integration

integration/.gitignore

@@ -0,0 +1,34 @@
+# dependencies (bun install)
+node_modules
+
+# output
+out
+dist
+*.tgz
+
+# code coverage
+coverage
+*.lcov
+
+# logs
+logs
+_.log
+report.[0-9]_.[0-9]_.[0-9]_.[0-9]_.json
+
+# dotenv environment variable files
+.env
+.env.development.local
+.env.test.local
+.env.production.local
+.env.local
+
+# caches
+.eslintcache
+.cache
+*.tsbuildinfo
+
+# IntelliJ based IDEs
+.idea
+
+# Finder (MacOS) folder config
+.DS_Store

integration/README.md

@@ -0,0 +1,15 @@
+# integration
+
+To install dependencies:
+
+```bash
+bun install
+```
+
+To run:
+
+```bash
+bun run index.ts
+```
+
+This project was created using `bun init` in bun v1.2.13. [Bun](https://bun.sh) is a fast all-in-one JavaScript runtime.

integration/compose.yml

@@ -0,0 +1,69 @@
+version: '3.3'
+services:
+  postgres-container:
+    image: postgres
+    restart: always
+    environment:
+      POSTGRES_PASSWORD: your_password
+    ports:
+      - 5432:5432
+    volumes:
+      - ./init.sql:/docker-entrypoint-initdb.d/init.sql
+    healthcheck:
+      test: [ "CMD-SHELL", "pg_isready -U postgres" ]
+      interval: 5s
+      retries: 5
+      start_period: 30s
+      # psql -h localhost -p 5432 -U postgres
+  end:
+    image: sixwaaaay/end:0.25.5
+    restart: always
+    ports:
+      - 5151:5151
+    environment:
+      ConnectionStrings__Default: "Host=postgres-container;Username=postgres;Password=your_password"
+      ConnectionStrings__ReplicationConnection: "Host=postgres-container;Username=postgres;Password=your_password"
+      Application__Secret: "the secret key|the secret key|the secret key"
+      ASPNETCORE_URLS: "http://+:5151"
+    depends_on:
+      postgres-container:
+        condition: service_healthy
+  meilisearch:
+    image: getmeili/meilisearch:v1.15
+    environment:
+      MEILI_MASTER_KEY: masterKey|masterKey|masterKey|masterKey
+    ports:
+      - 7700:7700
+  qdrant:
+    image: qdrant/qdrant:v1.15
+    environment:
+      QDRANT__SERVICE__API_KEY: qdrant|qdrant|qdrant|qdrant|qdrant|qdrant
+    ports:
+      - 6333:6333
+  valkey:
+    image: valkey/valkey:8-alpine3.22 # redis alternative
+    ports:
+      - 6379:6379
+  content:
+    image: sixwaaaay/content:latest
+    ports:
+      - 5000:5000
+    environment:
+      ConnectionStrings__Default: "Host=postgres-container;Username=postgres;Password=your_password"
+      ConnectionStrings__User: "http://end:5151"
+      ConnectionStrings__Vote: "http://end:5151"
+      ConnectionStrings__Search: "http://meilisearch:7700"
+      ConnectionStrings__Redis: "valkey:6379"
+      ConnectionStrings__QdrantUrl: "http://qdrant:6334"
+      ConnectionStrings__QdrantApiKey: "qdrant|qdrant|qdrant|qdrant|qdrant|qdrant"
+      Secret: "the secret key|the secret key|the secret key"
+      Token: "masterKey|masterKey|masterKey|masterKey"
+  bunserver:
+    image: oven/bun:1
+    command: "bun embeddingserver.ts"
+    ports:
+      - "8000:8000"
+    volumes:
+      - ./embeddingserver.ts:/app/embeddingserver.ts
+    working_dir: /app
+    restart: always

integration/embeddingserver.ts

@@ -0,0 +1,112 @@
+// 定义响应结构
+type EmbeddingData = {
+    object: "embedding";
+    embedding: number[];
+    index: number;
+};
+
+type EmbeddingResponse = {
+    object: "list";
+    data: EmbeddingData[];
+    model: string;
+    usage: {
+        prompt_tokens: number;
+        total_tokens: number;
+    };
+};
+
+// 定义支持的模型及其维度
+const modelDimensions: Record<string, number> = {
+    "text-embedding-ada-002": 1536,
+    "text-similarity-ada-001": 1024,
+    "text-search-ada-001": 1024,
+    "code-search-ada-code-001": 1024,
+    "simple-vector": 24
+};
+
+// 生成随机嵌入向量
+function generateEmbedding(dimensions: number): number[] {
+    return Array.from({ length: dimensions }, () => Math.random() * 2 - 1);
+}
+
+// 简单的 token 计数器
+function countTokens(text: string | string[]): number {
+    if (Array.isArray(text)) {
+        return text.reduce((acc, t) => acc + countTokens(t), 0);
+    }
+    return text.split(/\s+/).length;
+}
+
+// 创建 HTTP 服务器
+const server = Bun.serve({
+    port: 8000,
+    fetch(req) {
+        const url = new URL(req.url);
+
+        // 处理 Embedding API 请求
+        if (req.method === "POST" && url.pathname === "/v1/embeddings") {
+            return handleEmbeddingRequest(req);
+        }
+
+        // 默认返回 404
+        return new Response(JSON.stringify({ error: "Not Found" }), {
+            status: 404,
+            headers: { "Content-Type": "application/json" },
+        });
+    },
+});
+
+// 处理嵌入请求
+async function handleEmbeddingRequest(req: Request): Promise<Response> {
+    try {
+        // 解析请求体
+        const { input, model = "text-embedding-ada-002" } = await req.json();
+
+        // 验证输入
+        if (input === undefined) {
+            return new Response(JSON.stringify({ error: "Missing 'input' parameter" }), {
+                status: 400,
+                headers: { "Content-Type": "application/json" },
+            });
+        }
+
+        // 确保 input 是数组
+        const inputList = Array.isArray(input) ? input : [input];
+
+        // 获取模型维度
+        const dimensions = modelDimensions[model] || 1536;
+
+        // 生成嵌入向量
+        const data = inputList.map((text, index) => ({
+            object: "embedding",
+            embedding: generateEmbedding(dimensions),
+            index,
+        })) as EmbeddingData[];
+
+        // 计算 token 使用量
+        const promptTokens = countTokens(inputList);
+
+        // 构建响应
+        const response: EmbeddingResponse = {
+            object: "list",
+            data,
+            model,
+            usage: {
+                prompt_tokens: promptTokens,
+                total_tokens: promptTokens,
+            },
+        };
+
+        return new Response(JSON.stringify(response), {
+            headers: { "Content-Type": "application/json" },
+        });
+    } catch (error) {
+        console.error("Error handling request:", error);
+        return new Response(JSON.stringify({ error: "Internal Server Error" }), {
+            status: 500,
+            headers: { "Content-Type": "application/json" },
+        });
+    }
+}
+
+console.log(`Server running at http://localhost:${server.port}`);  

integration/index.ts

@@ -0,0 +1 @@
+console.log("the integration via Bun!");

integration/init.sql

@@ -0,0 +1,82 @@
+CREATE TABLE users (
+    id bigserial,
+    name character varying(255) NOT NULL,
+    email character varying(255) NOT NULL,
+    code character varying(6) NOT NULL DEFAULT ''::character varying,
+    code_time timestamptz NOT NULL DEFAULT to_timestamp('2020-01-01 00:00:00'::text, 'YYYY-MM-DD HH24:MI:SS'::text),
+    code_try integer NOT NULL DEFAULT 0,
+    bio character varying(255) NOT NULL DEFAULT ''::character varying,
+    avatar character varying(255) NOT NULL DEFAULT ''::character varying,
+    created_at timestamptz NOT NULL  DEFAULT now(),
+    background character varying(255) NOT NULL DEFAULT ''::character varying,
+    PRIMARY KEY (id),
+    UNIQUE (email)
+);
+
+
+-- 一个脚本，生成 10 万 条数据
+INSERT INTO users (name, email, code, code_time, code_try, bio, avatar, created_at, background)
+SELECT
+    'user_' || i::text,
+    'user_' || i::text || '@example.com',
+    '123456',
+    now(),
+    0,
+    'This is a bio for user ' || i::text,
+    'https://example.com/avatar_' || i::text || '.jpg',
+    now(),
+    'https://example.com/background_' || i::text || '.jpg'
+FROM generate_series(1, 100000) AS s(i);
+
+CREATE TABLE graph (
+    id bigserial,
+    relation integer NOT NULL,
+    subject_id bigint NOT NULL,
+    object_id bigint NOT NULL,
+    created_at timestamptz NOT NULL DEFAULT now(),
+    PRIMARY KEY (id),
+    UNIQUE (relation, subject_id, object_id)
+);
+
+-- 一个脚本，生成 10 万 条数据
+INSERT INTO graph (relation, subject_id, object_id)
+SELECT-- 从序列获取下一个值作为 id
+    floor(random() * 3) + 1, -- 生成 1 到 3 之间的随机整数
+    floor(random() * 100000) + 1, -- 生成 1 到 100000 之间的随机整数
+    floor(random() * 100000) + 1 -- 生成 1 到 100000 之间的随机整数
+FROM generate_series(1, 100000) AS s(i)
+ON CONFLICT (relation, subject_id, object_id) DO NOTHING;
+
+
+
+CREATE TABLE videos (
+    id bigserial,
+    user_id bigint NOT NULL,
+    title character varying(255) NOT NULL,
+    des text NOT NULL,
+    cover_url character varying(255) DEFAULT ''::character varying NOT NULL,
+    video_url character varying(255) DEFAULT ''::character varying NOT NULL,
+    duration integer,
+    view_count integer DEFAULT 0 NOT NULL,
+    like_count integer DEFAULT 0 NOT NULL,
+    created_at timestamptz DEFAULT now() NOT NULL,
+    updated_at timestamptz DEFAULT now() NOT NULL,
+    processed integer DEFAULT 0 NOT NULL,
+    PRIMARY KEY (id)
+);
+
+-- 一个脚本，生成 10 万 条数据
+INSERT INTO videos (user_id, title, des, cover_url, video_url, duration, view_count, like_count, created_at, updated_at, processed)
+SELECT
+    floor(random() * 100000) + 1, -- 生成 1 到 100000 之间的随机整数
+    'Video ' || i::text,
+    'This is a description for video ' || i::text,
+    'https://example.com/cover_' || i::text || '.jpg',
+    'https://example.com/video_' || i::text || '.mp4',
+    floor(random() * 3600) + 1, -- 生成 1 到 3600 之间的随机整数
+    floor(random() * 10000) + 1, -- 生成 1 到 10000 之间的随机整数
+    floor(random() * 1000) + 1, -- 生成 1 到 1000 之间的随机整数
+    now(),
+    now(),
+    floor(random() * 2) -- 生成 0 或 1
+FROM generate_series(1, 100000) AS s(i);