diff --git a/.gitignore b/.gitignore
index ca210db9a..e6198b72c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -31,3 +31,4 @@ CLAUDE.md
.claude/
docs/.docusaurus/
docs/node_modules/
+docs/static/imported-files/
diff --git a/docs/docs/getting_started/quickstart.mdx b/docs/docs/getting_started/quickstart.mdx
index c213cd04b..16d1e5f05 100644
--- a/docs/docs/getting_started/quickstart.mdx
+++ b/docs/docs/getting_started/quickstart.mdx
@@ -34,7 +34,7 @@ Now open up a new terminal and copy the following script into a file named `demo
import CodeFromFile from '@site/src/components/CodeFromFile';
-
+
We will use `uv` to run the script
```
uv run --with llama-stack-client,fire,requests demo_script.py
diff --git a/docs/docusaurus.config.ts b/docs/docusaurus.config.ts
index 70406474f..ab382c917 100644
--- a/docs/docusaurus.config.ts
+++ b/docs/docusaurus.config.ts
@@ -222,6 +222,7 @@ const config: Config = {
} satisfies Preset.ThemeConfig,
plugins: [
+ require.resolve('./plugins/file-sync-plugin'),
[
"docusaurus-plugin-openapi-docs",
{
diff --git a/docs/scripts/sync-files.js b/docs/scripts/sync-files.js
index 6b1fc86ca..a9b5b3eaf 100755
--- a/docs/scripts/sync-files.js
+++ b/docs/scripts/sync-files.js
@@ -47,6 +47,57 @@ function trackFileUsage(filePath) {
}
}
+// Filter content based on file type and options
+function filterContent(content, filePath) {
+ let lines = content.split('\n');
+
+ // Skip copyright header for Python files
+ if (filePath.endsWith('.py')) {
+ // Read the license header file
+ const licenseHeaderPath = path.join(repoRoot, 'docs', 'license_header.txt');
+ if (fs.existsSync(licenseHeaderPath)) {
+ try {
+ const licenseText = fs.readFileSync(licenseHeaderPath, 'utf8');
+ const licenseLines = licenseText.trim().split('\n');
+
+ // Check if file starts with the license header (accounting for # comments)
+ if (lines.length >= licenseLines.length) {
+ let matches = true;
+ for (let i = 0; i < licenseLines.length; i++) {
+ const codeLine = lines[i]?.replace(/^#\s*/, '').trim();
+ const licenseLine = licenseLines[i]?.trim();
+ if (codeLine !== licenseLine) {
+ matches = false;
+ break;
+ }
+ }
+
+ if (matches) {
+ // Skip the license header and any trailing empty lines
+ let skipTo = licenseLines.length;
+ while (skipTo < lines.length && lines[skipTo].trim() === '') {
+ skipTo++;
+ }
+ lines = lines.slice(skipTo);
+ }
+ }
+ } catch (error) {
+ console.warn(`Could not read license header, skipping filtering for ${filePath}`);
+ }
+ }
+ }
+
+ // Trim empty lines from start and end
+ while (lines.length > 0 && lines[0].trim() === '') {
+ lines.shift();
+ }
+ while (lines.length > 0 && lines[lines.length - 1].trim() === '') {
+ lines.pop();
+ }
+
+ return lines.join('\n');
+}
+
// Sync a file from repo root to static directory
function syncFile(filePath) {
const sourcePath = path.join(repoRoot, filePath);
@@ -61,7 +112,8 @@ function syncFile(filePath) {
try {
if (fs.existsSync(sourcePath)) {
const content = fs.readFileSync(sourcePath, 'utf8');
- fs.writeFileSync(destPath, content);
+ const filteredContent = filterContent(content, filePath);
+ fs.writeFileSync(destPath, filteredContent);
console.log(`ā
Synced ${filePath}`);
trackFileUsage(filePath);
return true;
diff --git a/docs/src/components/CodeFromFile.jsx b/docs/src/components/CodeFromFile.jsx
index e2ef1d7cf..94580f8c5 100644
--- a/docs/src/components/CodeFromFile.jsx
+++ b/docs/src/components/CodeFromFile.jsx
@@ -15,33 +15,7 @@ export default function CodeFromFile({
useEffect(() => {
async function loadFile() {
try {
- // Register this file for syncing (build-time only)
- if (typeof window === 'undefined') {
- // This runs during build - register the file
- const fs = require('fs');
- const path = require('path');
-
- const usageFile = path.join(process.cwd(), 'static', 'imported-files', 'usage.json');
- const usageDir = path.dirname(usageFile);
-
- if (!fs.existsSync(usageDir)) {
- fs.mkdirSync(usageDir, { recursive: true });
- }
-
- let usage = { files: [] };
- if (fs.existsSync(usageFile)) {
- try {
- usage = JSON.parse(fs.readFileSync(usageFile, 'utf8'));
- } catch (error) {
- console.warn('Could not read existing usage file');
- }
- }
-
- if (!usage.files.includes(src)) {
- usage.files.push(src);
- fs.writeFileSync(usageFile, JSON.stringify(usage, null, 2));
- }
- }
+ // File registration is now handled by the file-sync-plugin during build
// Load file from static/imported-files directory
const response = await fetch(`/imported-files/${src}`);
@@ -50,7 +24,7 @@ export default function CodeFromFile({
}
let text = await response.text();
- // Handle line range if specified
+ // Handle line range if specified (filtering is done at build time)
if (startLine || endLine) {
const lines = text.split('\n');
const start = startLine ? Math.max(0, startLine - 1) : 0;
diff --git a/docs/static/imported-files/README.md b/docs/static/imported-files/README.md
deleted file mode 100644
index 75e9989d7..000000000
--- a/docs/static/imported-files/README.md
+++ /dev/null
@@ -1,207 +0,0 @@
-# Llama Stack
-
-[](https://pypi.org/project/llama_stack/)
-[](https://pypi.org/project/llama-stack/)
-[](https://github.com/meta-llama/llama-stack/blob/main/LICENSE)
-[](https://discord.gg/llama-stack)
-[](https://github.com/meta-llama/llama-stack/actions/workflows/unit-tests.yml?query=branch%3Amain)
-[](https://github.com/meta-llama/llama-stack/actions/workflows/integration-tests.yml?query=branch%3Amain)
-
-[**Quick Start**](https://llamastack.github.io/docs/getting_started/quickstart) | [**Documentation**](https://llamastack.github.io/docs) | [**Colab Notebook**](./docs/getting_started.ipynb) | [**Discord**](https://discord.gg/llama-stack)
-
-
-### āØš Llama 4 Support šāØ
-We released [Version 0.2.0](https://github.com/meta-llama/llama-stack/releases/tag/v0.2.0) with support for the Llama 4 herd of models released by Meta.
-
-
-
-š Click here to see how to run Llama 4 models on Llama Stack
-
-\
-*Note you need 8xH100 GPU-host to run these models*
-
-```bash
-pip install -U llama_stack
-
-MODEL="Llama-4-Scout-17B-16E-Instruct"
-# get meta url from llama.com
-huggingface-cli download meta-llama/$MODEL --local-dir ~/.llama/$MODEL
-
-# start a llama stack server
-INFERENCE_MODEL=meta-llama/$MODEL llama stack build --run --template meta-reference-gpu
-
-# install client to interact with the server
-pip install llama-stack-client
-```
-### CLI
-```bash
-# Run a chat completion
-MODEL="Llama-4-Scout-17B-16E-Instruct"
-
-llama-stack-client --endpoint http://localhost:8321 \
-inference chat-completion \
---model-id meta-llama/$MODEL \
---message "write a haiku for meta's llama 4 models"
-
-OpenAIChatCompletion(
- ...
- choices=[
- OpenAIChatCompletionChoice(
- finish_reason='stop',
- index=0,
- message=OpenAIChatCompletionChoiceMessageOpenAIAssistantMessageParam(
- role='assistant',
- content='...**Silent minds awaken,** \n**Whispers of billions of words,** \n**Reasoning breaks the night.** \n\nā \n*This haiku blends the essence of LLaMA 4\'s capabilities with nature-inspired metaphor, evoking its vast training data and transformative potential.*',
- ...
- ),
- ...
- )
- ],
- ...
-)
-```
-### Python SDK
-```python
-from llama_stack_client import LlamaStackClient
-
-client = LlamaStackClient(base_url=f"http://localhost:8321")
-
-model_id = "meta-llama/Llama-4-Scout-17B-16E-Instruct"
-prompt = "Write a haiku about coding"
-
-print(f"User> {prompt}")
-response = client.chat.completions.create(
- model=model_id,
- messages=[
- {"role": "system", "content": "You are a helpful assistant."},
- {"role": "user", "content": prompt},
- ],
-)
-print(f"Assistant> {response.choices[0].message.content}")
-```
-As more providers start supporting Llama 4, you can use them in Llama Stack as well. We are adding to the list. Stay tuned!
-
-
-
-
-### š One-Line Installer š
-
-To try Llama Stack locally, run:
-
-```bash
-curl -LsSf https://github.com/meta-llama/llama-stack/raw/main/scripts/install.sh | bash
-```
-
-### Overview
-
-Llama Stack standardizes the core building blocks that simplify AI application development. It codifies best practices across the Llama ecosystem. More specifically, it provides
-
-- **Unified API layer** for Inference, RAG, Agents, Tools, Safety, Evals, and Telemetry.
-- **Plugin architecture** to support the rich ecosystem of different API implementations in various environments, including local development, on-premises, cloud, and mobile.
-- **Prepackaged verified distributions** which offer a one-stop solution for developers to get started quickly and reliably in any environment.
-- **Multiple developer interfaces** like CLI and SDKs for Python, Typescript, iOS, and Android.
-- **Standalone applications** as examples for how to build production-grade AI applications with Llama Stack.
-
-
-
-
-
diff --git a/docs/static/imported-files/usage.json b/docs/static/imported-files/usage.json
deleted file mode 100644
index 3692a65e5..000000000
--- a/docs/static/imported-files/usage.json
+++ /dev/null
@@ -1,6 +0,0 @@
-{
- "files": [
- "docs/getting_started/demo_script.py",
- "README.md"
- ]
-}