hjxdl 0.1.3__py3-none-any.whl → 0.1.4__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.
- hdl/_version.py +2 -2
- hdl/utils/llm/extract.py +10 -0
- {hjxdl-0.1.3.dist-info → hjxdl-0.1.4.dist-info}/METADATA +1 -1
- {hjxdl-0.1.3.dist-info → hjxdl-0.1.4.dist-info}/RECORD +6 -6
- {hjxdl-0.1.3.dist-info → hjxdl-0.1.4.dist-info}/WHEEL +0 -0
- {hjxdl-0.1.3.dist-info → hjxdl-0.1.4.dist-info}/top_level.txt +0 -0
hdl/_version.py
CHANGED
hdl/utils/llm/extract.py
CHANGED
@@ -10,10 +10,20 @@ from spire.doc.common import *
|
|
10
10
|
class DocExtractor():
|
11
11
|
def __init__(
|
12
12
|
self,
|
13
|
+
ltp_model_path: str = None,
|
13
14
|
lang: str = "chi_sim"
|
14
15
|
) -> None:
|
16
|
+
self.ltp_model_path = ltp_model_path
|
15
17
|
self.lang = lang
|
16
18
|
|
19
|
+
self.split = None
|
20
|
+
if self.ltp_model_path is not None:
|
21
|
+
from ltp import StnSplit, LTP
|
22
|
+
ltp = LTP(ltp_model)
|
23
|
+
self.split = StnSplit()
|
24
|
+
# sents = self.split.split(text)
|
25
|
+
|
26
|
+
|
17
27
|
@classmethod
|
18
28
|
def text_from_doc(
|
19
29
|
doc_path
|
@@ -1,5 +1,5 @@
|
|
1
1
|
hdl/__init__.py,sha256=5sZZNySv08wwfzJcSDssGTqUn9wlmDsR6R4XB8J8mFM,70
|
2
|
-
hdl/_version.py,sha256=
|
2
|
+
hdl/_version.py,sha256=9GTNkADgEYZ6fEjCvZZUdKyqxiPIgtskLFZNJz7nq_U,411
|
3
3
|
hdl/args/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
4
4
|
hdl/args/loss_args.py,sha256=s7YzSdd7IjD24rZvvOrxLLFqMZQb9YylxKeyelSdrTk,70
|
5
5
|
hdl/controllers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
@@ -86,10 +86,10 @@ hdl/utils/general/glob.py,sha256=8-RCnt6L297wMIfn34ZAMCsGCZUjHG3MGglGZI1cX0g,491
|
|
86
86
|
hdl/utils/llm/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
87
87
|
hdl/utils/llm/chat.py,sha256=H2c8assJlSdZQKIfPkYrVZHqv66TsdsxtaLXv0kNe1w,11565
|
88
88
|
hdl/utils/llm/embs.py,sha256=sC8tga7HgDwPI2m7TDWKp9kkxEIMxEyMtgmEhfRi4vI,6362
|
89
|
-
hdl/utils/llm/extract.py,sha256=
|
89
|
+
hdl/utils/llm/extract.py,sha256=qlthQiFQm5DfHDzimjQKotzLB7oPk5UTODsw22pzs80,4891
|
90
90
|
hdl/utils/schedulers/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
91
91
|
hdl/utils/schedulers/norm_lr.py,sha256=bDwCmdEK-WkgxQMFBiMuchv8Mm7C0-GZJ6usm-PQk14,4461
|
92
|
-
hjxdl-0.1.
|
93
|
-
hjxdl-0.1.
|
94
|
-
hjxdl-0.1.
|
95
|
-
hjxdl-0.1.
|
92
|
+
hjxdl-0.1.4.dist-info/METADATA,sha256=SCG5RpSG11LK0MmcU22aJOOV5Dmh_D7cCgi6kYaSnd0,542
|
93
|
+
hjxdl-0.1.4.dist-info/WHEEL,sha256=-oYQCr74JF3a37z2nRlQays_SX2MqOANoqVjBBAP2yE,91
|
94
|
+
hjxdl-0.1.4.dist-info/top_level.txt,sha256=-kxwTM5JPhylp06z3zAVO3w6_h7wtBfBo2zgM6YZoTk,4
|
95
|
+
hjxdl-0.1.4.dist-info/RECORD,,
|
File without changes
|
File without changes
|