groundx 2.3.6__py3-none-any.whl → 2.3.8__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.
- groundx/core/client_wrapper.py +2 -2
- groundx/documents/client.py +52 -6
- groundx/documents/raw_client.py +48 -2
- groundx/ingest.py +3 -0
- {groundx-2.3.6.dist-info → groundx-2.3.8.dist-info}/METADATA +1 -1
- {groundx-2.3.6.dist-info → groundx-2.3.8.dist-info}/RECORD +8 -8
- {groundx-2.3.6.dist-info → groundx-2.3.8.dist-info}/LICENSE +0 -0
- {groundx-2.3.6.dist-info → groundx-2.3.8.dist-info}/WHEEL +0 -0
groundx/core/client_wrapper.py
CHANGED
@@ -14,10 +14,10 @@ class BaseClientWrapper:
|
|
14
14
|
|
15
15
|
def get_headers(self) -> typing.Dict[str, str]:
|
16
16
|
headers: typing.Dict[str, str] = {
|
17
|
-
"User-Agent": "groundx/2.3.
|
17
|
+
"User-Agent": "groundx/2.3.8",
|
18
18
|
"X-Fern-Language": "Python",
|
19
19
|
"X-Fern-SDK-Name": "groundx",
|
20
|
-
"X-Fern-SDK-Version": "2.3.
|
20
|
+
"X-Fern-SDK-Version": "2.3.8",
|
21
21
|
}
|
22
22
|
headers["X-API-Key"] = self.api_key
|
23
23
|
return headers
|
groundx/documents/client.py
CHANGED
@@ -40,6 +40,8 @@ class DocumentsClient:
|
|
40
40
|
self,
|
41
41
|
*,
|
42
42
|
documents: typing.Sequence[IngestRemoteDocument],
|
43
|
+
callback_url: typing.Optional[str] = OMIT,
|
44
|
+
callback_data: typing.Optional[str] = OMIT,
|
43
45
|
request_options: typing.Optional[RequestOptions] = None,
|
44
46
|
) -> IngestResponse:
|
45
47
|
"""
|
@@ -51,6 +53,12 @@ class DocumentsClient:
|
|
51
53
|
----------
|
52
54
|
documents : typing.Sequence[IngestRemoteDocument]
|
53
55
|
|
56
|
+
callback_url : typing.Optional[str]
|
57
|
+
An endpoint that will receive processing event updates as POST.
|
58
|
+
|
59
|
+
callback_data : typing.Optional[str]
|
60
|
+
A string that is returned, along with processing event updates, to the callback URL.
|
61
|
+
|
54
62
|
request_options : typing.Optional[RequestOptions]
|
55
63
|
Request-specific configuration.
|
56
64
|
|
@@ -77,7 +85,9 @@ class DocumentsClient:
|
|
77
85
|
],
|
78
86
|
)
|
79
87
|
"""
|
80
|
-
_response = self._raw_client.ingest_remote(
|
88
|
+
_response = self._raw_client.ingest_remote(
|
89
|
+
documents=documents, callback_url=callback_url, callback_data=callback_data, request_options=request_options
|
90
|
+
)
|
81
91
|
return _response.data
|
82
92
|
|
83
93
|
def ingest_local(
|
@@ -124,7 +134,12 @@ class DocumentsClient:
|
|
124
134
|
return _response.data
|
125
135
|
|
126
136
|
def crawl_website(
|
127
|
-
self,
|
137
|
+
self,
|
138
|
+
*,
|
139
|
+
websites: typing.Sequence[WebsiteSource],
|
140
|
+
callback_url: typing.Optional[str] = OMIT,
|
141
|
+
callback_data: typing.Optional[str] = OMIT,
|
142
|
+
request_options: typing.Optional[RequestOptions] = None,
|
128
143
|
) -> IngestResponse:
|
129
144
|
"""
|
130
145
|
Upload the content of a publicly accessible website for ingestion into a GroundX bucket. This is done by following links within a specified URL, recursively, up to a specified depth or number of pages.
|
@@ -138,6 +153,12 @@ class DocumentsClient:
|
|
138
153
|
----------
|
139
154
|
websites : typing.Sequence[WebsiteSource]
|
140
155
|
|
156
|
+
callback_url : typing.Optional[str]
|
157
|
+
The URL that will receive processing event updates.
|
158
|
+
|
159
|
+
callback_data : typing.Optional[str]
|
160
|
+
A string that is returned, along with processing event updates, to the callback URL.
|
161
|
+
|
141
162
|
request_options : typing.Optional[RequestOptions]
|
142
163
|
Request-specific configuration.
|
143
164
|
|
@@ -165,7 +186,9 @@ class DocumentsClient:
|
|
165
186
|
],
|
166
187
|
)
|
167
188
|
"""
|
168
|
-
_response = self._raw_client.crawl_website(
|
189
|
+
_response = self._raw_client.crawl_website(
|
190
|
+
websites=websites, callback_url=callback_url, callback_data=callback_data, request_options=request_options
|
191
|
+
)
|
169
192
|
return _response.data
|
170
193
|
|
171
194
|
def list(
|
@@ -490,6 +513,8 @@ class AsyncDocumentsClient:
|
|
490
513
|
self,
|
491
514
|
*,
|
492
515
|
documents: typing.Sequence[IngestRemoteDocument],
|
516
|
+
callback_url: typing.Optional[str] = OMIT,
|
517
|
+
callback_data: typing.Optional[str] = OMIT,
|
493
518
|
request_options: typing.Optional[RequestOptions] = None,
|
494
519
|
) -> IngestResponse:
|
495
520
|
"""
|
@@ -501,6 +526,12 @@ class AsyncDocumentsClient:
|
|
501
526
|
----------
|
502
527
|
documents : typing.Sequence[IngestRemoteDocument]
|
503
528
|
|
529
|
+
callback_url : typing.Optional[str]
|
530
|
+
An endpoint that will receive processing event updates as POST.
|
531
|
+
|
532
|
+
callback_data : typing.Optional[str]
|
533
|
+
A string that is returned, along with processing event updates, to the callback URL.
|
534
|
+
|
504
535
|
request_options : typing.Optional[RequestOptions]
|
505
536
|
Request-specific configuration.
|
506
537
|
|
@@ -535,7 +566,9 @@ class AsyncDocumentsClient:
|
|
535
566
|
|
536
567
|
asyncio.run(main())
|
537
568
|
"""
|
538
|
-
_response = await self._raw_client.ingest_remote(
|
569
|
+
_response = await self._raw_client.ingest_remote(
|
570
|
+
documents=documents, callback_url=callback_url, callback_data=callback_data, request_options=request_options
|
571
|
+
)
|
539
572
|
return _response.data
|
540
573
|
|
541
574
|
async def ingest_local(
|
@@ -594,7 +627,12 @@ class AsyncDocumentsClient:
|
|
594
627
|
return _response.data
|
595
628
|
|
596
629
|
async def crawl_website(
|
597
|
-
self,
|
630
|
+
self,
|
631
|
+
*,
|
632
|
+
websites: typing.Sequence[WebsiteSource],
|
633
|
+
callback_url: typing.Optional[str] = OMIT,
|
634
|
+
callback_data: typing.Optional[str] = OMIT,
|
635
|
+
request_options: typing.Optional[RequestOptions] = None,
|
598
636
|
) -> IngestResponse:
|
599
637
|
"""
|
600
638
|
Upload the content of a publicly accessible website for ingestion into a GroundX bucket. This is done by following links within a specified URL, recursively, up to a specified depth or number of pages.
|
@@ -608,6 +646,12 @@ class AsyncDocumentsClient:
|
|
608
646
|
----------
|
609
647
|
websites : typing.Sequence[WebsiteSource]
|
610
648
|
|
649
|
+
callback_url : typing.Optional[str]
|
650
|
+
The URL that will receive processing event updates.
|
651
|
+
|
652
|
+
callback_data : typing.Optional[str]
|
653
|
+
A string that is returned, along with processing event updates, to the callback URL.
|
654
|
+
|
611
655
|
request_options : typing.Optional[RequestOptions]
|
612
656
|
Request-specific configuration.
|
613
657
|
|
@@ -643,7 +687,9 @@ class AsyncDocumentsClient:
|
|
643
687
|
|
644
688
|
asyncio.run(main())
|
645
689
|
"""
|
646
|
-
_response = await self._raw_client.crawl_website(
|
690
|
+
_response = await self._raw_client.crawl_website(
|
691
|
+
websites=websites, callback_url=callback_url, callback_data=callback_data, request_options=request_options
|
692
|
+
)
|
647
693
|
return _response.data
|
648
694
|
|
649
695
|
async def list(
|
groundx/documents/raw_client.py
CHANGED
@@ -36,6 +36,8 @@ class RawDocumentsClient:
|
|
36
36
|
self,
|
37
37
|
*,
|
38
38
|
documents: typing.Sequence[IngestRemoteDocument],
|
39
|
+
callback_url: typing.Optional[str] = OMIT,
|
40
|
+
callback_data: typing.Optional[str] = OMIT,
|
39
41
|
request_options: typing.Optional[RequestOptions] = None,
|
40
42
|
) -> HttpResponse[IngestResponse]:
|
41
43
|
"""
|
@@ -47,6 +49,12 @@ class RawDocumentsClient:
|
|
47
49
|
----------
|
48
50
|
documents : typing.Sequence[IngestRemoteDocument]
|
49
51
|
|
52
|
+
callback_url : typing.Optional[str]
|
53
|
+
An endpoint that will receive processing event updates as POST.
|
54
|
+
|
55
|
+
callback_data : typing.Optional[str]
|
56
|
+
A string that is returned, along with processing event updates, to the callback URL.
|
57
|
+
|
50
58
|
request_options : typing.Optional[RequestOptions]
|
51
59
|
Request-specific configuration.
|
52
60
|
|
@@ -62,6 +70,8 @@ class RawDocumentsClient:
|
|
62
70
|
"documents": convert_and_respect_annotation_metadata(
|
63
71
|
object_=documents, annotation=typing.Sequence[IngestRemoteDocument], direction="write"
|
64
72
|
),
|
73
|
+
"callbackUrl": callback_url,
|
74
|
+
"callbackData": callback_data,
|
65
75
|
},
|
66
76
|
headers={
|
67
77
|
"content-type": "application/json",
|
@@ -176,7 +186,12 @@ class RawDocumentsClient:
|
|
176
186
|
raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
|
177
187
|
|
178
188
|
def crawl_website(
|
179
|
-
self,
|
189
|
+
self,
|
190
|
+
*,
|
191
|
+
websites: typing.Sequence[WebsiteSource],
|
192
|
+
callback_url: typing.Optional[str] = OMIT,
|
193
|
+
callback_data: typing.Optional[str] = OMIT,
|
194
|
+
request_options: typing.Optional[RequestOptions] = None,
|
180
195
|
) -> HttpResponse[IngestResponse]:
|
181
196
|
"""
|
182
197
|
Upload the content of a publicly accessible website for ingestion into a GroundX bucket. This is done by following links within a specified URL, recursively, up to a specified depth or number of pages.
|
@@ -190,6 +205,12 @@ class RawDocumentsClient:
|
|
190
205
|
----------
|
191
206
|
websites : typing.Sequence[WebsiteSource]
|
192
207
|
|
208
|
+
callback_url : typing.Optional[str]
|
209
|
+
The URL that will receive processing event updates.
|
210
|
+
|
211
|
+
callback_data : typing.Optional[str]
|
212
|
+
A string that is returned, along with processing event updates, to the callback URL.
|
213
|
+
|
193
214
|
request_options : typing.Optional[RequestOptions]
|
194
215
|
Request-specific configuration.
|
195
216
|
|
@@ -205,6 +226,8 @@ class RawDocumentsClient:
|
|
205
226
|
"websites": convert_and_respect_annotation_metadata(
|
206
227
|
object_=websites, annotation=typing.Sequence[WebsiteSource], direction="write"
|
207
228
|
),
|
229
|
+
"callbackUrl": callback_url,
|
230
|
+
"callbackData": callback_data,
|
208
231
|
},
|
209
232
|
headers={
|
210
233
|
"content-type": "application/json",
|
@@ -724,6 +747,8 @@ class AsyncRawDocumentsClient:
|
|
724
747
|
self,
|
725
748
|
*,
|
726
749
|
documents: typing.Sequence[IngestRemoteDocument],
|
750
|
+
callback_url: typing.Optional[str] = OMIT,
|
751
|
+
callback_data: typing.Optional[str] = OMIT,
|
727
752
|
request_options: typing.Optional[RequestOptions] = None,
|
728
753
|
) -> AsyncHttpResponse[IngestResponse]:
|
729
754
|
"""
|
@@ -735,6 +760,12 @@ class AsyncRawDocumentsClient:
|
|
735
760
|
----------
|
736
761
|
documents : typing.Sequence[IngestRemoteDocument]
|
737
762
|
|
763
|
+
callback_url : typing.Optional[str]
|
764
|
+
An endpoint that will receive processing event updates as POST.
|
765
|
+
|
766
|
+
callback_data : typing.Optional[str]
|
767
|
+
A string that is returned, along with processing event updates, to the callback URL.
|
768
|
+
|
738
769
|
request_options : typing.Optional[RequestOptions]
|
739
770
|
Request-specific configuration.
|
740
771
|
|
@@ -750,6 +781,8 @@ class AsyncRawDocumentsClient:
|
|
750
781
|
"documents": convert_and_respect_annotation_metadata(
|
751
782
|
object_=documents, annotation=typing.Sequence[IngestRemoteDocument], direction="write"
|
752
783
|
),
|
784
|
+
"callbackUrl": callback_url,
|
785
|
+
"callbackData": callback_data,
|
753
786
|
},
|
754
787
|
headers={
|
755
788
|
"content-type": "application/json",
|
@@ -864,7 +897,12 @@ class AsyncRawDocumentsClient:
|
|
864
897
|
raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
|
865
898
|
|
866
899
|
async def crawl_website(
|
867
|
-
self,
|
900
|
+
self,
|
901
|
+
*,
|
902
|
+
websites: typing.Sequence[WebsiteSource],
|
903
|
+
callback_url: typing.Optional[str] = OMIT,
|
904
|
+
callback_data: typing.Optional[str] = OMIT,
|
905
|
+
request_options: typing.Optional[RequestOptions] = None,
|
868
906
|
) -> AsyncHttpResponse[IngestResponse]:
|
869
907
|
"""
|
870
908
|
Upload the content of a publicly accessible website for ingestion into a GroundX bucket. This is done by following links within a specified URL, recursively, up to a specified depth or number of pages.
|
@@ -878,6 +916,12 @@ class AsyncRawDocumentsClient:
|
|
878
916
|
----------
|
879
917
|
websites : typing.Sequence[WebsiteSource]
|
880
918
|
|
919
|
+
callback_url : typing.Optional[str]
|
920
|
+
The URL that will receive processing event updates.
|
921
|
+
|
922
|
+
callback_data : typing.Optional[str]
|
923
|
+
A string that is returned, along with processing event updates, to the callback URL.
|
924
|
+
|
881
925
|
request_options : typing.Optional[RequestOptions]
|
882
926
|
Request-specific configuration.
|
883
927
|
|
@@ -893,6 +937,8 @@ class AsyncRawDocumentsClient:
|
|
893
937
|
"websites": convert_and_respect_annotation_metadata(
|
894
938
|
object_=websites, annotation=typing.Sequence[WebsiteSource], direction="write"
|
895
939
|
),
|
940
|
+
"callbackUrl": callback_url,
|
941
|
+
"callbackData": callback_data,
|
896
942
|
},
|
897
943
|
headers={
|
898
944
|
"content-type": "application/json",
|
groundx/ingest.py
CHANGED
@@ -111,6 +111,7 @@ def prep_documents(
|
|
111
111
|
bucket_id=document.bucket_id,
|
112
112
|
file_name=document.file_name,
|
113
113
|
file_type=document.file_type,
|
114
|
+
filter=document.filter,
|
114
115
|
process_level=document.process_level,
|
115
116
|
search_data=document.search_data,
|
116
117
|
source_url=document.file_path,
|
@@ -431,6 +432,7 @@ class GroundX(GroundXBase):
|
|
431
432
|
bucket_id=d.bucket_id,
|
432
433
|
file_name=fn,
|
433
434
|
file_type=ft,
|
435
|
+
filter=d.filter,
|
434
436
|
process_level=d.process_level,
|
435
437
|
search_data=d.search_data,
|
436
438
|
source_url=url,
|
@@ -610,6 +612,7 @@ class AsyncGroundX(AsyncGroundXBase):
|
|
610
612
|
bucket_id=d.bucket_id,
|
611
613
|
file_name=fn,
|
612
614
|
file_type=ft,
|
615
|
+
filter=d.filter,
|
613
616
|
process_level=d.process_level,
|
614
617
|
search_data=d.search_data,
|
615
618
|
source_url=url,
|
@@ -5,7 +5,7 @@ groundx/buckets/raw_client.py,sha256=T2Ty5obN7eHbaxHGAimzjM8MGOmSOQEckhciyZkzcjE
|
|
5
5
|
groundx/client.py,sha256=FsVhPSZ1kd70pOVv37zTbNSwBM7XdttSx4aEPobPoew,6412
|
6
6
|
groundx/core/__init__.py,sha256=lTcqUPXcx4112yLDd70RAPeqq6tu3eFMe1pKOqkW9JQ,1562
|
7
7
|
groundx/core/api_error.py,sha256=44vPoTyWN59gonCIZMdzw7M1uspygiLnr3GNFOoVL2Q,614
|
8
|
-
groundx/core/client_wrapper.py,sha256=
|
8
|
+
groundx/core/client_wrapper.py,sha256=6kt4UKqg0xo6rR-WTr5MysDjueo-vbjqXq2vVg_sXWs,1822
|
9
9
|
groundx/core/datetime_utils.py,sha256=nBys2IsYrhPdszxGKCNRPSOCwa-5DWOHG95FB8G9PKo,1047
|
10
10
|
groundx/core/file.py,sha256=d4NNbX8XvXP32z8KpK2Xovv33nFfruIrpz0QWxlgpZk,2663
|
11
11
|
groundx/core/force_multipart.py,sha256=awxh5MtcRYe74ehY8U76jzv6fYM_w_D3Rur7KQQzSDk,429
|
@@ -22,8 +22,8 @@ groundx/customer/__init__.py,sha256=_VhToAyIt_5axN6CLJwtxg3-CO7THa_23pbUzqhXJa4,
|
|
22
22
|
groundx/customer/client.py,sha256=OAW3fJcOjvSvmGBbQEiNRlPE-dt15yFZHYXq9qrSXnw,2710
|
23
23
|
groundx/customer/raw_client.py,sha256=7qz8GU8Qe4G16YzeZ2Rz_cHNODPMTevOt4toPqCe0io,3403
|
24
24
|
groundx/documents/__init__.py,sha256=_VhToAyIt_5axN6CLJwtxg3-CO7THa_23pbUzqhXJa4,85
|
25
|
-
groundx/documents/client.py,sha256=
|
26
|
-
groundx/documents/raw_client.py,sha256=
|
25
|
+
groundx/documents/client.py,sha256=PX6UsmF9-ISORcAjbG3Na-XCY1q1Y1H4C8r5VKBHjkY,33597
|
26
|
+
groundx/documents/raw_client.py,sha256=u_qX6LSVsb2HxzNGC3DguCLqSZbGvSsQcStj1PyCoDA,59355
|
27
27
|
groundx/environment.py,sha256=CInm1_DKtZ1mrxutmKb1qqv82P33r_S87hZD3Hc1VB0,159
|
28
28
|
groundx/errors/__init__.py,sha256=Ua3Z6OWyRhcgrq0FSXOpwmOc4RxyTgzP2LXbkzGbMhk,234
|
29
29
|
groundx/errors/bad_request_error.py,sha256=PnE3v3kETCXm9E3LiNcHLNtjPEUvpe98-r59q-kQb78,338
|
@@ -34,7 +34,7 @@ groundx/groups/raw_client.py,sha256=nP9yFh7MexjDUQU8TtB5j-HAmZJjQWOd78hu-KeMnRs,
|
|
34
34
|
groundx/health/__init__.py,sha256=_VhToAyIt_5axN6CLJwtxg3-CO7THa_23pbUzqhXJa4,85
|
35
35
|
groundx/health/client.py,sha256=kcGIlqCEzBl6fuwJaf3x-obOagXxyAlEFaPRH3qgdDs,4566
|
36
36
|
groundx/health/raw_client.py,sha256=_TDa-O13PtC0RYCAq4bx5FESz1oLDLp9WExyOKjsIjs,7430
|
37
|
-
groundx/ingest.py,sha256=
|
37
|
+
groundx/ingest.py,sha256=Tg2tQXJ5WtfyktMXMIM6qXgEYlRHXiC6-mXx58-bcxQ,22521
|
38
38
|
groundx/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
39
39
|
groundx/search/__init__.py,sha256=Y1EKHPBEh-ebo1YOikCHTHU9E8kBP2s7K4J_kZGzcOA,165
|
40
40
|
groundx/search/client.py,sha256=P4-oektRdgtfxoi_NiGDSOrB2dDWfO9M5kVy61CnCPQ,13599
|
@@ -90,7 +90,7 @@ groundx/types/subscription_detail.py,sha256=GEEivqyiLsZtd8Ow7mqqwF1y0m0tHD-t9r9d
|
|
90
90
|
groundx/types/subscription_detail_meters.py,sha256=vGqiR2uupVh5177DfOghjoe5mwzVhoWljKzPF-twUc0,794
|
91
91
|
groundx/types/website_source.py,sha256=53jWDBtSrJVOsBVtVbZbjhEAsd0QGkXa7IuKO4AooLs,1542
|
92
92
|
groundx/version.py,sha256=1yVogKaq260fQfckM2RYN2144SEw0QROsZW8ICtkG4U,74
|
93
|
-
groundx-2.3.
|
94
|
-
groundx-2.3.
|
95
|
-
groundx-2.3.
|
96
|
-
groundx-2.3.
|
93
|
+
groundx-2.3.8.dist-info/LICENSE,sha256=dFE6nY1bHnSn6NqmdlghlU1gQqLqYNphrceGVehSa7o,1065
|
94
|
+
groundx-2.3.8.dist-info/METADATA,sha256=-QQUskjzs6nFZm4McDzrqSZKRVULQqNyNCawYRYuGk0,5173
|
95
|
+
groundx-2.3.8.dist-info/WHEEL,sha256=Zb28QaM1gQi8f4VCBhsUklF61CTlNYfs9YAZn-TOGFk,88
|
96
|
+
groundx-2.3.8.dist-info/RECORD,,
|
File without changes
|
File without changes
|