new template

2026-06-30 21:38:03 -04:00 · 2025-05-28 16:30:36 -04:00
commit 0f4e8f5fd6
20 changed files with 423 additions and 0 deletions
@@ -0,0 +1,9 @@
+# questions
+project_name:
+    type: str
+    help: What is your project name?
+    default: "{{_folder_name}}"
+    validator: |-
+        {% if not project_name.replace("-", "").isalpha() %}
+            Project name must contain only letters and dashes
+        {% endif %}
@@ -0,0 +1,22 @@
+name: "{{project_name}}"
+
+control-plane:
+  port: 8000
+
+default-service: echo_workflow
+
+services:
+  loop-files:
+    name: Main Workflow
+    source:
+      type: local
+      name: workflow
+    path: workflow/loop_files:workflow
+    python-dependencies:
+      - "llama-cloud-services"
+
+ui:
+  name: "{{project_name}} UI"
+  source:
+    type: local
+    name: ui
@@ -0,0 +1,41 @@
+# See https://help.github.com/articles/ignoring-files/ for more about ignoring files.
+
+# dependencies
+/node_modules
+/.pnp
+.pnp.*
+.yarn/*
+!.yarn/patches
+!.yarn/plugins
+!.yarn/releases
+!.yarn/versions
+
+# testing
+/coverage
+
+# next.js
+/.next/
+/out/
+
+# production
+/build
+
+# misc
+.DS_Store
+*.pem
+
+# debug
+npm-debug.log*
+yarn-debug.log*
+yarn-error.log*
+.pnpm-debug.log*
+
+# env files (can opt-in for committing if needed)
+.env*
+
+# vercel
+.vercel
+
+# typescript
+*.tsbuildinfo
+next-env.d.ts
@@ -0,0 +1 @@
+# Next.JS Agent App Starter
@@ -0,0 +1,9 @@
+import type { NextConfig } from "next";
+
+const nextConfig: NextConfig = {
+  /* config options here */
+  transpilePackages: ["@llamaindex/agent-app"],
+
+};
+
+export default nextConfig;
@@ -0,0 +1,27 @@
+{
+  "name": "{{project_name}}-ui",
+  "version": "0.1.0",
+  "private": true,
+  "scripts": {
+    "dev": "next dev --turbopack",
+    "build": "next build --experimental-build-mode compile",
+    "start": "next start",
+    "lint": "tsc --noEmit"
+  },
+  "dependencies": {
+    "@llamaindex/agent-app": "workspace:*",
+    "@llamaindex/extracted-data-client": "workspace:*",
+    "@radix-ui/themes": "^3.2.1",
+    "next": "15.3.2",
+    "react": "^19.0.0",
+    "react-dom": "^19.0.0",
+    "zod": "^3.25.30"
+  },
+  "devDependencies": {
+    "@types/node": "^20",
+    "@types/react": "^19",
+    "@types/react-dom": "^19",
+    "prettier": "^3.5.3",
+    "typescript": "^5"
+  }
+}
@@ -0,0 +1,22 @@
+import {
+  ExtractedDataGrid,
+  zodToJsonSchema,
+} from "@llamaindex/agent-app/server";
+// TODO - import your schema from @/schemas/SchemaName
+import { Placeholder } from "@/schemas/Placeholder";
+
+interface PageProps {
+  params: Promise<{ fileId: string }>;
+}
+
+export default async function FilePage({ params }: PageProps) {
+  const { fileId } = await params;
+  return (
+    <div>
+      <ExtractedDataGrid
+        fileId={fileId}
+        schema={zodToJsonSchema(Placeholder)}
+      />
+    </div>
+  );
+}
@@ -0,0 +1,22 @@
+
+html,
+body {
+  max-width: 100vw;
+  overflow-x: hidden;
+}
+
+body {
+  -webkit-font-smoothing: antialiased;
+  -moz-osx-font-smoothing: grayscale;
+}
+
+* {
+  box-sizing: border-box;
+  padding: 0;
+  margin: 0;
+}
+
+a {
+  color: inherit;
+  text-decoration: none;
+}
@@ -0,0 +1,35 @@
+import type { Metadata } from "next";
+import { Geist, Geist_Mono } from "next/font/google";
+import "./globals.css";
+import { Theme } from "@radix-ui/themes";
+
+const geistSans = Geist({
+  variable: "--font-geist-sans",
+  subsets: ["latin"],
+});
+
+const geistMono = Geist_Mono({
+  variable: "--font-geist-mono",
+  subsets: ["latin"],
+});
+
+export const metadata: Metadata = {
+  title: "{{project_name}}",
+  description: "{{project_name}} Data Review",
+};
+
+export default function RootLayout({
+  children,
+}: Readonly<{
+  children: React.ReactNode;
+}>) {
+  return (
+    <html lang="en">
+      <body className={`${geistSans.variable} ${geistMono.variable}`}>
+      <Theme>
+        {children}
+      </Theme>
+      </body>
+    </html>
+  );
+}
@@ -0,0 +1,19 @@
+.page {
+
+}
+
+.main {
+  padding: 1rem;
+}
+
+.grid {
+  display: flex;
+  flex-direction: row;
+  gap: 1rem;
+  margin-bottom: 1rem;
+  & > * {
+    flex: 1;
+  }
+}
+
+
@@ -0,0 +1,48 @@
+import { FileCount, FileGrid } from "@llamaindex/agent-app/server";
+import styles from "./page.module.css";
+
+export default function Home() {
+  const lastMonth = new Date(
+    new Date().setMonth(new Date().getMonth() - 1)
+  ).toISOString();
+  return (
+    <div className={styles.page}>
+      <main className={styles.main}>
+        <div className={styles.grid}>
+          <FileCount
+            title="Total Documents"
+            filter_fields={{ created_at: { gt: lastMonth } }}
+            filter_status_counts={{}}
+          />
+          <FileCount
+            title="Reviewed"
+            filter_fields={{ created_at: { gt: lastMonth } }}
+            filter_status_counts={{ pending_review: { eq: 0 } }}
+          />
+          <FileCount
+            title="Needs Review"
+            filter_fields={{ created_at: { gt: lastMonth } }}
+            filter_status_counts={{ pending_review: { gt: 0 } }}
+          />
+        </div>
+        <FileGrid
+          fileRoute="/file"
+          includeColumns={[
+            {
+              standardColumn: "file_name",
+            },
+            {
+              standardColumn: "status",
+            },
+            {
+              standardColumn: "synced_at",
+            },
+            {
+              standardColumn: "created_at",
+            },
+          ]}
+        />
+      </main>
+    </div>
+  );
+}
@@ -0,0 +1,8 @@
+import { z } from "zod/v4";
+
+export const Placeholder = z.object({
+  name: z.string(),
+  age: z.number(),
+});
+
+export type Placeholder = z.infer<typeof Placeholder>;
@@ -0,0 +1,27 @@
+{
+  "compilerOptions": {
+    "target": "ES2017",
+    "lib": ["dom", "dom.iterable", "esnext"],
+    "allowJs": true,
+    "skipLibCheck": true,
+    "strict": true,
+    "noEmit": true,
+    "esModuleInterop": true,
+    "module": "esnext",
+    "moduleResolution": "bundler",
+    "resolveJsonModule": true,
+    "isolatedModules": true,
+    "jsx": "preserve",
+    "incremental": true,
+    "plugins": [
+      {
+        "name": "next"
+      }
+    ],
+    "paths": {
+      "@/*": ["./src/*"]
+    }
+  },
+  "include": ["next-env.d.ts", "**/*.ts", "**/*.tsx", ".next/types/**/*.ts"],
+  "exclude": ["node_modules"]
+}
@@ -0,0 +1,6 @@
+# place secrets here
+EXTRACTED_DATA_TOKEN="{{project_name}}"
+LLAMA_CLOUD_API_KEY="ADD ME"
+# these may be required for your API key or depending on the API called
+LLAMA_CLOUD_PROJECT_ID=""
+LLAMA_CLOUD_PROJECT_ID=""
@@ -0,0 +1,28 @@
+import functools
+import os
+
+from extracted_data_client import AuthenticatedClient
+from llama_cloud_services import LlamaExtract
+
+import dotenv
+
+dotenv.load_dotenv()
+
+# Add getters for clients and environment variables here.
+
+
+@functools.lru_cache(maxsize=None)
+def get_extract_api() -> LlamaExtract:
+    return LlamaExtract(
+        api_key=os.environ["LLAMA_CLOUD_API_KEY"],
+        project_id=os.environ.get("LLAMA_CLOUD_PROJECT_ID", None),
+        organization_id=os.environ.get("LLAMA_CLOUD_ORG_ID", None),
+    )
+
+
+@functools.lru_cache(maxsize=None)
+def get_extracted_data_client():
+    return AuthenticatedClient(
+        base_url=os.environ.get("EXTRACTED_DATA_BASE_URL", "http://localhost:9182"),
+        token=os.environ["EXTRACTED_DATA_TOKEN"],
+    )
@@ -0,0 +1,59 @@
+import asyncio
+import logging
+
+from llama_index.core.workflow import (
+    Context,
+    Event,
+    StartEvent,
+    StopEvent,
+    Workflow,
+    step,
+)
+
+logger = logging.getLogger(__name__)
+
+
+class ProcessFile(Event):
+    file_path: str
+    total_files: int
+
+
+class ProcessFileCompleted(Event):
+    total_files: int
+    did_succeed: bool
+
+
+LOOP_SLEEP_TIME = 60
+
+
+class LoopFiles(Workflow):
+    """
+    This workflow is a simple loop that processes all files in the data directory.
+    It will process the files in parallel, and then sleep for a configurable amount of time.
+    """
+
+    @step
+    async def start(self, event: StartEvent, ctx: Context) -> StartEvent | StopEvent:
+        logger.info("Checking for files to process")
+        # Get the files to process
+        # check if they have already been processed
+        # process the files that haven't been processed
+        # sleep a bit
+        await asyncio.sleep(LOOP_SLEEP_TIME)
+        return StartEvent()
+
+workflow = LoopFiles(timeout=None)
+
+if __name__ == "__main__":
+    logging.basicConfig(level=logging.INFO)
+
+
+    async def main():
+        await workflow.run()
+
+    loop = asyncio.new_event_loop()
+    asyncio.set_event_loop(loop)
+    try:
+        loop.run_until_complete(main())
+    finally:
+        loop.close()
@@ -0,0 +1,22 @@
+import logging
+
+from llama_index.core.workflow import StartEvent, StopEvent, Workflow, step
+from llama_index.core.workflow.retry_policy import ConstantDelayRetryPolicy
+
+logger = logging.getLogger(__name__)
+
+
+class FileEvent(StartEvent):
+    file_path: str
+
+
+class ProcessFileWorkflow(Workflow):
+    """
+    Given a file path, this workflow will process a single file through the custom extraction logic.
+    """
+
+    @step(retry_policy=ConstantDelayRetryPolicy(maximum_attempts=3, delay=10))
+    async def run_file(self, event: FileEvent) -> StopEvent:
+        logger.info(f"Processing file {event.file_path}")
+        # TODO: process the file
+        return StopEvent()
@@ -0,0 +1,10 @@
+[project]
+name = "{{project_name}}-workflow"
+version = "0.1.0"
+description = "Extracts data"
+readme = "README.md"
+requires-python = ">=3.12"
+dependencies = [
+    "extraction-utils",
+    "llama-cloud-services"
+]
@@ -0,0 +1,6 @@
+from pydantic import BaseModel
+
+
+class MySchema(BaseModel):
+    # Replace this with the actual schema you want to use for extraction
+    pass
@@ -0,0 +1,2 @@
+# Changes here will be overwritten by Copier; NEVER EDIT MANUALLY
+{{ _copier_answers|to_nice_yaml -}}