llama-cloud 0.1.11__py3-none-any.whl → 0.1.13__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Potentially problematic release.
This version of llama-cloud might be problematic. Click here for more details.
- llama_cloud/__init__.py +12 -4
- llama_cloud/resources/files/client.py +12 -2
- llama_cloud/resources/llama_extract/client.py +24 -4
- llama_cloud/resources/parsing/client.py +131 -88
- llama_cloud/resources/reports/client.py +22 -4
- llama_cloud/types/__init__.py +12 -4
- llama_cloud/types/chunk_mode.py +25 -0
- llama_cloud/types/eval_dataset_job_record.py +1 -2
- llama_cloud/types/job_record.py +2 -3
- llama_cloud/types/llama_extract_settings.py +9 -4
- llama_cloud/types/llama_parse_parameters.py +6 -0
- llama_cloud/types/llm_parameters.py +1 -0
- llama_cloud/types/page_screenshot_metadata.py +1 -0
- llama_cloud/types/parsing_mode.py +37 -0
- llama_cloud/types/{report_file_info.py → prompt_conf.py} +4 -8
- llama_cloud/types/report_metadata.py +1 -2
- llama_cloud/types/schema_relax_mode.py +25 -0
- llama_cloud/types/struct_mode.py +29 -0
- llama_cloud/types/struct_parse_conf.py +50 -0
- llama_cloud/types/supported_llm_model_names.py +0 -4
- {llama_cloud-0.1.11.dist-info → llama_cloud-0.1.13.dist-info}/METADATA +2 -4
- {llama_cloud-0.1.11.dist-info → llama_cloud-0.1.13.dist-info}/RECORD +24 -20
- {llama_cloud-0.1.11.dist-info → llama_cloud-0.1.13.dist-info}/WHEEL +1 -1
- llama_cloud/types/base.py +0 -29
- {llama_cloud-0.1.11.dist-info → llama_cloud-0.1.13.dist-info}/LICENSE +0 -0
|
@@ -18,6 +18,7 @@ from ...types.parsing_job_json_result import ParsingJobJsonResult
|
|
|
18
18
|
from ...types.parsing_job_markdown_result import ParsingJobMarkdownResult
|
|
19
19
|
from ...types.parsing_job_structured_result import ParsingJobStructuredResult
|
|
20
20
|
from ...types.parsing_job_text_result import ParsingJobTextResult
|
|
21
|
+
from ...types.parsing_mode import ParsingMode
|
|
21
22
|
from ...types.parsing_usage import ParsingUsage
|
|
22
23
|
from ...types.presigned_url import PresignedUrl
|
|
23
24
|
|
|
@@ -210,17 +211,12 @@ class ParsingClient:
|
|
|
210
211
|
bbox_left: float,
|
|
211
212
|
bbox_right: float,
|
|
212
213
|
bbox_top: float,
|
|
213
|
-
complemental_formatting_instruction: str,
|
|
214
|
-
content_guideline_instruction: str,
|
|
215
|
-
continuous_mode: bool,
|
|
216
214
|
disable_ocr: bool,
|
|
217
215
|
disable_reconstruction: bool,
|
|
218
216
|
disable_image_extraction: bool,
|
|
219
217
|
do_not_cache: bool,
|
|
220
218
|
do_not_unroll_columns: bool,
|
|
221
219
|
extract_charts: bool,
|
|
222
|
-
fast_mode: bool,
|
|
223
|
-
formatting_instruction: str,
|
|
224
220
|
guess_xlsx_sheet_name: bool,
|
|
225
221
|
html_make_all_elements_visible: bool,
|
|
226
222
|
html_remove_fixed_elements: bool,
|
|
@@ -230,7 +226,6 @@ class ParsingClient:
|
|
|
230
226
|
input_s_3_region: str,
|
|
231
227
|
input_url: str,
|
|
232
228
|
invalidate_cache: bool,
|
|
233
|
-
is_formatting_instruction: bool,
|
|
234
229
|
language: typing.List[ParserLanguages],
|
|
235
230
|
extract_layout: bool,
|
|
236
231
|
max_pages: typing.Optional[int] = OMIT,
|
|
@@ -240,8 +235,7 @@ class ParsingClient:
|
|
|
240
235
|
page_prefix: str,
|
|
241
236
|
page_separator: str,
|
|
242
237
|
page_suffix: str,
|
|
243
|
-
|
|
244
|
-
premium_mode: bool,
|
|
238
|
+
preserve_layout_alignment_across_pages: bool,
|
|
245
239
|
skip_diagonal_text: bool,
|
|
246
240
|
spreadsheet_extract_sub_tables: bool,
|
|
247
241
|
structured_output: bool,
|
|
@@ -249,13 +243,13 @@ class ParsingClient:
|
|
|
249
243
|
structured_output_json_schema_name: str,
|
|
250
244
|
take_screenshot: bool,
|
|
251
245
|
target_pages: str,
|
|
252
|
-
use_vendor_multimodal_model: bool,
|
|
253
246
|
vendor_multimodal_api_key: str,
|
|
254
247
|
vendor_multimodal_model_name: str,
|
|
255
248
|
webhook_url: str,
|
|
256
|
-
|
|
257
|
-
|
|
258
|
-
|
|
249
|
+
parse_mode: typing.Optional[ParsingMode] = OMIT,
|
|
250
|
+
system_prompt: str,
|
|
251
|
+
system_prompt_append: str,
|
|
252
|
+
user_prompt: str,
|
|
259
253
|
job_timeout_in_seconds: float,
|
|
260
254
|
job_timeout_extra_time_per_page_in_seconds: float,
|
|
261
255
|
strict_mode_image_extraction: bool,
|
|
@@ -264,6 +258,18 @@ class ParsingClient:
|
|
|
264
258
|
strict_mode_buggy_font: bool,
|
|
265
259
|
ignore_document_elements_for_layout_detection: bool,
|
|
266
260
|
output_tables_as_html: bool,
|
|
261
|
+
use_vendor_multimodal_model: bool,
|
|
262
|
+
bounding_box: str,
|
|
263
|
+
gpt_4_o_mode: bool,
|
|
264
|
+
gpt_4_o_api_key: str,
|
|
265
|
+
complemental_formatting_instruction: str,
|
|
266
|
+
content_guideline_instruction: str,
|
|
267
|
+
premium_mode: bool,
|
|
268
|
+
is_formatting_instruction: bool,
|
|
269
|
+
continuous_mode: bool,
|
|
270
|
+
parsing_instruction: str,
|
|
271
|
+
fast_mode: bool,
|
|
272
|
+
formatting_instruction: str,
|
|
267
273
|
) -> ParsingJob:
|
|
268
274
|
"""
|
|
269
275
|
Upload a file to s3 and create a job. return a job id
|
|
@@ -303,12 +309,6 @@ class ParsingClient:
|
|
|
303
309
|
|
|
304
310
|
- bbox_top: float.
|
|
305
311
|
|
|
306
|
-
- complemental_formatting_instruction: str.
|
|
307
|
-
|
|
308
|
-
- content_guideline_instruction: str.
|
|
309
|
-
|
|
310
|
-
- continuous_mode: bool.
|
|
311
|
-
|
|
312
312
|
- disable_ocr: bool.
|
|
313
313
|
|
|
314
314
|
- disable_reconstruction: bool.
|
|
@@ -321,10 +321,6 @@ class ParsingClient:
|
|
|
321
321
|
|
|
322
322
|
- extract_charts: bool.
|
|
323
323
|
|
|
324
|
-
- fast_mode: bool.
|
|
325
|
-
|
|
326
|
-
- formatting_instruction: str.
|
|
327
|
-
|
|
328
324
|
- guess_xlsx_sheet_name: bool.
|
|
329
325
|
|
|
330
326
|
- html_make_all_elements_visible: bool.
|
|
@@ -343,8 +339,6 @@ class ParsingClient:
|
|
|
343
339
|
|
|
344
340
|
- invalidate_cache: bool.
|
|
345
341
|
|
|
346
|
-
- is_formatting_instruction: bool.
|
|
347
|
-
|
|
348
342
|
- language: typing.List[ParserLanguages].
|
|
349
343
|
|
|
350
344
|
- extract_layout: bool.
|
|
@@ -363,9 +357,7 @@ class ParsingClient:
|
|
|
363
357
|
|
|
364
358
|
- page_suffix: str.
|
|
365
359
|
|
|
366
|
-
-
|
|
367
|
-
|
|
368
|
-
- premium_mode: bool.
|
|
360
|
+
- preserve_layout_alignment_across_pages: bool.
|
|
369
361
|
|
|
370
362
|
- skip_diagonal_text: bool.
|
|
371
363
|
|
|
@@ -381,19 +373,19 @@ class ParsingClient:
|
|
|
381
373
|
|
|
382
374
|
- target_pages: str.
|
|
383
375
|
|
|
384
|
-
- use_vendor_multimodal_model: bool.
|
|
385
|
-
|
|
386
376
|
- vendor_multimodal_api_key: str.
|
|
387
377
|
|
|
388
378
|
- vendor_multimodal_model_name: str.
|
|
389
379
|
|
|
390
380
|
- webhook_url: str.
|
|
391
381
|
|
|
392
|
-
-
|
|
382
|
+
- parse_mode: typing.Optional[ParsingMode].
|
|
393
383
|
|
|
394
|
-
-
|
|
384
|
+
- system_prompt: str.
|
|
395
385
|
|
|
396
|
-
-
|
|
386
|
+
- system_prompt_append: str.
|
|
387
|
+
|
|
388
|
+
- user_prompt: str.
|
|
397
389
|
|
|
398
390
|
- job_timeout_in_seconds: float.
|
|
399
391
|
|
|
@@ -410,6 +402,30 @@ class ParsingClient:
|
|
|
410
402
|
- ignore_document_elements_for_layout_detection: bool.
|
|
411
403
|
|
|
412
404
|
- output_tables_as_html: bool.
|
|
405
|
+
|
|
406
|
+
- use_vendor_multimodal_model: bool.
|
|
407
|
+
|
|
408
|
+
- bounding_box: str.
|
|
409
|
+
|
|
410
|
+
- gpt_4_o_mode: bool.
|
|
411
|
+
|
|
412
|
+
- gpt_4_o_api_key: str.
|
|
413
|
+
|
|
414
|
+
- complemental_formatting_instruction: str.
|
|
415
|
+
|
|
416
|
+
- content_guideline_instruction: str.
|
|
417
|
+
|
|
418
|
+
- premium_mode: bool.
|
|
419
|
+
|
|
420
|
+
- is_formatting_instruction: bool.
|
|
421
|
+
|
|
422
|
+
- continuous_mode: bool.
|
|
423
|
+
|
|
424
|
+
- parsing_instruction: str.
|
|
425
|
+
|
|
426
|
+
- fast_mode: bool.
|
|
427
|
+
|
|
428
|
+
- formatting_instruction: str.
|
|
413
429
|
"""
|
|
414
430
|
_request: typing.Dict[str, typing.Any] = {
|
|
415
431
|
"annotate_links": annotate_links,
|
|
@@ -426,17 +442,12 @@ class ParsingClient:
|
|
|
426
442
|
"bbox_left": bbox_left,
|
|
427
443
|
"bbox_right": bbox_right,
|
|
428
444
|
"bbox_top": bbox_top,
|
|
429
|
-
"complemental_formatting_instruction": complemental_formatting_instruction,
|
|
430
|
-
"content_guideline_instruction": content_guideline_instruction,
|
|
431
|
-
"continuous_mode": continuous_mode,
|
|
432
445
|
"disable_ocr": disable_ocr,
|
|
433
446
|
"disable_reconstruction": disable_reconstruction,
|
|
434
447
|
"disable_image_extraction": disable_image_extraction,
|
|
435
448
|
"do_not_cache": do_not_cache,
|
|
436
449
|
"do_not_unroll_columns": do_not_unroll_columns,
|
|
437
450
|
"extract_charts": extract_charts,
|
|
438
|
-
"fast_mode": fast_mode,
|
|
439
|
-
"formatting_instruction": formatting_instruction,
|
|
440
451
|
"guess_xlsx_sheet_name": guess_xlsx_sheet_name,
|
|
441
452
|
"html_make_all_elements_visible": html_make_all_elements_visible,
|
|
442
453
|
"html_remove_fixed_elements": html_remove_fixed_elements,
|
|
@@ -446,7 +457,6 @@ class ParsingClient:
|
|
|
446
457
|
"input_s3_region": input_s_3_region,
|
|
447
458
|
"input_url": input_url,
|
|
448
459
|
"invalidate_cache": invalidate_cache,
|
|
449
|
-
"is_formatting_instruction": is_formatting_instruction,
|
|
450
460
|
"language": language,
|
|
451
461
|
"extract_layout": extract_layout,
|
|
452
462
|
"output_pdf_of_document": output_pdf_of_document,
|
|
@@ -455,8 +465,7 @@ class ParsingClient:
|
|
|
455
465
|
"page_prefix": page_prefix,
|
|
456
466
|
"page_separator": page_separator,
|
|
457
467
|
"page_suffix": page_suffix,
|
|
458
|
-
"
|
|
459
|
-
"premium_mode": premium_mode,
|
|
468
|
+
"preserve_layout_alignment_across_pages": preserve_layout_alignment_across_pages,
|
|
460
469
|
"skip_diagonal_text": skip_diagonal_text,
|
|
461
470
|
"spreadsheet_extract_sub_tables": spreadsheet_extract_sub_tables,
|
|
462
471
|
"structured_output": structured_output,
|
|
@@ -464,13 +473,12 @@ class ParsingClient:
|
|
|
464
473
|
"structured_output_json_schema_name": structured_output_json_schema_name,
|
|
465
474
|
"take_screenshot": take_screenshot,
|
|
466
475
|
"target_pages": target_pages,
|
|
467
|
-
"use_vendor_multimodal_model": use_vendor_multimodal_model,
|
|
468
476
|
"vendor_multimodal_api_key": vendor_multimodal_api_key,
|
|
469
477
|
"vendor_multimodal_model_name": vendor_multimodal_model_name,
|
|
470
478
|
"webhook_url": webhook_url,
|
|
471
|
-
"
|
|
472
|
-
"
|
|
473
|
-
"
|
|
479
|
+
"system_prompt": system_prompt,
|
|
480
|
+
"system_prompt_append": system_prompt_append,
|
|
481
|
+
"user_prompt": user_prompt,
|
|
474
482
|
"job_timeout_in_seconds": job_timeout_in_seconds,
|
|
475
483
|
"job_timeout_extra_time_per_page_in_seconds": job_timeout_extra_time_per_page_in_seconds,
|
|
476
484
|
"strict_mode_image_extraction": strict_mode_image_extraction,
|
|
@@ -479,11 +487,25 @@ class ParsingClient:
|
|
|
479
487
|
"strict_mode_buggy_font": strict_mode_buggy_font,
|
|
480
488
|
"ignore_document_elements_for_layout_detection": ignore_document_elements_for_layout_detection,
|
|
481
489
|
"output_tables_as_HTML": output_tables_as_html,
|
|
490
|
+
"use_vendor_multimodal_model": use_vendor_multimodal_model,
|
|
491
|
+
"bounding_box": bounding_box,
|
|
492
|
+
"gpt4o_mode": gpt_4_o_mode,
|
|
493
|
+
"gpt4o_api_key": gpt_4_o_api_key,
|
|
494
|
+
"complemental_formatting_instruction": complemental_formatting_instruction,
|
|
495
|
+
"content_guideline_instruction": content_guideline_instruction,
|
|
496
|
+
"premium_mode": premium_mode,
|
|
497
|
+
"is_formatting_instruction": is_formatting_instruction,
|
|
498
|
+
"continuous_mode": continuous_mode,
|
|
499
|
+
"parsing_instruction": parsing_instruction,
|
|
500
|
+
"fast_mode": fast_mode,
|
|
501
|
+
"formatting_instruction": formatting_instruction,
|
|
482
502
|
}
|
|
483
503
|
if file is not OMIT:
|
|
484
504
|
_request["file"] = file
|
|
485
505
|
if max_pages is not OMIT:
|
|
486
506
|
_request["max_pages"] = max_pages
|
|
507
|
+
if parse_mode is not OMIT:
|
|
508
|
+
_request["parse_mode"] = parse_mode
|
|
487
509
|
_response = self._client_wrapper.httpx_client.request(
|
|
488
510
|
"POST",
|
|
489
511
|
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),
|
|
@@ -1157,17 +1179,12 @@ class AsyncParsingClient:
|
|
|
1157
1179
|
bbox_left: float,
|
|
1158
1180
|
bbox_right: float,
|
|
1159
1181
|
bbox_top: float,
|
|
1160
|
-
complemental_formatting_instruction: str,
|
|
1161
|
-
content_guideline_instruction: str,
|
|
1162
|
-
continuous_mode: bool,
|
|
1163
1182
|
disable_ocr: bool,
|
|
1164
1183
|
disable_reconstruction: bool,
|
|
1165
1184
|
disable_image_extraction: bool,
|
|
1166
1185
|
do_not_cache: bool,
|
|
1167
1186
|
do_not_unroll_columns: bool,
|
|
1168
1187
|
extract_charts: bool,
|
|
1169
|
-
fast_mode: bool,
|
|
1170
|
-
formatting_instruction: str,
|
|
1171
1188
|
guess_xlsx_sheet_name: bool,
|
|
1172
1189
|
html_make_all_elements_visible: bool,
|
|
1173
1190
|
html_remove_fixed_elements: bool,
|
|
@@ -1177,7 +1194,6 @@ class AsyncParsingClient:
|
|
|
1177
1194
|
input_s_3_region: str,
|
|
1178
1195
|
input_url: str,
|
|
1179
1196
|
invalidate_cache: bool,
|
|
1180
|
-
is_formatting_instruction: bool,
|
|
1181
1197
|
language: typing.List[ParserLanguages],
|
|
1182
1198
|
extract_layout: bool,
|
|
1183
1199
|
max_pages: typing.Optional[int] = OMIT,
|
|
@@ -1187,8 +1203,7 @@ class AsyncParsingClient:
|
|
|
1187
1203
|
page_prefix: str,
|
|
1188
1204
|
page_separator: str,
|
|
1189
1205
|
page_suffix: str,
|
|
1190
|
-
|
|
1191
|
-
premium_mode: bool,
|
|
1206
|
+
preserve_layout_alignment_across_pages: bool,
|
|
1192
1207
|
skip_diagonal_text: bool,
|
|
1193
1208
|
spreadsheet_extract_sub_tables: bool,
|
|
1194
1209
|
structured_output: bool,
|
|
@@ -1196,13 +1211,13 @@ class AsyncParsingClient:
|
|
|
1196
1211
|
structured_output_json_schema_name: str,
|
|
1197
1212
|
take_screenshot: bool,
|
|
1198
1213
|
target_pages: str,
|
|
1199
|
-
use_vendor_multimodal_model: bool,
|
|
1200
1214
|
vendor_multimodal_api_key: str,
|
|
1201
1215
|
vendor_multimodal_model_name: str,
|
|
1202
1216
|
webhook_url: str,
|
|
1203
|
-
|
|
1204
|
-
|
|
1205
|
-
|
|
1217
|
+
parse_mode: typing.Optional[ParsingMode] = OMIT,
|
|
1218
|
+
system_prompt: str,
|
|
1219
|
+
system_prompt_append: str,
|
|
1220
|
+
user_prompt: str,
|
|
1206
1221
|
job_timeout_in_seconds: float,
|
|
1207
1222
|
job_timeout_extra_time_per_page_in_seconds: float,
|
|
1208
1223
|
strict_mode_image_extraction: bool,
|
|
@@ -1211,6 +1226,18 @@ class AsyncParsingClient:
|
|
|
1211
1226
|
strict_mode_buggy_font: bool,
|
|
1212
1227
|
ignore_document_elements_for_layout_detection: bool,
|
|
1213
1228
|
output_tables_as_html: bool,
|
|
1229
|
+
use_vendor_multimodal_model: bool,
|
|
1230
|
+
bounding_box: str,
|
|
1231
|
+
gpt_4_o_mode: bool,
|
|
1232
|
+
gpt_4_o_api_key: str,
|
|
1233
|
+
complemental_formatting_instruction: str,
|
|
1234
|
+
content_guideline_instruction: str,
|
|
1235
|
+
premium_mode: bool,
|
|
1236
|
+
is_formatting_instruction: bool,
|
|
1237
|
+
continuous_mode: bool,
|
|
1238
|
+
parsing_instruction: str,
|
|
1239
|
+
fast_mode: bool,
|
|
1240
|
+
formatting_instruction: str,
|
|
1214
1241
|
) -> ParsingJob:
|
|
1215
1242
|
"""
|
|
1216
1243
|
Upload a file to s3 and create a job. return a job id
|
|
@@ -1250,12 +1277,6 @@ class AsyncParsingClient:
|
|
|
1250
1277
|
|
|
1251
1278
|
- bbox_top: float.
|
|
1252
1279
|
|
|
1253
|
-
- complemental_formatting_instruction: str.
|
|
1254
|
-
|
|
1255
|
-
- content_guideline_instruction: str.
|
|
1256
|
-
|
|
1257
|
-
- continuous_mode: bool.
|
|
1258
|
-
|
|
1259
1280
|
- disable_ocr: bool.
|
|
1260
1281
|
|
|
1261
1282
|
- disable_reconstruction: bool.
|
|
@@ -1268,10 +1289,6 @@ class AsyncParsingClient:
|
|
|
1268
1289
|
|
|
1269
1290
|
- extract_charts: bool.
|
|
1270
1291
|
|
|
1271
|
-
- fast_mode: bool.
|
|
1272
|
-
|
|
1273
|
-
- formatting_instruction: str.
|
|
1274
|
-
|
|
1275
1292
|
- guess_xlsx_sheet_name: bool.
|
|
1276
1293
|
|
|
1277
1294
|
- html_make_all_elements_visible: bool.
|
|
@@ -1290,8 +1307,6 @@ class AsyncParsingClient:
|
|
|
1290
1307
|
|
|
1291
1308
|
- invalidate_cache: bool.
|
|
1292
1309
|
|
|
1293
|
-
- is_formatting_instruction: bool.
|
|
1294
|
-
|
|
1295
1310
|
- language: typing.List[ParserLanguages].
|
|
1296
1311
|
|
|
1297
1312
|
- extract_layout: bool.
|
|
@@ -1310,9 +1325,7 @@ class AsyncParsingClient:
|
|
|
1310
1325
|
|
|
1311
1326
|
- page_suffix: str.
|
|
1312
1327
|
|
|
1313
|
-
-
|
|
1314
|
-
|
|
1315
|
-
- premium_mode: bool.
|
|
1328
|
+
- preserve_layout_alignment_across_pages: bool.
|
|
1316
1329
|
|
|
1317
1330
|
- skip_diagonal_text: bool.
|
|
1318
1331
|
|
|
@@ -1328,19 +1341,19 @@ class AsyncParsingClient:
|
|
|
1328
1341
|
|
|
1329
1342
|
- target_pages: str.
|
|
1330
1343
|
|
|
1331
|
-
- use_vendor_multimodal_model: bool.
|
|
1332
|
-
|
|
1333
1344
|
- vendor_multimodal_api_key: str.
|
|
1334
1345
|
|
|
1335
1346
|
- vendor_multimodal_model_name: str.
|
|
1336
1347
|
|
|
1337
1348
|
- webhook_url: str.
|
|
1338
1349
|
|
|
1339
|
-
-
|
|
1350
|
+
- parse_mode: typing.Optional[ParsingMode].
|
|
1340
1351
|
|
|
1341
|
-
-
|
|
1352
|
+
- system_prompt: str.
|
|
1342
1353
|
|
|
1343
|
-
-
|
|
1354
|
+
- system_prompt_append: str.
|
|
1355
|
+
|
|
1356
|
+
- user_prompt: str.
|
|
1344
1357
|
|
|
1345
1358
|
- job_timeout_in_seconds: float.
|
|
1346
1359
|
|
|
@@ -1357,6 +1370,30 @@ class AsyncParsingClient:
|
|
|
1357
1370
|
- ignore_document_elements_for_layout_detection: bool.
|
|
1358
1371
|
|
|
1359
1372
|
- output_tables_as_html: bool.
|
|
1373
|
+
|
|
1374
|
+
- use_vendor_multimodal_model: bool.
|
|
1375
|
+
|
|
1376
|
+
- bounding_box: str.
|
|
1377
|
+
|
|
1378
|
+
- gpt_4_o_mode: bool.
|
|
1379
|
+
|
|
1380
|
+
- gpt_4_o_api_key: str.
|
|
1381
|
+
|
|
1382
|
+
- complemental_formatting_instruction: str.
|
|
1383
|
+
|
|
1384
|
+
- content_guideline_instruction: str.
|
|
1385
|
+
|
|
1386
|
+
- premium_mode: bool.
|
|
1387
|
+
|
|
1388
|
+
- is_formatting_instruction: bool.
|
|
1389
|
+
|
|
1390
|
+
- continuous_mode: bool.
|
|
1391
|
+
|
|
1392
|
+
- parsing_instruction: str.
|
|
1393
|
+
|
|
1394
|
+
- fast_mode: bool.
|
|
1395
|
+
|
|
1396
|
+
- formatting_instruction: str.
|
|
1360
1397
|
"""
|
|
1361
1398
|
_request: typing.Dict[str, typing.Any] = {
|
|
1362
1399
|
"annotate_links": annotate_links,
|
|
@@ -1373,17 +1410,12 @@ class AsyncParsingClient:
|
|
|
1373
1410
|
"bbox_left": bbox_left,
|
|
1374
1411
|
"bbox_right": bbox_right,
|
|
1375
1412
|
"bbox_top": bbox_top,
|
|
1376
|
-
"complemental_formatting_instruction": complemental_formatting_instruction,
|
|
1377
|
-
"content_guideline_instruction": content_guideline_instruction,
|
|
1378
|
-
"continuous_mode": continuous_mode,
|
|
1379
1413
|
"disable_ocr": disable_ocr,
|
|
1380
1414
|
"disable_reconstruction": disable_reconstruction,
|
|
1381
1415
|
"disable_image_extraction": disable_image_extraction,
|
|
1382
1416
|
"do_not_cache": do_not_cache,
|
|
1383
1417
|
"do_not_unroll_columns": do_not_unroll_columns,
|
|
1384
1418
|
"extract_charts": extract_charts,
|
|
1385
|
-
"fast_mode": fast_mode,
|
|
1386
|
-
"formatting_instruction": formatting_instruction,
|
|
1387
1419
|
"guess_xlsx_sheet_name": guess_xlsx_sheet_name,
|
|
1388
1420
|
"html_make_all_elements_visible": html_make_all_elements_visible,
|
|
1389
1421
|
"html_remove_fixed_elements": html_remove_fixed_elements,
|
|
@@ -1393,7 +1425,6 @@ class AsyncParsingClient:
|
|
|
1393
1425
|
"input_s3_region": input_s_3_region,
|
|
1394
1426
|
"input_url": input_url,
|
|
1395
1427
|
"invalidate_cache": invalidate_cache,
|
|
1396
|
-
"is_formatting_instruction": is_formatting_instruction,
|
|
1397
1428
|
"language": language,
|
|
1398
1429
|
"extract_layout": extract_layout,
|
|
1399
1430
|
"output_pdf_of_document": output_pdf_of_document,
|
|
@@ -1402,8 +1433,7 @@ class AsyncParsingClient:
|
|
|
1402
1433
|
"page_prefix": page_prefix,
|
|
1403
1434
|
"page_separator": page_separator,
|
|
1404
1435
|
"page_suffix": page_suffix,
|
|
1405
|
-
"
|
|
1406
|
-
"premium_mode": premium_mode,
|
|
1436
|
+
"preserve_layout_alignment_across_pages": preserve_layout_alignment_across_pages,
|
|
1407
1437
|
"skip_diagonal_text": skip_diagonal_text,
|
|
1408
1438
|
"spreadsheet_extract_sub_tables": spreadsheet_extract_sub_tables,
|
|
1409
1439
|
"structured_output": structured_output,
|
|
@@ -1411,13 +1441,12 @@ class AsyncParsingClient:
|
|
|
1411
1441
|
"structured_output_json_schema_name": structured_output_json_schema_name,
|
|
1412
1442
|
"take_screenshot": take_screenshot,
|
|
1413
1443
|
"target_pages": target_pages,
|
|
1414
|
-
"use_vendor_multimodal_model": use_vendor_multimodal_model,
|
|
1415
1444
|
"vendor_multimodal_api_key": vendor_multimodal_api_key,
|
|
1416
1445
|
"vendor_multimodal_model_name": vendor_multimodal_model_name,
|
|
1417
1446
|
"webhook_url": webhook_url,
|
|
1418
|
-
"
|
|
1419
|
-
"
|
|
1420
|
-
"
|
|
1447
|
+
"system_prompt": system_prompt,
|
|
1448
|
+
"system_prompt_append": system_prompt_append,
|
|
1449
|
+
"user_prompt": user_prompt,
|
|
1421
1450
|
"job_timeout_in_seconds": job_timeout_in_seconds,
|
|
1422
1451
|
"job_timeout_extra_time_per_page_in_seconds": job_timeout_extra_time_per_page_in_seconds,
|
|
1423
1452
|
"strict_mode_image_extraction": strict_mode_image_extraction,
|
|
@@ -1426,11 +1455,25 @@ class AsyncParsingClient:
|
|
|
1426
1455
|
"strict_mode_buggy_font": strict_mode_buggy_font,
|
|
1427
1456
|
"ignore_document_elements_for_layout_detection": ignore_document_elements_for_layout_detection,
|
|
1428
1457
|
"output_tables_as_HTML": output_tables_as_html,
|
|
1458
|
+
"use_vendor_multimodal_model": use_vendor_multimodal_model,
|
|
1459
|
+
"bounding_box": bounding_box,
|
|
1460
|
+
"gpt4o_mode": gpt_4_o_mode,
|
|
1461
|
+
"gpt4o_api_key": gpt_4_o_api_key,
|
|
1462
|
+
"complemental_formatting_instruction": complemental_formatting_instruction,
|
|
1463
|
+
"content_guideline_instruction": content_guideline_instruction,
|
|
1464
|
+
"premium_mode": premium_mode,
|
|
1465
|
+
"is_formatting_instruction": is_formatting_instruction,
|
|
1466
|
+
"continuous_mode": continuous_mode,
|
|
1467
|
+
"parsing_instruction": parsing_instruction,
|
|
1468
|
+
"fast_mode": fast_mode,
|
|
1469
|
+
"formatting_instruction": formatting_instruction,
|
|
1429
1470
|
}
|
|
1430
1471
|
if file is not OMIT:
|
|
1431
1472
|
_request["file"] = file
|
|
1432
1473
|
if max_pages is not OMIT:
|
|
1433
1474
|
_request["max_pages"] = max_pages
|
|
1475
|
+
if parse_mode is not OMIT:
|
|
1476
|
+
_request["parse_mode"] = parse_mode
|
|
1434
1477
|
_response = await self._client_wrapper.httpx_client.request(
|
|
1435
1478
|
"POST",
|
|
1436
1479
|
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/parsing/upload"),
|
|
@@ -252,7 +252,12 @@ class ReportsClient:
|
|
|
252
252
|
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
253
253
|
|
|
254
254
|
def delete_report(
|
|
255
|
-
self,
|
|
255
|
+
self,
|
|
256
|
+
report_id: str,
|
|
257
|
+
*,
|
|
258
|
+
cascade_delete: typing.Optional[bool] = None,
|
|
259
|
+
project_id: typing.Optional[str] = None,
|
|
260
|
+
organization_id: typing.Optional[str] = None,
|
|
256
261
|
) -> typing.Any:
|
|
257
262
|
"""
|
|
258
263
|
Delete a report.
|
|
@@ -260,6 +265,8 @@ class ReportsClient:
|
|
|
260
265
|
Parameters:
|
|
261
266
|
- report_id: str.
|
|
262
267
|
|
|
268
|
+
- cascade_delete: typing.Optional[bool]. Whether to delete associated retriever and pipeline data
|
|
269
|
+
|
|
263
270
|
- project_id: typing.Optional[str].
|
|
264
271
|
|
|
265
272
|
- organization_id: typing.Optional[str].
|
|
@@ -276,7 +283,9 @@ class ReportsClient:
|
|
|
276
283
|
_response = self._client_wrapper.httpx_client.request(
|
|
277
284
|
"DELETE",
|
|
278
285
|
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/reports/{report_id}"),
|
|
279
|
-
params=remove_none_from_dict(
|
|
286
|
+
params=remove_none_from_dict(
|
|
287
|
+
{"cascade_delete": cascade_delete, "project_id": project_id, "organization_id": organization_id}
|
|
288
|
+
),
|
|
280
289
|
headers=self._client_wrapper.get_headers(),
|
|
281
290
|
timeout=60,
|
|
282
291
|
)
|
|
@@ -835,7 +844,12 @@ class AsyncReportsClient:
|
|
|
835
844
|
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
836
845
|
|
|
837
846
|
async def delete_report(
|
|
838
|
-
self,
|
|
847
|
+
self,
|
|
848
|
+
report_id: str,
|
|
849
|
+
*,
|
|
850
|
+
cascade_delete: typing.Optional[bool] = None,
|
|
851
|
+
project_id: typing.Optional[str] = None,
|
|
852
|
+
organization_id: typing.Optional[str] = None,
|
|
839
853
|
) -> typing.Any:
|
|
840
854
|
"""
|
|
841
855
|
Delete a report.
|
|
@@ -843,6 +857,8 @@ class AsyncReportsClient:
|
|
|
843
857
|
Parameters:
|
|
844
858
|
- report_id: str.
|
|
845
859
|
|
|
860
|
+
- cascade_delete: typing.Optional[bool]. Whether to delete associated retriever and pipeline data
|
|
861
|
+
|
|
846
862
|
- project_id: typing.Optional[str].
|
|
847
863
|
|
|
848
864
|
- organization_id: typing.Optional[str].
|
|
@@ -859,7 +875,9 @@ class AsyncReportsClient:
|
|
|
859
875
|
_response = await self._client_wrapper.httpx_client.request(
|
|
860
876
|
"DELETE",
|
|
861
877
|
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/reports/{report_id}"),
|
|
862
|
-
params=remove_none_from_dict(
|
|
878
|
+
params=remove_none_from_dict(
|
|
879
|
+
{"cascade_delete": cascade_delete, "project_id": project_id, "organization_id": organization_id}
|
|
880
|
+
),
|
|
863
881
|
headers=self._client_wrapper.get_headers(),
|
|
864
882
|
timeout=60,
|
|
865
883
|
)
|
llama_cloud/types/__init__.py
CHANGED
|
@@ -19,7 +19,6 @@ from .app_schema_chat_chat_message import AppSchemaChatChatMessage
|
|
|
19
19
|
from .auto_transform_config import AutoTransformConfig
|
|
20
20
|
from .azure_open_ai_embedding import AzureOpenAiEmbedding
|
|
21
21
|
from .azure_open_ai_embedding_config import AzureOpenAiEmbeddingConfig
|
|
22
|
-
from .base import Base
|
|
23
22
|
from .base_prompt_template import BasePromptTemplate
|
|
24
23
|
from .bedrock_embedding import BedrockEmbedding
|
|
25
24
|
from .bedrock_embedding_config import BedrockEmbeddingConfig
|
|
@@ -29,6 +28,7 @@ from .character_splitter import CharacterSplitter
|
|
|
29
28
|
from .chat_app import ChatApp
|
|
30
29
|
from .chat_app_response import ChatAppResponse
|
|
31
30
|
from .chat_data import ChatData
|
|
31
|
+
from .chunk_mode import ChunkMode
|
|
32
32
|
from .cloud_az_storage_blob_data_source import CloudAzStorageBlobDataSource
|
|
33
33
|
from .cloud_azure_ai_search_vector_store import CloudAzureAiSearchVectorStore
|
|
34
34
|
from .cloud_box_data_source import CloudBoxDataSource
|
|
@@ -199,6 +199,7 @@ from .parsing_job_json_result import ParsingJobJsonResult
|
|
|
199
199
|
from .parsing_job_markdown_result import ParsingJobMarkdownResult
|
|
200
200
|
from .parsing_job_structured_result import ParsingJobStructuredResult
|
|
201
201
|
from .parsing_job_text_result import ParsingJobTextResult
|
|
202
|
+
from .parsing_mode import ParsingMode
|
|
202
203
|
from .parsing_usage import ParsingUsage
|
|
203
204
|
from .partition_names import PartitionNames
|
|
204
205
|
from .permission import Permission
|
|
@@ -254,6 +255,7 @@ from .progress_event import ProgressEvent
|
|
|
254
255
|
from .progress_event_status import ProgressEventStatus
|
|
255
256
|
from .project import Project
|
|
256
257
|
from .project_create import ProjectCreate
|
|
258
|
+
from .prompt_conf import PromptConf
|
|
257
259
|
from .prompt_mixin_prompts import PromptMixinPrompts
|
|
258
260
|
from .prompt_spec import PromptSpec
|
|
259
261
|
from .pydantic_program_mode import PydanticProgramMode
|
|
@@ -271,7 +273,6 @@ from .report_event_item_event_data import (
|
|
|
271
273
|
ReportEventItemEventData_ReportStateUpdate,
|
|
272
274
|
)
|
|
273
275
|
from .report_event_type import ReportEventType
|
|
274
|
-
from .report_file_info import ReportFileInfo
|
|
275
276
|
from .report_metadata import ReportMetadata
|
|
276
277
|
from .report_plan import ReportPlan
|
|
277
278
|
from .report_plan_block import ReportPlanBlock
|
|
@@ -286,10 +287,13 @@ from .retriever import Retriever
|
|
|
286
287
|
from .retriever_create import RetrieverCreate
|
|
287
288
|
from .retriever_pipeline import RetrieverPipeline
|
|
288
289
|
from .role import Role
|
|
290
|
+
from .schema_relax_mode import SchemaRelaxMode
|
|
289
291
|
from .semantic_chunking_config import SemanticChunkingConfig
|
|
290
292
|
from .sentence_chunking_config import SentenceChunkingConfig
|
|
291
293
|
from .sentence_splitter import SentenceSplitter
|
|
292
294
|
from .status_enum import StatusEnum
|
|
295
|
+
from .struct_mode import StructMode
|
|
296
|
+
from .struct_parse_conf import StructParseConf
|
|
293
297
|
from .supported_llm_model import SupportedLlmModel
|
|
294
298
|
from .supported_llm_model_names import SupportedLlmModelNames
|
|
295
299
|
from .text_block import TextBlock
|
|
@@ -328,7 +332,6 @@ __all__ = [
|
|
|
328
332
|
"AutoTransformConfig",
|
|
329
333
|
"AzureOpenAiEmbedding",
|
|
330
334
|
"AzureOpenAiEmbeddingConfig",
|
|
331
|
-
"Base",
|
|
332
335
|
"BasePromptTemplate",
|
|
333
336
|
"BedrockEmbedding",
|
|
334
337
|
"BedrockEmbeddingConfig",
|
|
@@ -338,6 +341,7 @@ __all__ = [
|
|
|
338
341
|
"ChatApp",
|
|
339
342
|
"ChatAppResponse",
|
|
340
343
|
"ChatData",
|
|
344
|
+
"ChunkMode",
|
|
341
345
|
"CloudAzStorageBlobDataSource",
|
|
342
346
|
"CloudAzureAiSearchVectorStore",
|
|
343
347
|
"CloudBoxDataSource",
|
|
@@ -502,6 +506,7 @@ __all__ = [
|
|
|
502
506
|
"ParsingJobMarkdownResult",
|
|
503
507
|
"ParsingJobStructuredResult",
|
|
504
508
|
"ParsingJobTextResult",
|
|
509
|
+
"ParsingMode",
|
|
505
510
|
"ParsingUsage",
|
|
506
511
|
"PartitionNames",
|
|
507
512
|
"Permission",
|
|
@@ -551,6 +556,7 @@ __all__ = [
|
|
|
551
556
|
"ProgressEventStatus",
|
|
552
557
|
"Project",
|
|
553
558
|
"ProjectCreate",
|
|
559
|
+
"PromptConf",
|
|
554
560
|
"PromptMixinPrompts",
|
|
555
561
|
"PromptSpec",
|
|
556
562
|
"PydanticProgramMode",
|
|
@@ -566,7 +572,6 @@ __all__ = [
|
|
|
566
572
|
"ReportEventItemEventData_ReportBlockUpdate",
|
|
567
573
|
"ReportEventItemEventData_ReportStateUpdate",
|
|
568
574
|
"ReportEventType",
|
|
569
|
-
"ReportFileInfo",
|
|
570
575
|
"ReportMetadata",
|
|
571
576
|
"ReportPlan",
|
|
572
577
|
"ReportPlanBlock",
|
|
@@ -581,10 +586,13 @@ __all__ = [
|
|
|
581
586
|
"RetrieverCreate",
|
|
582
587
|
"RetrieverPipeline",
|
|
583
588
|
"Role",
|
|
589
|
+
"SchemaRelaxMode",
|
|
584
590
|
"SemanticChunkingConfig",
|
|
585
591
|
"SentenceChunkingConfig",
|
|
586
592
|
"SentenceSplitter",
|
|
587
593
|
"StatusEnum",
|
|
594
|
+
"StructMode",
|
|
595
|
+
"StructParseConf",
|
|
588
596
|
"SupportedLlmModel",
|
|
589
597
|
"SupportedLlmModelNames",
|
|
590
598
|
"TextBlock",
|