feat(mcpedia): Phase 1 MVP — monorepo, Core, Web UI, MCP server, Postgres FTS
- bun workspaces + Turborepo monorepo (apps/web, apps/mcp; packages/*, scripts) - @mcpedia/core single business-logic layer (Document/Content/Search services) - @mcpedia/db Drizzle schema: documents + weighted tsvector (GIN) for FTS - @mcpedia/parser frontmatter, @mcpedia/search Postgres FTS (ts_rank+ts_headline) - Next.js 16 Web UI (home/doc SSG, search dynamic) + react-markdown render - MCP server (stdio) with 4 tools + in-memory smoke test - scripts/indexer walks content/ -> upserts into Postgres - 4 seed docs; README + PHASES status
This commit is contained in:
asepharyana
@@ -0,0 +1,11 @@
|
||||
import { defineConfig } from "drizzle-kit";
|
||||
import { DATABASE_URL } from "@mcpedia/config";
|
||||
|
||||
export default defineConfig({
|
||||
dialect: "postgresql",
|
||||
schema: "./src/schema.ts",
|
||||
out: "./drizzle",
|
||||
dbCredentials: { url: DATABASE_URL },
|
||||
verbose: true,
|
||||
strict: true,
|
||||
});
|
||||
@@ -0,0 +1,19 @@
|
||||
CREATE TABLE "documents" (
|
||||
"id" text PRIMARY KEY NOT NULL,
|
||||
"slug" text NOT NULL,
|
||||
"title" text NOT NULL,
|
||||
"type" text NOT NULL,
|
||||
"section" text NOT NULL,
|
||||
"status" text DEFAULT 'published' NOT NULL,
|
||||
"author" text DEFAULT '' NOT NULL,
|
||||
"tags" text[] DEFAULT '{}' NOT NULL,
|
||||
"path" text NOT NULL,
|
||||
"body" text DEFAULT '' NOT NULL,
|
||||
"search_vector" "tsvector" GENERATED ALWAYS AS (setweight(to_tsvector('simple', coalesce("documents"."title", '')), 'A') || setweight(to_tsvector('simple', coalesce("documents"."body", '')), 'B')) STORED NOT NULL,
|
||||
"created_at" timestamp with time zone NOT NULL,
|
||||
"updated_at" timestamp with time zone NOT NULL,
|
||||
CONSTRAINT "documents_slug_unique" UNIQUE("slug")
|
||||
);
|
||||
--> statement-breakpoint
|
||||
CREATE INDEX "documents_search_idx" ON "documents" USING gin ("search_vector");--> statement-breakpoint
|
||||
CREATE INDEX "documents_section_idx" ON "documents" USING btree ("section");
|
||||
@@ -0,0 +1,157 @@
|
||||
{
|
||||
"id": "249f80c0-d953-42f2-a98b-6701e2115856",
|
||||
"prevId": "00000000-0000-0000-0000-000000000000",
|
||||
"version": "7",
|
||||
"dialect": "postgresql",
|
||||
"tables": {
|
||||
"public.documents": {
|
||||
"name": "documents",
|
||||
"schema": "",
|
||||
"columns": {
|
||||
"id": {
|
||||
"name": "id",
|
||||
"type": "text",
|
||||
"primaryKey": true,
|
||||
"notNull": true
|
||||
},
|
||||
"slug": {
|
||||
"name": "slug",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true
|
||||
},
|
||||
"title": {
|
||||
"name": "title",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true
|
||||
},
|
||||
"type": {
|
||||
"name": "type",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true
|
||||
},
|
||||
"section": {
|
||||
"name": "section",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true
|
||||
},
|
||||
"status": {
|
||||
"name": "status",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"default": "'published'"
|
||||
},
|
||||
"author": {
|
||||
"name": "author",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"default": "''"
|
||||
},
|
||||
"tags": {
|
||||
"name": "tags",
|
||||
"type": "text[]",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"default": "'{}'"
|
||||
},
|
||||
"path": {
|
||||
"name": "path",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true
|
||||
},
|
||||
"body": {
|
||||
"name": "body",
|
||||
"type": "text",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"default": "''"
|
||||
},
|
||||
"search_vector": {
|
||||
"name": "search_vector",
|
||||
"type": "tsvector",
|
||||
"primaryKey": false,
|
||||
"notNull": true,
|
||||
"generated": {
|
||||
"as": "setweight(to_tsvector('simple', coalesce(\"documents\".\"title\", '')), 'A') || setweight(to_tsvector('simple', coalesce(\"documents\".\"body\", '')), 'B')",
|
||||
"type": "stored"
|
||||
}
|
||||
},
|
||||
"created_at": {
|
||||
"name": "created_at",
|
||||
"type": "timestamp with time zone",
|
||||
"primaryKey": false,
|
||||
"notNull": true
|
||||
},
|
||||
"updated_at": {
|
||||
"name": "updated_at",
|
||||
"type": "timestamp with time zone",
|
||||
"primaryKey": false,
|
||||
"notNull": true
|
||||
}
|
||||
},
|
||||
"indexes": {
|
||||
"documents_search_idx": {
|
||||
"name": "documents_search_idx",
|
||||
"columns": [
|
||||
{
|
||||
"expression": "search_vector",
|
||||
"isExpression": false,
|
||||
"asc": true,
|
||||
"nulls": "last"
|
||||
}
|
||||
],
|
||||
"isUnique": false,
|
||||
"concurrently": false,
|
||||
"method": "gin",
|
||||
"with": {}
|
||||
},
|
||||
"documents_section_idx": {
|
||||
"name": "documents_section_idx",
|
||||
"columns": [
|
||||
{
|
||||
"expression": "section",
|
||||
"isExpression": false,
|
||||
"asc": true,
|
||||
"nulls": "last"
|
||||
}
|
||||
],
|
||||
"isUnique": false,
|
||||
"concurrently": false,
|
||||
"method": "btree",
|
||||
"with": {}
|
||||
}
|
||||
},
|
||||
"foreignKeys": {},
|
||||
"compositePrimaryKeys": {},
|
||||
"uniqueConstraints": {
|
||||
"documents_slug_unique": {
|
||||
"name": "documents_slug_unique",
|
||||
"nullsNotDistinct": false,
|
||||
"columns": [
|
||||
"slug"
|
||||
]
|
||||
}
|
||||
},
|
||||
"policies": {},
|
||||
"checkConstraints": {},
|
||||
"isRLSEnabled": false
|
||||
}
|
||||
},
|
||||
"enums": {},
|
||||
"schemas": {},
|
||||
"sequences": {},
|
||||
"roles": {},
|
||||
"policies": {},
|
||||
"views": {},
|
||||
"_meta": {
|
||||
"columns": {},
|
||||
"schemas": {},
|
||||
"tables": {}
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"version": "7",
|
||||
"dialect": "postgresql",
|
||||
"entries": [
|
||||
{
|
||||
"idx": 0,
|
||||
"version": "7",
|
||||
"when": 1787133375079,
|
||||
"tag": "0000_grey_toro",
|
||||
"breakpoints": true
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"name": "@mcpedia/db",
|
||||
"version": "0.1.0",
|
||||
"private": true,
|
||||
"type": "module",
|
||||
"exports": {
|
||||
".": "./src/client.ts",
|
||||
"./schema": "./src/schema.ts"
|
||||
},
|
||||
"dependencies": {
|
||||
"@mcpedia/config": "workspace:*",
|
||||
"drizzle-orm": "^0.38.0",
|
||||
"postgres": "^3.4.5"
|
||||
},
|
||||
"devDependencies": {
|
||||
"drizzle-kit": "^0.30.0",
|
||||
"@types/node": "^20"
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,15 @@
|
||||
import { drizzle } from "drizzle-orm/postgres-js";
|
||||
import postgres from "postgres";
|
||||
import { DATABASE_URL } from "@mcpedia/config";
|
||||
import * as schema from "./schema";
|
||||
|
||||
// PgBouncer (imrnes :6432) uses transaction pooling, which rejects protocol
|
||||
//-level prepared statements. prepare:false makes postgres-js use simple queries.
|
||||
const client = postgres(DATABASE_URL, {
|
||||
prepare: false,
|
||||
max: 5,
|
||||
onnotice: () => {},
|
||||
});
|
||||
|
||||
export const db = drizzle(client, { schema });
|
||||
export { schema, client };
|
||||
@@ -0,0 +1,59 @@
|
||||
import { sql, SQL } from "drizzle-orm";
|
||||
import {
|
||||
customType,
|
||||
index,
|
||||
integer,
|
||||
pgTable,
|
||||
text,
|
||||
timestamp,
|
||||
} from "drizzle-orm/pg-core";
|
||||
|
||||
// tsvector isn't a first-class drizzle type; wrap the raw Postgres type.
|
||||
const tsvector = customType<{ data: string }>({
|
||||
dataType() {
|
||||
return "tsvector";
|
||||
},
|
||||
});
|
||||
|
||||
export const documents = pgTable(
|
||||
"documents",
|
||||
{
|
||||
id: text("id").primaryKey(), // slug
|
||||
slug: text("slug").notNull().unique(),
|
||||
title: text("title").notNull(),
|
||||
type: text("type").notNull(),
|
||||
section: text("section").notNull(),
|
||||
status: text("status").notNull().default("published"),
|
||||
author: text("author").notNull().default(""),
|
||||
tags: text("tags").array().notNull().default(sql`'{}'`),
|
||||
path: text("path").notNull(),
|
||||
body: text("body").notNull().default(""),
|
||||
// Weighted search vector: title (A) + body (B), using the 'simple' config so
|
||||
// mixed ID/EN queries match literally without stemming. Lazy closure over
|
||||
// `documents` (must NOT reference the table eagerly — it is in TDZ here).
|
||||
searchVector: tsvector("search_vector")
|
||||
.notNull()
|
||||
.generatedAlwaysAs(
|
||||
(): SQL =>
|
||||
sql`setweight(to_tsvector('simple', coalesce(${documents.title}, '')), 'A') || setweight(to_tsvector('simple', coalesce(${documents.body}, '')), 'B')`,
|
||||
),
|
||||
createdAt: timestamp("created_at", { withTimezone: true }).notNull(),
|
||||
updatedAt: timestamp("updated_at", { withTimezone: true }).notNull(),
|
||||
},
|
||||
(t) => ({
|
||||
searchIdx: index("documents_search_idx").using("gin", t.searchVector),
|
||||
sectionIdx: index("documents_section_idx").on(t.section),
|
||||
}),
|
||||
);
|
||||
|
||||
// Phase 2 (semantic search) — defined here for reference, NOT created yet:
|
||||
// export const documentChunks = pgTable("document_chunks", {
|
||||
// id: text("id").primaryKey(),
|
||||
// documentId: text("document_id").notNull().references(() => documents.id, { onDelete: "cascade" }),
|
||||
// content: text("content").notNull(),
|
||||
// position: integer("position").notNull(),
|
||||
// embedding: customType<{ data: number[] }>({ dataType: () => "vector(1536)" })("embedding"),
|
||||
// });
|
||||
|
||||
export type DocumentRow = typeof documents.$inferSelect;
|
||||
export type NewDocumentRow = typeof documents.$inferInsert;
|
||||
Reference in New Issue
Block a user