Merge pull request #1 from DennisTraub/main

Python Foundation Model (FM) Playground

.gitignore

@@ -0,0 +1,5 @@
+.idea/
+.vscode/
+__pycache__/
+
+**/venv/

README.md

@@ -1,17 +1,102 @@
-## My Project
+# 🐍 Python FM Playground
 
-TODO: Fill this README out!
+Welcome to the Python Foundation Model (FM) Playground, an example app to explore how to use **Amazon Bedrock** with boto3, the AWS SDK for Python.
 
-Be sure to:
+> 🚨 **Important:** This application is for educational purposes and not intended for production use.
 
-* Change the title in this README
-* Edit your repository description on GitHub
+## Overview
 
-## Security
+This repository includes a **FastAPI** application and a **Next.js** frontend, both executable locally. Below is a screenshot of the app in action.
 
-See [CONTRIBUTING](CONTRIBUTING.md#security-issue-notifications) for more information.
+
+<img src="screenshot.png" alt="Screenshot of the Python FM Playground" width="720" />
+
+## Prerequisites
+
+Ensure you have the following installed:
+
+- [Python 3.8+](https://www.python.org/downloads/) with pip
+- [Node.js (v18.17+)](https://docs.npmjs.com/downloading-and-installing-node-js-and-npm) with npm (for the Next.js frontend)
+- An [AWS account](https://aws.amazon.com/free/) with permissions to access Amazon Bedrock
+- To use Bedrock, you must [enable access](https://docs.aws.amazon.com/bedrock/latest/userguide/model-access.html#add-model-access) to at least the following models in `us-east-1`: 
+  1. Anthropic: Claude
+  2. Stability AI: Stable Diffusion XL
+
+## Running the Application
+
+After verifying the prerequisites, follow these steps:
+
+### Clone the repository
+
+Open a terminal, navigate to a directory of your choice, and execute the following command:
+
+```shell
+git clone https://github.com/build-on-aws/python-fm-playground.git
+```
+
+### Backend Setup
+
+**Note:** It's a good practice to use a virtual environment for your Python projects to manage dependencies separately for each project. If you're not already in a virtual environment, [you can create one and then install your packages there](https://packaging.python.org/en/latest/guides/installing-using-pip-and-virtual-environments/).
+
+In the `python-fm-playground/backend` directory, run:
+
+```shell
+pip install -r requirements.txt
+python main.py
+```
+
+> 🛠 The backend runs on port 55500 by default. See below for port changes.
+
+### Frontent Setup
+
+In a new terminal window, navigate to `python-fm-playground/frontend` and execute:
+
+```shell
+npm install
+npm run dev
+```
+
+> 🛠 The frontend runs on port 3000 by default. See below for port changes.
+
+## Accessing the Application
+
+Open `http://localhost:3000` in your web browser to interact with the application.
+
+## Stopping the Application
+
+To halt the application, you will need to stop both the backend and frontend processes.
+
+### Stopping the Frontend
+
+In the terminal where the frontend is running, press `Ctrl + C` to terminate the process.
+
+### Stopping the Backend
+
+Similarly, in the backend terminal, use the `Ctrl + C` shortcut to stop the server.
+
+If you encounter any issues, you can forcefully terminate the processes by finding the process ID (`PID`) and using the `kill` command on Unix-based systems or Task Manager on Windows.
+
+
+## Using Different Ports
+
+Change the backend port in the following files:
+- `backend/config.py`
+- `frontend/app/app.config.js`
+
+To run the frontend on a different port:
+
+```shell
+npm run dev -- --port NEW_PORT
+```
+
+## Troubleshooting
+
+The AWS Region is hard-coded in the application. However, if your local `AWS_REGION` environment variable is set to a different region, the application may fail. In this case, please make sure to either unset `AWS_REGION`, or set it to `us-east-1`.
 
 ## License
 
-This library is licensed under the MIT-0 License. See the LICENSE file.
+This library is licensed under the MIT-0 License. See the [LICENSE](LICENSE) file.
+
+## Security
 
+See [CONTRIBUTING](CONTRIBUTING.md#security-issue-notifications) for more information.

backend/.gitignore

@@ -0,0 +1,155 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+.idea/

backend/chat_playground/models.py

@@ -0,0 +1,7 @@
+from pydantic import BaseModel
+
+class ChatRequest(BaseModel):
+    prompt: str
+
+class ChatResponse(BaseModel):
+    completion: str

backend/chat_playground/routes.py

@@ -0,0 +1,14 @@
+from fastapi import APIRouter
+from . import models
+from . import services
+
+router = APIRouter()
+
+
+@router.post("/foundation-models/model/chat/anthropic.claude-v2/invoke")
+def invoke(body: models.ChatRequest):
+    completion = services.invoke(body.prompt)
+
+    return models.ChatResponse(
+        completion=completion
+    )

backend/chat_playground/services.py

@@ -0,0 +1,31 @@
+import boto3
+import json
+
+bedrock_runtime = boto3.client(
+    service_name="bedrock-runtime",
+    region_name="us-east-1",
+)
+
+def invoke(prompt):
+
+    systemPrompt = """
+                    Take the role of a friendly chat bot. Your responses are brief.
+                    You sometimes use emojis where appropriate, but you don't overdo it.
+                    You engage human in a dialog by regularly asking questions,
+                    except when Human indicates that the conversation is over.
+                   """;
+
+    prompt_config = {
+        "prompt": f'\n\nHuman: {systemPrompt}\n\n{prompt}\n\nAssistant:',
+        "max_tokens_to_sample": 1024,
+        "temperature": 0.8
+    }
+
+    response = bedrock_runtime.invoke_model(
+        body=json.dumps(prompt_config),
+        modelId="anthropic.claude-v2"
+    )
+
+    response_body = json.loads(response.get("body").read())
+
+    return response_body.get("completion")

backend/config.py

@@ -0,0 +1,7 @@
+HOST = "0.0.0.0"
+PORT = 55500
+
+# Enable CORS for all domains, remember to change this for production purposes
+ALLOWED_CORS_ORIGINS = [ "*" ]
+ALLOWED_CORS_HEADERS = [ "*" ]
+ALLOWED_CORS_METHODS = [ "GET", "POST" ]

backend/foundation_models/routes.py

@@ -0,0 +1,12 @@
+from fastapi import APIRouter
+from . import service
+
+router = APIRouter()
+
+@router.get("/foundation-models")
+def list_foundation_models():
+    return service.list_foundation_models()
+
+@router.get("/foundation-models/model/{model_id}")
+def get_foundation_model_details(model_id: str):
+    return service.get_foundation_model(model_id)

backend/foundation_models/service.py

@@ -0,0 +1,21 @@
+import boto3
+
+
+bedrock_client = boto3.client(
+    service_name="bedrock",
+    region_name="us-east-1"
+)
+
+
+def list_foundation_models():
+    response = bedrock_client.list_foundation_models()
+
+    return response['modelSummaries']
+
+
+def get_foundation_model(model_id):
+    response = bedrock_client.get_foundation_model(
+        modelIdentifier=model_id
+    )
+
+    return response['modelDetails']

backend/image_playground/models.py

@@ -0,0 +1,8 @@
+from pydantic import BaseModel
+
+class ImageRequest(BaseModel):
+    prompt: str
+    stylePreset: str
+
+# class ImageResponse(BaseModel):
+#     imageByteArray: bytes