hamtaa-texttools 1.1.9__py3-none-any.whl → 1.1.11__py3-none-any.whl

texttools/tools/internals/{operator.py → sync_operator.py}

@@ -1,4 +1,4 @@
-from typing import Any, TypeVar, Type, Literal, Callable
+from typing import Any, TypeVar, Type, Callable
 import logging
 
 from openai import OpenAI
@@ -25,8 +25,7 @@ class Operator(BaseOperator):
     """
 
     def __init__(self, client: OpenAI, model: str):
-        self.client = client
-        self.model = model
+        super().__init__(client, model)
 
     def _analyze(self, prompt_configs: dict[str, str], temperature: float) -> str:
         """
@@ -35,8 +34,8 @@ class Operator(BaseOperator):
         """
         analyze_prompt = prompt_configs["analyze_template"]
         analyze_message = [self._build_user_message(analyze_prompt)]
-        completion = self.client.chat.completions.create(
-            model=self.model,
+        completion = self._client.chat.completions.create(
+            model=self._model,
             messages=analyze_message,
             temperature=temperature,
         )
@@ -56,7 +55,7 @@ class Operator(BaseOperator):
         Returns both the parsed object and the raw completion for logging.
         """
         request_kwargs = {
-            "model": self.model,
+            "model": self._model,
             "messages": message,
             "response_format": output_model,
             "temperature": temperature,
@@ -66,43 +65,10 @@ class Operator(BaseOperator):
             request_kwargs["logprobs"] = True
             request_kwargs["top_logprobs"] = top_logprobs
 
-        completion = self.client.beta.chat.completions.parse(**request_kwargs)
+        completion = self._client.beta.chat.completions.parse(**request_kwargs)
         parsed = completion.choices[0].message.parsed
         return parsed, completion
 
-    def _vllm_completion(
-        self,
-        message: list[dict[str, str]],
-        output_model: Type[T],
-        temperature: float,
-        logprobs: bool = False,
-        top_logprobs: int = 3,
-    ) -> tuple[T, Any]:
-        """
-        Generates a completion using vLLM with JSON schema guidance.
-        Returns the parsed output model and raw completion.
-        """
-        json_schema = output_model.model_json_schema()
-
-        # Build kwargs dynamically
-        request_kwargs = {
-            "model": self.model,
-            "messages": message,
-            "extra_body": {"guided_json": json_schema},
-            "temperature": temperature,
-        }
-
-        if logprobs:
-            request_kwargs["logprobs"] = True
-            request_kwargs["top_logprobs"] = top_logprobs
-
-        completion = self.client.chat.completions.create(**request_kwargs)
-        response = completion.choices[0].message.content
-
-        # Convert the string response to output model
-        parsed = self._convert_to_output_model(response, output_model)
-        return parsed, completion
-
     def run(
         self,
         # User parameters
@@ -114,10 +80,10 @@ class Operator(BaseOperator):
         logprobs: bool,
         top_logprobs: int | None,
         validator: Callable[[Any], bool] | None,
+        max_validation_retries: int | None,
         # Internal parameters
         prompt_file: str,
         output_model: Type[T],
-        resp_format: Literal["vllm", "parse"],
         mode: str | None,
         **extra_kwargs,
     ) -> ToolOutput:
@@ -159,14 +125,9 @@ class Operator(BaseOperator):
             messages.append(self._build_user_message(prompt_configs["main_template"]))
             messages
 
-            if resp_format == "vllm":
-                parsed, completion = self._vllm_completion(
-                    messages, output_model, temperature, logprobs, top_logprobs
-                )
-            elif resp_format == "parse":
-                parsed, completion = self._parse_completion(
-                    messages, output_model, temperature, logprobs, top_logprobs
-                )
+            parsed, completion = self._parse_completion(
+                messages, output_model, temperature, logprobs, top_logprobs
+            )
 
             # Ensure output_model has a `result` field
             if not hasattr(parsed, "result"):
@@ -179,7 +140,7 @@ class Operator(BaseOperator):
 
             # Retry logic if validation fails
             if validator and not validator(output.result):
-                for attempt in range(self.MAX_RETRIES):
+                for attempt in range(max_validation_retries):
                     logger.warning(
                         f"Validation failed, retrying for the {attempt + 1} time."
                     )
@@ -187,22 +148,13 @@ class Operator(BaseOperator):
                     # Generate new temperature for retry
                     retry_temperature = self._get_retry_temp(temperature)
                     try:
-                        if resp_format == "vllm":
-                            parsed, completion = self._vllm_completion(
-                                messages,
-                                output_model,
-                                retry_temperature,
-                                logprobs,
-                                top_logprobs,
-                            )
-                        elif resp_format == "parse":
-                            parsed, completion = self._parse_completion(
-                                messages,
-                                output_model,
-                                retry_temperature,
-                                logprobs,
-                                top_logprobs,
-                            )
+                        parsed, completion = self._parse_completion(
+                            messages,
+                            output_model,
+                            retry_temperature,
+                            logprobs,
+                            top_logprobs,
+                        )
 
                         output.result = parsed.result
 

texttools/tools/sync_tools.py

@@ -2,8 +2,8 @@ from typing import Literal, Any, Callable
 
 from openai import OpenAI
 
-from texttools.tools.internals.operator import Operator
-import texttools.tools.internals.output_models as OutputModels
+from texttools.tools.internals.sync_operator import Operator
+import texttools.tools.internals.output_models as OM
 
 
 class TheTool:
@@ -22,7 +22,7 @@ class TheTool:
         client: OpenAI,
         model: str,
     ):
-        self.operator = Operator(client=client, model=model)
+        self._operator = Operator(client=client, model=model)
 
     def categorize(
         self,
@@ -33,7 +33,8 @@ class TheTool:
         logprobs: bool = False,
         top_logprobs: int | None = None,
         validator: Callable[[Any], bool] | None = None,
-    ) -> OutputModels.ToolOutput:
+        max_validation_retries: int | None = None,
+    ) -> OM.ToolOutput:
         """
         Categorize a text into a single Islamic studies domain category.
 
@@ -43,7 +44,7 @@ class TheTool:
                 - logprobs (list | None): Probability data if logprobs enabled
                 - analysis (str | None): Detailed reasoning if with_analysis enabled
         """
-        return self.operator.run(
+        return self._operator.run(
             # User parameters
             text=text,
             with_analysis=with_analysis,
@@ -52,10 +53,10 @@ class TheTool:
             logprobs=logprobs,
             top_logprobs=top_logprobs,
             validator=validator,
+            max_validation_retries=max_validation_retries,
             # Internal parameters
             prompt_file="categorizer.yaml",
-            output_model=OutputModels.CategorizerOutput,
-            resp_format="parse",
+            output_model=OM.CategorizerOutput,
             mode=None,
             output_lang=None,
         )
@@ -70,7 +71,8 @@ class TheTool:
         logprobs: bool = False,
         top_logprobs: int | None = None,
         validator: Callable[[Any], bool] | None = None,
-    ) -> OutputModels.ToolOutput:
+        max_validation_retries: int | None = None,
+    ) -> OM.ToolOutput:
         """
         Extract salient keywords from text.
 
@@ -80,7 +82,7 @@ class TheTool:
                 - logprobs (list | None): Probability data if logprobs enabled
                 - analysis (str | None): Detailed reasoning if with_analysis enabled
         """
-        return self.operator.run(
+        return self._operator.run(
             # User parameters
             text=text,
             with_analysis=with_analysis,
@@ -90,10 +92,10 @@ class TheTool:
             logprobs=logprobs,
             top_logprobs=top_logprobs,
             validator=validator,
+            max_validation_retries=max_validation_retries,
             # Internal parameters
             prompt_file="extract_keywords.yaml",
-            output_model=OutputModels.ListStrOutput,
-            resp_format="parse",
+            output_model=OM.ListStrOutput,
             mode=None,
         )
 
@@ -107,7 +109,8 @@ class TheTool:
         logprobs: bool = False,
         top_logprobs: int | None = None,
         validator: Callable[[Any], bool] | None = None,
-    ) -> OutputModels.ToolOutput:
+        max_validation_retries: int | None = None,
+    ) -> OM.ToolOutput:
         """
         Perform Named Entity Recognition (NER) over the input text.
 
@@ -117,7 +120,7 @@ class TheTool:
                 - logprobs (list | None): Probability data if logprobs enabled
                 - analysis (str | None): Detailed reasoning if with_analysis enabled
         """
-        return self.operator.run(
+        return self._operator.run(
             # User parameters
             text=text,
             with_analysis=with_analysis,
@@ -127,10 +130,10 @@ class TheTool:
             logprobs=logprobs,
             top_logprobs=top_logprobs,
             validator=validator,
+            max_validation_retries=max_validation_retries,
             # Internal parameters
             prompt_file="extract_entities.yaml",
-            output_model=OutputModels.ListDictStrStrOutput,
-            resp_format="parse",
+            output_model=OM.ListDictStrStrOutput,
             mode=None,
         )
 
@@ -143,7 +146,8 @@ class TheTool:
         logprobs: bool = False,
         top_logprobs: int | None = None,
         validator: Callable[[Any], bool] | None = None,
-    ) -> OutputModels.ToolOutput:
+        max_validation_retries: int | None = None,
+    ) -> OM.ToolOutput:
         """
         Detect if the input is phrased as a question.
 
@@ -153,7 +157,7 @@ class TheTool:
                 - logprobs (list | None): Probability data if logprobs enabled
                 - analysis (str | None): Detailed reasoning if with_analysis enabled
         """
-        return self.operator.run(
+        return self._operator.run(
             # User parameters
             text=text,
             with_analysis=with_analysis,
@@ -162,10 +166,10 @@ class TheTool:
             logprobs=logprobs,
             top_logprobs=top_logprobs,
             validator=validator,
+            max_validation_retries=max_validation_retries,
             # Internal parameters
             prompt_file="is_question.yaml",
-            output_model=OutputModels.BoolOutput,
-            resp_format="parse",
+            output_model=OM.BoolOutput,
             mode=None,
             output_lang=None,
         )
@@ -180,7 +184,8 @@ class TheTool:
         logprobs: bool = False,
         top_logprobs: int | None = None,
         validator: Callable[[Any], bool] | None = None,
-    ) -> OutputModels.ToolOutput:
+        max_validation_retries: int | None = None,
+    ) -> OM.ToolOutput:
         """
         Generate a single question from the given text.
 
@@ -190,7 +195,7 @@ class TheTool:
                 - logprobs (list | None): Probability data if logprobs enabled
                 - analysis (str | None): Detailed reasoning if with_analysis enabled
         """
-        return self.operator.run(
+        return self._operator.run(
             # User parameters
             text=text,
             with_analysis=with_analysis,
@@ -200,10 +205,10 @@ class TheTool:
             logprobs=logprobs,
             top_logprobs=top_logprobs,
             validator=validator,
+            max_validation_retries=max_validation_retries,
             # Internal parameters
             prompt_file="text_to_question.yaml",
-            output_model=OutputModels.StrOutput,
-            resp_format="parse",
+            output_model=OM.StrOutput,
             mode=None,
         )
 
@@ -218,7 +223,8 @@ class TheTool:
         top_logprobs: int | None = None,
         mode: Literal["default", "reason"] = "default",
         validator: Callable[[Any], bool] | None = None,
-    ) -> OutputModels.ToolOutput:
+        max_validation_retries: int | None = None,
+    ) -> OM.ToolOutput:
         """
         Merge multiple questions into a single unified question.
 
@@ -229,7 +235,7 @@ class TheTool:
                 - analysis (str | None): Detailed reasoning if with_analysis enabled
         """
         text = ", ".join(text)
-        return self.operator.run(
+        return self._operator.run(
             # User parameters
             text=text,
             with_analysis=with_analysis,
@@ -239,10 +245,10 @@ class TheTool:
             logprobs=logprobs,
             top_logprobs=top_logprobs,
             validator=validator,
+            max_validation_retries=max_validation_retries,
             # Internal parameters
             prompt_file="merge_questions.yaml",
-            output_model=OutputModels.StrOutput,
-            resp_format="parse",
+            output_model=OM.StrOutput,
             mode=mode,
         )
 
@@ -257,7 +263,8 @@ class TheTool:
         top_logprobs: int | None = None,
         mode: Literal["positive", "negative", "hard_negative"] = "positive",
         validator: Callable[[Any], bool] | None = None,
-    ) -> OutputModels.ToolOutput:
+        max_validation_retries: int | None = None,
+    ) -> OM.ToolOutput:
         """
         Rewrite a text with different modes.
 
@@ -267,7 +274,7 @@ class TheTool:
                 - logprobs (list | None): Probability data if logprobs enabled
                 - analysis (str | None): Detailed reasoning if with_analysis enabled
         """
-        return self.operator.run(
+        return self._operator.run(
             # User parameters
             text=text,
             with_analysis=with_analysis,
@@ -277,10 +284,10 @@ class TheTool:
             logprobs=logprobs,
             top_logprobs=top_logprobs,
             validator=validator,
+            max_validation_retries=max_validation_retries,
             # Internal parameters
             prompt_file="rewrite.yaml",
-            output_model=OutputModels.StrOutput,
-            resp_format="parse",
+            output_model=OM.StrOutput,
             mode=mode,
         )
 
@@ -295,7 +302,8 @@ class TheTool:
         logprobs: bool = False,
         top_logprobs: int | None = None,
         validator: Callable[[Any], bool] | None = None,
-    ) -> OutputModels.ToolOutput:
+        max_validation_retries: int | None = None,
+    ) -> OM.ToolOutput:
         """
         Generate a list of questions about a subject.
 
@@ -305,7 +313,7 @@ class TheTool:
                 - logprobs (list | None): Probability data if logprobs enabled
                 - analysis (str | None): Detailed reasoning if with_analysis enabled
         """
-        return self.operator.run(
+        return self._operator.run(
             # User parameters
             text=text,
             number_of_questions=number_of_questions,
@@ -316,10 +324,10 @@ class TheTool:
             logprobs=logprobs,
             top_logprobs=top_logprobs,
             validator=validator,
+            max_validation_retries=max_validation_retries,
             # Internal parameters
             prompt_file="subject_to_question.yaml",
-            output_model=OutputModels.ReasonListStrOutput,
-            resp_format="parse",
+            output_model=OM.ReasonListStrOutput,
             mode=None,
         )
 
@@ -333,7 +341,8 @@ class TheTool:
         logprobs: bool = False,
         top_logprobs: int | None = None,
         validator: Callable[[Any], bool] | None = None,
-    ) -> OutputModels.ToolOutput:
+        max_validation_retries: int | None = None,
+    ) -> OM.ToolOutput:
         """
         Summarize the given subject text.
 
@@ -343,7 +352,7 @@ class TheTool:
                 - logprobs (list | None): Probability data if logprobs enabled
                 - analysis (str | None): Detailed reasoning if with_analysis enabled
         """
-        return self.operator.run(
+        return self._operator.run(
             # User parameters
             text=text,
             with_analysis=with_analysis,
@@ -353,10 +362,10 @@ class TheTool:
             logprobs=logprobs,
             top_logprobs=top_logprobs,
             validator=validator,
+            max_validation_retries=max_validation_retries,
             # Internal parameters
             prompt_file="summarize.yaml",
-            output_model=OutputModels.StrOutput,
-            resp_format="parse",
+            output_model=OM.StrOutput,
             mode=None,
         )
 
@@ -370,7 +379,8 @@ class TheTool:
         logprobs: bool = False,
         top_logprobs: int | None = None,
         validator: Callable[[Any], bool] | None = None,
-    ) -> OutputModels.ToolOutput:
+        max_validation_retries: int | None = None,
+    ) -> OM.ToolOutput:
         """
         Translate text between languages.
 
@@ -380,7 +390,7 @@ class TheTool:
                 - logprobs (list | None): Probability data if logprobs enabled
                 - analysis (str | None): Detailed reasoning if with_analysis enabled
         """
-        return self.operator.run(
+        return self._operator.run(
             # User parameters
             text=text,
             target_language=target_language,
@@ -390,10 +400,10 @@ class TheTool:
             logprobs=logprobs,
             top_logprobs=top_logprobs,
             validator=validator,
+            max_validation_retries=max_validation_retries,
             # Internal parameters
             prompt_file="translate.yaml",
-            output_model=OutputModels.StrOutput,
-            resp_format="parse",
+            output_model=OM.StrOutput,
             mode=None,
             output_lang=None,
         )
@@ -406,7 +416,7 @@ class TheTool:
         temperature: float | None = None,
         logprobs: bool | None = None,
         top_logprobs: int | None = None,
-    ) -> OutputModels.ToolOutput:
+    ) -> OM.ToolOutput:
         """
         Custom tool that can do almost anything!
 
@@ -414,7 +424,7 @@ class TheTool:
             ToolOutput: Object with fields:
                 - result (str): The output result
         """
-        return self.operator.run(
+        return self._operator.run(
             # User paramaeters
             text=prompt,
             output_model=output_model,
@@ -425,7 +435,6 @@ class TheTool:
             top_logprobs=top_logprobs,
             # Internal parameters
             prompt_file="run_custom.yaml",
-            resp_format="parse",
             user_prompt=None,
             with_analysis=False,
             mode=None,

hamtaa_texttools-1.1.9.dist-info/RECORD

@@ -1,30 +0,0 @@
-hamtaa_texttools-1.1.9.dist-info/licenses/LICENSE,sha256=Hb2YOBKy2MJQLnyLrX37B4ZVuac8eaIcE71SvVIMOLg,1082
-texttools/__init__.py,sha256=lFYe1jdssHC1h8qcPpV3whANxiDi8aiiFdY-7L0Ck10,164
-texttools/batch/__init__.py,sha256=DJGJTfR6F3Yv4_alsj9g1tesGzdcSV27Zw74DonhW_s,102
-texttools/batch/batch_manager.py,sha256=ZgLiO9maCHnx2cJbUjsYXFnlUsMLI2TP3Vc9uKU0BLg,8706
-texttools/batch/batch_runner.py,sha256=X0YQmaowO_jUSAFWBHdxOLoRrX_gvmrJDgp9qPlOSEw,10254
-texttools/prompts/README.md,sha256=-5YO93CN93QLifqZpUeUnCOCBbDiOTV-cFQeJ7Gg0I4,1377
-texttools/prompts/categorizer.yaml,sha256=GMqIIzQFhgnlpkgU1qi3FAD3mD4A2jiWD5TilQ2XnnE,1204
-texttools/prompts/extract_entities.yaml,sha256=KiKjeDpHaeh3JVtZ6q1pa3k4DYucUIU9WnEcRTCA-SE,651
-texttools/prompts/extract_keywords.yaml,sha256=0O7ypL_OsEOxtvlQ2CZjnsv9637DJwAKprZsf9Vo2_s,769
-texttools/prompts/is_question.yaml,sha256=d0-vKRbXWkxvO64ikvxRjEmpAXGpCYIPGhgexvPPjws,471
-texttools/prompts/merge_questions.yaml,sha256=0J85GvTirZB4ELwH3sk8ub_WcqqpYf6PrMKr3djlZeo,1792
-texttools/prompts/rewrite.yaml,sha256=LO7He_IA3MZKz8a-LxH9DHJpOjpYwaYN1pbjp1Y0tFo,5392
-texttools/prompts/run_custom.yaml,sha256=38OkCoVITbuuS9c08UZSP1jZW4WjSmRIi8fR0RAiPu4,108
-texttools/prompts/subject_to_question.yaml,sha256=C7x7rNNm6U_ZG9HOn6zuzYOtvJUZ2skuWbL1-aYdd3E,1147
-texttools/prompts/summarize.yaml,sha256=o6rxGPfWtZd61Duvm8NVvCJqfq73b-wAuMSKR6UYUqY,459
-texttools/prompts/text_to_question.yaml,sha256=UheKYpDn6iyKI8NxunHZtFpNyfCLZZe5cvkuXpurUJY,783
-texttools/prompts/translate.yaml,sha256=mGT2uBCei6uucWqVbs4silk-UV060v3G0jnt0P6sr50,634
-texttools/tools/__init__.py,sha256=3fPoeB-E5wGxWgv7axztHkeolR7ZDUJudd0xmpPFjao,113
-texttools/tools/async_tools.py,sha256=2ZY7Lo6Jj9xoTF8bfdh_g8VOXZ7ljMMesd1_QHXyf4s,15395
-texttools/tools/sync_tools.py,sha256=XKgZuzriFnk8B-YihJfs6BKivxjGCgOFfe7hnCpEiXs,15161
-texttools/tools/internals/async_operator.py,sha256=egBsrcpGBmkDY5YzUvGHh1TjPmsH9IOVXDGmYMWjzMs,8960
-texttools/tools/internals/base_operator.py,sha256=qV9LlVo_DzSCzQnjYTFi-6mlHN4gE0edPE2y_9WwQFw,3292
-texttools/tools/internals/formatters.py,sha256=tACNLP6PeoqaRpNudVxBaHA25zyWqWYPZQuYysIu88g,941
-texttools/tools/internals/operator.py,sha256=xgbt1Mm67SEC-KD9jwXjXGTCcaCsaVLhG6iCYOqLDcc,8709
-texttools/tools/internals/output_models.py,sha256=ekpbyocmXj_dee7ieOT1zOkMo9cPHT7xcUFCZoUaXA0,1886
-texttools/tools/internals/prompt_loader.py,sha256=8uD7JUatKXSLXhGwWs46iQpcjWdhF9p32SFDLMndy1o,1940
-hamtaa_texttools-1.1.9.dist-info/METADATA,sha256=nQFuGr_7aVHlO7nRsTbubEtO0QVUofcdUKwMATzHhUU,9129
-hamtaa_texttools-1.1.9.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-hamtaa_texttools-1.1.9.dist-info/top_level.txt,sha256=5Mh0jIxxZ5rOXHGJ6Mp-JPKviywwN0MYuH0xk5bEWqE,10
-hamtaa_texttools-1.1.9.dist-info/RECORD,,

texttools/batch/__init__.py

@@ -1,3 +0,0 @@
-from .batch_runner import BatchJobRunner, BatchConfig
-
-__all__ = ["BatchJobRunner", "BatchConfig"]

texttools/tools/__init__.py

@@ -1,4 +0,0 @@
-from .sync_tools import TheTool
-from .async_tools import AsyncTheTool
-
-__all__ = ["TheTool", "AsyncTheTool"]