hamtaa-texttools 0.1.50__tar.gz → 0.1.51__tar.gz

{hamtaa_texttools-0.1.50 → hamtaa_texttools-0.1.51}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hamtaa-texttools
-Version: 0.1.50
+Version: 0.1.51
 Summary: A set of high-level NLP tools
 Author: Tohidi, Montazer, Givechi, Mousavinezhad
 Requires-Python: >=3.8

{hamtaa_texttools-0.1.50 → hamtaa_texttools-0.1.51}/hamtaa_texttools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hamtaa-texttools
-Version: 0.1.50
+Version: 0.1.51
 Summary: A set of high-level NLP tools
 Author: Tohidi, Montazer, Givechi, Mousavinezhad
 Requires-Python: >=3.8

{hamtaa_texttools-0.1.50 → hamtaa_texttools-0.1.51}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hamtaa-texttools"
-version = "0.1.50"
+version = "0.1.51"
 description = "A set of high-level NLP tools"
 readme = "README.md"
 requires-python = ">=3.8"

{hamtaa_texttools-0.1.50 → hamtaa_texttools-0.1.51}/texttools/tools/translator/gemma_translator.py

@@ -1,7 +1,7 @@
-from typing import Any, Optional
+from typing import Any, List, Optional
 
 from openai import OpenAI
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 
 from texttools.base.base_translator import BaseTranslator
 from texttools.formatter.gemma3_formatter import Gemma3Formatter
@@ -10,8 +10,16 @@ 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):
-    text: str
-    text_type: str
+    """
+    A single proper-name entity 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.'
+    )
 
 
 class GemmaTranslator(BaseTranslator):
@@ -135,7 +143,7 @@ class GemmaTranslator(BaseTranslator):
         completion = self.client.chat.completions.parse(
             model=self.model,
             messages=restructured,
-            response_format=PreprocessorOutput,
+            response_format=List[PreprocessorOutput],
             temperature=self.temperature,
             extra_body=dict(guided_decoding_backend="auto") ** self.client_kwargs,
         )
@@ -153,7 +161,7 @@ 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 = [e.text for e in extracted]
 
         reason_summary = None
         if self.use_reason: