Merge pull request #36 from google-ai-edge:docs/restructure-readme

PiperOrigin-RevId: 917272419

Author: copybara-github

README.md

@@ -1,133 +1,143 @@
 # LiteRT CLI (Preview)
 
-A convenient command-line toolkit to streamline LiteRT development workflow,
+A convenient command-line toolkit to streamline
+[LiteRT](https://ai.google.dev/edge/litert) related development workflow,
 including converting, quantizing, compiling, managing, running, and benchmarking
 LiteRT (TFLite) models on various hardware (CPU / GPU / NPU) across platforms
 (desktop, mobile, or cloud).
 
-## 🤖 Use in Coding Agent
-
-Add the LiteRT CLI skill
-[`SKILL.md`](file:///.agents/skills/litert_cli/SKILL.md) into your AI coding
-agent (like Antigravity or Gemini CLI) to enable prompts such as:
-
-*   "Download LiteRT model `litert-community/efficientnet_b1` and run it on CPU"
-*   "Benchmark LiteRT model `litert-community/efficientnet_b1` on my Android
-    GPU"
-*   "Compile LiteRT model `litert-community/efficientnet_b1` for NPU target
-    `sm8750`"
-*   "Visualize LiteRT model `litert-community/efficientnet_b1`"
-
-The agent will automatically install the necessary tools, including Python
-virtual environments, `litert-cli`, and all required dependencies.
+> [!NOTE] It's a still early preview release under active development, thus has
+> limited platform and feature support, plus possible bugs. We appreciate your
+> patience and feedback to help us improve it.
 
 --------------------------------------------------------------------------------
 
 ## 🚀 Installation
 
-We support installation using either **`uv`** (recommended for ultra-fast
-dependency resolution) or standard **`pip`** within a virtual environment.
+You can install `litert-cli-nightly` from PyPI or from local clone. LiteRT CLI
+will install the dependencies on-demands, based on which commands to run, to
+speed up initial installation.
 
-### Option 1: Use UV (Recommended)
+We support installation using either
+**[uv](https://docs.astral.sh/uv/getting-started/installation/)** (recommended
+for ultra-fast dependency resolution) or standard
+**[pip](https://pip.pypa.io/)** within a Python virtual environment.
 
-`uv` is an extremely fast Python package manager written in Rust.
+#### Option 1: Use UV (Recommended)
 
-#### 1. Create and Activate Virtual Environment
+`uv` is an extremely fast Python package manager written in Rust.
 
 ```bash
-# Create a virtual environment with Python 3.13 in the current directory.
-# When meeting dependency resolution error, try to set environment variable:
-# UV_INDEX_URL=https://pypi.org/simple
+# 1. Create a virtual environment with Python 3.13.
+# TIP: When meeting dependency resolution error, try to set environment variable:
+#    export UV_INDEX_URL=https://pypi.org/simple
 uv venv --clear --python=3.13 --seed
 source .venv/bin/activate
-```
 
-#### 2. Install `litert-cli`
+# 2. Install the package into the active virtual environment
+uv pip install litert-cli-nightly
 
-##### 2a. Install from PyPI
+# 3. Run help command
+litert --help
+```
+
+### Option 2: Use Standard Pip
 
 ```bash
-# Install the package into the active virtual environment
-uv pip install -q litert-cli-nightly
+python3 -m venv .venv
+source .venv/bin/activate
+pip install -q litert-cli-nightly
+litert --help
 ```
 
-##### 2b. Or Install from Local Clone (Recommended for Development)
+#### Option 3. Install from Local Clone (for development)
 
 ```bash
-# Clone the repository via SSH
+uv venv --clear --python=3.13 --seed
+source .venv/bin/activate
 git clone git@github.com:google-ai-edge/LiteRT-CLI.git
-# Or clone using your Personal Access Token (PAT)
-git clone https://<your-access-token>@github.com/google-ai-edge/LiteRT-CLI.git
 cd LiteRT-CLI
-
-# Install in editable mode inside the active virtual environment
 uv pip install -e .
 ```
 
-#### 3. Run Commands
+--------------------------------------------------------------------------------
+
+## Quick Start
+
+### Try colab
+
+Try
+[LiteRT CLI Colab](https://github.com/google-ai-edge/LiteRT-CLI/blob/main/examples/litert_cli.ipynb)
+to explore different features quickly.
 
-Check more comprehensive usage examples under the `examples/` directory. You can
-run our automated demo drivers: - **Run all command demos**:
-`./examples/run_commands.sh` - **Run all model demos**:
-`./examples/run_models.sh` - **Run a specific model demo**:
-`./examples/run_models.sh efficientnet`
+### Follow command help
+
+You can always follow `litert --help` or `litert {command} --help` to find how
+to use the CLI tool. Check detailed instructions for each command below.
 
 ```bash
 # Run help command
 litert --help
 
 # Download a LiteRT model
-litert download litert-community/MobileNet-v3-large --file "*.tflite" --output mobilenet
+litert download --help
+litert download litert-community/efficientnet_b1 --file "*.tflite" --output efficientnet
+
+# Run and benchmark a LiteRT model on your devices
+litert run --help
+litert run efficientnet/efficientnet_b1.tflite --desktop --cpu
+litert benchmark --help
+litert benchmark efficientnet/efficientnet_b1.tflite --android --gpu
 ```
 
---------------------------------------------------------------------------------
+### Quick Demos
 
-### Option 2: Use Standard Pip
+Check comprehensive usage examples under the `examples/` directory, which
+contains per-command demos and model-specific demos.
 
-#### 1. Create and Activate Virtual Environment
+If you have cloned the repo, you can run the following commands to see the
+demos:
 
 ```bash
-# Create and activate a Python virtual environment
-python3 -m venv .venv
-source .venv/bin/activate
-```
+# Run all command demos
+./examples/run_commands.sh
 
-#### 2. Install `litert-cli`
+# Run all model demos
+./examples/run_models.sh
 
-##### 2a. Install from PyPI
-
-```bash
-pip install -q litert-cli-nightly
+# Run a specific model demo
+./examples/run_models.sh efficientnet
 ```
 
-##### 2b. Or Install from Local Clone
+## 🤖 Use in Coding Agent
 
-```bash
-# Clone the repository
-git clone git@github.com:google-ai-edge/LiteRT-CLI.git
-cd LiteRT-CLI
+Add the LiteRT CLI skill
+[`SKILL.md`]([file:///.agents/skills/litert_cli/SKILL.md]\(https://github.com/google-ai-edge/LiteRT-CLI/blob/main/.agents/skills/litert_cli/SKILL.md\))
+into your AI coding agent (like Google Antigravity) and try prompts such as:
 
-# Install in editable mode
-pip install -e .
-```
+*   "Download LiteRT model `litert-community/efficientnet_b1` and run it on CPU"
+*   "Benchmark LiteRT model `litert-community/efficientnet_b1` on my Android
+    GPU"
+*   "Compile LiteRT model `litert-community/efficientnet_b1` for NPU target
+    `sm8750`"
+*   "Visualize LiteRT model `litert-community/efficientnet_b1`"
 
-#### 3. Run Commands
+The agent will automatically install the necessary tools, including Python
+virtual environments, `litert-cli-nightly`, and all required dependencies.
 
-```bash
-# Run help command
-litert --help
+--------------------------------------------------------------------------------
 
-# Download a LiteRT model
-litert download litert-community/MobileNet-v3-large --file "*.tflite" --output mobilenet
-```
+### Verified Platforms
 
-### Tested Platforms
+Verified in Python 3.13.
 
 *   **Host Machines**:
-    *   Linux (Ubuntu) with Python 3.13
-    *   macOS (Apple Silicon) with Python 3.13
-*   **Android Devices**:
-    *   Qualcomm Snapdragon 8750
+    *   Linux (Ubuntu)
+    *   macOS (Apple Silicon): don't support `litert compile`
+    *   Windows: partially supported
+*   **Android**:
+    *   CPU, GPU
+    *   NPU: Qualcomm (supported), MediaTek (soon), Google Tensor (soon)
 
 --------------------------------------------------------------------------------
 
@@ -316,4 +326,4 @@ litert lm run gemma-4-E2B-it.litertlm --prompt "Hello, how are you?"
 ```bash
 # Clean up model cache, etc.
 litert clean
-```
+```