unique_toolkit 1.42.4__py3-none-any.whl → 1.42.5__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.
- unique_toolkit/_common/docx_generator/service.py +0 -9
- unique_toolkit/content/utils.py +11 -6
- {unique_toolkit-1.42.4.dist-info → unique_toolkit-1.42.5.dist-info}/METADATA +5 -1
- {unique_toolkit-1.42.4.dist-info → unique_toolkit-1.42.5.dist-info}/RECORD +6 -6
- {unique_toolkit-1.42.4.dist-info → unique_toolkit-1.42.5.dist-info}/LICENSE +0 -0
- {unique_toolkit-1.42.4.dist-info → unique_toolkit-1.42.5.dist-info}/WHEEL +0 -0
|
@@ -33,15 +33,6 @@ class DocxGeneratorService:
|
|
|
33
33
|
# Initialize markdown-it parser
|
|
34
34
|
md = MarkdownIt()
|
|
35
35
|
|
|
36
|
-
# Preprocess markdown.
|
|
37
|
-
# - Replace all headings with the correct heading level
|
|
38
|
-
# - Remove "Relevant sources" heading
|
|
39
|
-
# - Replace "# Proposed answer" with "#### Proposed answer"
|
|
40
|
-
markdown = re.sub(r"(?m)^\s*## ", "#### ", markdown)
|
|
41
|
-
markdown = re.sub(r"(?m)^\s*### ", "##### ", markdown)
|
|
42
|
-
markdown = markdown.replace("# Relevant sources", "")
|
|
43
|
-
markdown = markdown.replace("# Proposed answer", "#### Proposed answer")
|
|
44
|
-
|
|
45
36
|
tokens = md.parse(markdown)
|
|
46
37
|
|
|
47
38
|
elements = []
|
unique_toolkit/content/utils.py
CHANGED
|
@@ -3,10 +3,7 @@ import re
|
|
|
3
3
|
import tiktoken
|
|
4
4
|
import unique_sdk
|
|
5
5
|
|
|
6
|
-
from unique_toolkit.content.schemas import
|
|
7
|
-
Content,
|
|
8
|
-
ContentChunk,
|
|
9
|
-
)
|
|
6
|
+
from unique_toolkit.content.schemas import Content, ContentChunk, ContentMetadata
|
|
10
7
|
|
|
11
8
|
|
|
12
9
|
def _map_content_id_to_chunks(content_chunks: list[ContentChunk]):
|
|
@@ -190,7 +187,12 @@ def count_tokens(text: str, encoding_model="cl100k_base") -> int:
|
|
|
190
187
|
return len(encoding.encode(text))
|
|
191
188
|
|
|
192
189
|
|
|
193
|
-
def map_content_chunk(
|
|
190
|
+
def map_content_chunk(
|
|
191
|
+
content_id: str, content_key: str, content_chunk: dict, metadata: dict | None
|
|
192
|
+
):
|
|
193
|
+
content_metadata = (
|
|
194
|
+
ContentMetadata(**metadata) if metadata else None if metadata else None
|
|
195
|
+
)
|
|
194
196
|
return ContentChunk(
|
|
195
197
|
id=content_id,
|
|
196
198
|
key=content_key,
|
|
@@ -199,23 +201,26 @@ def map_content_chunk(content_id: str, content_key: str, content_chunk: dict):
|
|
|
199
201
|
start_page=content_chunk["startPage"],
|
|
200
202
|
end_page=content_chunk["endPage"],
|
|
201
203
|
order=content_chunk["order"],
|
|
204
|
+
metadata=content_metadata,
|
|
202
205
|
)
|
|
203
206
|
|
|
204
207
|
|
|
205
208
|
def map_content(content: dict):
|
|
209
|
+
metadata = content.get("metadata")
|
|
206
210
|
return Content(
|
|
207
211
|
id=content["id"],
|
|
208
212
|
key=content["key"],
|
|
209
213
|
title=content["title"],
|
|
210
214
|
url=content["url"],
|
|
211
215
|
chunks=[
|
|
212
|
-
map_content_chunk(content["id"], content["key"], chunk)
|
|
216
|
+
map_content_chunk(content["id"], content["key"], chunk, metadata)
|
|
213
217
|
for chunk in content["chunks"]
|
|
214
218
|
],
|
|
215
219
|
created_at=content["createdAt"],
|
|
216
220
|
updated_at=content["updatedAt"],
|
|
217
221
|
ingestion_state=content.get("ingestionState"),
|
|
218
222
|
expired_at=content.get("expiredAt"),
|
|
223
|
+
metadata=content.get("metadata"),
|
|
219
224
|
)
|
|
220
225
|
|
|
221
226
|
|
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
Metadata-Version: 2.1
|
|
2
2
|
Name: unique_toolkit
|
|
3
|
-
Version: 1.42.
|
|
3
|
+
Version: 1.42.5
|
|
4
4
|
Summary:
|
|
5
5
|
License: Proprietary
|
|
6
6
|
Author: Cedric Klinkert
|
|
@@ -124,6 +124,10 @@ All notable changes to this project will be documented in this file.
|
|
|
124
124
|
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
|
|
125
125
|
and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
|
|
126
126
|
|
|
127
|
+
## [1.42.5] - 2026-01-07
|
|
128
|
+
- Add Mapping of metadata to the `search_content` calls
|
|
129
|
+
- Remove additional indentation by the markdown to docx converter
|
|
130
|
+
|
|
127
131
|
## [1.42.4] - 2026-01-07
|
|
128
132
|
- Added `additionalSheetInformation` to magic table event.
|
|
129
133
|
|
|
@@ -12,7 +12,7 @@ unique_toolkit/_common/default_language_model.py,sha256=XCZu6n270QkxEeTpj5NZJda6
|
|
|
12
12
|
unique_toolkit/_common/docx_generator/__init__.py,sha256=dqzO4NvzdXClq42vVRqqOvzKwmzqAB8CaufAo_QEv1s,226
|
|
13
13
|
unique_toolkit/_common/docx_generator/config.py,sha256=uJOa0GXvi3InuLkRDbLSD0RxMRelU2bPI73g4XcHIVc,354
|
|
14
14
|
unique_toolkit/_common/docx_generator/schemas.py,sha256=4U4SCCjBQ-R8XBkSSO3QigYqONp26r7Fcwy8P885do8,2420
|
|
15
|
-
unique_toolkit/_common/docx_generator/service.py,sha256=
|
|
15
|
+
unique_toolkit/_common/docx_generator/service.py,sha256=LM-kIfS2X3P507KLqsUJsb-rm6-i-G2yz2Nb5AEfY3w,7770
|
|
16
16
|
unique_toolkit/_common/docx_generator/template/Doc Template.docx,sha256=USnCg8h6d-N0751riNjqYr6ALLffU-EoJ8WY57K55r0,34757
|
|
17
17
|
unique_toolkit/_common/endpoint_builder.py,sha256=pEDwgeDzt67qbyaM98u8X7UAy29mQIw9Qufjz2bxgEA,11410
|
|
18
18
|
unique_toolkit/_common/endpoint_requestor.py,sha256=TBLYUVpfdYIPpeKfEVYfH8BrNxnn4yAcSUjfdVDkT78,15443
|
|
@@ -167,7 +167,7 @@ unique_toolkit/content/functions.py,sha256=cYbILIufzX1btSPiEAglH4cd2eI5MfHoZmaUB
|
|
|
167
167
|
unique_toolkit/content/schemas.py,sha256=uuS1UsuWK6eC7cP4dTC1q3DJ39xl6zenN2zL4ghFmzk,6424
|
|
168
168
|
unique_toolkit/content/service.py,sha256=hwycIbxtLn1p0IgNQMVIxN2NUhy_4AVsTfatytGi-gY,24919
|
|
169
169
|
unique_toolkit/content/smart_rules.py,sha256=z2gHToPrdyj3HqO8Uu-JE5G2ClvJPuhR2XERmmkgoug,9668
|
|
170
|
-
unique_toolkit/content/utils.py,sha256=
|
|
170
|
+
unique_toolkit/content/utils.py,sha256=w2VKLoe88cRsJ9Os-6Grj7d_0X3Hdl5Ic4yyBd1QW3k,8271
|
|
171
171
|
unique_toolkit/data_extraction/README.md,sha256=5KxzqPHC29wxBiWJ-87wBQisSgRBkuSnPTb38pGH1wA,3138
|
|
172
172
|
unique_toolkit/data_extraction/__init__.py,sha256=y6uSp8PAqgPZMoBgXWp1Ep0gsk9MD-NV8qn2QpOY-xY,330
|
|
173
173
|
unique_toolkit/data_extraction/augmented/__init__.py,sha256=_8G35ZgOPvcOR3a_2xvJDowoQ3ivQ9ehhJvbk1xzFs0,131
|
|
@@ -215,7 +215,7 @@ unique_toolkit/short_term_memory/service.py,sha256=5PeVBu1ZCAfyDb2HLVvlmqSbyzBBu
|
|
|
215
215
|
unique_toolkit/smart_rules/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
|
|
216
216
|
unique_toolkit/smart_rules/compile.py,sha256=Ozhh70qCn2yOzRWr9d8WmJeTo7AQurwd3tStgBMPFLA,1246
|
|
217
217
|
unique_toolkit/test_utilities/events.py,sha256=_mwV2bs5iLjxS1ynDCjaIq-gjjKhXYCK-iy3dRfvO3g,6410
|
|
218
|
-
unique_toolkit-1.42.
|
|
219
|
-
unique_toolkit-1.42.
|
|
220
|
-
unique_toolkit-1.42.
|
|
221
|
-
unique_toolkit-1.42.
|
|
218
|
+
unique_toolkit-1.42.5.dist-info/LICENSE,sha256=GlN8wHNdh53xwOPg44URnwag6TEolCjoq3YD_KrWgss,193
|
|
219
|
+
unique_toolkit-1.42.5.dist-info/METADATA,sha256=t1naUZXw9AHM32vCOwkWodfBH-OoR3eLI8CjnW6DOCY,47048
|
|
220
|
+
unique_toolkit-1.42.5.dist-info/WHEEL,sha256=sP946D7jFCHeNz5Iq4fL4Lu-PrWrFsgfLXbbkciIZwg,88
|
|
221
|
+
unique_toolkit-1.42.5.dist-info/RECORD,,
|
|
File without changes
|
|
File without changes
|