|
22 | 22 | "cell_type": "markdown", |
23 | 23 | "metadata": {}, |
24 | 24 | "source": [ |
25 | | - "## 1. Install Dependencies\n", |
| 25 | + "## 1. Setup AWS Access" |
| 26 | + ] |
| 27 | + }, |
| 28 | + { |
| 29 | + "cell_type": "code", |
| 30 | + "execution_count": null, |
| 31 | + "metadata": {}, |
| 32 | + "outputs": [], |
| 33 | + "source": [ |
| 34 | + "%reload_ext autoreload\n", |
| 35 | + "%autoreload 2\n", |
| 36 | + "\n", |
| 37 | + "import boto3\n", |
| 38 | + "import os\n", |
| 39 | + "\n", |
| 40 | + "os.environ['AWS_PROFILE'] = 'default' # change to desired AWS profile\n", |
| 41 | + "\n", |
| 42 | + "sts_client = boto3.client('sts')\n", |
| 43 | + "sts_client.get_caller_identity()['Arn']" |
| 44 | + ] |
| 45 | + }, |
| 46 | + { |
| 47 | + "cell_type": "markdown", |
| 48 | + "metadata": {}, |
| 49 | + "source": [ |
| 50 | + "## 2. Install Dependencies\n", |
26 | 51 | "\n", |
27 | 52 | "The IDP common package supports granular installation through extras. You can install:\n", |
28 | 53 | "- `[core]` - Just core functionality \n", |
|
68 | 93 | "cell_type": "markdown", |
69 | 94 | "metadata": {}, |
70 | 95 | "source": [ |
71 | | - "## 2. Import Libraries and Set Up Environment" |
| 96 | + "## 3. Import Libraries and Set Up Environment" |
72 | 97 | ] |
73 | 98 | }, |
74 | 99 | { |
|
145 | 170 | "cell_type": "markdown", |
146 | 171 | "metadata": {}, |
147 | 172 | "source": [ |
148 | | - "## 3. Set Up S3 Buckets and Upload Sample File" |
| 173 | + "## 4. Set Up S3 Buckets and Upload Sample File" |
149 | 174 | ] |
150 | 175 | }, |
151 | 176 | { |
|
196 | 221 | "cell_type": "markdown", |
197 | 222 | "metadata": {}, |
198 | 223 | "source": [ |
199 | | - "## 4. Set Up Configuration" |
| 224 | + "## 5. Set Up Configuration" |
200 | 225 | ] |
201 | 226 | }, |
202 | 227 | { |
|
217 | 242 | "cell_type": "markdown", |
218 | 243 | "metadata": {}, |
219 | 244 | "source": [ |
220 | | - "## 5. Process Document with OCR" |
| 245 | + "## 6. Process Document with OCR" |
221 | 246 | ] |
222 | 247 | }, |
223 | 248 | { |
|
271 | 296 | "cell_type": "markdown", |
272 | 297 | "metadata": {}, |
273 | 298 | "source": [ |
274 | | - "## 6. Classify the Document" |
| 299 | + "## 7. Classify the Document" |
275 | 300 | ] |
276 | 301 | }, |
277 | 302 | { |
|
326 | 351 | "cell_type": "markdown", |
327 | 352 | "metadata": {}, |
328 | 353 | "source": [ |
329 | | - "## 7. Extract Information from Document Sections" |
| 354 | + "## 8. Extract Information from Document Sections" |
330 | 355 | ] |
331 | 356 | }, |
332 | 357 | { |
|
375 | 400 | "cell_type": "markdown", |
376 | 401 | "metadata": {}, |
377 | 402 | "source": [ |
378 | | - "## 8. Final Document Status Summary" |
| 403 | + "## 9. Final Document Status Summary" |
379 | 404 | ] |
380 | 405 | }, |
381 | 406 | { |
|
405 | 430 | "cell_type": "markdown", |
406 | 431 | "metadata": {}, |
407 | 432 | "source": [ |
408 | | - "## 9. Evaluate Results\n", |
| 433 | + "## 10. Evaluate Results\n", |
409 | 434 | "\n", |
410 | 435 | "In this section, we'll demonstrate how to evaluate extraction results by comparing them with expected (ground truth) values. The evaluation process involves:\n", |
411 | 436 | "\n", |
|
612 | 637 | "cell_type": "markdown", |
613 | 638 | "metadata": {}, |
614 | 639 | "source": [ |
615 | | - "# 10. Clean Up (Optional)" |
| 640 | + "# 11. Clean Up (Optional)" |
616 | 641 | ] |
617 | 642 | }, |
618 | 643 | { |
|
0 commit comments