llama-cloud 0.0.10__py3-none-any.whl → 0.0.11__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 +14 -0
- llama_cloud/resources/__init__.py +2 -1
- llama_cloud/resources/extraction/__init__.py +2 -2
- llama_cloud/resources/extraction/client.py +139 -48
- llama_cloud/resources/extraction/types/__init__.py +2 -1
- llama_cloud/resources/extraction/types/extraction_schema_create_data_schema_value.py +7 -0
- llama_cloud/resources/pipelines/client.py +96 -2
- llama_cloud/types/__init__.py +12 -0
- llama_cloud/types/auto_transform_config.py +32 -0
- llama_cloud/types/embedding_config.py +36 -0
- llama_cloud/types/embedding_config_component.py +19 -0
- llama_cloud/types/embedding_config_type.py +41 -0
- llama_cloud/types/pipeline_create.py +8 -0
- llama_cloud/types/transform_config.py +36 -0
- llama_cloud/types/transform_config_mode.py +21 -0
- {llama_cloud-0.0.10.dist-info → llama_cloud-0.0.11.dist-info}/METADATA +1 -1
- {llama_cloud-0.0.10.dist-info → llama_cloud-0.0.11.dist-info}/RECORD +19 -12
- {llama_cloud-0.0.10.dist-info → llama_cloud-0.0.11.dist-info}/LICENSE +0 -0
- {llama_cloud-0.0.10.dist-info → llama_cloud-0.0.11.dist-info}/WHEEL +0 -0
llama_cloud/__init__.py
CHANGED
|
@@ -1,6 +1,7 @@
|
|
|
1
1
|
# This file was auto-generated by Fern from our API Definition.
|
|
2
2
|
|
|
3
3
|
from .types import (
|
|
4
|
+
AutoTransformConfig,
|
|
4
5
|
AzureOpenAiEmbedding,
|
|
5
6
|
Base,
|
|
6
7
|
BasePromptTemplate,
|
|
@@ -48,6 +49,9 @@ from .types import (
|
|
|
48
49
|
DataSourceCreateCustomMetadataValue,
|
|
49
50
|
DataSourceCustomMetadataValue,
|
|
50
51
|
DataSourceDefinition,
|
|
52
|
+
EmbeddingConfig,
|
|
53
|
+
EmbeddingConfigComponent,
|
|
54
|
+
EmbeddingConfigType,
|
|
51
55
|
EvalDataset,
|
|
52
56
|
EvalDatasetJobParams,
|
|
53
57
|
EvalDatasetJobRecord,
|
|
@@ -134,6 +138,8 @@ from .types import (
|
|
|
134
138
|
TextNodeRelationshipsValue,
|
|
135
139
|
TextNodeWithScore,
|
|
136
140
|
TokenTextSplitter,
|
|
141
|
+
TransformConfig,
|
|
142
|
+
TransformConfigMode,
|
|
137
143
|
TransformationCategoryNames,
|
|
138
144
|
UserOrganization,
|
|
139
145
|
UserOrganizationCreate,
|
|
@@ -148,6 +154,7 @@ from .resources import (
|
|
|
148
154
|
DataSourceUpdateComponent,
|
|
149
155
|
DataSourceUpdateComponentOne,
|
|
150
156
|
DataSourceUpdateCustomMetadataValue,
|
|
157
|
+
ExtractionSchemaCreateDataSchemaValue,
|
|
151
158
|
ExtractionSchemaUpdateDataSchemaValue,
|
|
152
159
|
FileCreateResourceInfoValue,
|
|
153
160
|
PipelineFileUpdateCustomMetadataValue,
|
|
@@ -165,6 +172,7 @@ from .resources import (
|
|
|
165
172
|
from .environment import LlamaCloudEnvironment
|
|
166
173
|
|
|
167
174
|
__all__ = [
|
|
175
|
+
"AutoTransformConfig",
|
|
168
176
|
"AzureOpenAiEmbedding",
|
|
169
177
|
"Base",
|
|
170
178
|
"BasePromptTemplate",
|
|
@@ -217,6 +225,9 @@ __all__ = [
|
|
|
217
225
|
"DataSourceUpdateComponent",
|
|
218
226
|
"DataSourceUpdateComponentOne",
|
|
219
227
|
"DataSourceUpdateCustomMetadataValue",
|
|
228
|
+
"EmbeddingConfig",
|
|
229
|
+
"EmbeddingConfigComponent",
|
|
230
|
+
"EmbeddingConfigType",
|
|
220
231
|
"EvalDataset",
|
|
221
232
|
"EvalDatasetJobParams",
|
|
222
233
|
"EvalDatasetJobRecord",
|
|
@@ -230,6 +241,7 @@ __all__ = [
|
|
|
230
241
|
"ExtractionResult",
|
|
231
242
|
"ExtractionResultDataValue",
|
|
232
243
|
"ExtractionSchema",
|
|
244
|
+
"ExtractionSchemaCreateDataSchemaValue",
|
|
233
245
|
"ExtractionSchemaDataSchemaValue",
|
|
234
246
|
"ExtractionSchemaUpdateDataSchemaValue",
|
|
235
247
|
"File",
|
|
@@ -307,6 +319,8 @@ __all__ = [
|
|
|
307
319
|
"TextNodeRelationshipsValue",
|
|
308
320
|
"TextNodeWithScore",
|
|
309
321
|
"TokenTextSplitter",
|
|
322
|
+
"TransformConfig",
|
|
323
|
+
"TransformConfigMode",
|
|
310
324
|
"TransformationCategoryNames",
|
|
311
325
|
"UnprocessableEntityError",
|
|
312
326
|
"UserOrganization",
|
|
@@ -14,7 +14,7 @@ from . import (
|
|
|
14
14
|
)
|
|
15
15
|
from .data_sinks import DataSinkUpdateComponent, DataSinkUpdateComponentOne
|
|
16
16
|
from .data_sources import DataSourceUpdateComponent, DataSourceUpdateComponentOne, DataSourceUpdateCustomMetadataValue
|
|
17
|
-
from .extraction import ExtractionSchemaUpdateDataSchemaValue
|
|
17
|
+
from .extraction import ExtractionSchemaCreateDataSchemaValue, ExtractionSchemaUpdateDataSchemaValue
|
|
18
18
|
from .files import FileCreateResourceInfoValue
|
|
19
19
|
from .pipelines import PipelineFileUpdateCustomMetadataValue
|
|
20
20
|
|
|
@@ -24,6 +24,7 @@ __all__ = [
|
|
|
24
24
|
"DataSourceUpdateComponent",
|
|
25
25
|
"DataSourceUpdateComponentOne",
|
|
26
26
|
"DataSourceUpdateCustomMetadataValue",
|
|
27
|
+
"ExtractionSchemaCreateDataSchemaValue",
|
|
27
28
|
"ExtractionSchemaUpdateDataSchemaValue",
|
|
28
29
|
"FileCreateResourceInfoValue",
|
|
29
30
|
"PipelineFileUpdateCustomMetadataValue",
|
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
# This file was auto-generated by Fern from our API Definition.
|
|
2
2
|
|
|
3
|
-
from .types import ExtractionSchemaUpdateDataSchemaValue
|
|
3
|
+
from .types import ExtractionSchemaCreateDataSchemaValue, ExtractionSchemaUpdateDataSchemaValue
|
|
4
4
|
|
|
5
|
-
__all__ = ["ExtractionSchemaUpdateDataSchemaValue"]
|
|
5
|
+
__all__ = ["ExtractionSchemaCreateDataSchemaValue", "ExtractionSchemaUpdateDataSchemaValue"]
|
|
@@ -13,6 +13,7 @@ from ...types.extraction_job import ExtractionJob
|
|
|
13
13
|
from ...types.extraction_result import ExtractionResult
|
|
14
14
|
from ...types.extraction_schema import ExtractionSchema
|
|
15
15
|
from ...types.http_validation_error import HttpValidationError
|
|
16
|
+
from .types.extraction_schema_create_data_schema_value import ExtractionSchemaCreateDataSchemaValue
|
|
16
17
|
from .types.extraction_schema_update_data_schema_value import ExtractionSchemaUpdateDataSchemaValue
|
|
17
18
|
|
|
18
19
|
try:
|
|
@@ -31,47 +32,66 @@ class ExtractionClient:
|
|
|
31
32
|
def __init__(self, *, client_wrapper: SyncClientWrapper):
|
|
32
33
|
self._client_wrapper = client_wrapper
|
|
33
34
|
|
|
34
|
-
def
|
|
35
|
+
def list_schemas(self, *, project_id: typing.Optional[str] = None) -> typing.List[ExtractionSchema]:
|
|
36
|
+
"""
|
|
37
|
+
Parameters:
|
|
38
|
+
- project_id: typing.Optional[str].
|
|
39
|
+
---
|
|
40
|
+
from llama_cloud.client import LlamaCloud
|
|
41
|
+
|
|
42
|
+
client = LlamaCloud(
|
|
43
|
+
token="YOUR_TOKEN",
|
|
44
|
+
)
|
|
45
|
+
client.extraction.list_schemas()
|
|
46
|
+
"""
|
|
47
|
+
_response = self._client_wrapper.httpx_client.request(
|
|
48
|
+
"GET",
|
|
49
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas"),
|
|
50
|
+
params=remove_none_from_dict({"project_id": project_id}),
|
|
51
|
+
headers=self._client_wrapper.get_headers(),
|
|
52
|
+
timeout=60,
|
|
53
|
+
)
|
|
54
|
+
if 200 <= _response.status_code < 300:
|
|
55
|
+
return pydantic.parse_obj_as(typing.List[ExtractionSchema], _response.json()) # type: ignore
|
|
56
|
+
if _response.status_code == 422:
|
|
57
|
+
raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore
|
|
58
|
+
try:
|
|
59
|
+
_response_json = _response.json()
|
|
60
|
+
except JSONDecodeError:
|
|
61
|
+
raise ApiError(status_code=_response.status_code, body=_response.text)
|
|
62
|
+
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
63
|
+
|
|
64
|
+
def create_schema(
|
|
35
65
|
self,
|
|
36
66
|
*,
|
|
37
|
-
schema_id: typing.Optional[str] = OMIT,
|
|
38
67
|
name: str,
|
|
39
68
|
project_id: typing.Optional[str] = OMIT,
|
|
40
|
-
|
|
41
|
-
stream: typing.Optional[bool] = OMIT,
|
|
69
|
+
data_schema: typing.Dict[str, ExtractionSchemaCreateDataSchemaValue],
|
|
42
70
|
) -> ExtractionSchema:
|
|
43
71
|
"""
|
|
44
72
|
Parameters:
|
|
45
|
-
- schema_id: typing.Optional[str]. The ID of a schema to update with the new schema
|
|
46
|
-
|
|
47
73
|
- name: str. The name of the extraction schema
|
|
48
74
|
|
|
49
75
|
- project_id: typing.Optional[str]. The ID of the project that the extraction schema belongs to
|
|
50
76
|
|
|
51
|
-
-
|
|
52
|
-
|
|
53
|
-
- stream: typing.Optional[bool]. Whether to stream the results of the extraction schema
|
|
77
|
+
- data_schema: typing.Dict[str, ExtractionSchemaCreateDataSchemaValue]. The schema of the data
|
|
54
78
|
---
|
|
55
79
|
from llama_cloud.client import LlamaCloud
|
|
56
80
|
|
|
57
81
|
client = LlamaCloud(
|
|
58
82
|
token="YOUR_TOKEN",
|
|
59
83
|
)
|
|
60
|
-
client.extraction.
|
|
84
|
+
client.extraction.create_schema(
|
|
61
85
|
name="string",
|
|
62
|
-
|
|
86
|
+
data_schema={},
|
|
63
87
|
)
|
|
64
88
|
"""
|
|
65
|
-
_request: typing.Dict[str, typing.Any] = {"name": name, "
|
|
66
|
-
if schema_id is not OMIT:
|
|
67
|
-
_request["schema_id"] = schema_id
|
|
89
|
+
_request: typing.Dict[str, typing.Any] = {"name": name, "data_schema": data_schema}
|
|
68
90
|
if project_id is not OMIT:
|
|
69
91
|
_request["project_id"] = project_id
|
|
70
|
-
if stream is not OMIT:
|
|
71
|
-
_request["stream"] = stream
|
|
72
92
|
_response = self._client_wrapper.httpx_client.request(
|
|
73
93
|
"POST",
|
|
74
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas
|
|
94
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas"),
|
|
75
95
|
json=jsonable_encoder(_request),
|
|
76
96
|
headers=self._client_wrapper.get_headers(),
|
|
77
97
|
timeout=60,
|
|
@@ -86,27 +106,53 @@ class ExtractionClient:
|
|
|
86
106
|
raise ApiError(status_code=_response.status_code, body=_response.text)
|
|
87
107
|
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
88
108
|
|
|
89
|
-
def
|
|
109
|
+
def infer_schema(
|
|
110
|
+
self,
|
|
111
|
+
*,
|
|
112
|
+
schema_id: typing.Optional[str] = OMIT,
|
|
113
|
+
name: str,
|
|
114
|
+
project_id: typing.Optional[str] = OMIT,
|
|
115
|
+
file_ids: typing.List[str],
|
|
116
|
+
stream: typing.Optional[bool] = OMIT,
|
|
117
|
+
) -> ExtractionSchema:
|
|
90
118
|
"""
|
|
91
119
|
Parameters:
|
|
92
|
-
-
|
|
120
|
+
- schema_id: typing.Optional[str]. The ID of a schema to update with the new schema
|
|
121
|
+
|
|
122
|
+
- name: str. The name of the extraction schema
|
|
123
|
+
|
|
124
|
+
- project_id: typing.Optional[str]. The ID of the project that the extraction schema belongs to
|
|
125
|
+
|
|
126
|
+
- file_ids: typing.List[str]. The IDs of the files that the extraction schema contains
|
|
127
|
+
|
|
128
|
+
- stream: typing.Optional[bool]. Whether to stream the results of the extraction schema
|
|
93
129
|
---
|
|
94
130
|
from llama_cloud.client import LlamaCloud
|
|
95
131
|
|
|
96
132
|
client = LlamaCloud(
|
|
97
133
|
token="YOUR_TOKEN",
|
|
98
134
|
)
|
|
99
|
-
client.extraction.
|
|
135
|
+
client.extraction.infer_schema(
|
|
136
|
+
name="string",
|
|
137
|
+
file_ids=[],
|
|
138
|
+
)
|
|
100
139
|
"""
|
|
140
|
+
_request: typing.Dict[str, typing.Any] = {"name": name, "file_ids": file_ids}
|
|
141
|
+
if schema_id is not OMIT:
|
|
142
|
+
_request["schema_id"] = schema_id
|
|
143
|
+
if project_id is not OMIT:
|
|
144
|
+
_request["project_id"] = project_id
|
|
145
|
+
if stream is not OMIT:
|
|
146
|
+
_request["stream"] = stream
|
|
101
147
|
_response = self._client_wrapper.httpx_client.request(
|
|
102
|
-
"
|
|
103
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas"),
|
|
104
|
-
|
|
148
|
+
"POST",
|
|
149
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas/infer"),
|
|
150
|
+
json=jsonable_encoder(_request),
|
|
105
151
|
headers=self._client_wrapper.get_headers(),
|
|
106
152
|
timeout=60,
|
|
107
153
|
)
|
|
108
154
|
if 200 <= _response.status_code < 300:
|
|
109
|
-
return pydantic.parse_obj_as(
|
|
155
|
+
return pydantic.parse_obj_as(ExtractionSchema, _response.json()) # type: ignore
|
|
110
156
|
if _response.status_code == 422:
|
|
111
157
|
raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore
|
|
112
158
|
try:
|
|
@@ -350,47 +396,66 @@ class AsyncExtractionClient:
|
|
|
350
396
|
def __init__(self, *, client_wrapper: AsyncClientWrapper):
|
|
351
397
|
self._client_wrapper = client_wrapper
|
|
352
398
|
|
|
353
|
-
async def
|
|
399
|
+
async def list_schemas(self, *, project_id: typing.Optional[str] = None) -> typing.List[ExtractionSchema]:
|
|
400
|
+
"""
|
|
401
|
+
Parameters:
|
|
402
|
+
- project_id: typing.Optional[str].
|
|
403
|
+
---
|
|
404
|
+
from llama_cloud.client import AsyncLlamaCloud
|
|
405
|
+
|
|
406
|
+
client = AsyncLlamaCloud(
|
|
407
|
+
token="YOUR_TOKEN",
|
|
408
|
+
)
|
|
409
|
+
await client.extraction.list_schemas()
|
|
410
|
+
"""
|
|
411
|
+
_response = await self._client_wrapper.httpx_client.request(
|
|
412
|
+
"GET",
|
|
413
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas"),
|
|
414
|
+
params=remove_none_from_dict({"project_id": project_id}),
|
|
415
|
+
headers=self._client_wrapper.get_headers(),
|
|
416
|
+
timeout=60,
|
|
417
|
+
)
|
|
418
|
+
if 200 <= _response.status_code < 300:
|
|
419
|
+
return pydantic.parse_obj_as(typing.List[ExtractionSchema], _response.json()) # type: ignore
|
|
420
|
+
if _response.status_code == 422:
|
|
421
|
+
raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore
|
|
422
|
+
try:
|
|
423
|
+
_response_json = _response.json()
|
|
424
|
+
except JSONDecodeError:
|
|
425
|
+
raise ApiError(status_code=_response.status_code, body=_response.text)
|
|
426
|
+
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
427
|
+
|
|
428
|
+
async def create_schema(
|
|
354
429
|
self,
|
|
355
430
|
*,
|
|
356
|
-
schema_id: typing.Optional[str] = OMIT,
|
|
357
431
|
name: str,
|
|
358
432
|
project_id: typing.Optional[str] = OMIT,
|
|
359
|
-
|
|
360
|
-
stream: typing.Optional[bool] = OMIT,
|
|
433
|
+
data_schema: typing.Dict[str, ExtractionSchemaCreateDataSchemaValue],
|
|
361
434
|
) -> ExtractionSchema:
|
|
362
435
|
"""
|
|
363
436
|
Parameters:
|
|
364
|
-
- schema_id: typing.Optional[str]. The ID of a schema to update with the new schema
|
|
365
|
-
|
|
366
437
|
- name: str. The name of the extraction schema
|
|
367
438
|
|
|
368
439
|
- project_id: typing.Optional[str]. The ID of the project that the extraction schema belongs to
|
|
369
440
|
|
|
370
|
-
-
|
|
371
|
-
|
|
372
|
-
- stream: typing.Optional[bool]. Whether to stream the results of the extraction schema
|
|
441
|
+
- data_schema: typing.Dict[str, ExtractionSchemaCreateDataSchemaValue]. The schema of the data
|
|
373
442
|
---
|
|
374
443
|
from llama_cloud.client import AsyncLlamaCloud
|
|
375
444
|
|
|
376
445
|
client = AsyncLlamaCloud(
|
|
377
446
|
token="YOUR_TOKEN",
|
|
378
447
|
)
|
|
379
|
-
await client.extraction.
|
|
448
|
+
await client.extraction.create_schema(
|
|
380
449
|
name="string",
|
|
381
|
-
|
|
450
|
+
data_schema={},
|
|
382
451
|
)
|
|
383
452
|
"""
|
|
384
|
-
_request: typing.Dict[str, typing.Any] = {"name": name, "
|
|
385
|
-
if schema_id is not OMIT:
|
|
386
|
-
_request["schema_id"] = schema_id
|
|
453
|
+
_request: typing.Dict[str, typing.Any] = {"name": name, "data_schema": data_schema}
|
|
387
454
|
if project_id is not OMIT:
|
|
388
455
|
_request["project_id"] = project_id
|
|
389
|
-
if stream is not OMIT:
|
|
390
|
-
_request["stream"] = stream
|
|
391
456
|
_response = await self._client_wrapper.httpx_client.request(
|
|
392
457
|
"POST",
|
|
393
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas
|
|
458
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas"),
|
|
394
459
|
json=jsonable_encoder(_request),
|
|
395
460
|
headers=self._client_wrapper.get_headers(),
|
|
396
461
|
timeout=60,
|
|
@@ -405,27 +470,53 @@ class AsyncExtractionClient:
|
|
|
405
470
|
raise ApiError(status_code=_response.status_code, body=_response.text)
|
|
406
471
|
raise ApiError(status_code=_response.status_code, body=_response_json)
|
|
407
472
|
|
|
408
|
-
async def
|
|
473
|
+
async def infer_schema(
|
|
474
|
+
self,
|
|
475
|
+
*,
|
|
476
|
+
schema_id: typing.Optional[str] = OMIT,
|
|
477
|
+
name: str,
|
|
478
|
+
project_id: typing.Optional[str] = OMIT,
|
|
479
|
+
file_ids: typing.List[str],
|
|
480
|
+
stream: typing.Optional[bool] = OMIT,
|
|
481
|
+
) -> ExtractionSchema:
|
|
409
482
|
"""
|
|
410
483
|
Parameters:
|
|
411
|
-
-
|
|
484
|
+
- schema_id: typing.Optional[str]. The ID of a schema to update with the new schema
|
|
485
|
+
|
|
486
|
+
- name: str. The name of the extraction schema
|
|
487
|
+
|
|
488
|
+
- project_id: typing.Optional[str]. The ID of the project that the extraction schema belongs to
|
|
489
|
+
|
|
490
|
+
- file_ids: typing.List[str]. The IDs of the files that the extraction schema contains
|
|
491
|
+
|
|
492
|
+
- stream: typing.Optional[bool]. Whether to stream the results of the extraction schema
|
|
412
493
|
---
|
|
413
494
|
from llama_cloud.client import AsyncLlamaCloud
|
|
414
495
|
|
|
415
496
|
client = AsyncLlamaCloud(
|
|
416
497
|
token="YOUR_TOKEN",
|
|
417
498
|
)
|
|
418
|
-
await client.extraction.
|
|
499
|
+
await client.extraction.infer_schema(
|
|
500
|
+
name="string",
|
|
501
|
+
file_ids=[],
|
|
502
|
+
)
|
|
419
503
|
"""
|
|
504
|
+
_request: typing.Dict[str, typing.Any] = {"name": name, "file_ids": file_ids}
|
|
505
|
+
if schema_id is not OMIT:
|
|
506
|
+
_request["schema_id"] = schema_id
|
|
507
|
+
if project_id is not OMIT:
|
|
508
|
+
_request["project_id"] = project_id
|
|
509
|
+
if stream is not OMIT:
|
|
510
|
+
_request["stream"] = stream
|
|
420
511
|
_response = await self._client_wrapper.httpx_client.request(
|
|
421
|
-
"
|
|
422
|
-
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas"),
|
|
423
|
-
|
|
512
|
+
"POST",
|
|
513
|
+
urllib.parse.urljoin(f"{self._client_wrapper.get_base_url()}/", "api/v1/extraction/schemas/infer"),
|
|
514
|
+
json=jsonable_encoder(_request),
|
|
424
515
|
headers=self._client_wrapper.get_headers(),
|
|
425
516
|
timeout=60,
|
|
426
517
|
)
|
|
427
518
|
if 200 <= _response.status_code < 300:
|
|
428
|
-
return pydantic.parse_obj_as(
|
|
519
|
+
return pydantic.parse_obj_as(ExtractionSchema, _response.json()) # type: ignore
|
|
429
520
|
if _response.status_code == 422:
|
|
430
521
|
raise UnprocessableEntityError(pydantic.parse_obj_as(HttpValidationError, _response.json())) # type: ignore
|
|
431
522
|
try:
|
|
@@ -1,5 +1,6 @@
|
|
|
1
1
|
# This file was auto-generated by Fern from our API Definition.
|
|
2
2
|
|
|
3
|
+
from .extraction_schema_create_data_schema_value import ExtractionSchemaCreateDataSchemaValue
|
|
3
4
|
from .extraction_schema_update_data_schema_value import ExtractionSchemaUpdateDataSchemaValue
|
|
4
5
|
|
|
5
|
-
__all__ = ["ExtractionSchemaUpdateDataSchemaValue"]
|
|
6
|
+
__all__ = ["ExtractionSchemaCreateDataSchemaValue", "ExtractionSchemaUpdateDataSchemaValue"]
|
|
@@ -15,6 +15,7 @@ from ...types.cloud_document import CloudDocument
|
|
|
15
15
|
from ...types.cloud_document_create import CloudDocumentCreate
|
|
16
16
|
from ...types.configured_transformation_item import ConfiguredTransformationItem
|
|
17
17
|
from ...types.data_sink_create import DataSinkCreate
|
|
18
|
+
from ...types.embedding_config import EmbeddingConfig
|
|
18
19
|
from ...types.eval_dataset_job_record import EvalDatasetJobRecord
|
|
19
20
|
from ...types.eval_execution_params import EvalExecutionParams
|
|
20
21
|
from ...types.eval_execution_params_override import EvalExecutionParamsOverride
|
|
@@ -35,6 +36,7 @@ from ...types.preset_retrieval_params import PresetRetrievalParams
|
|
|
35
36
|
from ...types.retrieval_mode import RetrievalMode
|
|
36
37
|
from ...types.retrieve_results import RetrieveResults
|
|
37
38
|
from ...types.text_node import TextNode
|
|
39
|
+
from ...types.transform_config import TransformConfig
|
|
38
40
|
from .types.pipeline_file_update_custom_metadata_value import PipelineFileUpdateCustomMetadataValue
|
|
39
41
|
|
|
40
42
|
try:
|
|
@@ -117,8 +119,11 @@ class PipelinesClient:
|
|
|
117
119
|
- request: PipelineCreate.
|
|
118
120
|
---
|
|
119
121
|
from llama_cloud import (
|
|
122
|
+
AutoTransformConfig,
|
|
120
123
|
ConfigurableDataSinkNames,
|
|
121
124
|
DataSinkCreate,
|
|
125
|
+
EmbeddingConfig,
|
|
126
|
+
EmbeddingConfigType,
|
|
122
127
|
EvalExecutionParams,
|
|
123
128
|
FilterCondition,
|
|
124
129
|
LlamaParseParameters,
|
|
@@ -128,6 +133,8 @@ class PipelinesClient:
|
|
|
128
133
|
PresetRetrievalParams,
|
|
129
134
|
RetrievalMode,
|
|
130
135
|
SupportedEvalLlmModelNames,
|
|
136
|
+
TransformConfig,
|
|
137
|
+
TransformConfigMode,
|
|
131
138
|
)
|
|
132
139
|
from llama_cloud.client import LlamaCloud
|
|
133
140
|
|
|
@@ -136,6 +143,13 @@ class PipelinesClient:
|
|
|
136
143
|
)
|
|
137
144
|
client.pipelines.create_pipeline(
|
|
138
145
|
request=PipelineCreate(
|
|
146
|
+
embedding_config=EmbeddingConfig(
|
|
147
|
+
type=EmbeddingConfigType.OPENAI_EMBEDDING,
|
|
148
|
+
),
|
|
149
|
+
transform_config=TransformConfig(
|
|
150
|
+
mode=TransformConfigMode.AUTO,
|
|
151
|
+
config=AutoTransformConfig(),
|
|
152
|
+
),
|
|
139
153
|
data_sink=DataSinkCreate(
|
|
140
154
|
name="string",
|
|
141
155
|
sink_type=ConfigurableDataSinkNames.CHROMA,
|
|
@@ -185,8 +199,11 @@ class PipelinesClient:
|
|
|
185
199
|
- request: PipelineCreate.
|
|
186
200
|
---
|
|
187
201
|
from llama_cloud import (
|
|
202
|
+
AutoTransformConfig,
|
|
188
203
|
ConfigurableDataSinkNames,
|
|
189
204
|
DataSinkCreate,
|
|
205
|
+
EmbeddingConfig,
|
|
206
|
+
EmbeddingConfigType,
|
|
190
207
|
EvalExecutionParams,
|
|
191
208
|
FilterCondition,
|
|
192
209
|
LlamaParseParameters,
|
|
@@ -196,6 +213,8 @@ class PipelinesClient:
|
|
|
196
213
|
PresetRetrievalParams,
|
|
197
214
|
RetrievalMode,
|
|
198
215
|
SupportedEvalLlmModelNames,
|
|
216
|
+
TransformConfig,
|
|
217
|
+
TransformConfigMode,
|
|
199
218
|
)
|
|
200
219
|
from llama_cloud.client import LlamaCloud
|
|
201
220
|
|
|
@@ -204,6 +223,13 @@ class PipelinesClient:
|
|
|
204
223
|
)
|
|
205
224
|
client.pipelines.upsert_pipeline(
|
|
206
225
|
request=PipelineCreate(
|
|
226
|
+
embedding_config=EmbeddingConfig(
|
|
227
|
+
type=EmbeddingConfigType.OPENAI_EMBEDDING,
|
|
228
|
+
),
|
|
229
|
+
transform_config=TransformConfig(
|
|
230
|
+
mode=TransformConfigMode.AUTO,
|
|
231
|
+
config=AutoTransformConfig(),
|
|
232
|
+
),
|
|
207
233
|
data_sink=DataSinkCreate(
|
|
208
234
|
name="string",
|
|
209
235
|
sink_type=ConfigurableDataSinkNames.CHROMA,
|
|
@@ -278,6 +304,8 @@ class PipelinesClient:
|
|
|
278
304
|
self,
|
|
279
305
|
pipeline_id: str,
|
|
280
306
|
*,
|
|
307
|
+
embedding_config: typing.Optional[EmbeddingConfig] = OMIT,
|
|
308
|
+
transform_config: typing.Optional[TransformConfig] = OMIT,
|
|
281
309
|
configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]] = OMIT,
|
|
282
310
|
data_sink_id: typing.Optional[str] = OMIT,
|
|
283
311
|
data_sink: typing.Optional[DataSinkCreate] = OMIT,
|
|
@@ -293,7 +321,11 @@ class PipelinesClient:
|
|
|
293
321
|
Parameters:
|
|
294
322
|
- pipeline_id: str.
|
|
295
323
|
|
|
296
|
-
-
|
|
324
|
+
- embedding_config: typing.Optional[EmbeddingConfig]. Configuration for the embedding model.
|
|
325
|
+
|
|
326
|
+
- transform_config: typing.Optional[TransformConfig]. Configuration for the transformation.
|
|
327
|
+
|
|
328
|
+
- configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]]. List of configured transformations.
|
|
297
329
|
|
|
298
330
|
- data_sink_id: typing.Optional[str]. Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID.
|
|
299
331
|
|
|
@@ -310,8 +342,11 @@ class PipelinesClient:
|
|
|
310
342
|
- managed_pipeline_id: typing.Optional[str]. The ID of the ManagedPipeline this playground pipeline is linked to.
|
|
311
343
|
---
|
|
312
344
|
from llama_cloud import (
|
|
345
|
+
AutoTransformConfig,
|
|
313
346
|
ConfigurableDataSinkNames,
|
|
314
347
|
DataSinkCreate,
|
|
348
|
+
EmbeddingConfig,
|
|
349
|
+
EmbeddingConfigType,
|
|
315
350
|
EvalExecutionParams,
|
|
316
351
|
FilterCondition,
|
|
317
352
|
LlamaParseParameters,
|
|
@@ -319,6 +354,8 @@ class PipelinesClient:
|
|
|
319
354
|
PresetRetrievalParams,
|
|
320
355
|
RetrievalMode,
|
|
321
356
|
SupportedEvalLlmModelNames,
|
|
357
|
+
TransformConfig,
|
|
358
|
+
TransformConfigMode,
|
|
322
359
|
)
|
|
323
360
|
from llama_cloud.client import LlamaCloud
|
|
324
361
|
|
|
@@ -327,6 +364,13 @@ class PipelinesClient:
|
|
|
327
364
|
)
|
|
328
365
|
client.pipelines.update_existing_pipeline(
|
|
329
366
|
pipeline_id="string",
|
|
367
|
+
embedding_config=EmbeddingConfig(
|
|
368
|
+
type=EmbeddingConfigType.OPENAI_EMBEDDING,
|
|
369
|
+
),
|
|
370
|
+
transform_config=TransformConfig(
|
|
371
|
+
mode=TransformConfigMode.AUTO,
|
|
372
|
+
config=AutoTransformConfig(),
|
|
373
|
+
),
|
|
330
374
|
data_sink=DataSinkCreate(
|
|
331
375
|
name="string",
|
|
332
376
|
sink_type=ConfigurableDataSinkNames.CHROMA,
|
|
@@ -345,6 +389,10 @@ class PipelinesClient:
|
|
|
345
389
|
)
|
|
346
390
|
"""
|
|
347
391
|
_request: typing.Dict[str, typing.Any] = {}
|
|
392
|
+
if embedding_config is not OMIT:
|
|
393
|
+
_request["embedding_config"] = embedding_config
|
|
394
|
+
if transform_config is not OMIT:
|
|
395
|
+
_request["transform_config"] = transform_config
|
|
348
396
|
if configured_transformations is not OMIT:
|
|
349
397
|
_request["configured_transformations"] = configured_transformations
|
|
350
398
|
if data_sink_id is not OMIT:
|
|
@@ -1676,8 +1724,11 @@ class AsyncPipelinesClient:
|
|
|
1676
1724
|
- request: PipelineCreate.
|
|
1677
1725
|
---
|
|
1678
1726
|
from llama_cloud import (
|
|
1727
|
+
AutoTransformConfig,
|
|
1679
1728
|
ConfigurableDataSinkNames,
|
|
1680
1729
|
DataSinkCreate,
|
|
1730
|
+
EmbeddingConfig,
|
|
1731
|
+
EmbeddingConfigType,
|
|
1681
1732
|
EvalExecutionParams,
|
|
1682
1733
|
FilterCondition,
|
|
1683
1734
|
LlamaParseParameters,
|
|
@@ -1687,6 +1738,8 @@ class AsyncPipelinesClient:
|
|
|
1687
1738
|
PresetRetrievalParams,
|
|
1688
1739
|
RetrievalMode,
|
|
1689
1740
|
SupportedEvalLlmModelNames,
|
|
1741
|
+
TransformConfig,
|
|
1742
|
+
TransformConfigMode,
|
|
1690
1743
|
)
|
|
1691
1744
|
from llama_cloud.client import AsyncLlamaCloud
|
|
1692
1745
|
|
|
@@ -1695,6 +1748,13 @@ class AsyncPipelinesClient:
|
|
|
1695
1748
|
)
|
|
1696
1749
|
await client.pipelines.create_pipeline(
|
|
1697
1750
|
request=PipelineCreate(
|
|
1751
|
+
embedding_config=EmbeddingConfig(
|
|
1752
|
+
type=EmbeddingConfigType.OPENAI_EMBEDDING,
|
|
1753
|
+
),
|
|
1754
|
+
transform_config=TransformConfig(
|
|
1755
|
+
mode=TransformConfigMode.AUTO,
|
|
1756
|
+
config=AutoTransformConfig(),
|
|
1757
|
+
),
|
|
1698
1758
|
data_sink=DataSinkCreate(
|
|
1699
1759
|
name="string",
|
|
1700
1760
|
sink_type=ConfigurableDataSinkNames.CHROMA,
|
|
@@ -1744,8 +1804,11 @@ class AsyncPipelinesClient:
|
|
|
1744
1804
|
- request: PipelineCreate.
|
|
1745
1805
|
---
|
|
1746
1806
|
from llama_cloud import (
|
|
1807
|
+
AutoTransformConfig,
|
|
1747
1808
|
ConfigurableDataSinkNames,
|
|
1748
1809
|
DataSinkCreate,
|
|
1810
|
+
EmbeddingConfig,
|
|
1811
|
+
EmbeddingConfigType,
|
|
1749
1812
|
EvalExecutionParams,
|
|
1750
1813
|
FilterCondition,
|
|
1751
1814
|
LlamaParseParameters,
|
|
@@ -1755,6 +1818,8 @@ class AsyncPipelinesClient:
|
|
|
1755
1818
|
PresetRetrievalParams,
|
|
1756
1819
|
RetrievalMode,
|
|
1757
1820
|
SupportedEvalLlmModelNames,
|
|
1821
|
+
TransformConfig,
|
|
1822
|
+
TransformConfigMode,
|
|
1758
1823
|
)
|
|
1759
1824
|
from llama_cloud.client import AsyncLlamaCloud
|
|
1760
1825
|
|
|
@@ -1763,6 +1828,13 @@ class AsyncPipelinesClient:
|
|
|
1763
1828
|
)
|
|
1764
1829
|
await client.pipelines.upsert_pipeline(
|
|
1765
1830
|
request=PipelineCreate(
|
|
1831
|
+
embedding_config=EmbeddingConfig(
|
|
1832
|
+
type=EmbeddingConfigType.OPENAI_EMBEDDING,
|
|
1833
|
+
),
|
|
1834
|
+
transform_config=TransformConfig(
|
|
1835
|
+
mode=TransformConfigMode.AUTO,
|
|
1836
|
+
config=AutoTransformConfig(),
|
|
1837
|
+
),
|
|
1766
1838
|
data_sink=DataSinkCreate(
|
|
1767
1839
|
name="string",
|
|
1768
1840
|
sink_type=ConfigurableDataSinkNames.CHROMA,
|
|
@@ -1837,6 +1909,8 @@ class AsyncPipelinesClient:
|
|
|
1837
1909
|
self,
|
|
1838
1910
|
pipeline_id: str,
|
|
1839
1911
|
*,
|
|
1912
|
+
embedding_config: typing.Optional[EmbeddingConfig] = OMIT,
|
|
1913
|
+
transform_config: typing.Optional[TransformConfig] = OMIT,
|
|
1840
1914
|
configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]] = OMIT,
|
|
1841
1915
|
data_sink_id: typing.Optional[str] = OMIT,
|
|
1842
1916
|
data_sink: typing.Optional[DataSinkCreate] = OMIT,
|
|
@@ -1852,7 +1926,11 @@ class AsyncPipelinesClient:
|
|
|
1852
1926
|
Parameters:
|
|
1853
1927
|
- pipeline_id: str.
|
|
1854
1928
|
|
|
1855
|
-
-
|
|
1929
|
+
- embedding_config: typing.Optional[EmbeddingConfig]. Configuration for the embedding model.
|
|
1930
|
+
|
|
1931
|
+
- transform_config: typing.Optional[TransformConfig]. Configuration for the transformation.
|
|
1932
|
+
|
|
1933
|
+
- configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]]. List of configured transformations.
|
|
1856
1934
|
|
|
1857
1935
|
- data_sink_id: typing.Optional[str]. Data sink ID. When provided instead of data_sink, the data sink will be looked up by ID.
|
|
1858
1936
|
|
|
@@ -1869,8 +1947,11 @@ class AsyncPipelinesClient:
|
|
|
1869
1947
|
- managed_pipeline_id: typing.Optional[str]. The ID of the ManagedPipeline this playground pipeline is linked to.
|
|
1870
1948
|
---
|
|
1871
1949
|
from llama_cloud import (
|
|
1950
|
+
AutoTransformConfig,
|
|
1872
1951
|
ConfigurableDataSinkNames,
|
|
1873
1952
|
DataSinkCreate,
|
|
1953
|
+
EmbeddingConfig,
|
|
1954
|
+
EmbeddingConfigType,
|
|
1874
1955
|
EvalExecutionParams,
|
|
1875
1956
|
FilterCondition,
|
|
1876
1957
|
LlamaParseParameters,
|
|
@@ -1878,6 +1959,8 @@ class AsyncPipelinesClient:
|
|
|
1878
1959
|
PresetRetrievalParams,
|
|
1879
1960
|
RetrievalMode,
|
|
1880
1961
|
SupportedEvalLlmModelNames,
|
|
1962
|
+
TransformConfig,
|
|
1963
|
+
TransformConfigMode,
|
|
1881
1964
|
)
|
|
1882
1965
|
from llama_cloud.client import AsyncLlamaCloud
|
|
1883
1966
|
|
|
@@ -1886,6 +1969,13 @@ class AsyncPipelinesClient:
|
|
|
1886
1969
|
)
|
|
1887
1970
|
await client.pipelines.update_existing_pipeline(
|
|
1888
1971
|
pipeline_id="string",
|
|
1972
|
+
embedding_config=EmbeddingConfig(
|
|
1973
|
+
type=EmbeddingConfigType.OPENAI_EMBEDDING,
|
|
1974
|
+
),
|
|
1975
|
+
transform_config=TransformConfig(
|
|
1976
|
+
mode=TransformConfigMode.AUTO,
|
|
1977
|
+
config=AutoTransformConfig(),
|
|
1978
|
+
),
|
|
1889
1979
|
data_sink=DataSinkCreate(
|
|
1890
1980
|
name="string",
|
|
1891
1981
|
sink_type=ConfigurableDataSinkNames.CHROMA,
|
|
@@ -1904,6 +1994,10 @@ class AsyncPipelinesClient:
|
|
|
1904
1994
|
)
|
|
1905
1995
|
"""
|
|
1906
1996
|
_request: typing.Dict[str, typing.Any] = {}
|
|
1997
|
+
if embedding_config is not OMIT:
|
|
1998
|
+
_request["embedding_config"] = embedding_config
|
|
1999
|
+
if transform_config is not OMIT:
|
|
2000
|
+
_request["transform_config"] = transform_config
|
|
1907
2001
|
if configured_transformations is not OMIT:
|
|
1908
2002
|
_request["configured_transformations"] = configured_transformations
|
|
1909
2003
|
if data_sink_id is not OMIT:
|
llama_cloud/types/__init__.py
CHANGED
|
@@ -1,5 +1,6 @@
|
|
|
1
1
|
# This file was auto-generated by Fern from our API Definition.
|
|
2
2
|
|
|
3
|
+
from .auto_transform_config import AutoTransformConfig
|
|
3
4
|
from .azure_open_ai_embedding import AzureOpenAiEmbedding
|
|
4
5
|
from .base import Base
|
|
5
6
|
from .base_prompt_template import BasePromptTemplate
|
|
@@ -47,6 +48,9 @@ from .data_source_create_component_one import DataSourceCreateComponentOne
|
|
|
47
48
|
from .data_source_create_custom_metadata_value import DataSourceCreateCustomMetadataValue
|
|
48
49
|
from .data_source_custom_metadata_value import DataSourceCustomMetadataValue
|
|
49
50
|
from .data_source_definition import DataSourceDefinition
|
|
51
|
+
from .embedding_config import EmbeddingConfig
|
|
52
|
+
from .embedding_config_component import EmbeddingConfigComponent
|
|
53
|
+
from .embedding_config_type import EmbeddingConfigType
|
|
50
54
|
from .eval_dataset import EvalDataset
|
|
51
55
|
from .eval_dataset_job_params import EvalDatasetJobParams
|
|
52
56
|
from .eval_dataset_job_record import EvalDatasetJobRecord
|
|
@@ -133,6 +137,8 @@ from .text_node import TextNode
|
|
|
133
137
|
from .text_node_relationships_value import TextNodeRelationshipsValue
|
|
134
138
|
from .text_node_with_score import TextNodeWithScore
|
|
135
139
|
from .token_text_splitter import TokenTextSplitter
|
|
140
|
+
from .transform_config import TransformConfig
|
|
141
|
+
from .transform_config_mode import TransformConfigMode
|
|
136
142
|
from .transformation_category_names import TransformationCategoryNames
|
|
137
143
|
from .user_organization import UserOrganization
|
|
138
144
|
from .user_organization_create import UserOrganizationCreate
|
|
@@ -141,6 +147,7 @@ from .validation_error import ValidationError
|
|
|
141
147
|
from .validation_error_loc_item import ValidationErrorLocItem
|
|
142
148
|
|
|
143
149
|
__all__ = [
|
|
150
|
+
"AutoTransformConfig",
|
|
144
151
|
"AzureOpenAiEmbedding",
|
|
145
152
|
"Base",
|
|
146
153
|
"BasePromptTemplate",
|
|
@@ -188,6 +195,9 @@ __all__ = [
|
|
|
188
195
|
"DataSourceCreateCustomMetadataValue",
|
|
189
196
|
"DataSourceCustomMetadataValue",
|
|
190
197
|
"DataSourceDefinition",
|
|
198
|
+
"EmbeddingConfig",
|
|
199
|
+
"EmbeddingConfigComponent",
|
|
200
|
+
"EmbeddingConfigType",
|
|
191
201
|
"EvalDataset",
|
|
192
202
|
"EvalDatasetJobParams",
|
|
193
203
|
"EvalDatasetJobRecord",
|
|
@@ -274,6 +284,8 @@ __all__ = [
|
|
|
274
284
|
"TextNodeRelationshipsValue",
|
|
275
285
|
"TextNodeWithScore",
|
|
276
286
|
"TokenTextSplitter",
|
|
287
|
+
"TransformConfig",
|
|
288
|
+
"TransformConfigMode",
|
|
277
289
|
"TransformationCategoryNames",
|
|
278
290
|
"UserOrganization",
|
|
279
291
|
"UserOrganizationCreate",
|
|
@@ -0,0 +1,32 @@
|
|
|
1
|
+
# This file was auto-generated by Fern from our API Definition.
|
|
2
|
+
|
|
3
|
+
import datetime as dt
|
|
4
|
+
import typing
|
|
5
|
+
|
|
6
|
+
from ..core.datetime_utils import serialize_datetime
|
|
7
|
+
|
|
8
|
+
try:
|
|
9
|
+
import pydantic
|
|
10
|
+
if pydantic.__version__.startswith("1."):
|
|
11
|
+
raise ImportError
|
|
12
|
+
import pydantic.v1 as pydantic # type: ignore
|
|
13
|
+
except ImportError:
|
|
14
|
+
import pydantic # type: ignore
|
|
15
|
+
|
|
16
|
+
|
|
17
|
+
class AutoTransformConfig(pydantic.BaseModel):
|
|
18
|
+
chunk_size: typing.Optional[int] = pydantic.Field(description="Chunk size for the transformation.")
|
|
19
|
+
chunk_overlap: typing.Optional[int] = pydantic.Field(description="Chunk overlap for the transformation.")
|
|
20
|
+
|
|
21
|
+
def json(self, **kwargs: typing.Any) -> str:
|
|
22
|
+
kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
|
|
23
|
+
return super().json(**kwargs_with_defaults)
|
|
24
|
+
|
|
25
|
+
def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
|
|
26
|
+
kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
|
|
27
|
+
return super().dict(**kwargs_with_defaults)
|
|
28
|
+
|
|
29
|
+
class Config:
|
|
30
|
+
frozen = True
|
|
31
|
+
smart_union = True
|
|
32
|
+
json_encoders = {dt.datetime: serialize_datetime}
|
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
# This file was auto-generated by Fern from our API Definition.
|
|
2
|
+
|
|
3
|
+
import datetime as dt
|
|
4
|
+
import typing
|
|
5
|
+
|
|
6
|
+
from ..core.datetime_utils import serialize_datetime
|
|
7
|
+
from .embedding_config_component import EmbeddingConfigComponent
|
|
8
|
+
from .embedding_config_type import EmbeddingConfigType
|
|
9
|
+
|
|
10
|
+
try:
|
|
11
|
+
import pydantic
|
|
12
|
+
if pydantic.__version__.startswith("1."):
|
|
13
|
+
raise ImportError
|
|
14
|
+
import pydantic.v1 as pydantic # type: ignore
|
|
15
|
+
except ImportError:
|
|
16
|
+
import pydantic # type: ignore
|
|
17
|
+
|
|
18
|
+
|
|
19
|
+
class EmbeddingConfig(pydantic.BaseModel):
|
|
20
|
+
type: typing.Optional[EmbeddingConfigType] = pydantic.Field(description="Type of the embedding model.")
|
|
21
|
+
component: typing.Optional[EmbeddingConfigComponent] = pydantic.Field(
|
|
22
|
+
description="Configuration for the transformation."
|
|
23
|
+
)
|
|
24
|
+
|
|
25
|
+
def json(self, **kwargs: typing.Any) -> str:
|
|
26
|
+
kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
|
|
27
|
+
return super().json(**kwargs_with_defaults)
|
|
28
|
+
|
|
29
|
+
def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
|
|
30
|
+
kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
|
|
31
|
+
return super().dict(**kwargs_with_defaults)
|
|
32
|
+
|
|
33
|
+
class Config:
|
|
34
|
+
frozen = True
|
|
35
|
+
smart_union = True
|
|
36
|
+
json_encoders = {dt.datetime: serialize_datetime}
|
|
@@ -0,0 +1,19 @@
|
|
|
1
|
+
# This file was auto-generated by Fern from our API Definition.
|
|
2
|
+
|
|
3
|
+
import typing
|
|
4
|
+
|
|
5
|
+
from .azure_open_ai_embedding import AzureOpenAiEmbedding
|
|
6
|
+
from .bedrock_embedding import BedrockEmbedding
|
|
7
|
+
from .cohere_embedding import CohereEmbedding
|
|
8
|
+
from .gemini_embedding import GeminiEmbedding
|
|
9
|
+
from .hugging_face_inference_api_embedding import HuggingFaceInferenceApiEmbedding
|
|
10
|
+
from .open_ai_embedding import OpenAiEmbedding
|
|
11
|
+
|
|
12
|
+
EmbeddingConfigComponent = typing.Union[
|
|
13
|
+
OpenAiEmbedding,
|
|
14
|
+
AzureOpenAiEmbedding,
|
|
15
|
+
BedrockEmbedding,
|
|
16
|
+
CohereEmbedding,
|
|
17
|
+
GeminiEmbedding,
|
|
18
|
+
HuggingFaceInferenceApiEmbedding,
|
|
19
|
+
]
|
|
@@ -0,0 +1,41 @@
|
|
|
1
|
+
# This file was auto-generated by Fern from our API Definition.
|
|
2
|
+
|
|
3
|
+
import enum
|
|
4
|
+
import typing
|
|
5
|
+
|
|
6
|
+
T_Result = typing.TypeVar("T_Result")
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
class EmbeddingConfigType(str, enum.Enum):
|
|
10
|
+
"""
|
|
11
|
+
An enumeration.
|
|
12
|
+
"""
|
|
13
|
+
|
|
14
|
+
OPENAI_EMBEDDING = "OPENAI_EMBEDDING"
|
|
15
|
+
AZURE_EMBEDDING = "AZURE_EMBEDDING"
|
|
16
|
+
BEDROCK_EMBEDDING = "BEDROCK_EMBEDDING"
|
|
17
|
+
COHERE_EMBEDDING = "COHERE_EMBEDDING"
|
|
18
|
+
GEMINI_EMBEDDING = "GEMINI_EMBEDDING"
|
|
19
|
+
HUGGINGFACE_API_EMBEDDING = "HUGGINGFACE_API_EMBEDDING"
|
|
20
|
+
|
|
21
|
+
def visit(
|
|
22
|
+
self,
|
|
23
|
+
openai_embedding: typing.Callable[[], T_Result],
|
|
24
|
+
azure_embedding: typing.Callable[[], T_Result],
|
|
25
|
+
bedrock_embedding: typing.Callable[[], T_Result],
|
|
26
|
+
cohere_embedding: typing.Callable[[], T_Result],
|
|
27
|
+
gemini_embedding: typing.Callable[[], T_Result],
|
|
28
|
+
huggingface_api_embedding: typing.Callable[[], T_Result],
|
|
29
|
+
) -> T_Result:
|
|
30
|
+
if self is EmbeddingConfigType.OPENAI_EMBEDDING:
|
|
31
|
+
return openai_embedding()
|
|
32
|
+
if self is EmbeddingConfigType.AZURE_EMBEDDING:
|
|
33
|
+
return azure_embedding()
|
|
34
|
+
if self is EmbeddingConfigType.BEDROCK_EMBEDDING:
|
|
35
|
+
return bedrock_embedding()
|
|
36
|
+
if self is EmbeddingConfigType.COHERE_EMBEDDING:
|
|
37
|
+
return cohere_embedding()
|
|
38
|
+
if self is EmbeddingConfigType.GEMINI_EMBEDDING:
|
|
39
|
+
return gemini_embedding()
|
|
40
|
+
if self is EmbeddingConfigType.HUGGINGFACE_API_EMBEDDING:
|
|
41
|
+
return huggingface_api_embedding()
|
|
@@ -6,10 +6,12 @@ import typing
|
|
|
6
6
|
from ..core.datetime_utils import serialize_datetime
|
|
7
7
|
from .configured_transformation_item import ConfiguredTransformationItem
|
|
8
8
|
from .data_sink_create import DataSinkCreate
|
|
9
|
+
from .embedding_config import EmbeddingConfig
|
|
9
10
|
from .eval_execution_params import EvalExecutionParams
|
|
10
11
|
from .llama_parse_parameters import LlamaParseParameters
|
|
11
12
|
from .pipeline_type import PipelineType
|
|
12
13
|
from .preset_retrieval_params import PresetRetrievalParams
|
|
14
|
+
from .transform_config import TransformConfig
|
|
13
15
|
|
|
14
16
|
try:
|
|
15
17
|
import pydantic
|
|
@@ -25,6 +27,12 @@ class PipelineCreate(pydantic.BaseModel):
|
|
|
25
27
|
Schema for creating a pipeline.
|
|
26
28
|
"""
|
|
27
29
|
|
|
30
|
+
embedding_config: typing.Optional[EmbeddingConfig] = pydantic.Field(
|
|
31
|
+
description="Configuration for the embedding model."
|
|
32
|
+
)
|
|
33
|
+
transform_config: typing.Optional[TransformConfig] = pydantic.Field(
|
|
34
|
+
description="Configuration for the transformation."
|
|
35
|
+
)
|
|
28
36
|
configured_transformations: typing.Optional[typing.List[ConfiguredTransformationItem]] = pydantic.Field(
|
|
29
37
|
description="List of configured transformations."
|
|
30
38
|
)
|
|
@@ -0,0 +1,36 @@
|
|
|
1
|
+
# This file was auto-generated by Fern from our API Definition.
|
|
2
|
+
|
|
3
|
+
import datetime as dt
|
|
4
|
+
import typing
|
|
5
|
+
|
|
6
|
+
from ..core.datetime_utils import serialize_datetime
|
|
7
|
+
from .auto_transform_config import AutoTransformConfig
|
|
8
|
+
from .transform_config_mode import TransformConfigMode
|
|
9
|
+
|
|
10
|
+
try:
|
|
11
|
+
import pydantic
|
|
12
|
+
if pydantic.__version__.startswith("1."):
|
|
13
|
+
raise ImportError
|
|
14
|
+
import pydantic.v1 as pydantic # type: ignore
|
|
15
|
+
except ImportError:
|
|
16
|
+
import pydantic # type: ignore
|
|
17
|
+
|
|
18
|
+
|
|
19
|
+
class TransformConfig(pydantic.BaseModel):
|
|
20
|
+
mode: typing.Optional[TransformConfigMode] = pydantic.Field(
|
|
21
|
+
description="Mode for the transformation configuration."
|
|
22
|
+
)
|
|
23
|
+
config: typing.Optional[AutoTransformConfig] = pydantic.Field(description="Configuration for the transformation.")
|
|
24
|
+
|
|
25
|
+
def json(self, **kwargs: typing.Any) -> str:
|
|
26
|
+
kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
|
|
27
|
+
return super().json(**kwargs_with_defaults)
|
|
28
|
+
|
|
29
|
+
def dict(self, **kwargs: typing.Any) -> typing.Dict[str, typing.Any]:
|
|
30
|
+
kwargs_with_defaults: typing.Any = {"by_alias": True, "exclude_unset": True, **kwargs}
|
|
31
|
+
return super().dict(**kwargs_with_defaults)
|
|
32
|
+
|
|
33
|
+
class Config:
|
|
34
|
+
frozen = True
|
|
35
|
+
smart_union = True
|
|
36
|
+
json_encoders = {dt.datetime: serialize_datetime}
|
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
# This file was auto-generated by Fern from our API Definition.
|
|
2
|
+
|
|
3
|
+
import enum
|
|
4
|
+
import typing
|
|
5
|
+
|
|
6
|
+
T_Result = typing.TypeVar("T_Result")
|
|
7
|
+
|
|
8
|
+
|
|
9
|
+
class TransformConfigMode(str, enum.Enum):
|
|
10
|
+
"""
|
|
11
|
+
An enumeration.
|
|
12
|
+
"""
|
|
13
|
+
|
|
14
|
+
AUTO = "AUTO"
|
|
15
|
+
ADVANCED = "ADVANCED"
|
|
16
|
+
|
|
17
|
+
def visit(self, auto: typing.Callable[[], T_Result], advanced: typing.Callable[[], T_Result]) -> T_Result:
|
|
18
|
+
if self is TransformConfigMode.AUTO:
|
|
19
|
+
return auto()
|
|
20
|
+
if self is TransformConfigMode.ADVANCED:
|
|
21
|
+
return advanced()
|
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
llama_cloud/__init__.py,sha256=
|
|
1
|
+
llama_cloud/__init__.py,sha256=xHcoQ60V5FpNig3XYhARv0-xupmVjF12yLEVk_Ov9X8,8919
|
|
2
2
|
llama_cloud/client.py,sha256=bhZPiYd1TQSn3PRgHZ66MgMnBneG4Skc9g6UsT0wQnE,4299
|
|
3
3
|
llama_cloud/core/__init__.py,sha256=QJS3CJ2TYP2E1Tge0CS6Z7r8LTNzJHQVX1hD3558eP0,519
|
|
4
4
|
llama_cloud/core/api_error.py,sha256=RE8LELok2QCjABadECTvtDp7qejA1VmINCh6TbqPwSE,426
|
|
@@ -9,7 +9,7 @@ llama_cloud/core/remove_none_from_dict.py,sha256=8m91FC3YuVem0Gm9_sXhJ2tGvP33owJ
|
|
|
9
9
|
llama_cloud/environment.py,sha256=q4q-uY5WgcSlzfHwEANOqFQPu0lstqvMnVOsSfifMKo,168
|
|
10
10
|
llama_cloud/errors/__init__.py,sha256=pbbVUFtB9LCocA1RMWMMF_RKjsy5YkOKX5BAuE49w6g,170
|
|
11
11
|
llama_cloud/errors/unprocessable_entity_error.py,sha256=FvR7XPlV3Xx5nu8HNlmLhBRdk4so_gCHjYT5PyZe6sM,313
|
|
12
|
-
llama_cloud/resources/__init__.py,sha256=
|
|
12
|
+
llama_cloud/resources/__init__.py,sha256=uHsQ6hgIBRAp4ozjPDH1Cd8CqkiNnoYBcO2-LBAvtNg,1189
|
|
13
13
|
llama_cloud/resources/component_definitions/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
|
|
14
14
|
llama_cloud/resources/component_definitions/client.py,sha256=YYfoXNa1qim2OdD5y4N5mvoBZKtrCuXS560mtqH_-1c,7569
|
|
15
15
|
llama_cloud/resources/data_sinks/__init__.py,sha256=nsMEyxkVilxvQGSdJi0Z0yKZoTaTWewZIGJNoMwNDsw,205
|
|
@@ -25,9 +25,10 @@ llama_cloud/resources/data_sources/types/data_source_update_component_one.py,sha
|
|
|
25
25
|
llama_cloud/resources/data_sources/types/data_source_update_custom_metadata_value.py,sha256=3aFC-p8MSxjhOu2nFtqk0pixj6RqNqcFnbOYngUdZUk,215
|
|
26
26
|
llama_cloud/resources/evals/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
|
|
27
27
|
llama_cloud/resources/evals/client.py,sha256=P0NmQPRu606DZ2U-RKZRgh25BMriWyKGB77X0Dfe4q0,27603
|
|
28
|
-
llama_cloud/resources/extraction/__init__.py,sha256=
|
|
29
|
-
llama_cloud/resources/extraction/client.py,sha256=
|
|
30
|
-
llama_cloud/resources/extraction/types/__init__.py,sha256=
|
|
28
|
+
llama_cloud/resources/extraction/__init__.py,sha256=trseRsayeGiyGThI4s_Folw5AHmdTSEP3KPrlvNhfVw,255
|
|
29
|
+
llama_cloud/resources/extraction/client.py,sha256=iYYBliMeMtExllJXV0FLeGz46Gc88Ksmk_8vk1TrAzg,31012
|
|
30
|
+
llama_cloud/resources/extraction/types/__init__.py,sha256=ePJKSJ6hGIsPnfpe0Sp5w4mBZgnZes4cdtZ8Gfw81Gc,347
|
|
31
|
+
llama_cloud/resources/extraction/types/extraction_schema_create_data_schema_value.py,sha256=igTdUjMeB-PI5xKrloRKHY-EvL6_V8OLshABu6Dyx4A,217
|
|
31
32
|
llama_cloud/resources/extraction/types/extraction_schema_update_data_schema_value.py,sha256=z_4tkLkWnHnd3Xa9uUctk9hG9Mo7GKU4dK4s2pm8qow,217
|
|
32
33
|
llama_cloud/resources/files/__init__.py,sha256=aZpyTj6KpZvA5XVwmuo1sIlRs7ba98btxVBZ6j5vIsI,155
|
|
33
34
|
llama_cloud/resources/files/client.py,sha256=pU7ugpqW4dAXJycVg3KxUI82ixiH6vZtcwAaHyPdsDA,22186
|
|
@@ -38,12 +39,13 @@ llama_cloud/resources/organizations/client.py,sha256=akn_3sytJW_VhuLVBbP0TKiKKbB
|
|
|
38
39
|
llama_cloud/resources/parsing/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
|
|
39
40
|
llama_cloud/resources/parsing/client.py,sha256=fLNVNa945yP76sTf6NdSm5ikifSFFrjxxHXy0vwNBUc,40450
|
|
40
41
|
llama_cloud/resources/pipelines/__init__.py,sha256=H7yaFIN62vjuhU3TOKzzuf8qpxZRgw1xVa-eyig-2YU,175
|
|
41
|
-
llama_cloud/resources/pipelines/client.py,sha256=
|
|
42
|
+
llama_cloud/resources/pipelines/client.py,sha256=V_j8f77_i0IyqjVBWRXIlHBJaymFRRDdSSKU6oR1SIs,129012
|
|
42
43
|
llama_cloud/resources/pipelines/types/__init__.py,sha256=xuT4OBPLrRfEe-E3UVdJvRjl9jTp7tNBK_YzZBb6Kj8,212
|
|
43
44
|
llama_cloud/resources/pipelines/types/pipeline_file_update_custom_metadata_value.py,sha256=trI48WLxPcAqV9207Q6-3cj1nl4EGlZpw7En56ZsPgg,217
|
|
44
45
|
llama_cloud/resources/projects/__init__.py,sha256=FTtvy8EDg9nNNg9WCatVgKTRYV8-_v1roeGPAKoa_pw,65
|
|
45
46
|
llama_cloud/resources/projects/client.py,sha256=nK81HdhGbWY1rh8rSEsKzRuvyvCQ-IkhLHIPDqEqVFU,47754
|
|
46
|
-
llama_cloud/types/__init__.py,sha256=
|
|
47
|
+
llama_cloud/types/__init__.py,sha256=Jdcar7UNhEXHZ7JB4Wanq6C388JZQbrge2Mr85IhVa8,12115
|
|
48
|
+
llama_cloud/types/auto_transform_config.py,sha256=HVeHZM75DMRznScqLTfrMwcZwIdyWPuaEYbPewnHqwc,1168
|
|
47
49
|
llama_cloud/types/azure_open_ai_embedding.py,sha256=-9LzRDNcxhRvEshA8SaI9zFMTpHLXJ34iMnpIVk88Cc,3590
|
|
48
50
|
llama_cloud/types/base.py,sha256=cn_Zn61yLMDCMm1iZTPvKILSRlqRzOqZtSYyYBY5dIE,938
|
|
49
51
|
llama_cloud/types/base_prompt_template.py,sha256=GO9k4EDVMf3gRQIA4bVfXqgIMKnKTXhi1JlGvhqXDRY,1576
|
|
@@ -91,6 +93,9 @@ llama_cloud/types/data_source_create_component_one.py,sha256=rkVjFBxh1wA1BcsDWsJ
|
|
|
91
93
|
llama_cloud/types/data_source_create_custom_metadata_value.py,sha256=ejSsQNbszYQaUWFh9r9kQpHf88qbhuRv1SI9J_MOSC0,215
|
|
92
94
|
llama_cloud/types/data_source_custom_metadata_value.py,sha256=pTZn5yjZYmuOhsLABFJOKZblZUkRqo1CqLAuP5tKji4,209
|
|
93
95
|
llama_cloud/types/data_source_definition.py,sha256=HlSlTxzYcQJOSo_2OSroAE8vAr-otDvTNBSEkA54vL8,1575
|
|
96
|
+
llama_cloud/types/embedding_config.py,sha256=eqW7xg1IHZcXIEsqVzAn1thxcWGTeBwhpDuqpS6EYKw,1319
|
|
97
|
+
llama_cloud/types/embedding_config_component.py,sha256=gi6-TKmeV2z72KSfJof6diEW4z7VXuNOyhJhDK7ZrPQ,601
|
|
98
|
+
llama_cloud/types/embedding_config_type.py,sha256=iLK2npXhXa0E1FjsZvCC1JTzwJ1ItHYkNgDJvTkofyc,1470
|
|
94
99
|
llama_cloud/types/eval_dataset.py,sha256=Uav-YJqAvyzCp1j2XavzzVLV975uki71beIBLkCt8LY,1408
|
|
95
100
|
llama_cloud/types/eval_dataset_job_params.py,sha256=vcXLJWO581uigNvGAurPDgMeEFtQURWucLF5pemdeS0,1343
|
|
96
101
|
llama_cloud/types/eval_dataset_job_record.py,sha256=mUBpT2CI1IYYxwvC7S3mKu5GhBKXzVR5btDLoGcXqSg,2763
|
|
@@ -144,7 +149,7 @@ llama_cloud/types/parsing_job_markdown_result.py,sha256=E3-CVNFH1IMyuGs_xzYfYdNg
|
|
|
144
149
|
llama_cloud/types/parsing_job_text_result.py,sha256=1QZielAWXuzPFOgr_DWshXPjmbExAAgAHKAEYVQVtJ8,1082
|
|
145
150
|
llama_cloud/types/parsing_usage.py,sha256=Wy_c-kAFADDBZgDwqNglsJv_t7vcjOm-8EY32oZEYzU,995
|
|
146
151
|
llama_cloud/types/pipeline.py,sha256=h-Xo7HirFCvgiu7NaqSrUTM2wJKd9WXzcqnZ_j_kRkU,2661
|
|
147
|
-
llama_cloud/types/pipeline_create.py,sha256=
|
|
152
|
+
llama_cloud/types/pipeline_create.py,sha256=oXSclyv8UNW58c6mfUkMavEf7T1xrZJWjbCxIP61r7k,3058
|
|
148
153
|
llama_cloud/types/pipeline_data_source.py,sha256=A3AlRzTD7zr1y-u5O5LFESqIupbbG-fqUndQgeYj77w,2062
|
|
149
154
|
llama_cloud/types/pipeline_data_source_component.py,sha256=Pk_K0Gv7xSWe5BKCdxz82EFd6AQDvZGN-6t3zg9h8NY,265
|
|
150
155
|
llama_cloud/types/pipeline_data_source_component_one.py,sha256=sYaNaVl2gk-Clq2BCOKT2fUOGa_B7kcsw1P7aVdn-jA,873
|
|
@@ -177,13 +182,15 @@ llama_cloud/types/text_node.py,sha256=ANT9oPqBs9IJFPhtq-6PC4l44FA3ZYjz_9nOE8h0RA
|
|
|
177
182
|
llama_cloud/types/text_node_relationships_value.py,sha256=qmXURTk1Xg7ZDzRSSV1uDEel0AXRLohND5ioezibHY0,217
|
|
178
183
|
llama_cloud/types/text_node_with_score.py,sha256=k-KYWO_mgJBvO6xUfOD5W6v1Ku9E586_HsvDoQbLfuQ,1229
|
|
179
184
|
llama_cloud/types/token_text_splitter.py,sha256=Mv8xBCvMXyYuQq1KInPe65O0YYCLWxs61pIbkBRfxG0,1883
|
|
185
|
+
llama_cloud/types/transform_config.py,sha256=Xci_UUMz_xzx_OzePxLNk-6NvXO0H2PZtgEOApoF2lk,1315
|
|
186
|
+
llama_cloud/types/transform_config_mode.py,sha256=4jH-_MnlkM758y0lzlMh9JwGtHrdgAHdm_V8ikk7CbY,518
|
|
180
187
|
llama_cloud/types/transformation_category_names.py,sha256=0xjYe-mDW9OKbTGqL5fSbTvqsfrG4LDu_stW_ubVLl4,582
|
|
181
188
|
llama_cloud/types/user_organization.py,sha256=fLgTKr1phJ4EdhTXmr5086bRy9RTAUy4km6mQz_jgRI,1964
|
|
182
189
|
llama_cloud/types/user_organization_create.py,sha256=YESlfcI64710OFdQzgGD4a7aItgBwcIKdM1xFPs1Szw,1209
|
|
183
190
|
llama_cloud/types/user_organization_delete.py,sha256=Z8RSRXc0AGAuGxv6eQPC2S1XIdRfNCXBggfEefgPseM,1209
|
|
184
191
|
llama_cloud/types/validation_error.py,sha256=yZDLtjUHDY5w82Ra6CW0H9sLAr18R0RY1UNgJKR72DQ,1084
|
|
185
192
|
llama_cloud/types/validation_error_loc_item.py,sha256=LAtjCHIllWRBFXvAZ5QZpp7CPXjdtN9EB7HrLVo6EP0,128
|
|
186
|
-
llama_cloud-0.0.
|
|
187
|
-
llama_cloud-0.0.
|
|
188
|
-
llama_cloud-0.0.
|
|
189
|
-
llama_cloud-0.0.
|
|
193
|
+
llama_cloud-0.0.11.dist-info/LICENSE,sha256=_iNqtPcw1Ue7dZKwOwgPtbegMUkWVy15hC7bffAdNmY,1067
|
|
194
|
+
llama_cloud-0.0.11.dist-info/METADATA,sha256=ZsJt0biJi2jFJ-AGbm6bQlTmY5UOC2BA0o5hjWLZKbI,751
|
|
195
|
+
llama_cloud-0.0.11.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
|
|
196
|
+
llama_cloud-0.0.11.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|