|
49 | 49 | },
|
50 | 50 | {
|
51 | 51 | "cell_type": "code",
|
52 |
| - "execution_count": 2, |
| 52 | + "execution_count": null, |
53 | 53 | "metadata": {},
|
54 | 54 | "outputs": [],
|
55 | 55 | "source": [
|
|
109 | 109 | },
|
110 | 110 | {
|
111 | 111 | "cell_type": "code",
|
112 |
| - "execution_count": 4, |
| 112 | + "execution_count": null, |
113 | 113 | "metadata": {},
|
114 |
| - "outputs": [ |
115 |
| - { |
116 |
| - "name": "stderr", |
117 |
| - "output_type": "stream", |
118 |
| - "text": [ |
119 |
| - "INFO:python.content_understanding_client:Analyzer train-sample-18473b27-6d27-4d51-8906-9e341ad3fb59 create request accepted.\n", |
120 |
| - "INFO:python.content_understanding_client:Request 7a0f7689-2b41-4a5e-96bc-c7ef8cb72c5e in progress ...\n", |
121 |
| - "INFO:python.content_understanding_client:Request 7a0f7689-2b41-4a5e-96bc-c7ef8cb72c5e in progress ...\n", |
122 |
| - "INFO:python.content_understanding_client:Request 7a0f7689-2b41-4a5e-96bc-c7ef8cb72c5e in progress ...\n", |
123 |
| - "INFO:python.content_understanding_client:Request 7a0f7689-2b41-4a5e-96bc-c7ef8cb72c5e in progress ...\n", |
124 |
| - "INFO:python.content_understanding_client:Request 7a0f7689-2b41-4a5e-96bc-c7ef8cb72c5e in progress ...\n", |
125 |
| - "INFO:python.content_understanding_client:Request result is ready after 13.72 seconds.\n", |
126 |
| - "INFO:root:Here is the analyzer detail for train-sample-18473b27-6d27-4d51-8906-9e341ad3fb59\n", |
127 |
| - "INFO:root:{\n", |
128 |
| - " \"id\": \"7a0f7689-2b41-4a5e-96bc-c7ef8cb72c5e\",\n", |
129 |
| - " \"status\": \"Succeeded\",\n", |
130 |
| - " \"result\": {\n", |
131 |
| - " \"analyzerId\": \"train-sample-18473b27-6d27-4d51-8906-9e341ad3fb59\",\n", |
132 |
| - " \"description\": \"Extract useful information from purchase order\",\n", |
133 |
| - " \"createdAt\": \"2024-12-09T23:58:59Z\",\n", |
134 |
| - " \"lastModifiedAt\": \"2024-12-09T23:59:14Z\",\n", |
135 |
| - " \"config\": {\n", |
136 |
| - " \"returnDetails\": false,\n", |
137 |
| - " \"enableOcr\": true,\n", |
138 |
| - " \"enableLayout\": true,\n", |
139 |
| - " \"enableBarcode\": false,\n", |
140 |
| - " \"enableFormula\": false\n", |
141 |
| - " },\n", |
142 |
| - " \"fieldSchema\": {\n", |
143 |
| - " \"fields\": {\n", |
144 |
| - " \"PurchaseOrderNumber\": {\n", |
145 |
| - " \"type\": \"string\",\n", |
146 |
| - " \"method\": \"extract\",\n", |
147 |
| - " \"description\": \"\"\n", |
148 |
| - " },\n", |
149 |
| - " \"PurchaseDate\": {\n", |
150 |
| - " \"type\": \"date\",\n", |
151 |
| - " \"method\": \"extract\",\n", |
152 |
| - " \"description\": \"\"\n", |
153 |
| - " },\n", |
154 |
| - " \"TotalPayment\": {\n", |
155 |
| - " \"type\": \"number\",\n", |
156 |
| - " \"method\": \"extract\",\n", |
157 |
| - " \"description\": \"\"\n", |
158 |
| - " },\n", |
159 |
| - " \"ShippedToAddress\": {\n", |
160 |
| - " \"type\": \"string\",\n", |
161 |
| - " \"method\": \"extract\",\n", |
162 |
| - " \"description\": \"\"\n", |
163 |
| - " }\n", |
164 |
| - " }\n", |
165 |
| - " },\n", |
166 |
| - " \"trainingData\": {\n", |
167 |
| - " \"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", |
168 |
| - " \"kind\": \"blob\",\n", |
169 |
| - " \"prefix\": \"train\"\n", |
170 |
| - " },\n", |
171 |
| - " \"warnings\": [],\n", |
172 |
| - " \"status\": \"ready\",\n", |
173 |
| - " \"scenario\": \"document\"\n", |
174 |
| - " }\n", |
175 |
| - "}\n" |
176 |
| - ] |
177 |
| - } |
178 |
| - ], |
| 114 | + "outputs": [], |
179 | 115 | "source": [
|
180 | 116 | "import uuid\n",
|
181 | 117 | "ANALYZER_ID = \"train-sample-\" + str(uuid.uuid4())\n",
|
|
206 | 142 | },
|
207 | 143 | {
|
208 | 144 | "cell_type": "code",
|
209 |
| - "execution_count": 5, |
| 145 | + "execution_count": null, |
210 | 146 | "metadata": {},
|
211 |
| - "outputs": [ |
212 |
| - { |
213 |
| - "name": "stderr", |
214 |
| - "output_type": "stream", |
215 |
| - "text": [ |
216 |
| - "INFO:python.content_understanding_client:Analyzing file ../data/purchase_order.jpg with analyzer: train-sample-18473b27-6d27-4d51-8906-9e341ad3fb59\n", |
217 |
| - "INFO:python.content_understanding_client:Request dced30f5-bb4d-473b-8b7a-13a7e29ed3ac in progress ...\n", |
218 |
| - "INFO:python.content_understanding_client:Request dced30f5-bb4d-473b-8b7a-13a7e29ed3ac in progress ...\n", |
219 |
| - "INFO:python.content_understanding_client:Request result is ready after 5.52 seconds.\n", |
220 |
| - "INFO:root:{\n", |
221 |
| - " \"id\": \"dced30f5-bb4d-473b-8b7a-13a7e29ed3ac\",\n", |
222 |
| - " \"status\": \"Succeeded\",\n", |
223 |
| - " \"result\": {\n", |
224 |
| - " \"analyzerId\": \"train-sample-18473b27-6d27-4d51-8906-9e341ad3fb59\",\n", |
225 |
| - " \"apiVersion\": \"2024-12-01-preview\",\n", |
226 |
| - " \"createdAt\": \"2024-12-09T23:59:16Z\",\n", |
227 |
| - " \"warnings\": [],\n", |
228 |
| - " \"contents\": [\n", |
229 |
| - " {\n", |
230 |
| - " \"markdown\": \"Purchase Order\\n\\n\\n# Hero Limited\\n\\nCompany Phone: 555-348-6512\\nWebsite: www.herolimited.com\\nEmail:\\ [email protected]\\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", |
231 |
| - " \"fields\": {\n", |
232 |
| - " \"PurchaseDate\": {\n", |
233 |
| - " \"type\": \"date\",\n", |
234 |
| - " \"valueDate\": \"2020-12-20\",\n", |
235 |
| - " \"spans\": [\n", |
236 |
| - " {\n", |
237 |
| - " \"offset\": 149,\n", |
238 |
| - " \"length\": 10\n", |
239 |
| - " }\n", |
240 |
| - " ],\n", |
241 |
| - " \"confidence\": 0.998,\n", |
242 |
| - " \"source\": \"D(1,1168,418,1318,418,1318,450,1168,450)\"\n", |
243 |
| - " },\n", |
244 |
| - " \"PurchaseOrderNumber\": {\n", |
245 |
| - " \"type\": \"string\",\n", |
246 |
| - " \"valueString\": \"948284\",\n", |
247 |
| - " \"spans\": [\n", |
248 |
| - " {\n", |
249 |
| - " \"offset\": 178,\n", |
250 |
| - " \"length\": 6\n", |
251 |
| - " }\n", |
252 |
| - " ],\n", |
253 |
| - " \"confidence\": 0.998,\n", |
254 |
| - " \"source\": \"D(1,1281,459,1376,459,1376,490,1281,490)\"\n", |
255 |
| - " },\n", |
256 |
| - " \"ShippedToAddress\": {\n", |
257 |
| - " \"type\": \"string\",\n", |
258 |
| - " \"valueString\": \"938 NE Burner Road Boulder City, CO 92848\",\n", |
259 |
| - " \"spans\": [\n", |
260 |
| - " {\n", |
261 |
| - " \"offset\": 268,\n", |
262 |
| - " \"length\": 18\n", |
263 |
| - " },\n", |
264 |
| - " {\n", |
265 |
| - " \"offset\": 287,\n", |
266 |
| - " \"length\": 22\n", |
267 |
| - " }\n", |
268 |
| - " ],\n", |
269 |
| - " \"confidence\": 0.998,\n", |
270 |
| - " \"source\": \"D(1,278,683,527,683,527,714,278,714);D(1,279,720,564,720,564,752,279,752)\"\n", |
271 |
| - " },\n", |
272 |
| - " \"TotalPayment\": {\n", |
273 |
| - " \"type\": \"number\",\n", |
274 |
| - " \"valueNumber\": 144,\n", |
275 |
| - " \"spans\": [\n", |
276 |
| - " {\n", |
277 |
| - " \"offset\": 991,\n", |
278 |
| - " \"length\": 7\n", |
279 |
| - " }\n", |
280 |
| - " ],\n", |
281 |
| - " \"confidence\": 0.997,\n", |
282 |
| - " \"source\": \"D(1,1428,1669,1531,1669,1531,1699,1428,1699)\"\n", |
283 |
| - " }\n", |
284 |
| - " },\n", |
285 |
| - " \"kind\": \"document\",\n", |
286 |
| - " \"startPageNumber\": 1,\n", |
287 |
| - " \"endPageNumber\": 1,\n", |
288 |
| - " \"unit\": \"pixel\",\n", |
289 |
| - " \"pages\": [\n", |
290 |
| - " {\n", |
291 |
| - " \"pageNumber\": 1,\n", |
292 |
| - " \"angle\": 0.05652412,\n", |
293 |
| - " \"width\": 1700,\n", |
294 |
| - " \"height\": 2200\n", |
295 |
| - " }\n", |
296 |
| - " ]\n", |
297 |
| - " }\n", |
298 |
| - " ]\n", |
299 |
| - " }\n", |
300 |
| - "}\n" |
301 |
| - ] |
302 |
| - } |
303 |
| - ], |
| 147 | + "outputs": [], |
304 | 148 | "source": [
|
305 | 149 | "response = client.begin_analyze(ANALYZER_ID, file_location='../data/purchase_order.jpg')\n",
|
306 | 150 | "result = client.poll_result(response)\n",
|
|
318 | 162 | },
|
319 | 163 | {
|
320 | 164 | "cell_type": "code",
|
321 |
| - "execution_count": 6, |
| 165 | + "execution_count": null, |
322 | 166 | "metadata": {},
|
323 |
| - "outputs": [ |
324 |
| - { |
325 |
| - "name": "stderr", |
326 |
| - "output_type": "stream", |
327 |
| - "text": [ |
328 |
| - "INFO:python.content_understanding_client:Analyzer train-sample-18473b27-6d27-4d51-8906-9e341ad3fb59 deleted.\n" |
329 |
| - ] |
330 |
| - }, |
331 |
| - { |
332 |
| - "data": { |
333 |
| - "text/plain": [ |
334 |
| - "<Response [204]>" |
335 |
| - ] |
336 |
| - }, |
337 |
| - "execution_count": 6, |
338 |
| - "metadata": {}, |
339 |
| - "output_type": "execute_result" |
340 |
| - } |
341 |
| - ], |
| 167 | + "outputs": [], |
342 | 168 | "source": [
|
343 | 169 | "client.delete_analyzer(ANALYZER_ID)"
|
344 | 170 | ]
|
|
0 commit comments