llama-cloud 0.1.12__py3-none-any.whl → 0.1.14__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 +38 -12
- llama_cloud/resources/__init__.py +0 -14
- llama_cloud/resources/llama_extract/__init__.py +0 -17
- llama_cloud/resources/llama_extract/client.py +113 -314
- llama_cloud/resources/organizations/client.py +15 -5
- llama_cloud/resources/parsing/client.py +153 -86
- llama_cloud/resources/pipelines/client.py +145 -10
- llama_cloud/resources/projects/client.py +25 -9
- llama_cloud/resources/reports/client.py +16 -6
- llama_cloud/types/__init__.py +44 -6
- llama_cloud/types/{plan.py → base_plan.py} +16 -13
- llama_cloud/types/base_plan_metronome_plan_type.py +17 -0
- llama_cloud/types/base_plan_name.py +45 -0
- llama_cloud/types/base_plan_plan_frequency.py +25 -0
- llama_cloud/types/billing_period.py +32 -0
- llama_cloud/types/{base.py → credit_type.py} +4 -1
- llama_cloud/types/data_source.py +1 -0
- llama_cloud/types/eval_dataset_job_record.py +1 -2
- llama_cloud/types/extract_agent_create.py +39 -0
- llama_cloud/types/extract_agent_update.py +38 -0
- llama_cloud/types/extract_schema_validate_request.py +32 -0
- llama_cloud/types/free_credits_usage.py +34 -0
- llama_cloud/types/job_record.py +2 -3
- llama_cloud/types/llama_parse_parameters.py +9 -0
- llama_cloud/types/llm_parameters.py +1 -0
- llama_cloud/types/page_screenshot_metadata.py +1 -0
- llama_cloud/types/paginated_list_cloud_documents_response.py +35 -0
- llama_cloud/types/parsing_mode.py +37 -0
- llama_cloud/types/pipeline_data_source.py +1 -0
- llama_cloud/types/pipeline_file.py +1 -0
- llama_cloud/types/plan_limits.py +52 -0
- llama_cloud/types/recurring_credit_grant.py +44 -0
- llama_cloud/types/usage.py +5 -4
- llama_cloud/types/usage_active_alerts_item.py +25 -0
- llama_cloud/types/{interval_usage_and_plan.py → usage_and_plan.py} +4 -6
- {llama_cloud-0.1.12.dist-info → llama_cloud-0.1.14.dist-info}/METADATA +2 -1
- {llama_cloud-0.1.12.dist-info → llama_cloud-0.1.14.dist-info}/RECORD +45 -33
- {llama_cloud-0.1.12.dist-info → llama_cloud-0.1.14.dist-info}/WHEEL +1 -1
- llama_cloud/resources/llama_extract/types/__init__.py +0 -17
- /llama_cloud/{resources/llama_extract/types → types}/extract_agent_create_data_schema.py +0 -0
- /llama_cloud/{resources/llama_extract/types → types}/extract_agent_create_data_schema_zero_value.py +0 -0
- /llama_cloud/{resources/llama_extract/types → types}/extract_agent_update_data_schema.py +0 -0
- /llama_cloud/{resources/llama_extract/types → types}/extract_agent_update_data_schema_zero_value.py +0 -0
- /llama_cloud/{resources/llama_extract/types → types}/extract_schema_validate_request_data_schema.py +0 -0
- /llama_cloud/{resources/llama_extract/types → types}/extract_schema_validate_request_data_schema_zero_value.py +0 -0
- {llama_cloud-0.1.12.dist-info → llama_cloud-0.1.14.dist-info}/LICENSE +0 -0
|
@@ -10,17 +10,16 @@ from ...core.jsonable_encoder import jsonable_encoder
|
|
|
10
10
|
from ...core.remove_none_from_dict import remove_none_from_dict
|
|
11
11
|
from ...errors.unprocessable_entity_error import UnprocessableEntityError
|
|
12
12
|
from ...types.extract_agent import ExtractAgent
|
|
13
|
-
from ...types.
|
|
13
|
+
from ...types.extract_agent_create import ExtractAgentCreate
|
|
14
|
+
from ...types.extract_agent_update import ExtractAgentUpdate
|
|
14
15
|
from ...types.extract_job import ExtractJob
|
|
15
16
|
from ...types.extract_job_create import ExtractJobCreate
|
|
16
17
|
from ...types.extract_resultset import ExtractResultset
|
|
17
18
|
from ...types.extract_run import ExtractRun
|
|
19
|
+
from ...types.extract_schema_validate_request import ExtractSchemaValidateRequest
|
|
18
20
|
from ...types.extract_schema_validate_response import ExtractSchemaValidateResponse
|
|
19
21
|
from ...types.http_validation_error import HttpValidationError
|
|
20
22
|
from ...types.llama_extract_settings import LlamaExtractSettings
|
|
21
|
-
from .types.extract_agent_create_data_schema import ExtractAgentCreateDataSchema
|
|
22
|
-
from .types.extract_agent_update_data_schema import ExtractAgentUpdateDataSchema
|
|
23
|
-
from .types.extract_schema_validate_request_data_schema import ExtractSchemaValidateRequestDataSchema
|
|
24
23
|
|
|
25
24
|
try:
|
|
26
25
|
import pydantic
|
|
@@ -52,7 +51,7 @@ class LlamaExtractClient:
|
|
|
52
51
|
"""
|
|
53
52
|
_response = self._client_wrapper.httpx_client.request(
|
|
54
53
|
"GET",
|
|
55
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
54
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"),
|
|
56
55
|
params=remove_none_from_dict({"project_id": project_id}),
|
|
57
56
|
headers=self._client_wrapper.get_headers(),
|
|
58
57
|
timeout=60,
|
|
@@ -72,9 +71,7 @@ class LlamaExtractClient:
|
|
|
72
71
|
*,
|
|
73
72
|
project_id: typing.Optional[str] = None,
|
|
74
73
|
organization_id: typing.Optional[str] = None,
|
|
75
|
-
|
|
76
|
-
data_schema: ExtractAgentCreateDataSchema,
|
|
77
|
-
config: ExtractConfig,
|
|
74
|
+
request: ExtractAgentCreate,
|
|
78
75
|
) -> ExtractAgent:
|
|
79
76
|
"""
|
|
80
77
|
Parameters:
|
|
@@ -82,31 +79,34 @@ class LlamaExtractClient:
|
|
|
82
79
|
|
|
83
80
|
- organization_id: typing.Optional[str].
|
|
84
81
|
|
|
85
|
-
-
|
|
86
|
-
|
|
87
|
-
- data_schema: ExtractAgentCreateDataSchema. The schema of the data.
|
|
88
|
-
|
|
89
|
-
- config: ExtractConfig. The configuration parameters for the extraction agent.
|
|
82
|
+
- request: ExtractAgentCreate.
|
|
90
83
|
---
|
|
91
|
-
from llama_cloud import
|
|
84
|
+
from llama_cloud import (
|
|
85
|
+
ExtractAgentCreate,
|
|
86
|
+
ExtractConfig,
|
|
87
|
+
ExtractMode,
|
|
88
|
+
ExtractTarget,
|
|
89
|
+
)
|
|
92
90
|
from llama_cloud.client import LlamaCloud
|
|
93
91
|
|
|
94
92
|
client = LlamaCloud(
|
|
95
93
|
token="YOUR_TOKEN",
|
|
96
94
|
)
|
|
97
95
|
client.llama_extract.create_extraction_agent(
|
|
98
|
-
|
|
99
|
-
|
|
100
|
-
|
|
101
|
-
|
|
96
|
+
request=ExtractAgentCreate(
|
|
97
|
+
name="string",
|
|
98
|
+
config=ExtractConfig(
|
|
99
|
+
extraction_target=ExtractTarget.PER_DOC,
|
|
100
|
+
extraction_mode=ExtractMode.FAST,
|
|
101
|
+
),
|
|
102
102
|
),
|
|
103
103
|
)
|
|
104
104
|
"""
|
|
105
105
|
_response = self._client_wrapper.httpx_client.request(
|
|
106
106
|
"POST",
|
|
107
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
107
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"),
|
|
108
108
|
params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
|
|
109
|
-
json=jsonable_encoder(
|
|
109
|
+
json=jsonable_encoder(request),
|
|
110
110
|
headers=self._client_wrapper.get_headers(),
|
|
111
111
|
timeout=60,
|
|
112
112
|
)
|
|
@@ -120,29 +120,30 @@ class LlamaExtractClient:
|
|
|
120
120
|
raise ApiError(status_code=_response.status_code, body=_response.text)
|
|
121
121
|
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
122
122
|
|
|
123
|
-
def validate_extraction_schema(
|
|
124
|
-
self, *, data_schema: ExtractSchemaValidateRequestDataSchema
|
|
125
|
-
) -> ExtractSchemaValidateResponse:
|
|
123
|
+
def validate_extraction_schema(self, *, request: ExtractSchemaValidateRequest) -> ExtractSchemaValidateResponse:
|
|
126
124
|
"""
|
|
127
125
|
Validates an extraction agent's schema definition.
|
|
128
126
|
Returns the normalized and validated schema if valid, otherwise raises an HTTP 400.
|
|
129
127
|
|
|
130
128
|
Parameters:
|
|
131
|
-
-
|
|
129
|
+
- request: ExtractSchemaValidateRequest.
|
|
132
130
|
---
|
|
131
|
+
from llama_cloud import ExtractSchemaValidateRequest
|
|
133
132
|
from llama_cloud.client import LlamaCloud
|
|
134
133
|
|
|
135
134
|
client = LlamaCloud(
|
|
136
135
|
token="YOUR_TOKEN",
|
|
137
136
|
)
|
|
138
|
-
client.llama_extract.validate_extraction_schema(
|
|
137
|
+
client.llama_extract.validate_extraction_schema(
|
|
138
|
+
request=ExtractSchemaValidateRequest(),
|
|
139
|
+
)
|
|
139
140
|
"""
|
|
140
141
|
_response = self._client_wrapper.httpx_client.request(
|
|
141
142
|
"POST",
|
|
142
143
|
urllib.parse.urljoin(
|
|
143
|
-
f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
144
|
+
f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/schema/validation"
|
|
144
145
|
),
|
|
145
|
-
json=jsonable_encoder(
|
|
146
|
+
json=jsonable_encoder(request),
|
|
146
147
|
headers=self._client_wrapper.get_headers(),
|
|
147
148
|
timeout=60,
|
|
148
149
|
)
|
|
@@ -175,7 +176,7 @@ class LlamaExtractClient:
|
|
|
175
176
|
_response = self._client_wrapper.httpx_client.request(
|
|
176
177
|
"GET",
|
|
177
178
|
urllib.parse.urljoin(
|
|
178
|
-
f"{self._client_wrapper.get_base_url()}/", f"api/v1/
|
|
179
|
+
f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/by-name/{name}"
|
|
179
180
|
),
|
|
180
181
|
params=remove_none_from_dict({"project_id": project_id}),
|
|
181
182
|
headers=self._client_wrapper.get_headers(),
|
|
@@ -208,8 +209,7 @@ class LlamaExtractClient:
|
|
|
208
209
|
_response = self._client_wrapper.httpx_client.request(
|
|
209
210
|
"GET",
|
|
210
211
|
urllib.parse.urljoin(
|
|
211
|
-
f"{self._client_wrapper.get_base_url()}/",
|
|
212
|
-
f"api/v1/extractionv2/extraction-agents/{extraction_agent_id}",
|
|
212
|
+
f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
|
|
213
213
|
),
|
|
214
214
|
headers=self._client_wrapper.get_headers(),
|
|
215
215
|
timeout=60,
|
|
@@ -224,18 +224,19 @@ class LlamaExtractClient:
|
|
|
224
224
|
raise ApiError(status_code=_response.status_code, body=_response.text)
|
|
225
225
|
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
226
226
|
|
|
227
|
-
def update_extraction_agent(
|
|
228
|
-
self, extraction_agent_id: str, *, data_schema: ExtractAgentUpdateDataSchema, config: ExtractConfig
|
|
229
|
-
) -> ExtractAgent:
|
|
227
|
+
def update_extraction_agent(self, extraction_agent_id: str, *, request: ExtractAgentUpdate) -> ExtractAgent:
|
|
230
228
|
"""
|
|
231
229
|
Parameters:
|
|
232
230
|
- extraction_agent_id: str.
|
|
233
231
|
|
|
234
|
-
-
|
|
235
|
-
|
|
236
|
-
- config: ExtractConfig. The configuration parameters for the extraction agent.
|
|
232
|
+
- request: ExtractAgentUpdate.
|
|
237
233
|
---
|
|
238
|
-
from llama_cloud import
|
|
234
|
+
from llama_cloud import (
|
|
235
|
+
ExtractAgentUpdate,
|
|
236
|
+
ExtractConfig,
|
|
237
|
+
ExtractMode,
|
|
238
|
+
ExtractTarget,
|
|
239
|
+
)
|
|
239
240
|
from llama_cloud.client import LlamaCloud
|
|
240
241
|
|
|
241
242
|
client = LlamaCloud(
|
|
@@ -243,19 +244,20 @@ class LlamaExtractClient:
|
|
|
243
244
|
)
|
|
244
245
|
client.llama_extract.update_extraction_agent(
|
|
245
246
|
extraction_agent_id="string",
|
|
246
|
-
|
|
247
|
-
|
|
248
|
-
|
|
247
|
+
request=ExtractAgentUpdate(
|
|
248
|
+
config=ExtractConfig(
|
|
249
|
+
extraction_target=ExtractTarget.PER_DOC,
|
|
250
|
+
extraction_mode=ExtractMode.FAST,
|
|
251
|
+
),
|
|
249
252
|
),
|
|
250
253
|
)
|
|
251
254
|
"""
|
|
252
255
|
_response = self._client_wrapper.httpx_client.request(
|
|
253
256
|
"PUT",
|
|
254
257
|
urllib.parse.urljoin(
|
|
255
|
-
f"{self._client_wrapper.get_base_url()}/",
|
|
256
|
-
f"api/v1/extractionv2/extraction-agents/{extraction_agent_id}",
|
|
258
|
+
f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
|
|
257
259
|
),
|
|
258
|
-
json=jsonable_encoder(
|
|
260
|
+
json=jsonable_encoder(request),
|
|
259
261
|
headers=self._client_wrapper.get_headers(),
|
|
260
262
|
timeout=60,
|
|
261
263
|
)
|
|
@@ -286,8 +288,7 @@ class LlamaExtractClient:
|
|
|
286
288
|
_response = self._client_wrapper.httpx_client.request(
|
|
287
289
|
"DELETE",
|
|
288
290
|
urllib.parse.urljoin(
|
|
289
|
-
f"{self._client_wrapper.get_base_url()}/",
|
|
290
|
-
f"api/v1/extractionv2/extraction-agents/{extraction_agent_id}",
|
|
291
|
+
f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
|
|
291
292
|
),
|
|
292
293
|
headers=self._client_wrapper.get_headers(),
|
|
293
294
|
timeout=60,
|
|
@@ -318,7 +319,7 @@ class LlamaExtractClient:
|
|
|
318
319
|
"""
|
|
319
320
|
_response = self._client_wrapper.httpx_client.request(
|
|
320
321
|
"GET",
|
|
321
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
322
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
|
|
322
323
|
params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
|
|
323
324
|
headers=self._client_wrapper.get_headers(),
|
|
324
325
|
timeout=60,
|
|
@@ -362,7 +363,7 @@ class LlamaExtractClient:
|
|
|
362
363
|
"""
|
|
363
364
|
_response = self._client_wrapper.httpx_client.request(
|
|
364
365
|
"POST",
|
|
365
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
366
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
|
|
366
367
|
json=jsonable_encoder(request),
|
|
367
368
|
headers=self._client_wrapper.get_headers(),
|
|
368
369
|
timeout=60,
|
|
@@ -393,7 +394,7 @@ class LlamaExtractClient:
|
|
|
393
394
|
"""
|
|
394
395
|
_response = self._client_wrapper.httpx_client.request(
|
|
395
396
|
"GET",
|
|
396
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/
|
|
397
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}"),
|
|
397
398
|
headers=self._client_wrapper.get_headers(),
|
|
398
399
|
timeout=60,
|
|
399
400
|
)
|
|
@@ -407,108 +408,6 @@ class LlamaExtractClient:
|
|
|
407
408
|
raise ApiError(status_code=_response.status_code, body=_response.text)
|
|
408
409
|
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
409
410
|
|
|
410
|
-
def run_job_with_parsed_file_test(
|
|
411
|
-
self, *, job_create: ExtractJobCreate, extract_settings: typing.Optional[LlamaExtractSettings] = OMIT
|
|
412
|
-
) -> ExtractResultset:
|
|
413
|
-
"""
|
|
414
|
-
Parameters:
|
|
415
|
-
- job_create: ExtractJobCreate.
|
|
416
|
-
|
|
417
|
-
- extract_settings: typing.Optional[LlamaExtractSettings].
|
|
418
|
-
---
|
|
419
|
-
from llama_cloud import (
|
|
420
|
-
ChunkMode,
|
|
421
|
-
ExtractConfig,
|
|
422
|
-
ExtractJobCreate,
|
|
423
|
-
ExtractMode,
|
|
424
|
-
ExtractTarget,
|
|
425
|
-
LlamaExtractSettings,
|
|
426
|
-
LlamaParseParameters,
|
|
427
|
-
)
|
|
428
|
-
from llama_cloud.client import LlamaCloud
|
|
429
|
-
|
|
430
|
-
client = LlamaCloud(
|
|
431
|
-
token="YOUR_TOKEN",
|
|
432
|
-
)
|
|
433
|
-
client.llama_extract.run_job_with_parsed_file_test(
|
|
434
|
-
job_create=ExtractJobCreate(
|
|
435
|
-
extraction_agent_id="string",
|
|
436
|
-
file_id="string",
|
|
437
|
-
config_override=ExtractConfig(
|
|
438
|
-
extraction_target=ExtractTarget.PER_DOC,
|
|
439
|
-
extraction_mode=ExtractMode.FAST,
|
|
440
|
-
),
|
|
441
|
-
),
|
|
442
|
-
extract_settings=LlamaExtractSettings(
|
|
443
|
-
chunk_mode=ChunkMode.PAGE,
|
|
444
|
-
llama_parse_params=LlamaParseParameters(),
|
|
445
|
-
),
|
|
446
|
-
)
|
|
447
|
-
"""
|
|
448
|
-
_request: typing.Dict[str, typing.Any] = {"job_create": job_create}
|
|
449
|
-
if extract_settings is not OMIT:
|
|
450
|
-
_request["extract_settings"] = extract_settings
|
|
451
|
-
_response = self._client_wrapper.httpx_client.request(
|
|
452
|
-
"POST",
|
|
453
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extractionv2/jobs/parsed/test"),
|
|
454
|
-
json=jsonable_encoder(_request),
|
|
455
|
-
headers=self._client_wrapper.get_headers(),
|
|
456
|
-
timeout=60,
|
|
457
|
-
)
|
|
458
|
-
if 200 <= _response.status_code < 300:
|
|
459
|
-
return pydantic.parse_obj_as(ExtractResultset, _response.json()) # type: ignore
|
|
460
|
-
if _response.status_code == 422:
|
|
461
|
-
raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore
|
|
462
|
-
try:
|
|
463
|
-
_response_json = _response.json()
|
|
464
|
-
except JSONDecodeError:
|
|
465
|
-
raise ApiError(status_code=_response.status_code, body=_response.text)
|
|
466
|
-
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
467
|
-
|
|
468
|
-
def run_job_with_parsed_file(self, *, request: ExtractJobCreate) -> ExtractResultset:
|
|
469
|
-
"""
|
|
470
|
-
Parameters:
|
|
471
|
-
- request: ExtractJobCreate.
|
|
472
|
-
---
|
|
473
|
-
from llama_cloud import (
|
|
474
|
-
ExtractConfig,
|
|
475
|
-
ExtractJobCreate,
|
|
476
|
-
ExtractMode,
|
|
477
|
-
ExtractTarget,
|
|
478
|
-
)
|
|
479
|
-
from llama_cloud.client import LlamaCloud
|
|
480
|
-
|
|
481
|
-
client = LlamaCloud(
|
|
482
|
-
token="YOUR_TOKEN",
|
|
483
|
-
)
|
|
484
|
-
client.llama_extract.run_job_with_parsed_file(
|
|
485
|
-
request=ExtractJobCreate(
|
|
486
|
-
extraction_agent_id="string",
|
|
487
|
-
file_id="string",
|
|
488
|
-
config_override=ExtractConfig(
|
|
489
|
-
extraction_target=ExtractTarget.PER_DOC,
|
|
490
|
-
extraction_mode=ExtractMode.FAST,
|
|
491
|
-
),
|
|
492
|
-
),
|
|
493
|
-
)
|
|
494
|
-
"""
|
|
495
|
-
_response = self._client_wrapper.httpx_client.request(
|
|
496
|
-
"POST",
|
|
497
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extractionv2/jobs/parsed"),
|
|
498
|
-
json=jsonable_encoder(request),
|
|
499
|
-
headers=self._client_wrapper.get_headers(),
|
|
500
|
-
timeout=60,
|
|
501
|
-
)
|
|
502
|
-
if 200 <= _response.status_code < 300:
|
|
503
|
-
return pydantic.parse_obj_as(ExtractResultset, _response.json()) # type: ignore
|
|
504
|
-
if _response.status_code == 422:
|
|
505
|
-
raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore
|
|
506
|
-
try:
|
|
507
|
-
_response_json = _response.json()
|
|
508
|
-
except JSONDecodeError:
|
|
509
|
-
raise ApiError(status_code=_response.status_code, body=_response.text)
|
|
510
|
-
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
511
|
-
|
|
512
411
|
def run_job_test_user(
|
|
513
412
|
self, *, job_create: ExtractJobCreate, extract_settings: typing.Optional[LlamaExtractSettings] = OMIT
|
|
514
413
|
) -> ExtractJob:
|
|
@@ -526,6 +425,7 @@ class LlamaExtractClient:
|
|
|
526
425
|
ExtractTarget,
|
|
527
426
|
LlamaExtractSettings,
|
|
528
427
|
LlamaParseParameters,
|
|
428
|
+
ParsingMode,
|
|
529
429
|
)
|
|
530
430
|
from llama_cloud.client import LlamaCloud
|
|
531
431
|
|
|
@@ -543,7 +443,9 @@ class LlamaExtractClient:
|
|
|
543
443
|
),
|
|
544
444
|
extract_settings=LlamaExtractSettings(
|
|
545
445
|
chunk_mode=ChunkMode.PAGE,
|
|
546
|
-
llama_parse_params=LlamaParseParameters(
|
|
446
|
+
llama_parse_params=LlamaParseParameters(
|
|
447
|
+
parse_mode=ParsingMode.PARSE_PAGE_WITHOUT_LLM,
|
|
448
|
+
),
|
|
547
449
|
),
|
|
548
450
|
)
|
|
549
451
|
"""
|
|
@@ -552,7 +454,7 @@ class LlamaExtractClient:
|
|
|
552
454
|
_request["extract_settings"] = extract_settings
|
|
553
455
|
_response = self._client_wrapper.httpx_client.request(
|
|
554
456
|
"POST",
|
|
555
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
457
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/test"),
|
|
556
458
|
json=jsonable_encoder(_request),
|
|
557
459
|
headers=self._client_wrapper.get_headers(),
|
|
558
460
|
timeout=60,
|
|
@@ -583,9 +485,7 @@ class LlamaExtractClient:
|
|
|
583
485
|
"""
|
|
584
486
|
_response = self._client_wrapper.httpx_client.request(
|
|
585
487
|
"GET",
|
|
586
|
-
urllib.parse.urljoin(
|
|
587
|
-
f"{self._client_wrapper.get_base_url()}/", f"api/v1/extractionv2/jobs/{job_id}/result"
|
|
588
|
-
),
|
|
488
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}/result"),
|
|
589
489
|
headers=self._client_wrapper.get_headers(),
|
|
590
490
|
timeout=60,
|
|
591
491
|
)
|
|
@@ -615,7 +515,7 @@ class LlamaExtractClient:
|
|
|
615
515
|
"""
|
|
616
516
|
_response = self._client_wrapper.httpx_client.request(
|
|
617
517
|
"GET",
|
|
618
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
518
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs"),
|
|
619
519
|
params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
|
|
620
520
|
headers=self._client_wrapper.get_headers(),
|
|
621
521
|
timeout=60,
|
|
@@ -646,9 +546,7 @@ class LlamaExtractClient:
|
|
|
646
546
|
"""
|
|
647
547
|
_response = self._client_wrapper.httpx_client.request(
|
|
648
548
|
"GET",
|
|
649
|
-
urllib.parse.urljoin(
|
|
650
|
-
f"{self._client_wrapper.get_base_url()}/", f"api/v1/extractionv2/runs/by-job/{job_id}"
|
|
651
|
-
),
|
|
549
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/by-job/{job_id}"),
|
|
652
550
|
headers=self._client_wrapper.get_headers(),
|
|
653
551
|
timeout=60,
|
|
654
552
|
)
|
|
@@ -678,7 +576,7 @@ class LlamaExtractClient:
|
|
|
678
576
|
"""
|
|
679
577
|
_response = self._client_wrapper.httpx_client.request(
|
|
680
578
|
"GET",
|
|
681
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/
|
|
579
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_id}"),
|
|
682
580
|
headers=self._client_wrapper.get_headers(),
|
|
683
581
|
timeout=60,
|
|
684
582
|
)
|
|
@@ -711,7 +609,7 @@ class AsyncLlamaExtractClient:
|
|
|
711
609
|
"""
|
|
712
610
|
_response = await self._client_wrapper.httpx_client.request(
|
|
713
611
|
"GET",
|
|
714
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
612
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"),
|
|
715
613
|
params=remove_none_from_dict({"project_id": project_id}),
|
|
716
614
|
headers=self._client_wrapper.get_headers(),
|
|
717
615
|
timeout=60,
|
|
@@ -731,9 +629,7 @@ class AsyncLlamaExtractClient:
|
|
|
731
629
|
*,
|
|
732
630
|
project_id: typing.Optional[str] = None,
|
|
733
631
|
organization_id: typing.Optional[str] = None,
|
|
734
|
-
|
|
735
|
-
data_schema: ExtractAgentCreateDataSchema,
|
|
736
|
-
config: ExtractConfig,
|
|
632
|
+
request: ExtractAgentCreate,
|
|
737
633
|
) -> ExtractAgent:
|
|
738
634
|
"""
|
|
739
635
|
Parameters:
|
|
@@ -741,31 +637,34 @@ class AsyncLlamaExtractClient:
|
|
|
741
637
|
|
|
742
638
|
- organization_id: typing.Optional[str].
|
|
743
639
|
|
|
744
|
-
-
|
|
745
|
-
|
|
746
|
-
- data_schema: ExtractAgentCreateDataSchema. The schema of the data.
|
|
747
|
-
|
|
748
|
-
- config: ExtractConfig. The configuration parameters for the extraction agent.
|
|
640
|
+
- request: ExtractAgentCreate.
|
|
749
641
|
---
|
|
750
|
-
from llama_cloud import
|
|
642
|
+
from llama_cloud import (
|
|
643
|
+
ExtractAgentCreate,
|
|
644
|
+
ExtractConfig,
|
|
645
|
+
ExtractMode,
|
|
646
|
+
ExtractTarget,
|
|
647
|
+
)
|
|
751
648
|
from llama_cloud.client import AsyncLlamaCloud
|
|
752
649
|
|
|
753
650
|
client = AsyncLlamaCloud(
|
|
754
651
|
token="YOUR_TOKEN",
|
|
755
652
|
)
|
|
756
653
|
await client.llama_extract.create_extraction_agent(
|
|
757
|
-
|
|
758
|
-
|
|
759
|
-
|
|
760
|
-
|
|
654
|
+
request=ExtractAgentCreate(
|
|
655
|
+
name="string",
|
|
656
|
+
config=ExtractConfig(
|
|
657
|
+
extraction_target=ExtractTarget.PER_DOC,
|
|
658
|
+
extraction_mode=ExtractMode.FAST,
|
|
659
|
+
),
|
|
761
660
|
),
|
|
762
661
|
)
|
|
763
662
|
"""
|
|
764
663
|
_response = await self._client_wrapper.httpx_client.request(
|
|
765
664
|
"POST",
|
|
766
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
665
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents"),
|
|
767
666
|
params=remove_none_from_dict({"project_id": project_id, "organization_id": organization_id}),
|
|
768
|
-
json=jsonable_encoder(
|
|
667
|
+
json=jsonable_encoder(request),
|
|
769
668
|
headers=self._client_wrapper.get_headers(),
|
|
770
669
|
timeout=60,
|
|
771
670
|
)
|
|
@@ -780,28 +679,31 @@ class AsyncLlamaExtractClient:
|
|
|
780
679
|
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
781
680
|
|
|
782
681
|
async def validate_extraction_schema(
|
|
783
|
-
self, *,
|
|
682
|
+
self, *, request: ExtractSchemaValidateRequest
|
|
784
683
|
) -> ExtractSchemaValidateResponse:
|
|
785
684
|
"""
|
|
786
685
|
Validates an extraction agent's schema definition.
|
|
787
686
|
Returns the normalized and validated schema if valid, otherwise raises an HTTP 400.
|
|
788
687
|
|
|
789
688
|
Parameters:
|
|
790
|
-
-
|
|
689
|
+
- request: ExtractSchemaValidateRequest.
|
|
791
690
|
---
|
|
691
|
+
from llama_cloud import ExtractSchemaValidateRequest
|
|
792
692
|
from llama_cloud.client import AsyncLlamaCloud
|
|
793
693
|
|
|
794
694
|
client = AsyncLlamaCloud(
|
|
795
695
|
token="YOUR_TOKEN",
|
|
796
696
|
)
|
|
797
|
-
await client.llama_extract.validate_extraction_schema(
|
|
697
|
+
await client.llama_extract.validate_extraction_schema(
|
|
698
|
+
request=ExtractSchemaValidateRequest(),
|
|
699
|
+
)
|
|
798
700
|
"""
|
|
799
701
|
_response = await self._client_wrapper.httpx_client.request(
|
|
800
702
|
"POST",
|
|
801
703
|
urllib.parse.urljoin(
|
|
802
|
-
f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
704
|
+
f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/extraction-agents/schema/validation"
|
|
803
705
|
),
|
|
804
|
-
json=jsonable_encoder(
|
|
706
|
+
json=jsonable_encoder(request),
|
|
805
707
|
headers=self._client_wrapper.get_headers(),
|
|
806
708
|
timeout=60,
|
|
807
709
|
)
|
|
@@ -834,7 +736,7 @@ class AsyncLlamaExtractClient:
|
|
|
834
736
|
_response = await self._client_wrapper.httpx_client.request(
|
|
835
737
|
"GET",
|
|
836
738
|
urllib.parse.urljoin(
|
|
837
|
-
f"{self._client_wrapper.get_base_url()}/", f"api/v1/
|
|
739
|
+
f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/by-name/{name}"
|
|
838
740
|
),
|
|
839
741
|
params=remove_none_from_dict({"project_id": project_id}),
|
|
840
742
|
headers=self._client_wrapper.get_headers(),
|
|
@@ -867,8 +769,7 @@ class AsyncLlamaExtractClient:
|
|
|
867
769
|
_response = await self._client_wrapper.httpx_client.request(
|
|
868
770
|
"GET",
|
|
869
771
|
urllib.parse.urljoin(
|
|
870
|
-
f"{self._client_wrapper.get_base_url()}/",
|
|
871
|
-
f"api/v1/extractionv2/extraction-agents/{extraction_agent_id}",
|
|
772
|
+
f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
|
|
872
773
|
),
|
|
873
774
|
headers=self._client_wrapper.get_headers(),
|
|
874
775
|
timeout=60,
|
|
@@ -883,18 +784,19 @@ class AsyncLlamaExtractClient:
|
|
|
883
784
|
raise ApiError(status_code=_response.status_code, body=_response.text)
|
|
884
785
|
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
885
786
|
|
|
886
|
-
async def update_extraction_agent(
|
|
887
|
-
self, extraction_agent_id: str, *, data_schema: ExtractAgentUpdateDataSchema, config: ExtractConfig
|
|
888
|
-
) -> ExtractAgent:
|
|
787
|
+
async def update_extraction_agent(self, extraction_agent_id: str, *, request: ExtractAgentUpdate) -> ExtractAgent:
|
|
889
788
|
"""
|
|
890
789
|
Parameters:
|
|
891
790
|
- extraction_agent_id: str.
|
|
892
791
|
|
|
893
|
-
-
|
|
894
|
-
|
|
895
|
-
- config: ExtractConfig. The configuration parameters for the extraction agent.
|
|
792
|
+
- request: ExtractAgentUpdate.
|
|
896
793
|
---
|
|
897
|
-
from llama_cloud import
|
|
794
|
+
from llama_cloud import (
|
|
795
|
+
ExtractAgentUpdate,
|
|
796
|
+
ExtractConfig,
|
|
797
|
+
ExtractMode,
|
|
798
|
+
ExtractTarget,
|
|
799
|
+
)
|
|
898
800
|
from llama_cloud.client import AsyncLlamaCloud
|
|
899
801
|
|
|
900
802
|
client = AsyncLlamaCloud(
|
|
@@ -902,19 +804,20 @@ class AsyncLlamaExtractClient:
|
|
|
902
804
|
)
|
|
903
805
|
await client.llama_extract.update_extraction_agent(
|
|
904
806
|
extraction_agent_id="string",
|
|
905
|
-
|
|
906
|
-
|
|
907
|
-
|
|
807
|
+
request=ExtractAgentUpdate(
|
|
808
|
+
config=ExtractConfig(
|
|
809
|
+
extraction_target=ExtractTarget.PER_DOC,
|
|
810
|
+
extraction_mode=ExtractMode.FAST,
|
|
811
|
+
),
|
|
908
812
|
),
|
|
909
813
|
)
|
|
910
814
|
"""
|
|
911
815
|
_response = await self._client_wrapper.httpx_client.request(
|
|
912
816
|
"PUT",
|
|
913
817
|
urllib.parse.urljoin(
|
|
914
|
-
f"{self._client_wrapper.get_base_url()}/",
|
|
915
|
-
f"api/v1/extractionv2/extraction-agents/{extraction_agent_id}",
|
|
818
|
+
f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
|
|
916
819
|
),
|
|
917
|
-
json=jsonable_encoder(
|
|
820
|
+
json=jsonable_encoder(request),
|
|
918
821
|
headers=self._client_wrapper.get_headers(),
|
|
919
822
|
timeout=60,
|
|
920
823
|
)
|
|
@@ -945,8 +848,7 @@ class AsyncLlamaExtractClient:
|
|
|
945
848
|
_response = await self._client_wrapper.httpx_client.request(
|
|
946
849
|
"DELETE",
|
|
947
850
|
urllib.parse.urljoin(
|
|
948
|
-
f"{self._client_wrapper.get_base_url()}/",
|
|
949
|
-
f"api/v1/extractionv2/extraction-agents/{extraction_agent_id}",
|
|
851
|
+
f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/extraction-agents/{extraction_agent_id}"
|
|
950
852
|
),
|
|
951
853
|
headers=self._client_wrapper.get_headers(),
|
|
952
854
|
timeout=60,
|
|
@@ -977,7 +879,7 @@ class AsyncLlamaExtractClient:
|
|
|
977
879
|
"""
|
|
978
880
|
_response = await self._client_wrapper.httpx_client.request(
|
|
979
881
|
"GET",
|
|
980
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
882
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
|
|
981
883
|
params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
|
|
982
884
|
headers=self._client_wrapper.get_headers(),
|
|
983
885
|
timeout=60,
|
|
@@ -1021,7 +923,7 @@ class AsyncLlamaExtractClient:
|
|
|
1021
923
|
"""
|
|
1022
924
|
_response = await self._client_wrapper.httpx_client.request(
|
|
1023
925
|
"POST",
|
|
1024
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
926
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs"),
|
|
1025
927
|
json=jsonable_encoder(request),
|
|
1026
928
|
headers=self._client_wrapper.get_headers(),
|
|
1027
929
|
timeout=60,
|
|
@@ -1052,7 +954,7 @@ class AsyncLlamaExtractClient:
|
|
|
1052
954
|
"""
|
|
1053
955
|
_response = await self._client_wrapper.httpx_client.request(
|
|
1054
956
|
"GET",
|
|
1055
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/
|
|
957
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}"),
|
|
1056
958
|
headers=self._client_wrapper.get_headers(),
|
|
1057
959
|
timeout=60,
|
|
1058
960
|
)
|
|
@@ -1066,108 +968,6 @@ class AsyncLlamaExtractClient:
|
|
|
1066
968
|
raise ApiError(status_code=_response.status_code, body=_response.text)
|
|
1067
969
|
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
1068
970
|
|
|
1069
|
-
async def run_job_with_parsed_file_test(
|
|
1070
|
-
self, *, job_create: ExtractJobCreate, extract_settings: typing.Optional[LlamaExtractSettings] = OMIT
|
|
1071
|
-
) -> ExtractResultset:
|
|
1072
|
-
"""
|
|
1073
|
-
Parameters:
|
|
1074
|
-
- job_create: ExtractJobCreate.
|
|
1075
|
-
|
|
1076
|
-
- extract_settings: typing.Optional[LlamaExtractSettings].
|
|
1077
|
-
---
|
|
1078
|
-
from llama_cloud import (
|
|
1079
|
-
ChunkMode,
|
|
1080
|
-
ExtractConfig,
|
|
1081
|
-
ExtractJobCreate,
|
|
1082
|
-
ExtractMode,
|
|
1083
|
-
ExtractTarget,
|
|
1084
|
-
LlamaExtractSettings,
|
|
1085
|
-
LlamaParseParameters,
|
|
1086
|
-
)
|
|
1087
|
-
from llama_cloud.client import AsyncLlamaCloud
|
|
1088
|
-
|
|
1089
|
-
client = AsyncLlamaCloud(
|
|
1090
|
-
token="YOUR_TOKEN",
|
|
1091
|
-
)
|
|
1092
|
-
await client.llama_extract.run_job_with_parsed_file_test(
|
|
1093
|
-
job_create=ExtractJobCreate(
|
|
1094
|
-
extraction_agent_id="string",
|
|
1095
|
-
file_id="string",
|
|
1096
|
-
config_override=ExtractConfig(
|
|
1097
|
-
extraction_target=ExtractTarget.PER_DOC,
|
|
1098
|
-
extraction_mode=ExtractMode.FAST,
|
|
1099
|
-
),
|
|
1100
|
-
),
|
|
1101
|
-
extract_settings=LlamaExtractSettings(
|
|
1102
|
-
chunk_mode=ChunkMode.PAGE,
|
|
1103
|
-
llama_parse_params=LlamaParseParameters(),
|
|
1104
|
-
),
|
|
1105
|
-
)
|
|
1106
|
-
"""
|
|
1107
|
-
_request: typing.Dict[str, typing.Any] = {"job_create": job_create}
|
|
1108
|
-
if extract_settings is not OMIT:
|
|
1109
|
-
_request["extract_settings"] = extract_settings
|
|
1110
|
-
_response = await self._client_wrapper.httpx_client.request(
|
|
1111
|
-
"POST",
|
|
1112
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extractionv2/jobs/parsed/test"),
|
|
1113
|
-
json=jsonable_encoder(_request),
|
|
1114
|
-
headers=self._client_wrapper.get_headers(),
|
|
1115
|
-
timeout=60,
|
|
1116
|
-
)
|
|
1117
|
-
if 200 <= _response.status_code < 300:
|
|
1118
|
-
return pydantic.parse_obj_as(ExtractResultset, _response.json()) # type: ignore
|
|
1119
|
-
if _response.status_code == 422:
|
|
1120
|
-
raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore
|
|
1121
|
-
try:
|
|
1122
|
-
_response_json = _response.json()
|
|
1123
|
-
except JSONDecodeError:
|
|
1124
|
-
raise ApiError(status_code=_response.status_code, body=_response.text)
|
|
1125
|
-
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
1126
|
-
|
|
1127
|
-
async def run_job_with_parsed_file(self, *, request: ExtractJobCreate) -> ExtractResultset:
|
|
1128
|
-
"""
|
|
1129
|
-
Parameters:
|
|
1130
|
-
- request: ExtractJobCreate.
|
|
1131
|
-
---
|
|
1132
|
-
from llama_cloud import (
|
|
1133
|
-
ExtractConfig,
|
|
1134
|
-
ExtractJobCreate,
|
|
1135
|
-
ExtractMode,
|
|
1136
|
-
ExtractTarget,
|
|
1137
|
-
)
|
|
1138
|
-
from llama_cloud.client import AsyncLlamaCloud
|
|
1139
|
-
|
|
1140
|
-
client = AsyncLlamaCloud(
|
|
1141
|
-
token="YOUR_TOKEN",
|
|
1142
|
-
)
|
|
1143
|
-
await client.llama_extract.run_job_with_parsed_file(
|
|
1144
|
-
request=ExtractJobCreate(
|
|
1145
|
-
extraction_agent_id="string",
|
|
1146
|
-
file_id="string",
|
|
1147
|
-
config_override=ExtractConfig(
|
|
1148
|
-
extraction_target=ExtractTarget.PER_DOC,
|
|
1149
|
-
extraction_mode=ExtractMode.FAST,
|
|
1150
|
-
),
|
|
1151
|
-
),
|
|
1152
|
-
)
|
|
1153
|
-
"""
|
|
1154
|
-
_response = await self._client_wrapper.httpx_client.request(
|
|
1155
|
-
"POST",
|
|
1156
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extractionv2/jobs/parsed"),
|
|
1157
|
-
json=jsonable_encoder(request),
|
|
1158
|
-
headers=self._client_wrapper.get_headers(),
|
|
1159
|
-
timeout=60,
|
|
1160
|
-
)
|
|
1161
|
-
if 200 <= _response.status_code < 300:
|
|
1162
|
-
return pydantic.parse_obj_as(ExtractResultset, _response.json()) # type: ignore
|
|
1163
|
-
if _response.status_code == 422:
|
|
1164
|
-
raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore
|
|
1165
|
-
try:
|
|
1166
|
-
_response_json = _response.json()
|
|
1167
|
-
except JSONDecodeError:
|
|
1168
|
-
raise ApiError(status_code=_response.status_code, body=_response.text)
|
|
1169
|
-
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
1170
|
-
|
|
1171
971
|
async def run_job_test_user(
|
|
1172
972
|
self, *, job_create: ExtractJobCreate, extract_settings: typing.Optional[LlamaExtractSettings] = OMIT
|
|
1173
973
|
) -> ExtractJob:
|
|
@@ -1185,6 +985,7 @@ class AsyncLlamaExtractClient:
|
|
|
1185
985
|
ExtractTarget,
|
|
1186
986
|
LlamaExtractSettings,
|
|
1187
987
|
LlamaParseParameters,
|
|
988
|
+
ParsingMode,
|
|
1188
989
|
)
|
|
1189
990
|
from llama_cloud.client import AsyncLlamaCloud
|
|
1190
991
|
|
|
@@ -1202,7 +1003,9 @@ class AsyncLlamaExtractClient:
|
|
|
1202
1003
|
),
|
|
1203
1004
|
extract_settings=LlamaExtractSettings(
|
|
1204
1005
|
chunk_mode=ChunkMode.PAGE,
|
|
1205
|
-
llama_parse_params=LlamaParseParameters(
|
|
1006
|
+
llama_parse_params=LlamaParseParameters(
|
|
1007
|
+
parse_mode=ParsingMode.PARSE_PAGE_WITHOUT_LLM,
|
|
1008
|
+
),
|
|
1206
1009
|
),
|
|
1207
1010
|
)
|
|
1208
1011
|
"""
|
|
@@ -1211,7 +1014,7 @@ class AsyncLlamaExtractClient:
|
|
|
1211
1014
|
_request["extract_settings"] = extract_settings
|
|
1212
1015
|
_response = await self._client_wrapper.httpx_client.request(
|
|
1213
1016
|
"POST",
|
|
1214
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
1017
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/jobs/test"),
|
|
1215
1018
|
json=jsonable_encoder(_request),
|
|
1216
1019
|
headers=self._client_wrapper.get_headers(),
|
|
1217
1020
|
timeout=60,
|
|
@@ -1242,9 +1045,7 @@ class AsyncLlamaExtractClient:
|
|
|
1242
1045
|
"""
|
|
1243
1046
|
_response = await self._client_wrapper.httpx_client.request(
|
|
1244
1047
|
"GET",
|
|
1245
|
-
urllib.parse.urljoin(
|
|
1246
|
-
f"{self._client_wrapper.get_base_url()}/", f"api/v1/extractionv2/jobs/{job_id}/result"
|
|
1247
|
-
),
|
|
1048
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/jobs/{job_id}/result"),
|
|
1248
1049
|
headers=self._client_wrapper.get_headers(),
|
|
1249
1050
|
timeout=60,
|
|
1250
1051
|
)
|
|
@@ -1274,7 +1075,7 @@ class AsyncLlamaExtractClient:
|
|
|
1274
1075
|
"""
|
|
1275
1076
|
_response = await self._client_wrapper.httpx_client.request(
|
|
1276
1077
|
"GET",
|
|
1277
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/
|
|
1078
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/runs"),
|
|
1278
1079
|
params=remove_none_from_dict({"extraction_agent_id": extraction_agent_id}),
|
|
1279
1080
|
headers=self._client_wrapper.get_headers(),
|
|
1280
1081
|
timeout=60,
|
|
@@ -1305,9 +1106,7 @@ class AsyncLlamaExtractClient:
|
|
|
1305
1106
|
"""
|
|
1306
1107
|
_response = await self._client_wrapper.httpx_client.request(
|
|
1307
1108
|
"GET",
|
|
1308
|
-
urllib.parse.urljoin(
|
|
1309
|
-
f"{self._client_wrapper.get_base_url()}/", f"api/v1/extractionv2/runs/by-job/{job_id}"
|
|
1310
|
-
),
|
|
1109
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/by-job/{job_id}"),
|
|
1311
1110
|
headers=self._client_wrapper.get_headers(),
|
|
1312
1111
|
timeout=60,
|
|
1313
1112
|
)
|
|
@@ -1337,7 +1136,7 @@ class AsyncLlamaExtractClient:
|
|
|
1337
1136
|
"""
|
|
1338
1137
|
_response = await self._client_wrapper.httpx_client.request(
|
|
1339
1138
|
"GET",
|
|
1340
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/
|
|
1139
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", f"api/v1/extraction/runs/{run_id}"),
|
|
1341
1140
|
headers=self._client_wrapper.get_headers(),
|
|
1342
1141
|
timeout=60,
|
|
1343
1142
|
)
|