initial commit (no RAG server)

2025-09-10 16:26:35 -04:00
parent b4756208c5
commit 2a6bed386c
8 changed files with 533 additions and 0 deletions
@@ -0,0 +1,41 @@
+# minimal backend for deepresearch: browser-use web-ui on :7788
+FROM python:3.11-slim
+
+ENV PIP_NO_CACHE_DIR=1 \
+	PYTHONUNBUFFERED=1 \
+	PLAYWRIGHT_BROWSERS_PATH=/ms-playwright \
+	WEBUI_IP=0.0.0.0 \
+	WEBUI_PORT=7788
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+	git curl ca-certificates xvfb dumb-init \
+	&& rm -rf /var/lib/apt/lists/*;
+
+# grab upstream repo
+WORKDIR /opt
+RUN git clone --depth=1 https://github.com/browser-use/web-ui.git
+
+# create app user with uid=1000 to match compose
+RUN useradd -u 1000 -ms /bin/bash appuser;
+
+WORKDIR /opt/web-ui
+
+# python deps + playwright browsers
+RUN pip install --upgrade pip \
+	&& pip install -r requirements.txt \
+	&& python -m playwright install chromium --with-deps;
+
+# prepare writable paths the app expects
+RUN mkdir -p /opt/web-ui/tmp /data && chown -R appuser:appuser /opt/web-ui /data
+
+USER appuser
+
+# copy default env
+COPY .env .env
+
+EXPOSE 7788
+HEALTHCHECK --interval=30s --timeout=5s --retries=5 \
+	CMD python -c "import urllib.request; urllib.request.urlopen('http://127.0.0.1:7788').read()" || exit 1
+
+ENTRYPOINT ["dumb-init", "--"]
+CMD ["python", "webui.py", "--ip", "0.0.0.0", "--port", "7788"]
@@ -0,0 +1,19 @@
+tunnel: ID
+credentials-file: /etc/cloudflared/ID.json
+ingress:
+    # The ollama instance
+  - hostname: mlep.domain.com
+    service: http://ollama-ip:11434
+    originRequest:
+      httpHostHeader: "localhost"
+
+    # The OpenWebUI instance
+  - hostname: owebui.domain.com
+    service: http://localhost:4000
+    originRequest:
+      httpHostHeader: "localhost"
+
+    # The tools instance
+  - hostname: owebtools.domain.com
+    service: http://mcp-server-ip:PORT
+  - service: http_status:404
@@ -0,0 +1,31 @@
+# syntax=docker/dockerfile:1
+FROM oven/bun:1.2.2-alpine
+
+WORKDIR /app
+
+# install docker cli + tini; no daemon, just the client
+RUN apk add --no-cache docker-cli tini curl;
+
+# ----- map container 'docker' group to host docker.sock GID -----
+# pass the host's docker.sock GID at build time: --build-arg DOCKER_GID=$(stat -c '%g' /var/run/docker.sock)
+ARG DOCKER_GID=977
+# create (or reuse) a group with that GID, then add the existing 'bun' user to it
+RUN addgroup -g "${DOCKER_GID}" -S docker || true \
+	&& addgroup bun docker;
+
+# switch to the nonroot bun user (already default in the base image, but explicit is nice)
+USER bun
+
+# your app
+COPY index.ts ./index.ts
+
+# expose your tool server
+EXPOSE 8787
+ENV PORT=8787
+# default docker host path; adjust if you mount elsewhere
+ENV DOCKER_HOST=unix:///var/run/docker.sock
+
+# pid 1 -> tini
+ENTRYPOINT ["/sbin/tini","--"]
+CMD ["bun","index.ts"]
+
@@ -0,0 +1,277 @@
+import http from "node:http";
+import { spawn } from "node:child_process";
+
+const PORT = Number(process.env.PORT || 8787);
+const HOST = "0.0.0.0";
+
+/**
+ * @example const imgObj = { image: "gcc:14", installcommands: [aptUpdateAndInstall("gpp")], filename: "main.cpp", run: ... },
+ */
+const aptUpdateAndInstall = (pkgs: string[] | string) => {
+	const istr = typeof pkgs === 'string' ? pkgs : pkgs.join(" ");
+
+	return `apt-get update \
+ && apt-get install -y --no-install-recommends ${istr} \
+ && rm -rf /var/lib/apt/lists/*;`
+}
+
+// allow-listed images and run commands per language
+const LANGS = {
+	python: { image: "python:3.12-alpine", filename: "main.py", run: ["python", "main.py"] },
+	node: { image: "node:22-alpine", filename: "main.mjs", run: ["node", "main.mjs"] },
+	bun: { image: "oven/bun:1.2.2-alpine", filename: "main.ts", run: ["bun", "run", "main.ts"] },
+	bash: { image: "alpine:3.20", filename: "main.sh", run: ["sh", "main.sh"] },
+	ruby: { image: "ruby:3.3-alpine", filename: "main.rb", run: ["ruby", "main.rb"] },
+	go: { image: "golang:1.22-alpine", filename: "main.go", run: ["go run main.go"] },
+	rust: { image: "rust:1-alpine", filename: "main.rs", run: ["rustc -O main.rs -o main && ./main"] },
+	java: { image: "eclipse-temurin:21-jdk", filename: "Main.java", run: ["javac Main.java && java Main"] },
+	c: { image: "gcc:14", filename: "main.c", run: ["gcc -O2 main.c -o main.out && ./main.out"] },
+	cpp: { image: "gcc:14", filename: "main.cpp", run: ["g++ -O2 main.cpp -o main.out && ./main.out"] },
+};
+
+type langObj = {
+	image: string,
+	filename: string,
+	run: string[],
+	installcommands?: string[]
+}
+
+type fileType = {
+	path: string,
+	content: string
+}
+
+// docker binary (or set DOCKER_BIN=podman)
+const DOCKER_BIN = process.env.DOCKER_BIN || "docker";
+
+// basic openapi for open webui
+const OPENAPI = {
+	openapi: "3.1.0",
+	info: {
+		title: "Container Code Runner",
+		version: "1.0.0",
+		description:
+			"run source code inside a sandboxed container. important: provide pure source code only; do not wrap code in shell commands or pipelines."
+	},
+	paths: {
+		"/execute": {
+			post: {
+				operationId: "execute",
+				summary: "Run code in a sandboxed container",
+				// the model sees this text
+				description:
+					"use the language directly, not bash + the language. e.g., `#include...` (good) vs `echo '#include...' && gcc` (bad). pass only pure source text in `code`.",
+				requestBody: {
+					required: true,
+					content: {
+						"application/json": {
+							schema: {
+								type: "object",
+								properties: {
+									language: {
+										type: "string",
+										enum: Object.keys(LANGS),
+										description:
+											"the programming language to run. do not use 'bash' to wrap or invoke compilers/interpreters; select the actual language (e.g., 'c', 'cpp', 'python')."
+									},
+									code: {
+										type: "string",
+										description:
+											"pure source code only. do not include shell commands, redirections, pipes, or `echo`/`printf` wrappers. examples: good: `print('hi')`; bad: `echo \"print('hi')\" | python`."
+									},
+									args: { type: "array", items: { type: "string" } },
+									files: {
+										type: "array",
+										items: {
+											type: "object",
+											properties: {
+												path: { type: "string" },
+												content: { type: "string" }
+											},
+											required: ["path", "content"],
+											description:
+												"optional supporting files. contents must be pure file text, not shell commands."
+										}
+									}
+								},
+								required: ["language", "code"]
+							}
+						}
+					}
+				},
+				responses: {
+					"200": {
+						description: "Execution result",
+						content: {
+							"application/json": {
+								schema: {
+									type: "object",
+									properties: {
+										stdout: { type: "string" },
+										stderr: { type: "string" },
+										exitCode: { type: "integer" },
+										timedOut: { type: "boolean" }
+									}
+								}
+							}
+						}
+					}
+				}
+			}
+		}
+	}
+};
+
+
+function sendJson(res, status, obj) {
+	const body = JSON.stringify(obj);
+	res.writeHead(status, { "content-type": "application/json; charset=utf-8" });
+	res.end(body);
+}
+
+async function ensureImage(spec: langObj) {
+	// note: 'docker run' has a --pull policy (missing|always|never),
+	const { spawn } = await import("node:child_process"),
+		DOCKER_BIN = process.env.DOCKER_BIN || "docker";
+
+	// check if image exists locally
+	const inspect = spawn(DOCKER_BIN, ["image", "inspect", spec.image], { stdio: "ignore" }),
+		ok = await new Promise((r) => inspect.on("close", (c) => r(c === 0)));
+	if (ok) return;
+
+	// pull with a bigger timeout the first time (4 minutes)
+	await new Promise((resolve) => {
+		const child = spawn(DOCKER_BIN, ["image", "pull", "--quiet", spec.image]);
+		let timer = setTimeout(() => {
+			child.kill("SIGKILL");
+			resolve(new Error("pull timeout"));
+		}, 240_000);
+
+		child.on("close", (code) => {
+			clearTimeout(timer);
+			resolve(code === 0 ? null : new Error(`pull failed: ${code}`));
+		});
+	}).then((err) => {
+		if (err) throw err;
+	});
+
+	// 	// dependancies
+	// 	if (spec.installcommands) {
+	// 		const commandFull = spec.installcommands.join(" && ");
+	// 		await new Promise((resolve) => {
+	// 			const child = spawn(DOCKER_BIN, ["image", "pull", "--quiet", spec.image]);
+	// 			let timer = setTimeout(() => {
+	// 				child.kill("SIGKILL");
+	// 				resolve(new Error("pull timeout"));
+	// 			}, 240_000);
+
+	// 			child.on("close", (code) => {
+	// 				clearTimeout(timer);
+	// 				resolve(code === 0 ? null : new Error(`pull failed: ${code}`));
+	// 			});
+	// 		}).then((err) => {
+	// 			if (err) throw err;
+	// 		})
+	// 	}
+}
+
+async function runInContainer({ language, code, args = [], files = [] }: {
+	language: string,
+	code: string,
+	args: string[],
+	files: fileType[]
+}) {
+	if (!LANGS[language]) throw new Error(`language not allowed: ${language}`);
+	const spec = LANGS[language];
+
+	await ensureImage(spec);
+
+	// build the Docker args
+	const dockerArgs = [
+		"run", "--rm",
+		"--network=none", "--read-only",
+		"--pids-limit=256",
+		"--cpus=1", "--memory=512m",
+		"--cap-drop=ALL", "--security-opt", "no-new-privileges",
+		"--tmpfs", "/work:rw,exec,size=64m",
+		"-w", "/work",
+		"--pull=never",
+		spec.image
+	];
+
+	// inside the container, write the files and run code
+	const script = [
+		// write the main file using base64
+		`echo ${JSON.stringify(Buffer.from(code, "utf8").toString("base64"))} | base64 -d > ${spec.filename}`,
+		// write any extra files using base64
+		...files.flatMap((f) => [
+			`mkdir -p "$(dirname "${f.path}")"`,
+			`echo ${JSON.stringify(Buffer.from(f.content, "utf8").toString("base64"))} | base64 -d > "${f.path}"`,
+		]),
+		// run it
+		`${spec.run.join(' ')} ${args.map((a) => JSON.stringify(a)).join(' ')}`
+	].join('\n');
+
+	dockerArgs.push("sh", "-lc", script);
+
+	const result = await new Promise((resolve) => {
+		const child = spawn(DOCKER_BIN, dockerArgs, { stdio: ["ignore", "pipe", "pipe"] });
+		let stdout = "", stderr = "";
+
+		const timer = setTimeout(() => {
+			child.kill("SIGKILL");
+			resolve({ stdout, stderr: stderr + "\n[killed: timeout]", exitCode: 137, timedOut: true });
+		}, 25_000);
+
+		child.stdout.on("data", (d) => { stdout += d.toString(); });
+		child.stderr.on("data", (d) => { stderr += d.toString(); });
+		child.on("close", (code) => {
+			clearTimeout(timer);
+			resolve({ stdout, stderr, exitCode: code ?? 1, timedOut: false });
+		});
+	});
+
+	return result;
+}
+
+const server = http.createServer(async (req, res) => {
+	try {
+		console.debug(`recieved ${req.method} request on ${req.url}`);
+
+		if (req.method === "GET" && req.url === "/openapi.json") {
+			sendJson(res, 200, OPENAPI);
+			return;
+		}
+
+		if (req.method === "GET" && req.url === "/") {
+			res.writeHead(200);
+			res.end("Ok");
+			return;
+		}
+
+		if (req.method === "POST" && req.url === "/execute") {
+			let body = "";
+			req.on("data", (c) => { body += c.toString(); });
+			req.on("end", async () => {
+				try {
+					const payload = JSON.parse(body || "{}");
+					const out = await runInContainer(payload);
+					sendJson(res, 200, out);
+				} catch (e) {
+					sendJson(res, 400, { error: String(e?.message || e) });
+				}
+			});
+			return;
+		}
+
+		res.writeHead(404);
+		res.end("not found");
+	} catch (e) {
+		sendJson(res, 500, { error: String(e?.message || e) });
+	}
+});
+
+server.listen(PORT, HOST, () => {
+	console.log(`[runner] listening on http://${HOST}:${PORT}`);
+});
+
@@ -0,0 +1,29 @@
+{
+  "name": "coderunner",
+  "lockfileVersion": 3,
+  "requires": true,
+  "packages": {
+    "": {
+      "devDependencies": {
+        "@types/node": "^24.3.1"
+      }
+    },
+    "node_modules/@types/node": {
+      "version": "24.3.1",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-24.3.1.tgz",
+      "integrity": "sha512-3vXmQDXy+woz+gnrTvuvNrPzekOi+Ds0ReMxw0LzBiK3a+1k0kQn9f2NWk+lgD4rJehFUmYy2gMhJ2ZI+7YP9g==",
+      "dev": true,
+      "license": "MIT",
+      "dependencies": {
+        "undici-types": "~7.10.0"
+      }
+    },
+    "node_modules/undici-types": {
+      "version": "7.10.0",
+      "resolved": "https://registry.npmjs.org/undici-types/-/undici-types-7.10.0.tgz",
+      "integrity": "sha512-t5Fy/nfn+14LuOc2KNYg75vZqClpAiqscVvMygNnlsHBFpSXdJaYtXMcdNLpl/Qvc3P2cB3s6lOV51nqsFq4ag==",
+      "dev": true,
+      "license": "MIT"
+    }
+  }
+}
@@ -0,0 +1,5 @@
+{
+  "devDependencies": {
+    "@types/node": "^24.3.1"
+  }
+}
@@ -0,0 +1,119 @@
+services:
+  open-webui:
+    image: ghcr.io/open-webui/open-webui:main
+    container_name: open-webui
+    ports:
+      - "4000:8080"
+    volumes:
+      - open-webui:/app/backend/data
+    extra_hosts:
+      - host.docker.internal:host-gateway
+    restart: always
+    depends_on:
+      - postgres
+    networks:
+      - internal
+
+  postgres:
+    image: postgres:latest
+    container_name: openwebui_postgres
+    restart: always
+    environment:
+      - POSTGRES_USER=postgres
+      - POSTGRES_PASSWORD=mypassword
+      - POSTGRES_DB=openwebui_db
+    volumes:
+      - pgdata:/var/lib/postgresql/data 
+    healthcheck:
+      test: ["CMD-SHELL", "pg_isready -U postgres"]
+      interval: 10s
+      timeout: 5s
+      retries: 5
+    networks:
+      - internal
+
+  # 8080
+  searxng:
+    image: searxng/searxng:latest
+    container_name: searxng
+    volumes:
+      - ./searxng.yml:/etc/searxng/settings.yml:ro,Z
+      - searxng_data:/etc/searxng:rw
+    restart: always
+
+    # DELETEME: for local testing only (extern port closed)
+    ports:
+      - "4001:8080"
+    networks:
+      - internal
+
+  coderunner:
+    build:
+      context: ./coderunner
+      dockerfile: Dockerfile
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "curl", "-fsS", "http://127.0.0.1:8787/openapi.json"]
+      interval: 30s
+      timeout: 3s
+      retries: 3
+      start_period: 10s
+
+    user: "1000:1000"
+    group_add:
+      - "977"
+
+    # death
+    environment:
+      DOCKER_HOST: "unix:///var/run/docker.sock"
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock:Z
+      # - ./tmp:/tmp
+
+    read_only: true
+    tmpfs:
+      - /run:rw,nosuid,nodev
+      - /tmp:rw,exec,nosuid,nodev,size=64m
+
+    security_opt:
+      - no-new-privileges:true
+      - label=disable
+    networks:
+      - internal
+
+  browser:
+    build:
+      context: ./browser
+      dockerfile: Dockerfile
+    container_name: browser
+    networks:
+      - internal
+    # playwright/chromium has larger /dev/shm :D
+    shm_size: "1gb"
+    user: "1000:1000"
+    environment:
+      WEBUI_IP: "0.0.0.0"
+      WEBUI_PORT: "7788"
+    ports:
+      - "7788:7788"
+    tmpfs:
+      - /opt/web-ui/tmp:rw,exec,nosuid,nodev,mode=1777,size=64m
+    volumes:
+      - webui_data:/data
+      # - webui_env:/opt/web-ui/.env
+    healthcheck:
+      test: ["CMD", "python", "-c", "import urllib.request; urllib.request.urlopen('http://127.0.0.1:7788').read()"]
+      interval: 30s
+      timeout: 5s
+      retries: 5
+    restart: unless-stopped
+
+volumes:
+  open-webui:
+  pgdata:
+  searxng_data:
+  webui_data:
+
+networks:
+  internal:
+    driver: bridge
@@ -0,0 +1,12 @@
+use_default_settings: true
+
+search:
+  formats:
+    - html
+    - json
+
+server:
+  secret_key: "784dd44a8d67eb0b306e508ad414b4e3ebc9d358f81073ca7cb4c0919204c51c"
+  public_instance: false
+  limiter: false
+