Code to access data

notebooks/ocr_azure_functions.ipynb

@@ -0,0 +1,182 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Step 1: download azure cli\n",
+    "\n",
+    "https://learn.microsoft.com/en-us/cli/azure/install-azure-cli\n",
+    "\n",
+    "# Step 2: Log in with az login \n",
+    "\n",
+    "https://learn.microsoft.com/en-us/cli/azure/authenticate-azure-cli"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Step 3: Create python virtual env we have 3.10\n",
+    "Packages:\n",
+    "\n",
+    "azure-common==1.1.28\n",
+    "\n",
+    "azure-core==1.26.1\n",
+    "\n",
+    "azure-identity==1.12.0\n",
+    "\n",
+    "azure-keyvault==4.2.0\n",
+    "\n",
+    "azure-keyvault-secrets==4.6.0\n",
+    "\n",
+    "azure-storage-blob==12.14.1"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "outputs": [],
+   "source": [
+    "!pip install azure-common==1.1.28\n",
+    "\n",
+    "!pip install azure-core==1.26.1\n",
+    "\n",
+    "!pip install azure-identity==1.12.0\n",
+    "\n",
+    "!pip install azure-keyvault==4.2.0\n",
+    "\n",
+    "!pip install azure-keyvault-secrets==4.6.0\n",
+    "\n",
+    "!pip install azure-storage-blob==12.14.1"
+   ],
+   "metadata": {
+    "collapsed": false
+   }
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-06-06T14:37:38.121268100Z",
+     "start_time": "2024-06-06T14:37:35.422323400Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "from azure.keyvault.secrets import SecretClient\n",
+    "from azure.storage.blob import BlobClient, BlobServiceClient\n",
+    "from azure.identity import DefaultAzureCredential, AzureCliCredential\n",
+    "import sys\n",
+    "\n",
+    "\n",
+    "keyvault_url = 'https://<keyvault name virginia>.vault.azure.net/'\n",
+    "secret_name = '<value given by virginia>'\n",
+    "\n",
+    "def get_az_credential():\n",
+    "    \"\"\"Obtains an Azure credential, based on the environment you run from (Linux, Windows (local vs DSVM))\n",
+    "    \n",
+    "    Parameters:\n",
+    "    None\n",
+    "    \n",
+    "    Returns:\n",
+    "    - Credential: Credential for connecting to Azure\n",
+    "    \"\"\"\n",
+    "    credential = AzureCliCredential()\n",
+    "    \n",
+    "    return credential\n",
+    "\n",
+    "# Connect to keyvault and fetch secret\n",
+    "def get_keyvault_secret(keyvault_url,secret_name, credential):\n",
+    "    \"\"\"Get a secret from the keyvault\n",
+    "    \n",
+    "    Parameters:\n",
+    "    - keyvault_url (string): The URL of the storage account.\n",
+    "    - secret_name (string): The name of the container in the storage account.\n",
+    "    - credential (object): The credentials to be used for authentication.\n",
+    "    \n",
+    "    Returns:\n",
+    "    - String containing the secret\n",
+    "    \"\"\"\n",
+    "    client = SecretClient(vault_url=keyvault_url, credential=credential)\n",
+    "    return client.get_secret(secret_name)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "metadata": {
+    "ExecuteTime": {
+     "end_time": "2024-06-06T14:06:26.863901Z",
+     "start_time": "2024-06-06T14:06:25.605394700Z"
+    }
+   },
+   "outputs": [],
+   "source": [
+    "credential = get_az_credential()\n",
+    "storage_account_key = get_keyvault_secret(keyvault_url, secret_name , credential)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from azure.storage.blob import BlobServiceClient\n",
+    "def list_blobs_in_container(storage_account_name, storage_account_key, container_name):\n",
+    "    try:\n",
+    "        # Construct the connection string\n",
+    "        connection_string = f\"DefaultEndpointsProtocol=https;AccountName={storage_account_name};AccountKey={storage_account_key.value};EndpointSuffix=core.windows.net\"\n",
+    "        \n",
+    "        # Create the BlobServiceClient object\n",
+    "        blob_service_client = BlobServiceClient.from_connection_string(connection_string)\n",
+    "\n",
+    "        # Get the container client\n",
+    "        container_client = blob_service_client.get_container_client(container_name)\n",
+    "\n",
+    "        # List blobs in the container\n",
+    "        blob_list = container_client.list_blobs()\n",
+    "        \n",
+    "        print(f\"Blobs in container '{container_name}':\")\n",
+    "        for blob in blob_list:\n",
+    "            print(f\"\\t{blob.name}\")\n",
+    "\n",
+    "    except Exception as ex:\n",
+    "        print(f\"Exception: {ex}\")\n",
+    "\n",
+    "# Example usage\n",
+    "storage_account_name = \"<account name from slack>\"  \n",
+    "container_name = \"<container name from slack>\"\n",
+    "\n",
+    "list_blobs_in_container(storage_account_name, storage_account_key, container_name)"
+   ]
+  }
+ ],
+ "metadata": {
+  "interpreter": {
+   "hash": "07354bbab23bd1645e2425723804091b7787c8b9f736ba6e074695e88a25cd31"
+  },
+  "kernelspec": {
+   "display_name": "Python 3.10.10 ('fenv': venv)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.10"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

pyproject.toml

@@ -22,10 +22,12 @@ classifiers = [
 
 # All the dependencies needed for running your module go here
 dependencies = [
-    "dvc>=2.42.0",
-    "numpy",
-    "pandas",
-    "scikit-learn",
+    "azure-common==1.1.28",
+    "azure-core==1.26.1",
+    "azure-identity==1.12.0",
+    "azure-keyvault==4.2.0",
+    "azure-keyvault-secrets==4.6.0",
+    "azure-storage-blob==12.14.1",
 ]
 
 [project.optional-dependencies]