Add auto-generated docs.

Author: squidarth

bin/generate_truss_examples.py

@@ -17,7 +17,7 @@
 import subprocess
 import sys
 from pathlib import Path
-from typing import List, Optional, Tuple
+from typing import Iterator, List, Optional, Tuple
 
 import yaml
 
@@ -235,10 +235,26 @@ def _format_group_name(group_name: str) -> str:
     into a more human readable format for the table of contents.
 
     Note that parent directory names are assumed to be in the format:
-    * 1_introduction/...
-    * 2_image_classification/...
+    * 1_introduction/... (becomes "Introduction")
+    * 2_image_classification/... (becomes "Image classification")
+    * 3_llms/... (becomes "LLMs")
     """
-    return " ".join(group_name.split("_")[1:]).capitalize()
+    lowercase_name = " ".join(group_name.split("_")[1:])
+    # Capitalize the first letter. We do this rather than
+    # use .capitalize() or .title() because we want to preserve
+    # the case of subsequent letters
+    return lowercase_name[0].upper() + lowercase_name[1:]
+
+
+def _toc_section(
+    example_group_name: str, example_group: Iterator[Tuple[str, ...]]
+) -> dict:
+    return {
+        "group": _format_group_name(example_group_name),
+        "pages": [
+            f"examples/{example[0]}/{example[1]}" for example in list(example_group)
+        ],
+    }
 
 
 def update_toc(example_dirs: List[str]):
@@ -269,18 +285,11 @@ def update_toc(example_dirs: List[str]):
         key=lambda example: example[0],
     )
 
-    # TODO: Chage this to instead of appending to pages, to instead replace the pages
-    # before we productionize this.
-    for example_group_name, example_group in grouped_examples:
-        examples_section["pages"].append(
-            {
-                "group": _format_group_name(example_group_name),
-                "pages": [
-                    f"examples/{example[0]}/{example[1]}"
-                    for example in list(example_group)
-                ],
-            }
-        )
+    examples_section["pages"] = [
+        _toc_section(example_group_name, example_group)
+        for example_group_name, example_group in grouped_examples
+    ]
+
     serialized_mint_config = json.dumps(mint_config, indent=2)
     Path(MINT_CONFIG_PATH).write_text(serialized_mint_config)
 

docs/examples/1_introduction/getting-started-bert.mdx

@@ -0,0 +1,156 @@
+---
+title: "Getting Started: Text Classification"
+description: "Building your first Truss"
+---
+
+In this example, we go through building your first Truss model. We'll be using the HuggingFace transformers
+library to build a text classification model that can detect sentiment of text.
+
+# Step 1: Implementing the model
+
+Set up imports for this model. In this example, we simply use the HuggingFace transformers library.
+
+```python model/model.py
+from transformers import pipeline
+
+```
+Every Truss model must implement a `Model` class. This class must have:
+ * an `__init__` function
+ * a `load` function
+ * a `predict` function
+
+In the `__init__` function, set up any variables that will be used in the `load` and `predict` functions.
+
+```python model/model.py
+class Model:
+    def __init__(self, **kwargs):
+        self._model = None
+
+```
+In the `load` function of the Truss, we implement logic
+involved in downloading the model and loading it into memory.
+For this Truss example, we define a HuggingFace pipeline, and choose
+the `text-classification` task, which uses BERT for text classification under the hood.
+
+Note that the the load function runs when the
+
+```python model/model.py
+    def load(self):
+        self._model = pipeline("text-classification")
+
+```
+In the `predict` function of the Truss, we implement logic related
+to actual inference. For this example,  we just call the HuggingFace pipeline
+that we set up in the `load` function.
+
+```python model/model.py
+    def predict(self, model_input):
+        return self._model(model_input)
+```
+
+# Step 2: Writing the config.yaml
+
+Each Truss has a config.yaml file where we can configure
+options related to the deployment. It's in this file where
+we can define requirements, resources, and runtime options like
+secrets and environment variables
+
+### Basic Options
+
+In this section, we can define basic metadata about the model,
+such as the name, and the Python version to build with.
+
+```yaml config.yaml
+model_name: bert
+python_version: py310
+model_metadata: {}
+
+```
+### Set up python requirements
+
+In this section, we define any pip requirements that
+we need to run the model. To run this, we need PyTorch
+and Tranformers.
+
+```yaml config.yaml
+requirements:
+  - torch==2.0.1
+  - transformers==4.33.2
+
+```
+### Configure the resources needed
+
+In this section, we can configure resources
+needed to deploy this model. Here, we have no need for a GPU
+so we leave the accelerator section blank.
+
+```yaml config.yaml
+resources:
+  accelerator: null
+  cpu: '1'
+  memory: 2Gi
+  use_gpu: false
+
+```
+### Other config options
+
+Truss also has provisions for adding other runtime options
+packages. In this example, we don't need these, so we leave
+this empty for now.
+
+```yaml config.yaml
+secrets: {}
+system_packages: []
+environment_variables: {}
+external_package_dirs: []
+
+```
+# Step 3: Deploying & running inference
+
+Deploy the model with the following command:
+
+```bash
+$ truss push
+```
+
+And then you can performance inference with:
+```
+$ truss predict -d '"Truss is awesome!"'
+```
+
+<RequestExample>
+```python model/model.py
+from transformers import pipeline
+
+class Model:
+    def __init__(self, **kwargs):
+        self._model = None
+
+    def load(self):
+        self._model = pipeline("text-classification")
+
+    def predict(self, model_input):
+        return self._model(model_input)
+```
+```yaml config.yaml
+model_name: bert
+python_version: py310
+model_metadata: {}
+
+requirements:
+  - torch==2.0.1
+  - transformers==4.33.2
+
+resources:
+  accelerator: null
+  cpu: '1'
+  memory: 2Gi
+  use_gpu: false
+
+secrets: {}
+system_packages: []
+environment_variables: {}
+external_package_dirs: []
+
+```
+</RequestExample>