unique_toolkit 1.42.4__tar.gz → 1.42.6__tar.gz

{unique_toolkit-1.42.4 → unique_toolkit-1.42.6}/CHANGELOG.md

@@ -5,6 +5,13 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), 
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.42.6] - 2026-01-07
+- Remove double redundant condition
+
+## [1.42.5] - 2026-01-07
+- Add Mapping of metadata to the `search_content` calls
+- Remove additional indentation by the markdown to docx converter
+
 ## [1.42.4] - 2026-01-07
 - Added `additionalSheetInformation` to magic table event.
 

{unique_toolkit-1.42.4 → unique_toolkit-1.42.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: unique_toolkit
-Version: 1.42.4
+Version: 1.42.6
 Summary: 
 License: Proprietary
 Author: Cedric Klinkert
@@ -124,6 +124,13 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/), 
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [1.42.6] - 2026-01-07
+- Remove double redundant condition
+
+## [1.42.5] - 2026-01-07
+- Add Mapping of metadata to the `search_content` calls
+- Remove additional indentation by the markdown to docx converter
+
 ## [1.42.4] - 2026-01-07
 - Added `additionalSheetInformation` to magic table event.
 

{unique_toolkit-1.42.4 → unique_toolkit-1.42.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "unique_toolkit"
-version = "1.42.4"
+version = "1.42.6"
 description = ""
 authors = [
     "Cedric Klinkert <cedric.klinkert@unique.ch>",

{unique_toolkit-1.42.4 → unique_toolkit-1.42.6}/unique_toolkit/_common/docx_generator/service.py

@@ -33,15 +33,6 @@ class DocxGeneratorService:
         # Initialize markdown-it parser
         md = MarkdownIt()
 
-        # Preprocess markdown.
-        # - Replace all headings with the correct heading level
-        # - Remove "Relevant sources" heading
-        # - Replace "# Proposed answer" with "#### Proposed answer"
-        markdown = re.sub(r"(?m)^\s*## ", "#### ", markdown)
-        markdown = re.sub(r"(?m)^\s*### ", "##### ", markdown)
-        markdown = markdown.replace("# Relevant sources", "")
-        markdown = markdown.replace("# Proposed answer", "#### Proposed answer")
-
         tokens = md.parse(markdown)
 
         elements = []

{unique_toolkit-1.42.4 → unique_toolkit-1.42.6}/unique_toolkit/content/utils.py

@@ -3,10 +3,7 @@ import re
 import tiktoken
 import unique_sdk
 
-from unique_toolkit.content.schemas import (
-    Content,
-    ContentChunk,
-)
+from unique_toolkit.content.schemas import Content, ContentChunk, ContentMetadata
 
 
 def _map_content_id_to_chunks(content_chunks: list[ContentChunk]):
@@ -190,7 +187,10 @@ def count_tokens(text: str, encoding_model="cl100k_base") -> int:
     return len(encoding.encode(text))
 
 
-def map_content_chunk(content_id: str, content_key: str, content_chunk: dict):
+def map_content_chunk(
+    content_id: str, content_key: str, content_chunk: dict, metadata: dict | None
+):
+    content_metadata = ContentMetadata(**metadata) if metadata else None
     return ContentChunk(
         id=content_id,
         key=content_key,
@@ -199,23 +199,26 @@ def map_content_chunk(content_id: str, content_key: str, content_chunk: dict):
         start_page=content_chunk["startPage"],
         end_page=content_chunk["endPage"],
         order=content_chunk["order"],
+        metadata=content_metadata,
     )
 
 
 def map_content(content: dict):
+    metadata = content.get("metadata")
     return Content(
         id=content["id"],
         key=content["key"],
         title=content["title"],
         url=content["url"],
         chunks=[
-            map_content_chunk(content["id"], content["key"], chunk)
+            map_content_chunk(content["id"], content["key"], chunk, metadata)
             for chunk in content["chunks"]
         ],
         created_at=content["createdAt"],
         updated_at=content["updatedAt"],
         ingestion_state=content.get("ingestionState"),
         expired_at=content.get("expiredAt"),
+        metadata=content.get("metadata"),
     )