Framework/Gradio: Add basic example about Gradio, reading sys.summits

Author: amotl

.github/dependabot.yml

@@ -80,6 +80,11 @@ updates:
     schedule:
       interval: "daily"
 
+  - directory: "/framework/gradio"
+    package-ecosystem: "pip"
+    schedule:
+      interval: "daily"
+
   - directory: "/framework/streamlit"
     package-ecosystem: "pip"
     schedule:

.github/workflows/framework-gradio.yml

@@ -0,0 +1,74 @@
+name: Gradio
+
+on:
+  pull_request:
+    branches: ~
+    paths:
+    - '.github/workflows/framework-gradio.yml'
+    - 'framework/gradio/**'
+    - '/requirements.txt'
+  push:
+    branches: [ main ]
+    paths:
+    - '.github/workflows/framework-gradio.yml'
+    - 'framework/gradio/**'
+    - '/requirements.txt'
+
+  # Allow job to be triggered manually.
+  workflow_dispatch:
+
+  # Run job each night after CrateDB nightly has been published.
+  schedule:
+    - cron: '0 3 * * *'
+
+# Cancel in-progress jobs when pushing to the same branch.
+concurrency:
+  cancel-in-progress: true
+  group: ${{ github.workflow }}-${{ github.ref }}
+
+jobs:
+  test:
+    name: "
+     Python: ${{ matrix.python-version }}
+     CrateDB: ${{ matrix.cratedb-version }}
+     on ${{ matrix.os }}"
+    runs-on: ${{ matrix.os }}
+    strategy:
+      fail-fast: false
+      matrix:
+        os: [ 'ubuntu-latest' ]
+        python-version: [ '3.10', '3.11', '3.12' ]
+        cratedb-version: [ 'nightly' ]
+
+    services:
+      cratedb:
+        image: crate/crate:${{ matrix.cratedb-version }}
+        ports:
+          - 4200:4200
+          - 5432:5432
+        env:
+          CRATE_HEAP_SIZE: 4g
+
+    steps:
+
+      - name: Acquire sources
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: ${{ matrix.python-version }}
+          architecture: x64
+          cache: 'pip'
+          cache-dependency-path: |
+            requirements.txt
+            framework/gradio/requirements.txt
+            framework/gradio/requirements-dev.txt
+
+      - name: Install utilities
+        run: |
+          pip install -r requirements.txt
+
+      - name: Validate framework/gradio
+        run: |
+          ngr test --accept-no-venv framework/gradio

framework/gradio/.gitignore

@@ -0,0 +1 @@
+/flagged

framework/gradio/README.md

@@ -0,0 +1,62 @@
+# Gradio with CrateDB Example
+
+## About
+Demonstrate connectivity from Gradio to CrateDB.
+
+## Configuration
+Configure database connection address and credentials by using
+an SQLAlchemy connection string, see variable `CRATEDB_SQLALCHEMY_URL`
+in `basic_sys_summits.py`. Please make sure to use valid credentials
+matching your environment.
+
+## Usage
+
+### CrateDB on localhost
+To start a CrateDB instance on your machine, invoke:
+```shell
+docker run -it --rm \
+  --publish=4200:4200 --publish=5432:5432 \
+  --env=CRATE_HEAP_SIZE=2g \
+  crate:latest -Cdiscovery.type=single-node
+```
+
+### CrateDB Cloud
+Please have a look at the [basic_sys_summits.py](basic_sys_summits.py) program
+as a blueprint. It includes a `CRATEDB_SQLALCHEMY_URL` variable definition
+that configures the application to connect to CrateDB Cloud.
+```python
+CRATEDB_SQLALCHEMY_URL = "crate://admin:g_,8.F0fNbVSk0.*!n54S5c,@example.gke1.us-central1.gcp.cratedb.net:4200?ssl=true"```
+```
+
+Install dependencies.
+```shell
+pip install -r requirements.txt
+```
+
+Invoke Gradio to serve the application.
+```shell
+gradio basic_sys_summits.py
+```
+
+## Screenshot
+
+Enjoy the list of mountains.
+
+![image](https://github.com/crate/cratedb-examples/assets/453543/af417966-b694-45ec-9391-f0e99a2ac014)
+
+
+## Development
+
+Acquire `cratedb-example` repository, and set up development sandbox.
+```shell
+git clone https://github.com/crate/cratedb-examples
+cd cratedb-examples
+python3 -m venv .venv
+source .venv/bin/activate
+pip install -r requirements.txt
+```
+
+Invoke the integration test cases.
+```shell
+ngr test framework/gradio
+```

framework/gradio/basic_sys_summits.py

@@ -0,0 +1,48 @@
+"""
+A basic Gradio application connecting to CrateDB using SQLAlchemy.
+
+It reads the built-in `sys.summits` table into a dataframe, and
+displays its contents.
+
+- https://www.gradio.app/guides/connecting-to-a-database
+- https://www.gradio.app/docs/gradio/dataframe
+- https://cratedb.com/docs/sqlalchemy-cratedb/
+"""
+import gradio as gr
+import pandas as pd
+
+# Connect to CrateDB on localhost.
+CRATEDB_SQLALCHEMY_URL = "crate://localhost:4200"
+
+# Connect to CrateDB Cloud.
+# CRATEDB_SQLALCHEMY_URL = "crate://admin:g_,8.F0fNbVSk0.*!n54S5c,@example.gke1.us-central1.gcp.cratedb.net:4200?ssl=true"
+
+
+def get_sys_summits():
+    """
+    Query the database using pandas.
+    """
+    return pd.read_sql('SELECT * FROM "sys"."summits";', con=CRATEDB_SQLALCHEMY_URL)
+
+
+def get_dataframe():
+    """
+    Create a dataframe widget.
+    """
+    df = get_sys_summits()
+    return gr.DataFrame(df)
+
+
+# Define the Gradio interface.
+demo = gr.Interface(
+    fn=get_dataframe,
+    inputs=[],
+    outputs=["dataframe"],
+    title="Gradio with CrateDB Example",
+    live=True,
+    allow_flagging="never",
+)
+
+
+if __name__ == "__main__":
+    demo.launch()

framework/gradio/pyproject.toml

@@ -0,0 +1,12 @@
+[tool.pytest.ini_options]
+minversion = "2.0"
+addopts = """
+  -rfEX -p pytester --strict-markers --verbosity=3
+  --capture=no
+  """
+log_level = "DEBUG"
+log_cli_level = "DEBUG"
+testpaths = ["*.py"]
+xfail_strict = true
+markers = [
+]

framework/gradio/requirements-dev.txt

@@ -0,0 +1,2 @@
+gradio-client==1.0.*
+pytest<9

framework/gradio/requirements.txt

@@ -0,0 +1,2 @@
+gradio==4.*
+sqlalchemy-cratedb==0.38.0

framework/gradio/test.py

@@ -0,0 +1,84 @@
+import logging
+import shlex
+import subprocess
+import sys
+import threading
+import time
+from urllib.error import HTTPError
+from urllib.request import urlopen
+
+import pytest
+from gradio_client import Client
+
+
+logger = logging.getLogger()
+
+GRADIO_SERVER_PORT = "7861"
+GRADIO_API_URL = f"http://localhost:{GRADIO_SERVER_PORT}"
+
+
+def run(command: str, env=None, timeout: int = None):
+    """
+    Invoke a command in a subprocess.
+    """
+    env = env or {}
+    env["PATH"] = ""
+    subprocess.call(shlex.split(command), env=env, timeout=timeout)
+
+
+def check_url(url):
+    """
+    Check if a service is reachable.
+
+    Makes a simple GET request to path of the HTTP endpoint. Service is
+    available if returned status code is < 500.
+    """
+    try:
+        r = urlopen(url)
+        return r.code < 500
+    except HTTPError as e:
+        # If service returns e.g. a 404 it's ok
+        return e.code < 500
+    except Exception:
+        # Possible service not yet started
+        return False
+
+
+@pytest.fixture(scope="session", autouse=True)
+def run_server():
+
+    def server_thread():
+        print("sys.exec:", sys.executable)
+        try:
+            run(f"{sys.executable} basic_sys_summits.py", env={"GRADIO_SERVER_PORT": GRADIO_SERVER_PORT}, timeout=5)
+        except subprocess.TimeoutExpired:
+            pass
+
+    thread = threading.Thread(target=server_thread)
+    try:
+        thread.start()
+    except KeyboardInterrupt:
+        pass
+
+    while not check_url(GRADIO_API_URL):
+        logger.info("Waiting for Gradio API to come up")
+        time.sleep(0.2)
+
+
+def test_read_sys_summits():
+    """
+    Verify reading CrateDB's built-in `sys.summits` database table through the Gradio API.
+
+    - https://www.gradio.app/guides/getting-started-with-the-python-client
+    - https://www.gradio.app/docs/python-client/
+    - https://www.gradio.app/docs/gradio/dataframe
+    """
+
+    # Connect to Gradio API, and submit a request.
+    client = Client(GRADIO_API_URL)
+    result = client.predict(api_name="/predict")
+
+    # Verify result.
+    assert "mountain" in result["value"]["headers"]
+    assert len(result["value"]["data"]) > 80
+    assert result["value"]["data"][0][5] == "Mont Blanc"