|
188 | 188 | }, |
189 | 189 | { |
190 | 190 | "cell_type": "code", |
191 | | - "execution_count": 3, |
| 191 | + "execution_count": 2, |
192 | 192 | "metadata": {}, |
193 | 193 | "outputs": [ |
194 | 194 | { |
195 | 195 | "data": { |
196 | 196 | "text/plain": [ |
197 | | - "<clarifai_datautils.multimodal.pipeline.base.Pipeline at 0x2e35a5810>" |
| 197 | + "<clarifai_datautils.multimodal.pipeline.base.Pipeline at 0x2deee6b60>" |
198 | 198 | ] |
199 | 199 | }, |
200 | | - "execution_count": 3, |
| 200 | + "execution_count": 2, |
201 | 201 | "metadata": {}, |
202 | 202 | "output_type": "execute_result" |
203 | 203 | } |
|
347 | 347 | }, |
348 | 348 | { |
349 | 349 | "cell_type": "code", |
350 | | - "execution_count": 4, |
| 350 | + "execution_count": 3, |
351 | 351 | "metadata": {}, |
352 | 352 | "outputs": [ |
353 | 353 | { |
354 | 354 | "name": "stderr", |
355 | 355 | "output_type": "stream", |
356 | 356 | "text": [ |
357 | | - "Applying Transformations: 100%|██████████| 3/3 [01:46<00:00, 35.57s/it]\n", |
358 | | - "Uploading Dataset: 100%|██████████| 2/2 [00:29<00:00, 14.69s/it]\n" |
| 357 | + "Applying Transformations: 33%|███▎ | 1/3 [00:08<00:16, 8.04s/it]" |
| 358 | + ] |
| 359 | + }, |
| 360 | + { |
| 361 | + "name": "stdout", |
| 362 | + "output_type": "stream", |
| 363 | + "text": [ |
| 364 | + "2\n", |
| 365 | + "dict_keys(['detection_class_prob', 'coordinates', 'last_modified', 'filetype', 'languages', 'page_number', 'image_base64', 'image_mime_type', 'file_directory', 'filename', 'is_original', 'input_id'])\n", |
| 366 | + "dict_keys(['detection_class_prob', 'coordinates', 'last_modified', 'filetype', 'languages', 'page_number', 'image_base64', 'image_mime_type', 'file_directory', 'filename', 'is_original', 'input_id'])\n" |
| 367 | + ] |
| 368 | + }, |
| 369 | + { |
| 370 | + "name": "stderr", |
| 371 | + "output_type": "stream", |
| 372 | + "text": [ |
| 373 | + "Applying Transformations: 100%|██████████| 3/3 [00:44<00:00, 14.69s/it]\n" |
| 374 | + ] |
| 375 | + }, |
| 376 | + { |
| 377 | + "name": "stdout", |
| 378 | + "output_type": "stream", |
| 379 | + "text": [ |
| 380 | + "########\n", |
| 381 | + "2\n", |
| 382 | + "<class 'unstructured.documents.elements.Image'>\n", |
| 383 | + "dict_keys(['detection_class_prob', 'coordinates', 'last_modified', 'filetype', 'languages', 'page_number', 'image_base64', 'image_mime_type', 'file_directory', 'filename', 'is_original', 'input_id'])\n", |
| 384 | + "<class 'unstructured.documents.elements.Image'>\n", |
| 385 | + "dict_keys(['detection_class_prob', 'coordinates', 'last_modified', 'filetype', 'languages', 'page_number', 'image_base64', 'image_mime_type', 'file_directory', 'filename', 'is_original', 'input_id'])\n" |
| 386 | + ] |
| 387 | + }, |
| 388 | + { |
| 389 | + "name": "stderr", |
| 390 | + "output_type": "stream", |
| 391 | + "text": [ |
| 392 | + "Uploading Dataset: 100%|██████████| 1/1 [00:29<00:00, 29.36s/it]\n" |
359 | 393 | ] |
360 | 394 | } |
361 | 395 | ], |
362 | 396 | "source": [ |
363 | 397 | "# Using SDK to upload\n", |
364 | 398 | "from clarifai.client import Dataset\n", |
365 | 399 | "dataset = Dataset(url='https://clarifai.com/mansi_k/datautils_testapp/datasets/d1', pat=os.environ['CLARIFAI_PAT'])\n", |
366 | | - "dataset.upload_dataset(new_pipeline.run(files=\"./200945-1.p65.pdf\", loader=True))" |
| 400 | + "dataset.upload_dataset(new_pipeline.run(files=\"/Users/mansikhamkar/work/clarifai/clarifai-python-datautils/tests/pipelines/assets/Multimodal_sample_file.pdf\", loader=True))" |
367 | 401 | ] |
368 | 402 | } |
369 | 403 | ], |
|
0 commit comments