hamtaa-texttools 0.1.52__py3-none-any.whl → 0.1.54__py3-none-any.whl

{hamtaa_texttools-0.1.52.dist-info → hamtaa_texttools-0.1.54.dist-info}/METADATA

@@ -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.dist-info → hamtaa_texttools-0.1.54.dist-info}/RECORD

@@ -50,12 +50,12 @@ texttools/tools/summarizer/__init__.py,sha256=phrR7qO20CNhO3hjXQBzhTRVumdVdGSufm
 texttools/tools/summarizer/gemma_summarizer.py,sha256=ikhsBv7AiZD1dT_d12AyjXxojzSW92e2y5WjchI_3bE,4474
 texttools/tools/summarizer/llm_summerizer.py,sha256=-0rUKbSnl1aDeBfJ5DCSbIlwd2k-9qIaCKgoQJa0hWc,3412
 texttools/tools/translator/__init__.py,sha256=KO1m08J2BZwRqBGO9ICB4l4cnH1jfHLHL5HbgYFUWM8,72
-texttools/tools/translator/gemma_translator.py,sha256=gtvSpz19aGlbAk98M4xX61F4CqyI0QeAxLuw7N8cAoI,7551
+texttools/tools/translator/gemma_translator.py,sha256=4bW9wVIkrlYDhWaOWB2sN7oC0xzeWJ-rfKRnp_lGrp4,7259
 texttools/utils/flex_processor.py,sha256=C-lMwMjpIM6uAPFxXdgajxcFV1ccngEfJqq6xe5S1J8,3123
 texttools/utils/batch_manager/__init__.py,sha256=3ZkxA395lRD4gNxJ1vp0fNuz_XuBr50GoP51rrwQ0Ks,87
 texttools/utils/batch_manager/batch_manager.py,sha256=jAmKskL3OTYwwsO1mWsWAB3VxMlOF07c2GW1Ev83ZhY,9283
 texttools/utils/batch_manager/batch_runner.py,sha256=DE6TFz3i_jR-ZiUYbgIdLgjqr3aitw-JM_tKnSvzGL0,7424
-hamtaa_texttools-0.1.52.dist-info/METADATA,sha256=tRdADD1IP3at6Bp043-KsnFBr1tAcguGvdIBCjAaFuo,1481
-hamtaa_texttools-0.1.52.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-hamtaa_texttools-0.1.52.dist-info/top_level.txt,sha256=5Mh0jIxxZ5rOXHGJ6Mp-JPKviywwN0MYuH0xk5bEWqE,10
-hamtaa_texttools-0.1.52.dist-info/RECORD,,
+hamtaa_texttools-0.1.54.dist-info/METADATA,sha256=ad_jTTDOoADppaC7jik-hrxEuWc5aOwtz5_XFW1dTp0,1481
+hamtaa_texttools-0.1.54.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+hamtaa_texttools-0.1.54.dist-info/top_level.txt,sha256=5Mh0jIxxZ5rOXHGJ6Mp-JPKviywwN0MYuH0xk5bEWqE,10
+hamtaa_texttools-0.1.54.dist-info/RECORD,,

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