Update docs (#17)

timctho · web-flow · commit 658f2f88ee06 · 2024-12-12T12:00:45.000-08:00
diff --git a/README.md b/README.md
@@ -61,6 +61,11 @@ You can run this repo virtually by using GitHub Codespaces, which will open a we
 
 Navigate to the `notebooks` directory and select the sample notebook you are interested in. Since Codespaces is pre-configured with the necessary environment, you can directly execute each step in the notebook.
 
+## More Samples using Azure Content Understanding
+[Azure Search with Content Understanding](https://github.com/Azure-Samples/azure-ai-search-with-content-understanding-python)
+
+[Azure Content Understanding with OpenAI](https://github.com/Azure-Samples/azure-ai-content-understanding-with-azure-openai-python)
+
 ## Notes
 
 * **Trademarks** - This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft trademarks or logos is subject to and must follow [Microsoft's Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks/usage/general). Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship. Any use of third-party trademarks or logos is subject to those third-party’s policies.
diff --git a/notebooks/analyzer_training.ipynb b/notebooks/analyzer_training.ipynb
@@ -49,7 +49,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -93,7 +93,7 @@
     "    endpoint=os.getenv(\"AZURE_AI_ENDPOINT\"),\n",
     "    api_version=os.getenv(\"AZURE_AI_API_VERSION\", \"2024-12-01-preview\"),\n",
     "    token_provider=token_provider,\n",
-    "    x_ms_useragent=\"azure-ai-content-understanding-python/analyzer_training\",\n",
+    "    x_ms_useragent=\"azure-ai-content-understanding-python/analyzer_training\", # This header is used for sample usage telemetry, please comment out this line if you want to opt out.\n",
     ")"
    ]
   },
@@ -109,73 +109,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "INFO:python.content_understanding_client:Analyzer train-sample-18473b27-6d27-4d51-8906-9e341ad3fb59 create request accepted.\n",
-      "INFO:python.content_understanding_client:Request 7a0f7689-2b41-4a5e-96bc-c7ef8cb72c5e in progress ...\n",
-      "INFO:python.content_understanding_client:Request 7a0f7689-2b41-4a5e-96bc-c7ef8cb72c5e in progress ...\n",
-      "INFO:python.content_understanding_client:Request 7a0f7689-2b41-4a5e-96bc-c7ef8cb72c5e in progress ...\n",
-      "INFO:python.content_understanding_client:Request 7a0f7689-2b41-4a5e-96bc-c7ef8cb72c5e in progress ...\n",
-      "INFO:python.content_understanding_client:Request 7a0f7689-2b41-4a5e-96bc-c7ef8cb72c5e in progress ...\n",
-      "INFO:python.content_understanding_client:Request result is ready after 13.72 seconds.\n",
-      "INFO:root:Here is the analyzer detail for train-sample-18473b27-6d27-4d51-8906-9e341ad3fb59\n",
-      "INFO:root:{\n",
-      "  \"id\": \"7a0f7689-2b41-4a5e-96bc-c7ef8cb72c5e\",\n",
-      "  \"status\": \"Succeeded\",\n",
-      "  \"result\": {\n",
-      "    \"analyzerId\": \"train-sample-18473b27-6d27-4d51-8906-9e341ad3fb59\",\n",
-      "    \"description\": \"Extract useful information from purchase order\",\n",
-      "    \"createdAt\": \"2024-12-09T23:58:59Z\",\n",
-      "    \"lastModifiedAt\": \"2024-12-09T23:59:14Z\",\n",
-      "    \"config\": {\n",
-      "      \"returnDetails\": false,\n",
-      "      \"enableOcr\": true,\n",
-      "      \"enableLayout\": true,\n",
-      "      \"enableBarcode\": false,\n",
-      "      \"enableFormula\": false\n",
-      "    },\n",
-      "    \"fieldSchema\": {\n",
-      "      \"fields\": {\n",
-      "        \"PurchaseOrderNumber\": {\n",
-      "          \"type\": \"string\",\n",
-      "          \"method\": \"extract\",\n",
-      "          \"description\": \"\"\n",
-      "        },\n",
-      "        \"PurchaseDate\": {\n",
-      "          \"type\": \"date\",\n",
-      "          \"method\": \"extract\",\n",
-      "          \"description\": \"\"\n",
-      "        },\n",
-      "        \"TotalPayment\": {\n",
-      "          \"type\": \"number\",\n",
-      "          \"method\": \"extract\",\n",
-      "          \"description\": \"\"\n",
-      "        },\n",
-      "        \"ShippedToAddress\": {\n",
-      "          \"type\": \"string\",\n",
-      "          \"method\": \"extract\",\n",
-      "          \"description\": \"\"\n",
-      "        }\n",
-      "      }\n",
-      "    },\n",
-      "    \"trainingData\": {\n",
-      "      \"containerUrl\": \"https://chethodevusw2.blob.core.windows.net/test?sv=2023-01-03&st=2024-12-09T19%3A27%3A04Z&se=2024-12-10T19%3A27%3A04Z&skoid=4de42c4d-0fe6-4b96-93a4-161b1303ea3b&sktid=72f988bf-86f1-41af-91ab-2d7cd011db47&skt=2024-12-09T19%3A27%3A04Z&ske=2024-12-10T19%3A27%3A04Z&sks=b&skv=2023-01-03&sr=c&sp=rl&sig=sbUVLXK2JfJdUG7Fxyakg1e9lR%2B%2B6oMISoZqfudtvgw%3D\",\n",
-      "      \"kind\": \"blob\",\n",
-      "      \"prefix\": \"train\"\n",
-      "    },\n",
-      "    \"warnings\": [],\n",
-      "    \"status\": \"ready\",\n",
-      "    \"scenario\": \"document\"\n",
-      "  }\n",
-      "}\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "import uuid\n",
     "ANALYZER_ID = \"train-sample-\" + str(uuid.uuid4())\n",
@@ -206,101 +142,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "INFO:python.content_understanding_client:Analyzing file ../data/purchase_order.jpg with analyzer: train-sample-18473b27-6d27-4d51-8906-9e341ad3fb59\n",
-      "INFO:python.content_understanding_client:Request dced30f5-bb4d-473b-8b7a-13a7e29ed3ac in progress ...\n",
-      "INFO:python.content_understanding_client:Request dced30f5-bb4d-473b-8b7a-13a7e29ed3ac in progress ...\n",
-      "INFO:python.content_understanding_client:Request result is ready after 5.52 seconds.\n",
-      "INFO:root:{\n",
-      "  \"id\": \"dced30f5-bb4d-473b-8b7a-13a7e29ed3ac\",\n",
-      "  \"status\": \"Succeeded\",\n",
-      "  \"result\": {\n",
-      "    \"analyzerId\": \"train-sample-18473b27-6d27-4d51-8906-9e341ad3fb59\",\n",
-      "    \"apiVersion\": \"2024-12-01-preview\",\n",
-      "    \"createdAt\": \"2024-12-09T23:59:16Z\",\n",
-      "    \"warnings\": [],\n",
-      "    \"contents\": [\n",
-      "      {\n",
-      "        \"markdown\": \"Purchase Order\\n\\n\\n# Hero Limited\\n\\nCompany Phone: 555-348-6512\\nWebsite: www.herolimited.com\\nEmail:\\naccounts@herolimited.com\\n\\nPurchase Order\\n\\nDated As: 12/20/2020\\nPurchase Order #: 948284\\n\\nShipped To\\n\\nVendor Name: Hillary Swank\\nCompany Name: Higgly Wiggly Books\\nAddress: 938 NE Burner Road\\nBoulder City, CO 92848\\nPhone: 938-294-2949\\n\\nShipped From\\n\\nName: Bernie Sanders\\nCompany Name: Jupiter Book Supply\\nAddress: 383 N Kinnick Road\\nSeattle, WA 38383\\n\\nPhone: 932-299-0292\\n\\n\\n<table>\\n<tr>\\n<th>Details</th>\\n<th>Quantity</th>\\n<th>Unit Price</th>\\n<th>Total</th>\\n</tr>\\n<tr>\\n<td>Bindings</td>\\n<td>20</td>\\n<td>1.00</td>\\n<td>20.00</td>\\n</tr>\\n<tr>\\n<td>Covers Small</td>\\n<td>20</td>\\n<td>1.00</td>\\n<td>20.00</td>\\n</tr>\\n<tr>\\n<td>Feather Bookmark</td>\\n<td>20</td>\\n<td>5.00</td>\\n<td>100.00</td>\\n</tr>\\n<tr>\\n<td>Copper Swirl Marker</td>\\n<td>20</td>\\n<td>5.00</td>\\n<td>100.00</td>\\n</tr>\\n</table>\\n\\n\\n<table>\\n<tr>\\n<td>SUBTOTAL</td>\\n<td>$140.00</td>\\n</tr>\\n<tr>\\n<td>TAX</td>\\n<td>$4.00</td>\\n</tr>\\n<tr>\\n<td>TOTAL</td>\\n<td>$144.00</td>\\n</tr>\\n</table>\\n\\n\\nBernie Sanders\\n\\nBernie Sanders\\nManager\\n\\nAdditional Notes:\\n\\nDo not Jostle Box. Unpack carefully. Enjoy.\\n\\nJupiter Book Supply will refund you 50% per book if returned within 60 days of reading and\\n\\noffer you 25% off you next total purchase.\\n\",\n",
-      "        \"fields\": {\n",
-      "          \"PurchaseDate\": {\n",
-      "            \"type\": \"date\",\n",
-      "            \"valueDate\": \"2020-12-20\",\n",
-      "            \"spans\": [\n",
-      "              {\n",
-      "                \"offset\": 149,\n",
-      "                \"length\": 10\n",
-      "              }\n",
-      "            ],\n",
-      "            \"confidence\": 0.998,\n",
-      "            \"source\": \"D(1,1168,418,1318,418,1318,450,1168,450)\"\n",
-      "          },\n",
-      "          \"PurchaseOrderNumber\": {\n",
-      "            \"type\": \"string\",\n",
-      "            \"valueString\": \"948284\",\n",
-      "            \"spans\": [\n",
-      "              {\n",
-      "                \"offset\": 178,\n",
-      "                \"length\": 6\n",
-      "              }\n",
-      "            ],\n",
-      "            \"confidence\": 0.998,\n",
-      "            \"source\": \"D(1,1281,459,1376,459,1376,490,1281,490)\"\n",
-      "          },\n",
-      "          \"ShippedToAddress\": {\n",
-      "            \"type\": \"string\",\n",
-      "            \"valueString\": \"938 NE Burner Road Boulder City, CO 92848\",\n",
-      "            \"spans\": [\n",
-      "              {\n",
-      "                \"offset\": 268,\n",
-      "                \"length\": 18\n",
-      "              },\n",
-      "              {\n",
-      "                \"offset\": 287,\n",
-      "                \"length\": 22\n",
-      "              }\n",
-      "            ],\n",
-      "            \"confidence\": 0.998,\n",
-      "            \"source\": \"D(1,278,683,527,683,527,714,278,714);D(1,279,720,564,720,564,752,279,752)\"\n",
-      "          },\n",
-      "          \"TotalPayment\": {\n",
-      "            \"type\": \"number\",\n",
-      "            \"valueNumber\": 144,\n",
-      "            \"spans\": [\n",
-      "              {\n",
-      "                \"offset\": 991,\n",
-      "                \"length\": 7\n",
-      "              }\n",
-      "            ],\n",
-      "            \"confidence\": 0.997,\n",
-      "            \"source\": \"D(1,1428,1669,1531,1669,1531,1699,1428,1699)\"\n",
-      "          }\n",
-      "        },\n",
-      "        \"kind\": \"document\",\n",
-      "        \"startPageNumber\": 1,\n",
-      "        \"endPageNumber\": 1,\n",
-      "        \"unit\": \"pixel\",\n",
-      "        \"pages\": [\n",
-      "          {\n",
-      "            \"pageNumber\": 1,\n",
-      "            \"angle\": 0.05652412,\n",
-      "            \"width\": 1700,\n",
-      "            \"height\": 2200\n",
-      "          }\n",
-      "        ]\n",
-      "      }\n",
-      "    ]\n",
-      "  }\n",
-      "}\n"
-     ]
-    }
-   ],
+   "outputs": [],
    "source": [
     "response = client.begin_analyze(ANALYZER_ID, file_location='../data/purchase_order.jpg')\n",
     "result = client.poll_result(response)\n",
@@ -318,27 +162,9 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": null,
    "metadata": {},
-   "outputs": [
-    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "INFO:python.content_understanding_client:Analyzer train-sample-18473b27-6d27-4d51-8906-9e341ad3fb59 deleted.\n"
-     ]
-    },
-    {
-     "data": {
-      "text/plain": [
-       "<Response [204]>"
-      ]
-     },
-     "execution_count": 6,
-     "metadata": {},
-     "output_type": "execute_result"
-    }
-   ],
+   "outputs": [],
    "source": [
     "client.delete_analyzer(ANALYZER_ID)"
    ]
diff --git a/notebooks/content_extraction.ipynb b/notebooks/content_extraction.ipynb
@@ -74,7 +74,7 @@
     "    endpoint=AZURE_AI_ENDPOINT,\n",
     "    api_version=AZURE_AI_API_VERSION,\n",
     "    token_provider=token_provider,\n",
-    "    x_ms_useragent=\"azure-ai-content-understanding-python/content_extraction\",\n",
+    "    x_ms_useragent=\"azure-ai-content-understanding-python/content_extraction\", # This header is used for sample usage telemetry, please comment out this line if you want to opt out.\n",
     ")"
    ]
   },
diff --git a/notebooks/field_extraction.ipynb b/notebooks/field_extraction.ipynb
@@ -50,16 +50,16 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
     "extraction_templates = {\n",
-    "    \"invoice\":         ('../analyzer_templates/invoice.json',         '../data/invoice.pdf'            ),\n",
-    "    \"chart\":           ('../analyzer_templates/image_chart.json',     '../data/pieChart.jpg'           ),\n",
-    "    \"call recording analytics\": ('../analyzer_templates/call_recording_analytics.json', '../data/callCenterRecording.mp3'),\n",
-    "    \"conversational audio analytics\": ('../analyzer_templates/conversational_audio_analytics.json', '../data/callCenterRecording.mp3'),\n",
-    "    \"marketing_video\": ('../analyzer_templates/marketing_video.json', '../data/video.mp4'              )\n",
+    "    \"invoice\":            ('../analyzer_templates/invoice.json',         '../data/invoice.pdf'            ),\n",
+    "    \"chart\":              ('../analyzer_templates/image_chart.json',     '../data/pieChart.jpg'           ),\n",
+    "    \"call_recording\":     ('../analyzer_templates/call_recording_analytics.json', '../data/callCenterRecording.mp3'),\n",
+    "    \"conversation_audio\": ('../analyzer_templates/conversational_audio_analytics.json', '../data/callCenterRecording.mp3'),\n",
+    "    \"marketing_video\":    ('../analyzer_templates/marketing_video.json', '../data/video.mp4'              )\n",
     "}"
    ]
   },
@@ -125,7 +125,7 @@
     "    endpoint=AZURE_AI_ENDPOINT,\n",
     "    api_version=AZURE_AI_API_VERSION,\n",
     "    token_provider=token_provider,\n",
-    "    x_ms_useragent=\"azure-ai-content-understanding-python/field_extraction\",\n",
+    "    x_ms_useragent=\"azure-ai-content-understanding-python/field_extraction\", # This header is used for sample usage telemetry, please comment out this line if you want to opt out.\n",
     ")"
    ]
   },
diff --git a/notebooks/management.ipynb b/notebooks/management.ipynb
@@ -73,7 +73,7 @@
     "    endpoint=AZURE_AI_ENDPOINT,\n",
     "    api_version=AZURE_AI_API_VERSION,\n",
     "    token_provider=token_provider,\n",
-    "    x_ms_useragent=\"azure-ai-content-understanding-python/field_extraction\",\n",
+    "    x_ms_useragent=\"azure-ai-content-understanding-python/analyzer_management\", # This header is used for sample usage telemetry, please comment out this line if you want to opt out.\n",
     ")"
    ]
   },

Original file line number	Diff line number	Diff line change
`@@ -74,7 +74,7 @@`
`74`	`74`	`" endpoint=AZURE_AI_ENDPOINT,\n",`
`75`	`75`	`" api_version=AZURE_AI_API_VERSION,\n",`
`76`	`76`	`" token_provider=token_provider,\n",`
`77`		`- " x_ms_useragent=\"azure-ai-content-understanding-python/content_extraction\",\n",`
	`77`	`+ " x_ms_useragent=\"azure-ai-content-understanding-python/content_extraction\", # This header is used for sample usage telemetry, please comment out this line if you want to opt out.\n",`
`78`	`78`	`")"`
`79`	`79`	`]`
`80`	`80`	`},`
Original file line number	Diff line number	Diff line change
`@@ -73,7 +73,7 @@`
`73`	`73`	`" endpoint=AZURE_AI_ENDPOINT,\n",`
`74`	`74`	`" api_version=AZURE_AI_API_VERSION,\n",`
`75`	`75`	`" token_provider=token_provider,\n",`
`76`		`- " x_ms_useragent=\"azure-ai-content-understanding-python/field_extraction\",\n",`
	`76`	`+ " x_ms_useragent=\"azure-ai-content-understanding-python/analyzer_management\", # This header is used for sample usage telemetry, please comment out this line if you want to opt out.\n",`
`77`	`77`	`")"`
`78`	`78`	`]`
`79`	`79`	`},`