hamtaa-texttools 1.0.2__py3-none-any.whl → 1.0.3__py3-none-any.whl

texttools/tools/the_tool.py

@@ -1,9 +1,9 @@
-from typing import Literal, Any
+from typing import Literal, Any, Optional
 
 from openai import OpenAI
 
-from texttools.tools.operator import Operator
-import texttools.tools.output_models as OutputModels
+from texttools.tools.internals.operator import Operator
+import texttools.tools.internals.output_models as OutputModels
 
 
 class TheTool:
@@ -46,7 +46,14 @@ class TheTool:
             **client_kwargs,
         )
 
-    def categorize(self, text: str, with_analysis: bool = False) -> dict[str, str]:
+    def categorize(
+        self,
+        text: str,
+        with_analysis: bool = False,
+        user_prompt: str = "",
+        logprobs: bool = False,
+        top_logprobs: int = 8,
+    ) -> dict[str, str]:
         """
         Categorize a text into a single Islamic studies domain category.
 
@@ -59,16 +66,28 @@ class TheTool:
             {"result": <category string>}
             Example: {"result": "باورهای دینی"}
         """
-        self.operator.PROMPT_FILE = "categorizer.yaml"
-        self.operator.OUTPUT_MODEL = OutputModels.CategorizerOutput
-        self.operator.WITH_ANALYSIS = with_analysis
-        self.operator.USE_MODES = False
 
-        results = self.operator.run(text)
+        results = self.operator.run(
+            text,
+            prompt_file="categorizer.yaml",
+            output_model=OutputModels.CategorizerOutput,
+            with_analysis=with_analysis,
+            resp_format="parse",
+            user_prompt=user_prompt,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+        )
+
         return results
 
     def extract_keywords(
-        self, text: str, with_analysis: bool = False
+        self,
+        text: str,
+        output_lang: Optional[str] = None,
+        with_analysis: bool = False,
+        user_prompt: str = "",
+        logprobs: bool = False,
+        top_logprobs: int = 3,
     ) -> dict[str, list[str]]:
         """
         Extract salient keywords from text.
@@ -80,16 +99,28 @@ class TheTool:
         Returns:
             {"result": [<keyword1>, <keyword2>, ...]}
         """
-        self.operator.PROMPT_FILE = "keyword_extractor.yaml"
-        self.operator.OUTPUT_MODEL = OutputModels.ListStrOutput
-        self.operator.WITH_ANALYSIS = with_analysis
-        self.operator.USE_MODES = False
+        results = self.operator.run(
+            text,
+            prompt_file="keyword_extractor.yaml",
+            output_model=OutputModels.ListStrOutput,
+            with_analysis=with_analysis,
+            resp_format="parse",
+            user_prompt=user_prompt,
+            output_lang=output_lang,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+        )
 
-        results = self.operator.run(text)
         return results
 
     def extract_entities(
-        self, text: str, with_analysis: bool = False
+        self,
+        text: str,
+        output_lang: Optional[str] = None,
+        with_analysis: bool = False,
+        user_prompt: str = "",
+        logprobs: bool = False,
+        top_logprobs: int = 3,
     ) -> dict[str, list[dict[str, str]]]:
         """
         Perform Named Entity Recognition (NER) over the input text.
@@ -101,17 +132,29 @@ class TheTool:
         Returns:
             {"result": [{"text": <entity>, "type": <entity_type>}, ...]}
         """
-        self.operator.PROMPT_FILE = "ner_extractor.yaml"
-        self.operator.OUTPUT_MODEL = OutputModels.ListDictStrStrOutput
-        self.operator.WITH_ANALYSIS = with_analysis
-        self.operator.USE_MODES = False
+        results = self.operator.run(
+            text,
+            prompt_file="ner_extractor.yaml",
+            output_model=OutputModels.ListDictStrStrOutput,
+            with_analysis=with_analysis,
+            resp_format="parse",
+            user_prompt=user_prompt,
+            output_lang=output_lang,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+        )
 
-        results = self.operator.run(text)
         return results
 
     def detect_question(
-        self, question: str, with_analysis: bool = False
-    ) -> dict[str, str]:
+        self,
+        question: str,
+        output_lang: Optional[str] = None,
+        with_analysis: bool = False,
+        user_prompt: str = "",
+        logprobs: bool = False,
+        top_logprobs: int = 2,
+    ) -> dict[str, bool]:
         """
         Detect if the input is phrased as a question.
 
@@ -122,16 +165,28 @@ class TheTool:
         Returns:
             {"result": "true"} or {"result": "false"}
         """
-        self.operator.PROMPT_FILE = "question_detector.yaml"
-        self.operator.OUTPUT_MODEL = OutputModels.StrOutput
-        self.operator.WITH_ANALYSIS = with_analysis
-        self.operator.USE_MODES = False
+        results = self.operator.run(
+            question,
+            prompt_file="question_detector.yaml",
+            output_model=OutputModels.BoolOutput,
+            with_analysis=with_analysis,
+            resp_format="parse",
+            user_prompt=user_prompt,
+            output_lang=output_lang,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+        )
 
-        results = self.operator.run(question)
         return results
 
     def generate_question_from_text(
-        self, text: str, with_analysis: bool = False
+        self,
+        text: str,
+        output_lang: Optional[str] = None,
+        with_analysis: bool = False,
+        user_prompt: str = "",
+        logprobs: bool = False,
+        top_logprobs: int = 3,
     ) -> dict[str, str]:
         """
         Generate a single question from the given text.
@@ -143,19 +198,29 @@ class TheTool:
         Returns:
             {"result": <generated_question>}
         """
-        self.operator.PROMPT_FILE = "question_generator.yaml"
-        self.operator.OUTPUT_MODEL = OutputModels.StrOutput
-        self.operator.WITH_ANALYSIS = with_analysis
-        self.operator.USE_MODES = False
+        results = self.operator.run(
+            text,
+            prompt_file="question_generator.yaml",
+            output_model=OutputModels.StrOutput,
+            with_analysis=with_analysis,
+            resp_format="parse",
+            user_prompt=user_prompt,
+            output_lang=output_lang,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+        )
 
-        results = self.operator.run(text)
         return results
 
     def merge_questions(
         self,
         questions: list[str],
-        mode: Literal["default_mode", "reason_mode"] = "default_mode",
+        output_lang: Optional[str] = None,
+        mode: Literal["default", "reason"] = "default",
         with_analysis: bool = False,
+        user_prompt: str = "",
+        logprobs: bool = False,
+        top_logprobs: int = 3,
     ) -> dict[str, str]:
         """
         Merge multiple questions into a single unified question.
@@ -163,8 +228,8 @@ class TheTool:
         Args:
             questions: List of question strings.
             mode: Merge strategy:
-                - "default_mode": simple merging.
-                - "reason_mode": merging with reasoning explanation.
+                - "default": simple merging.
+                - "reason": merging with reasoning explanation.
             with_analysis: Whether to use an analysis step.
 
         Returns:
@@ -172,23 +237,34 @@ class TheTool:
         """
         question_str = ", ".join(questions)
 
-        self.operator.PROMPT_FILE = "question_merger.yaml"
-        self.operator.OUTPUT_MODEL = OutputModels.StrOutput
-        self.operator.WITH_ANALYSIS = with_analysis
-        self.operator.USE_MODES = True
-        self.operator.MODE = mode
+        results = self.operator.run(
+            question_str,
+            prompt_file="question_merger.yaml",
+            output_model=OutputModels.StrOutput,
+            with_analysis=with_analysis,
+            use_modes=True,
+            mode=mode,
+            resp_format="parse",
+            user_prompt=user_prompt,
+            output_lang=output_lang,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+        )
 
-        results = self.operator.run(question_str)
         return results
 
     def rewrite_question(
         self,
         question: str,
+        output_lang: Optional[str] = None,
         mode: Literal[
-            "same_meaning_different_wording_mode",
-            "different_meaning_similar_wording_mode",
-        ] = "same_meaning_different_wording_mode",
+            "same_meaning_different_wording",
+            "different_meaning_similar_wording",
+        ] = "same_meaning_different_wording",
         with_analysis: bool = False,
+        user_prompt: str = "",
+        logprobs: bool = False,
+        top_logprobs: int = 3,
     ) -> dict[str, str]:
         """
         Rewrite a question with different wording or meaning.
@@ -196,28 +272,38 @@ class TheTool:
         Args:
             question: Input question to rewrite.
             mode: Rewrite strategy:
-                - "same_meaning_different_wording_mode": keep meaning, change words.
-                - "different_meaning_similar_wording_mode": alter meaning, preserve wording style.
+                - "same_meaning_different_wording": keep meaning, change words.
+                - "different_meaning_similar_wording": alter meaning, preserve wording style.
             with_analysis: Whether to include an analysis step.
 
         Returns:
             {"result": <rewritten_question>}
         """
-        self.operator.PROMPT_FILE = "question_rewriter.yaml"
-        self.operator.OUTPUT_MODEL = OutputModels.StrOutput
-        self.operator.WITH_ANALYSIS = with_analysis
-        self.operator.USE_MODES = True
-        self.operator.MODE = mode
+        results = self.operator.run(
+            question,
+            prompt_file="question_rewriter.yaml",
+            output_model=OutputModels.StrOutput,
+            with_analysis=with_analysis,
+            use_modes=True,
+            mode=mode,
+            resp_format="parse",
+            user_prompt=user_prompt,
+            output_lang=output_lang,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+        )
 
-        results = self.operator.run(question)
         return results
 
     def generate_questions_from_subject(
         self,
         subject: str,
         number_of_questions: int,
-        language: str = "English",
+        output_lang: Optional[str] = None,
         with_analysis: bool = False,
+        user_prompt: str = "",
+        logprobs: bool = False,
+        top_logprobs: int = 3,
     ) -> dict[str, list[str]]:
         """
         Generate a list of questions about a subject.
@@ -231,19 +317,30 @@ class TheTool:
         Returns:
             {"result": [<question1>, <question2>, ...]}
         """
-        self.operator.PROMPT_FILE = "subject_question_generator.yaml"
-        self.operator.OUTPUT_MODEL = OutputModels.ReasonListStrOutput
-        self.operator.WITH_ANALYSIS = with_analysis
-        self.operator.USE_MODES = False
-
         results = self.operator.run(
             subject,
+            prompt_file="subject_question_generator.yaml",
+            output_model=OutputModels.ReasonListStrOutput,
+            with_analysis=with_analysis,
+            resp_format="parse",
+            user_prompt=user_prompt,
             number_of_questions=number_of_questions,
-            language=language,
+            output_lang=output_lang,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
         )
+
         return results
 
-    def summarize(self, subject: str, with_analysis: bool = False) -> dict[str, str]:
+    def summarize(
+        self,
+        text: str,
+        output_lang: Optional[str] = None,
+        with_analysis: bool = False,
+        user_prompt: str = "",
+        logprobs: bool = False,
+        top_logprobs: int = 3,
+    ) -> dict[str, str]:
         """
         Summarize the given subject text.
 
@@ -254,12 +351,18 @@ class TheTool:
         Returns:
             {"result": <summary>}
         """
-        self.operator.PROMPT_FILE = "summarizer.yaml"
-        self.operator.OUTPUT_MODEL = OutputModels.StrOutput
-        self.operator.WITH_ANALYSIS = with_analysis
-        self.operator.USE_MODES = False
+        results = self.operator.run(
+            text,
+            prompt_file="summarizer.yaml",
+            output_model=OutputModels.StrOutput,
+            with_analysis=with_analysis,
+            resp_format="parse",
+            user_prompt=user_prompt,
+            output_lang=output_lang,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
+        )
 
-        results = self.operator.run(subject)
         return results
 
     def translate(
@@ -267,6 +370,9 @@ class TheTool:
         text: str,
         target_language: str,
         with_analysis: bool = False,
+        user_prompt: str = "",
+        logprobs: bool = False,
+        top_logprobs: int = 3,
     ) -> dict[str, str]:
         """
         Translate text between languages.
@@ -279,13 +385,16 @@ class TheTool:
         Returns:
             {"result": <translated_text>}
         """
-        self.operator.PROMPT_FILE = "translator.yaml"
-        self.operator.OUTPUT_MODEL = OutputModels.StrOutput
-        self.operator.WITH_ANALYSIS = with_analysis
-        self.operator.USE_MODES = False
-
         results = self.operator.run(
             text,
+            prompt_file="translator.yaml",
+            output_model=OutputModels.StrOutput,
+            with_analysis=with_analysis,
+            resp_format="parse",
+            user_prompt=user_prompt,
             target_language=target_language,
+            logprobs=logprobs,
+            top_logprobs=top_logprobs,
         )
+
         return results

hamtaa_texttools-1.0.2.dist-info/RECORD

@@ -1,28 +0,0 @@
-hamtaa_texttools-1.0.2.dist-info/licenses/LICENSE,sha256=TJch8KUnfKaKJFkaRqgtghB7rtprhaHyGirYKr90U4o,1062
-texttools/__init__.py,sha256=DEPDeR8rKRye57x9kq00Adq9GOLFkmaWRq9sGBNQZ_c,241
-texttools/formatters/base_formatter.py,sha256=sUrISJcczTLDPMiMETG-kyfZ64u0NubFpT3mjEQBskk,1147
-texttools/formatters/user_merge_formatter/user_merge_formatter.py,sha256=R-e64Gwq6jARcpsnPYsgNIX7eqFDi0BtfiZOATvwxqo,1692
-texttools/prompts/README.md,sha256=OJwlvlsKYW2ukdCMvvvxEGu8ncNx8MY9L3pzQTqWlGo,1364
-texttools/prompts/categorizer.yaml,sha256=XZtZaMEqH646W4GNC7flI0TROoUAA7w-wBV-Y6dJT7U,756
-texttools/prompts/keyword_extractor.yaml,sha256=KUATHGFrrKZ50Rg3TJO-Ivx7reKxPH0AE8-wXKp0PgE,460
-texttools/prompts/ner_extractor.yaml,sha256=IeGsIPDsD_Cq6tyDToTK4xOOq1ZF3hedZs7AWNMupCk,597
-texttools/prompts/question_detector.yaml,sha256=0yoSetf7_RWhhHoOCJBTY-GKB-_TrW7BDbyk0W6fvEU,408
-texttools/prompts/question_generator.yaml,sha256=GXrX1N6I5C5Hw6Pc_TRa_qQ2P4HWM7Vh8T28CUCrFKQ,950
-texttools/prompts/question_merger.yaml,sha256=2hPVjlCkM0aatVrGJrfCZRkBNPapXcYYH5WQkPLt30s,2148
-texttools/prompts/question_rewriter.yaml,sha256=5Yen8M5RrkWnH3eNoYUtKjXW7_IWKeVui8GTMqAs1Y4,1985
-texttools/prompts/subject_question_generator.yaml,sha256=FmmMjeFwKJHubBZHGesG7DDKazuhyDMsDRWd0A8ILjI,1426
-texttools/prompts/summarizer.yaml,sha256=t95zcRLd8PI18nx_030ROqG8UWtsgUMnNr9H8Y1ui_c,360
-texttools/prompts/translator.yaml,sha256=JOWXywPmHXJbJYD17Z-XMxBhXwdGbR02SdMNGc_sTZ4,614
-texttools/tools/__init__.py,sha256=Gzqlobmbgd5wOvy27JYPKB74MFtqDgFy6LwlRygN240,53
-texttools/tools/operator.py,sha256=g3ZC5OSxG_oZQkkMbfzc8uUvw0FNvehNB5jPPY26KEg,7972
-texttools/tools/output_models.py,sha256=EdMGvPEp0k8l9Ps48Arw7GMcXSmdRLPrvAhaYnVqGj8,1099
-texttools/tools/prompt_loader.py,sha256=zrCgLNGkFV60u6b7CN4dNcml4cGLrC2ei0WcMfD28Bc,2817
-texttools/tools/the_tool.py,sha256=lEMVpqhJvPqVzSWx8NlmYV7jqZ1ul3IqJ9nHJLjz0bw,9653
-texttools/utils/__init__.py,sha256=XL_cVGbe8wKf8HQh_Q1JEZgGOlmpLijPoHNvzi1aYnc,167
-texttools/utils/batch_manager/__init__.py,sha256=WcnujCd_5XotN6emVCfDaO_lMpyk8EwJYcFgNRks5q0,139
-texttools/utils/batch_manager/batch_manager.py,sha256=N7dg1bE0QpGYjHtM0E9DWtXErZR_z0byls9d8RQdUbs,9104
-texttools/utils/batch_manager/batch_runner.py,sha256=3dhzmHrvCKqQVTtxeBIiUhCyRwKiQp_WmWqGX2WTG-o,7602
-hamtaa_texttools-1.0.2.dist-info/METADATA,sha256=jLnwyMWFXxCAn4gZFRVlWWE14nWaB5VF17zaB3r6IFg,5114
-hamtaa_texttools-1.0.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-hamtaa_texttools-1.0.2.dist-info/top_level.txt,sha256=5Mh0jIxxZ5rOXHGJ6Mp-JPKviywwN0MYuH0xk5bEWqE,10
-hamtaa_texttools-1.0.2.dist-info/RECORD,,

texttools/utils/__init__.py

@@ -1,4 +0,0 @@
-from .batch_manager.batch_manager import SimpleBatchManager
-from .batch_manager.batch_runner import BatchJobRunner
-
-__all__ = ["SimpleBatchManager", "BatchJobRunner"]