cli entries for create run deploy

README.md

@@ -1,11 +1,13 @@
-# Hal9: Create and Deploy GenAI Chatbots
+# Hal9: Create and Share Generative Apps
 
 [![Hal9 PyPi Downloads](https://img.shields.io/pypi/dm/hal9?label=PyPI)](https://pypi.org/project/hal9/)
 
-Create and deploy Large Language Model (LLM) chatbots in seconds.
-- **Open:** Use any LLM like OpenAI, LLama, Gemini, Groq, etc. and open libraries like LangChain.
-- **Intuitive:** No need to learn a chat framework, simply use stdin and stdout.
-- **Scalable:** Engineers can esily integrate your chatbot with Docker or use Hal9's self-service enterprise cloud.
+Create and deploy generative (LLMs and [difussers](https://github.com/huggingface/diffusers)) applications (chatbots and APIs) in seconds.
+- **Open:** Use any model (OpenAI, Llama, Groq, Midjourney) and any library like (LangChainl, DSPy).
+- **Intuitive:** No need to learn an app framework (streamlit, flask), simply use stdin and stdout.
+- **Scalable:** Engineers can esily integrate your app with Docker or use Hal9's self-service enterprise cloud.
+
+Focus on AI (RAG, fine-tuning, aligment, training) and skip engineering tasks (frontend development, backend integration, deployment, operations).
 
 ## Getting started
 
@@ -14,22 +16,25 @@ To create and deploy a chatbot in 10 seconds run the following:
 ```bash
 pip install hal9
 
-hal9 create my-project
-hal9 deploy my-project
+hal9 create chatbot
+hal9 deploy chatbot
 ```
 
-To customize, read the following sections.
+To customize further, read the following sections.
 
 ## Creation
 
-By default `hal9 create` we will use OpenAI, you can choose your template as follows:
+By default `hal9 create` we will use the OpenAI template, you can choose different ones as follows:
 
 ```bash
 hal9 create my-project --template openai
+hal9 create my-project --template midjourney
 hal9 create my-project --template groq
 hal9 create my-project --template langchain
 ```
 
+A template provides ready to use code with specific technologies and use cases. If you already have code, you can skip this step.
+
 Send a PR if you want to add additional templates.
 
 ## Development
@@ -44,20 +49,29 @@ cd my-project
 pip install -r requirements.txt
 
 export OPENAI_KEY=YOUR_OPENAI_KEY
-python app.py
 ```
 
 If you customized your template with `--template` make sure to set the correct key, for example `export GROQ_KEY=YOUR_GROQ_KEY`.
 
 ## Runtime
 
+Run your application as follows,
+
+```python
+python app.py
+```
+
 Use the command line tool to enter prompts, type `<enter>` twice to send the prompt to your code. Replies will be streamed back to console.
 
-We decided to use a simple chat interface to help AI teams focus what matters: Retrieval Augmented Generation (RAG) workflows. The interactivity and backend can be left to the engineering team or services like Hal9.
+From the parent folder, you can also run your application as follows:
+
+```bash
+hal9 run my-project
+```
 
 ## Deployment
 
-We currently support Docker and Hal9 Cloud, but community can send PR's with additional technologies or providers.
+We currently support Docker and `hal9.com`. Developers can send PR's with additional technologies or providers.
 
 ### Docker
 
@@ -72,8 +86,14 @@ Your backend and frontend engineers can then easily consume this as an API. You
 
 ### Hal9
 
-To deploy to Hal9's cloud run:
+To deploy to `hal9.com` run:
+
+```bash
+hal9 deploy my-project --target hal9.com
+```
+
+When Hal9 runs in your own cloud you can replace `--target hal9.com` with the correct domain, for example:
 
 ```bash
-hal9 deploy my-project --email email@email.com
+hal9 deploy my-project --target hal9.acme.com
 ```

python/hal9/__init__.py

@@ -1 +1 @@
-from hal9.core import *
+from hal9.api import *

python/hal9/api.py

@@ -0,0 +1,56 @@
+import requests
+import time
+import tempfile
+import sys
+import runpy
+
+def create(path :str, template :str) -> str:
+    """Create an application
+
+    Parameters
+    ----------
+    path : str 
+            Path to the application.
+    template : str 
+            The template to use.
+    """
+
+    print(f'Project created! {name}')
+
+def run(path :str) -> str:
+    """Run an application
+
+    Parameters
+    ----------
+    path : str 
+            Path to the application.
+    """
+
+    print(f'Project created! {name}')
+
+def deploy(path :str, target :str) -> str:
+    """Deploy an application
+
+    Parameters
+    ----------
+    path : str 
+            Path to the application.
+    target : str 
+            The deployment target, defaults to 'hal9.com'.
+    """
+
+    response = requests.post('https://api.hal9.com/api/v1/deploy', json = {
+        'name': 'name',
+        'title': 'title',
+        'description': 'description',
+        'access': 'access',
+        'code': 'code',
+        'prompt': 'prompt',
+        'thumbnail': 'thumbnail',
+        'token': 'token',
+        'user': 'user',
+    })
+
+    if not response.ok:
+        print('Failed to deploy')
+        exit()

python/hal9/cli.py

@@ -0,0 +1,50 @@
+import click
+from collections import OrderedDict
+from hal9.api import *
+
+@click.group()
+def cli():
+    """
+    Create and Deploy Generative Applications
+
+    Use this tool to create apps from templates that use Generative AI,
+    run them locally and deploy them to the cloud.
+    """
+    pass
+
+@click.command()
+@click.argument('path')
+def create(path):
+    """
+    Create Project
+
+    PATH: The path for the new project. Required argument.
+    """
+    print(f'Creating: {path}')
+
+@click.command()
+@click.argument('path')
+def run(path):
+    """
+    Run Project
+
+    PATH: The path to the project. Required argument.
+    """
+    print(f'Running {path}')
+
+@click.command()
+@click.argument('path')
+def deploy(path):
+    """
+    Deploy Project
+
+    PATH: The path to the project. Required argument.
+    """
+    print(f'Deploying {path}')
+
+cli.add_command(create)
+cli.add_command(run)
+cli.add_command(deploy)
+
+if __name__ == "__main__":
+    cli()

python/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "hal9"
-version = "2.0.0"
+version = "2.0.1"
 description = ""
 authors = ["Javier Luraschi <[email protected]>"]
 readme = "README.md"
@@ -9,6 +9,10 @@ readme = "README.md"
 python = ">=3.8,<3.9.7 || >3.9.7,<4.0"
 requests = "^2.28.2"
 
+click = "^8.1.7"
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
+
+[tool.poetry.scripts]
+hal9 = "hal9.cli:cli"