init documentation (#33)

Author: ultmaster

.github/workflows/docs.yml

@@ -0,0 +1,59 @@
+name: Deploy Documentation
+
+on:
+  push:
+    branches:
+      - main
+    tags:
+      - 'v*'
+  workflow_dispatch:
+
+permissions:
+  contents: write
+  pages: write
+  id-token: write
+
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.12'
+
+      - name: Install dependencies
+        run: |
+          ./scripts/setup_stable.sh
+
+      - name: Configure Git
+        run: |
+          git config --global user.name "GitHub Actions"
+          git config --global user.email "[email protected]"
+
+      - name: Get version and commit
+        id: version
+        run: |
+          if [[ $GITHUB_REF == refs/tags/* ]]; then
+            VERSION=${GITHUB_REF#refs/tags/v}
+            SOURCE_COMMIT=${GITHUB_SHA}
+          else
+            VERSION=$(python -c "import tomllib; print(tomllib.load(open('pyproject.toml', 'rb'))['project']['version'])")
+            SOURCE_COMMIT=${GITHUB_SHA}
+          fi
+          echo "version=$VERSION" >> $GITHUB_OUTPUT
+          echo "SOURCE_COMMIT=$SOURCE_COMMIT" >> $GITHUB_ENV
+
+      - name: Deploy versioned docs
+        if: startsWith(github.ref, 'refs/tags/')
+        run: |
+          mike deploy --push --update-aliases ${{ steps.version.outputs.version }} latest
+
+      - name: Deploy dev docs
+        if: github.ref == 'refs/heads/main'
+        run: |
+          mike deploy --push dev

.github/workflows/tests.yml

@@ -33,6 +33,33 @@ jobs:
         run: |
           black --check --diff --line-length=120 .
 
+  docs:
+    name: Build documentation
+    runs-on: ubuntu-latest
+    timeout-minutes: 10
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          fetch-depth: 0
+      - uses: actions/setup-python@v4
+        with:
+          python-version: '3.12'
+      - name: Install documentation dependencies
+        run: |
+          ./scripts/setup_stable.sh
+      - name: Set source commit for docs
+        run: |
+          echo "SOURCE_COMMIT=${{ github.sha }}" >> $GITHUB_ENV
+      - name: Build documentation
+        run: |
+          mkdocs build --strict
+      - name: Upload docs artifact
+        uses: actions/upload-artifact@v4
+        with:
+          name: documentation-site
+          path: site/
+          compression-level: 6
+
   test:
     strategy:
       matrix:

README.md

@@ -1,4 +1,4 @@
-![Agent-lightning-banner](assets/readme-banner.png)
+![Agent-lightning-banner](docs/assets/readme-banner.png)
 
 # Agent Lightning⚡
 
@@ -16,7 +16,7 @@
 - **Selectively** optimize one or more agents in a multi-agent system. 🎯
 - Embraces Reinforcement Learning, Automatic Prompt Optimization and more **algorithms**. 🤗
 
-![Agent-Lightning-code-diff](assets/readme-diff.png)
+![Agent-Lightning-code-diff](docs/assets/readme-diff.png)
 
 ## ⚡ Resources
 
@@ -107,7 +107,7 @@ Currently, Agent Lightning is built around a **training server** and one or mult
 * **Agents** retrieve samples from the server, process them (which may involve interacting with the LLM), and send the results back. These results, or "trajectories," are lists of prompts and responses from the LLM.
 * The **server** then collects these trajectories and computes the losses to optimize the language models.
 
-![Agent-Lightning-architecture](assets/readme-architecture.png)
+![Agent-Lightning-architecture](docs/assets/readme-architecture.png)
 
 ## ⚡ Development Instructions
 
@@ -126,6 +126,12 @@ pre-commit install
 pre-commit run --all-files --show-diff-on-failure --color=always
 ```
 
+Serve documentation locally:
+
+```bash
+mkdocs serve
+```
+
 ## ⚡ Contributing
 
 This project welcomes contributions and suggestions. Most contributions require you to agree to a Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us the rights to use your contribution. For details, visit https://cla.opensource.microsoft.com.

agentlightning/verl/__init__.py

@@ -0,0 +1,3 @@
+from .trainer import *
+from .daemon import *
+from .dataset import *

agentlightning/verl/daemon.py

@@ -31,8 +31,8 @@ def get_left_padded_ids_and_attention_mask(ids: List[int], max_length: int, pad_
         pad_token_id:    ID to use for padding.
 
     Returns:
-        padded_ids:      list of length == max_length.
-        attention_mask:  list of same length: 1 for non-pad tokens, 0 for pads.
+        padded_ids (any):      list of length == max_length.
+        attention_mask (any):  list of same length: 1 for non-pad tokens, 0 for pads.
     """
     seq_len = len(ids)
 
@@ -60,8 +60,8 @@ def get_right_padded_ids_and_attention_mask(ids: List[int], max_length: int, pad
         pad_token_id:   ID to use for padding.
 
     Returns:
-        padded_ids:     list of length == max_length.
-        attention_mask: list of same length: 1 for non-pad tokens, 0 for pads.
+        padded_ids (any):     list of length == max_length.
+        attention_mask (any): list of same length: 1 for non-pad tokens, 0 for pads.
     """
     seq_len = len(ids)