hamtaa-texttools 0.1.52__tar.gz → 0.1.54__tar.gz

{hamtaa_texttools-0.1.52 → hamtaa_texttools-0.1.54}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hamtaa-texttools
-Version: 0.1.52
+Version: 0.1.54
 Summary: A set of high-level NLP tools
 Author: Tohidi, Montazer, Givechi, Mousavinezhad
 Requires-Python: >=3.8

{hamtaa_texttools-0.1.52 → hamtaa_texttools-0.1.54}/hamtaa_texttools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hamtaa-texttools
-Version: 0.1.52
+Version: 0.1.54
 Summary: A set of high-level NLP tools
 Author: Tohidi, Montazer, Givechi, Mousavinezhad
 Requires-Python: >=3.8

{hamtaa_texttools-0.1.52 → hamtaa_texttools-0.1.54}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hamtaa-texttools"
-version = "0.1.52"
+version = "0.1.54"
 description = "A set of high-level NLP tools"
 readme = "README.md"
 requires-python = ">=3.8"

{hamtaa_texttools-0.1.52 → hamtaa_texttools-0.1.54}/texttools/tools/translator/gemma_translator.py

@@ -7,18 +7,13 @@ from texttools.base.base_translator import BaseTranslator
 from texttools.formatter.gemma3_formatter import Gemma3Formatter
 
 
-# Pydantic BaseModel to specify the output format of preprocessor
-# Preprocessor's job is to extract proper names
 class PreprocessorOutput(BaseModel):
     """
-    A single proper-name entity extracted from the source text.
+    List of proper-name strings extracted from the source text.
     """
 
-    text: str = Field(
-        description="The exact substring from the original text that represents a proper name."
-    )
-    text_type: str = Field(
-        description='Always use the literal value "Proper Name" when this entity is a real persons name.'
+    entities: List[str] = Field(
+        description="All proper names found in the text; return an empty list if none."
     )
 
 
@@ -73,7 +68,7 @@ class GemmaTranslator(BaseTranslator):
         """
         messages.append({"role": "user", "content": enforce_prompt})
 
-        clean_text = text.strip()
+        clean_text = text
         if reason:
             reason_prompt = f"""
             Based on the analysis conducted, translate the following text {"from" + source_language if source_language else ""} to {target_language}.
@@ -143,7 +138,7 @@ class GemmaTranslator(BaseTranslator):
         completion = self.client.chat.completions.parse(
             model=self.model,
             messages=restructured,
-            response_format=List[PreprocessorOutput],
+            response_format=PreprocessorOutput,
             temperature=self.temperature,
             extra_body={
                 "guided_decoding_backend": "auto",
@@ -164,11 +159,11 @@ class GemmaTranslator(BaseTranslator):
 
         # Extract proper names to tell the LLM what names not to translate, but to transliterate
         extracted = self.preprocess(text)
-        proper_names = [e.text for e in extracted]
+        proper_names = extracted.entities
 
         reason_summary = None
         if self.use_reason:
-            reason_summary = self._reason(text, target_language, source_language)
+            reason_summary = self._reason(text, target_language)
 
         messages = self._build_messages(
             text, target_language, source_language, reason_summary, proper_names