
- **Text mutation fields** — adds `{column}Text: String` companion fields on create/update inputs for vector columns
- **RAG queries** — adds `ragQuery` and `embedText` root query fields; detects `@hasChunks` smart tags for chunk-aware retrieval
- **Pluggable providers** — provider-based architecture for both embedding and chat completion (Ollama via `@agentic-kit/ollama`, extensible to OpenAI, etc.)
- **Per-database configuration** — reads `llm_module` from `constructive_routing_public.api_modules` for per-API provider config
- **Toggleable** — each capability (`enableTextSearch`, `enableTextMutations`, `enableRag`) can be independently enabled or disabled
- **Plugin-conditional** — fields only appear in the schema when the plugin is loaded
## Plugins
| Plugin | Description | Toggle |
|--------|-------------|--------|
| `LlmModulePlugin` | Resolves embedder and chat completer from config; stores on build context | Always included |
| `LlmTextSearchPlugin` | Adds `text: String` to `VectorNearbyInput` with resolve-time embedding | `enableTextSearch` (default: `true`) |
| `LlmTextMutationPlugin` | Adds `{column}Text` companion fields on mutation inputs | `enableTextMutations` (default: `true`) |
| `LlmRagPlugin` | Adds `ragQuery` and `embedText` root query fields | `enableRag` (default: `false`) |
## Configuration
```typescript
GraphileLlmPreset({
// Embedding provider (required for text fields and RAG)
defaultEmbedder: {
provider: 'ollama',
model: 'nomic-embed-text',
baseUrl: 'http://localhost:11434',
},
// Chat completion provider (required for RAG)
defaultChatCompleter: {
provider: 'ollama',
model: 'llama3',
baseUrl: 'http://localhost:11434',
},
// Toggle individual capabilities
enableTextSearch: true, // text field on VectorNearbyInput
enableTextMutations: true, // *Text companion fields on mutations
enableRag: false, // ragQuery + embedText root fields
// RAG defaults (overridable per-query)
ragDefaults: {
contextLimit: 10,
maxTokens: 4000,
minSimilarity: 0.3,
},
})
```
Providers can also be configured via environment variables (`EMBEDDER_PROVIDER`, `EMBEDDER_MODEL`, `EMBEDDER_BASE_URL`, `CHAT_PROVIDER`, `CHAT_MODEL`, `CHAT_BASE_URL`).
## RAG queries
When `enableRag: true` and tables have `@hasChunks` smart tags, the plugin adds:
```graphql
# Full RAG: embed prompt, search chunks, assemble context, call chat LLM
query {
ragQuery(
prompt: "What is machine learning?"
contextLimit: 5
minSimilarity: 0.3
) {
answer
sources { content similarity tableName parentId }
tokensUsed
}
}
# Standalone embedding
query {
embedText(text: "machine learning concepts") {
vector
dimensions
}
}
```
---
## Education and Tutorials
1. 🚀 [Quickstart: Getting Up and Running](https://constructive.io/learn/quickstart)
Get started with modular databases in minutes. Install prerequisites and deploy your first module.
2. 📦 [Modular PostgreSQL Development with Database Packages](https://constructive.io/learn/modular-postgres)
Learn to organize PostgreSQL projects with pgpm workspaces and reusable database modules.
3. ✏️ [Authoring Database Changes](https://constructive.io/learn/authoring-database-changes)
Master the workflow for adding, organizing, and managing database changes with pgpm.
4. 🧪 [End-to-End PostgreSQL Testing with TypeScript](https://constructive.io/learn/e2e-postgres-testing)
Master end-to-end PostgreSQL testing with ephemeral databases, RLS testing, and CI/CD automation.
5. ⚡ [Supabase Testing](https://constructive.io/learn/supabase)
Use TypeScript-first tools to test Supabase projects with realistic RLS, policies, and auth contexts.
6. 💧 [Drizzle ORM Testing](https://constructive.io/learn/drizzle-testing)
Run full-stack tests with Drizzle ORM, including database setup, teardown, and RLS enforcement.
7. 🔧 [Troubleshooting](https://constructive.io/learn/troubleshooting)
Common issues and solutions for pgpm, PostgreSQL, and testing.
## Related Constructive Tooling
### 📦 Package Management
* [pgpm](https://github.com/constructive-io/constructive/tree/main/pgpm/pgpm): **🖥️ PostgreSQL Package Manager** for modular Postgres development. Works with database workspaces, scaffolding, migrations, seeding, and installing database packages.
### 🧪 Testing
* [pgsql-test](https://github.com/constructive-io/constructive/tree/main/postgres/pgsql-test): **📊 Isolated testing environments** with per-test transaction rollbacks—ideal for integration tests, complex migrations, and RLS simulation.
* [pglite-test](https://github.com/constructive-io/constructive/tree/main/postgres/pglite-test): **🪶 Drop-in pgsql-test replacement backed by PGlite** — in-process Postgres, no server required, instance-per-suite isolation.
* [pgsql-seed](https://github.com/constructive-io/constructive/tree/main/postgres/pgsql-seed): **🌱 PostgreSQL seeding utilities** for CSV, JSON, SQL data loading, and pgpm deployment.
* [supabase-test](https://github.com/constructive-io/constructive/tree/main/postgres/supabase-test): **🧪 Supabase-native test harness** preconfigured for the local Supabase stack—per-test rollbacks, JWT/role context helpers, and CI/GitHub Actions ready.
* [graphile-test](https://github.com/constructive-io/constructive/tree/main/graphile/graphile-test): **🔐 Authentication mocking** for Graphile-focused test helpers and emulating row-level security contexts.
* [pg-query-context](https://github.com/constructive-io/constructive/tree/main/postgres/pg-query-context): **🔒 Session context injection** to add session-local context (e.g., `SET LOCAL`) into queries—ideal for setting `role`, `jwt.claims`, and other session settings.
### 🧠 Parsing & AST
* [pgsql-parser](https://www.npmjs.com/package/pgsql-parser): **🔄 SQL conversion engine** that interprets and converts PostgreSQL syntax.
* [libpg-query-node](https://www.npmjs.com/package/libpg-query): **🌉 Node.js bindings** for `libpg_query`, converting SQL into parse trees.
* [pg-proto-parser](https://www.npmjs.com/package/pg-proto-parser): **📦 Protobuf parser** for parsing PostgreSQL Protocol Buffers definitions to generate TypeScript interfaces, utility functions, and JSON mappings for enums.
* [@pgsql/enums](https://www.npmjs.com/package/@pgsql/enums): **🏷️ TypeScript enums** for PostgreSQL AST for safe and ergonomic parsing logic.
* [@pgsql/types](https://www.npmjs.com/package/@pgsql/types): **📝 Type definitions** for PostgreSQL AST nodes in TypeScript.
* [@pgsql/utils](https://www.npmjs.com/package/@pgsql/utils): **🛠️ AST utilities** for constructing and transforming PostgreSQL syntax trees.
### 📚 Documentation & Skills
* [constructive-skills](https://github.com/constructive-io/constructive-skills): **📖 Platform documentation and AI agent skills** — feature catalog, blueprint reference, SDK guides (i18n, billing, limits, events, uploads, security, entities, search, AI), and deployment guides.
Install skills for AI coding agents:
```bash
# All platform skills (security, blueprints, codegen, billing, etc.)
npx skills add constructive-io/constructive-skills
# Individual repo skills (pgpm, testing, CLI, search, etc.)
npx skills add https://github.com/constructive-io/constructive --skill pgpm
npx skills add https://github.com/constructive-io/constructive --skill constructive-testing
```
## Credits
**🛠 Built by the [Constructive](https://constructive.io) team — creators of modular Postgres tooling for secure, composable backends. If you like our work, contribute on [GitHub](https://github.com/constructive-io).**
## Disclaimer
AS DESCRIBED IN THE LICENSES, THE SOFTWARE IS PROVIDED "AS IS", AT YOUR OWN RISK, AND WITHOUT WARRANTIES OF ANY KIND.
No developer or entity involved in creating this software will be liable for any claims or damages whatsoever associated with your use, inability to use, or your interaction with other users of the code, including any direct, indirect, incidental, special, exemplary, punitive or consequential damages, or loss of profits, cryptocurrencies, tokens, or anything else of value.