hamtaa-texttools 1.1.3__tar.gz → 1.1.7__tar.gz

{hamtaa_texttools-1.1.3/hamtaa_texttools.egg-info → hamtaa_texttools-1.1.7}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hamtaa-texttools
-Version: 1.1.3
+Version: 1.1.7
 Summary: A high-level NLP toolkit built on top of modern LLMs.
 Author-email: Tohidi <the.mohammad.tohidi@gmail.com>, Montazer <montazerh82@gmail.com>, Givechi <mohamad.m.givechi@gmail.com>, MoosaviNejad <erfanmoosavi84@gmail.com>
 License: MIT License
@@ -86,6 +86,18 @@ All these parameters can be used individually or together to tailor the behavior
 
 ---
 
+## 🧩 ToolOutput
+
+Every tool of `TextTools` returns a `ToolOutput` object which is a BaseModel with attributes:
+- **`result`** → The output of LLM (`type=Any`)
+- **`analysis`** → The reasoning step before generating the final output (`type=str`)
+- **`logprobs`** → Token-level probabilities for the generated output (`type=list`)
+- **`errors`** → Any error that have occured during calling LLM (`type=str`)
+
+**None:** You can use `repr(ToolOutput)` to see details of an output.
+
+---
+
 ## 🚀 Installation
 
 Install the latest release via PyPI:
@@ -123,13 +135,13 @@ the_tool = TheTool(client=client, model=model)
 detection = the_tool.is_question("Is this project open source?", logprobs=True, top_logprobs=2)
 print(detection.result)
 print(detection.logprobs)
-# Output: True \n --logprobs
+# Output: True + logprobs
 
 # Example: Translation
 translation = the_tool.translate("سلام، حالت چطوره؟" target_language="English", with_analysis=True)
 print(translation.result)
 print(translation.analysis)
-# Output: "Hi! How are you?" \n --analysis
+# Output: "Hi! How are you?"  + analysis
 ```
 
 ---
@@ -149,19 +161,22 @@ async def main():
     model = "gpt-4o-mini"
 
     # Create an instance of AsyncTheTool
-    the_tool = AsyncTheTool(client=async_client, model=model)
+    async_the_tool = AsyncTheTool(client=async_client, model=model)
+    
+    # Example: Async Translation and Keyword Extraction
+    translation_task = async_the_tool.translate("سلام، حالت چطوره؟", target_language="English")
+    keywords_task = async_the_tool.extract_keywords("Tomorrow, we will be dead by the car crash")
 
-    # Example: Async Translation
-    translation = await the_tool.translate("سلام، حالت چطوره؟", target_language="English")
+    (translation, keywords) = await asyncio.gather(translation_task, keywords_task)
     print(translation.result)
-    # Output: "Hi! How are you?"
+    print(keywords.result)
 
 asyncio.run(main())
 ```
 
 ---
 
-## 📚 Use Cases
+## 👍 Use Cases
 
 Use **TextTools** when you need to:
 
@@ -169,7 +184,35 @@ Use **TextTools** when you need to:
 - 🌍 **Translate** and process multilingual corpora with ease  
 - 🧩 **Integrate** LLMs into production pipelines (structured outputs)  
 - 📊 **Analyze** large text collections using embeddings and categorization  
-- 👍 **Automate** common text-processing tasks without reinventing the wheel  
+
+---
+
+## 📚 Batch Processing
+
+Process large datasets efficiently using OpenAI's batch API.
+
+## Quick Start
+
+```python
+from texttools import BatchJobRunner, BatchConfig
+
+# Configure your batch job
+config = BatchConfig(
+    system_prompt="Extract entities from the text",
+    job_name="entity_extraction",
+    input_data_path="data.json",
+    output_data_filename="results.json",
+    model="gpt-4o-mini"
+)
+
+# Define your output schema
+class Output(BaseModel):
+    entities: list[str]
+
+# Run the batch job
+runner = BatchJobRunner(config, output_model=Output)
+runner.run()
+```
 
 ---
 

{hamtaa_texttools-1.1.3 → hamtaa_texttools-1.1.7}/README.md

@@ -52,6 +52,18 @@ All these parameters can be used individually or together to tailor the behavior
 
 ---
 
+## 🧩 ToolOutput
+
+Every tool of `TextTools` returns a `ToolOutput` object which is a BaseModel with attributes:
+- **`result`** → The output of LLM (`type=Any`)
+- **`analysis`** → The reasoning step before generating the final output (`type=str`)
+- **`logprobs`** → Token-level probabilities for the generated output (`type=list`)
+- **`errors`** → Any error that have occured during calling LLM (`type=str`)
+
+**None:** You can use `repr(ToolOutput)` to see details of an output.
+
+---
+
 ## 🚀 Installation
 
 Install the latest release via PyPI:
@@ -89,13 +101,13 @@ the_tool = TheTool(client=client, model=model)
 detection = the_tool.is_question("Is this project open source?", logprobs=True, top_logprobs=2)
 print(detection.result)
 print(detection.logprobs)
-# Output: True \n --logprobs
+# Output: True + logprobs
 
 # Example: Translation
 translation = the_tool.translate("سلام، حالت چطوره؟" target_language="English", with_analysis=True)
 print(translation.result)
 print(translation.analysis)
-# Output: "Hi! How are you?" \n --analysis
+# Output: "Hi! How are you?"  + analysis
 ```
 
 ---
@@ -115,19 +127,22 @@ async def main():
     model = "gpt-4o-mini"
 
     # Create an instance of AsyncTheTool
-    the_tool = AsyncTheTool(client=async_client, model=model)
+    async_the_tool = AsyncTheTool(client=async_client, model=model)
+    
+    # Example: Async Translation and Keyword Extraction
+    translation_task = async_the_tool.translate("سلام، حالت چطوره؟", target_language="English")
+    keywords_task = async_the_tool.extract_keywords("Tomorrow, we will be dead by the car crash")
 
-    # Example: Async Translation
-    translation = await the_tool.translate("سلام، حالت چطوره؟", target_language="English")
+    (translation, keywords) = await asyncio.gather(translation_task, keywords_task)
     print(translation.result)
-    # Output: "Hi! How are you?"
+    print(keywords.result)
 
 asyncio.run(main())
 ```
 
 ---
 
-## 📚 Use Cases
+## 👍 Use Cases
 
 Use **TextTools** when you need to:
 
@@ -135,7 +150,35 @@ Use **TextTools** when you need to:
 - 🌍 **Translate** and process multilingual corpora with ease  
 - 🧩 **Integrate** LLMs into production pipelines (structured outputs)  
 - 📊 **Analyze** large text collections using embeddings and categorization  
-- 👍 **Automate** common text-processing tasks without reinventing the wheel  
+
+---
+
+## 📚 Batch Processing
+
+Process large datasets efficiently using OpenAI's batch API.
+
+## Quick Start
+
+```python
+from texttools import BatchJobRunner, BatchConfig
+
+# Configure your batch job
+config = BatchConfig(
+    system_prompt="Extract entities from the text",
+    job_name="entity_extraction",
+    input_data_path="data.json",
+    output_data_filename="results.json",
+    model="gpt-4o-mini"
+)
+
+# Define your output schema
+class Output(BaseModel):
+    entities: list[str]
+
+# Run the batch job
+runner = BatchJobRunner(config, output_model=Output)
+runner.run()
+```
 
 ---
 

{hamtaa_texttools-1.1.3 → hamtaa_texttools-1.1.7/hamtaa_texttools.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hamtaa-texttools
-Version: 1.1.3
+Version: 1.1.7
 Summary: A high-level NLP toolkit built on top of modern LLMs.
 Author-email: Tohidi <the.mohammad.tohidi@gmail.com>, Montazer <montazerh82@gmail.com>, Givechi <mohamad.m.givechi@gmail.com>, MoosaviNejad <erfanmoosavi84@gmail.com>
 License: MIT License
@@ -86,6 +86,18 @@ All these parameters can be used individually or together to tailor the behavior
 
 ---
 
+## 🧩 ToolOutput
+
+Every tool of `TextTools` returns a `ToolOutput` object which is a BaseModel with attributes:
+- **`result`** → The output of LLM (`type=Any`)
+- **`analysis`** → The reasoning step before generating the final output (`type=str`)
+- **`logprobs`** → Token-level probabilities for the generated output (`type=list`)
+- **`errors`** → Any error that have occured during calling LLM (`type=str`)
+
+**None:** You can use `repr(ToolOutput)` to see details of an output.
+
+---
+
 ## 🚀 Installation
 
 Install the latest release via PyPI:
@@ -123,13 +135,13 @@ the_tool = TheTool(client=client, model=model)
 detection = the_tool.is_question("Is this project open source?", logprobs=True, top_logprobs=2)
 print(detection.result)
 print(detection.logprobs)
-# Output: True \n --logprobs
+# Output: True + logprobs
 
 # Example: Translation
 translation = the_tool.translate("سلام، حالت چطوره؟" target_language="English", with_analysis=True)
 print(translation.result)
 print(translation.analysis)
-# Output: "Hi! How are you?" \n --analysis
+# Output: "Hi! How are you?"  + analysis
 ```
 
 ---
@@ -149,19 +161,22 @@ async def main():
     model = "gpt-4o-mini"
 
     # Create an instance of AsyncTheTool
-    the_tool = AsyncTheTool(client=async_client, model=model)
+    async_the_tool = AsyncTheTool(client=async_client, model=model)
+    
+    # Example: Async Translation and Keyword Extraction
+    translation_task = async_the_tool.translate("سلام، حالت چطوره؟", target_language="English")
+    keywords_task = async_the_tool.extract_keywords("Tomorrow, we will be dead by the car crash")
 
-    # Example: Async Translation
-    translation = await the_tool.translate("سلام، حالت چطوره؟", target_language="English")
+    (translation, keywords) = await asyncio.gather(translation_task, keywords_task)
     print(translation.result)
-    # Output: "Hi! How are you?"
+    print(keywords.result)
 
 asyncio.run(main())
 ```
 
 ---
 
-## 📚 Use Cases
+## 👍 Use Cases
 
 Use **TextTools** when you need to:
 
@@ -169,7 +184,35 @@ Use **TextTools** when you need to:
 - 🌍 **Translate** and process multilingual corpora with ease  
 - 🧩 **Integrate** LLMs into production pipelines (structured outputs)  
 - 📊 **Analyze** large text collections using embeddings and categorization  
-- 👍 **Automate** common text-processing tasks without reinventing the wheel  
+
+---
+
+## 📚 Batch Processing
+
+Process large datasets efficiently using OpenAI's batch API.
+
+## Quick Start
+
+```python
+from texttools import BatchJobRunner, BatchConfig
+
+# Configure your batch job
+config = BatchConfig(
+    system_prompt="Extract entities from the text",
+    job_name="entity_extraction",
+    input_data_path="data.json",
+    output_data_filename="results.json",
+    model="gpt-4o-mini"
+)
+
+# Define your output schema
+class Output(BaseModel):
+    entities: list[str]
+
+# Run the batch job
+runner = BatchJobRunner(config, output_model=Output)
+runner.run()
+```
 
 ---
 

{hamtaa_texttools-1.1.3 → hamtaa_texttools-1.1.7}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hamtaa-texttools"
-version = "1.1.3"
+version = "1.1.7"
 authors = [
   { name = "Tohidi", email = "the.mohammad.tohidi@gmail.com" },
   { name = "Montazer", email = "montazerh82@gmail.com" },

hamtaa_texttools-1.1.7/texttools/__init__.py

@@ -0,0 +1,4 @@
+from .batch import BatchJobRunner, BatchConfig
+from .tools import AsyncTheTool, TheTool
+
+__all__ = ["TheTool", "AsyncTheTool", "BatchJobRunner", "BatchConfig"]

hamtaa_texttools-1.1.7/texttools/batch/__init__.py

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

{hamtaa_texttools-1.1.3 → hamtaa_texttools-1.1.7}/texttools/batch/batch_manager.py

@@ -1,18 +1,20 @@
 import json
 import uuid
 from pathlib import Path
-from typing import Any, Type
+from typing import Any, Type, TypeVar
 import logging
 
 from pydantic import BaseModel
 from openai import OpenAI
 from openai.lib._pydantic import to_strict_json_schema
 
-logger = logging.getLogger("batch_runner")
-logger.setLevel(logging.INFO)
+# Base Model type for output models
+T = TypeVar("T", bound=BaseModel)
 
+logger = logging.getLogger("texttools.batch_runner")
 
-class SimpleBatchManager:
+
+class BatchManager:
     """
     Manages batch processing jobs for OpenAI's chat completions with structured outputs.
 
@@ -25,9 +27,8 @@ class SimpleBatchManager:
         self,
         client: OpenAI,
         model: str,
-        output_model: Type[BaseModel],
+        output_model: Type[T],
         prompt_template: str,
-        handlers: list[Any] | None = None,
         state_dir: Path = Path(".batch_jobs"),
         custom_json_schema_obj_str: dict | None = None,
         **client_kwargs: Any,
@@ -36,7 +37,6 @@ class SimpleBatchManager:
         self.model = model
         self.output_model = output_model
         self.prompt_template = prompt_template
-        self.handlers = handlers or []
         self.state_dir = state_dir
         self.state_dir.mkdir(parents=True, exist_ok=True)
         self.custom_json_schema_obj_str = custom_json_schema_obj_str
@@ -45,7 +45,7 @@ class SimpleBatchManager:
 
         if self.custom_json_schema_obj_str:
             if self.custom_json_schema_obj_str is not dict:
-                raise ValueError("schema should be a dict")
+                raise ValueError("Schema should be a dict")
 
     def _state_file(self, job_name: str) -> Path:
         return self.state_dir / f"{job_name}.json"
@@ -126,7 +126,7 @@ class SimpleBatchManager:
 
         else:
             raise TypeError(
-                "The input must be either a list of texts or a dictionary in the form {'id': str, 'text': str}."
+                "The input must be either a list of texts or a dictionary in the form {'id': str, 'text': str}"
             )
 
         file_path = self.state_dir / f"batch_{uuid.uuid4().hex}.jsonl"
@@ -220,8 +220,6 @@ class SimpleBatchManager:
                 error_d = {custom_id: results[custom_id]}
                 log.append(error_d)
 
-        for handler in self.handlers:
-            handler.handle(results)
         if remove_cache:
             self._clear_state(job_name)
 

{hamtaa_texttools-1.1.3 → hamtaa_texttools-1.1.7}/texttools/batch/batch_runner.py

@@ -3,24 +3,23 @@ import os
 import time
 from dataclasses import dataclass
 from pathlib import Path
-from typing import Any, Callable
+from typing import Any, Callable, Type, TypeVar
 import logging
 
 from dotenv import load_dotenv
 from openai import OpenAI
 from pydantic import BaseModel
 
-from texttools.batch import SimpleBatchManager
+from texttools.batch.batch_manager import BatchManager
+from texttools.tools.internals.output_models import StrOutput
 
-logger = logging.getLogger("batch_runner")
-logger.setLevel(logging.INFO)
+# Base Model type for output models
+T = TypeVar("T", bound=BaseModel)
 
+logger = logging.getLogger("texttools.batch_runner")
 
-class OutputModel(BaseModel):
-    desired_output: str
 
-
-def export_data(data):
+def export_data(data) -> list[dict[str, str]]:
     """
     Produces a structure of the following form from an initial data structure:
     [{"id": str, "text": str},...]
@@ -28,7 +27,7 @@ def export_data(data):
     return data
 
 
-def import_data(data):
+def import_data(data) -> Any:
     """
     Takes the output and adds and aggregates it to the original structure.
     """
@@ -47,9 +46,9 @@ class BatchConfig:
     output_data_filename: str = ""
     model: str = "gpt-4.1-mini"
     MAX_BATCH_SIZE: int = 100
-    MAX_TOTAL_TOKENS: int = 2000000
+    MAX_TOTAL_TOKENS: int = 2_000_000
     CHARS_PER_TOKEN: float = 2.7
-    PROMPT_TOKEN_MULTIPLIER: int = 1000
+    PROMPT_TOKEN_MULTIPLIER: int = 1_000
     BASE_OUTPUT_DIR: str = "Data/batch_entity_result"
     import_function: Callable = import_data
     export_function: Callable = export_data
@@ -63,7 +62,7 @@ class BatchJobRunner:
     """
 
     def __init__(
-        self, config: BatchConfig = BatchConfig(), output_model: type = OutputModel
+        self, config: BatchConfig = BatchConfig(), output_model: Type[T] = StrOutput
     ):
         self.config = config
         self.system_prompt = config.system_prompt
@@ -82,11 +81,11 @@ class BatchJobRunner:
         # Track retry attempts per part
         self.part_attempts: dict[int, int] = {}
 
-    def _init_manager(self) -> SimpleBatchManager:
+    def _init_manager(self) -> BatchManager:
         load_dotenv()
         api_key = os.getenv("OPENAI_API_KEY")
         client = OpenAI(api_key=api_key)
-        return SimpleBatchManager(
+        return BatchManager(
             client=client,
             model=self.model,
             prompt_template=self.system_prompt,
@@ -101,12 +100,12 @@ class BatchJobRunner:
         # Ensure data is a list of dicts with 'id' and 'content' as strings
         if not isinstance(data, list):
             raise ValueError(
-                'Exported data must be a list in this form:  [ {"id": str, "content": str},...]'
+                "Exported data must be a list of dicts with 'id' and 'content' keys"
             )
         for item in data:
             if not (isinstance(item, dict) and "id" in item and "content" in item):
                 raise ValueError(
-                    "Each item must be a dict with 'id' and 'content' keys."
+                    f"Item must be a dict with 'id' and 'content' keys. Got: {type(item)}"
                 )
             if not (isinstance(item["id"], str) and isinstance(item["content"], str)):
                 raise ValueError("'id' and 'content' must be strings.")
@@ -161,7 +160,45 @@ class BatchJobRunner:
             logger.info("Uploading...")
             time.sleep(30)
 
+    def _save_results(
+        self,
+        output_data: list[dict[str, Any]] | dict[str, Any],
+        log: list[Any],
+        part_idx: int,
+    ):
+        part_suffix = f"_part_{part_idx + 1}" if len(self.parts) > 1 else ""
+        result_path = (
+            Path(self.config.BASE_OUTPUT_DIR)
+            / f"{Path(self.output_data_filename).stem}{part_suffix}.json"
+        )
+        if not output_data:
+            logger.info("No output data to save. Skipping this part.")
+            return
+        else:
+            with open(result_path, "w", encoding="utf-8") as f:
+                json.dump(output_data, f, ensure_ascii=False, indent=4)
+        if log:
+            log_path = (
+                Path(self.config.BASE_OUTPUT_DIR)
+                / f"{Path(self.output_data_filename).stem}{part_suffix}_log.json"
+            )
+            with open(log_path, "w", encoding="utf-8") as f:
+                json.dump(log, f, ensure_ascii=False, indent=4)
+
+    def _result_exists(self, part_idx: int) -> bool:
+        part_suffix = f"_part_{part_idx + 1}" if len(self.parts) > 1 else ""
+        result_path = (
+            Path(self.config.BASE_OUTPUT_DIR)
+            / f"{Path(self.output_data_filename).stem}{part_suffix}.json"
+        )
+        return result_path.exists()
+
     def run(self):
+        """
+        Execute the batch job processing pipeline.
+
+        Submits jobs, monitors progress, handles retries, and saves results.
+        """
         # Submit all jobs up-front for concurrent execution
         self._submit_all_jobs()
         pending_parts: set[int] = set(self.part_idx_to_job_name.keys())
@@ -215,48 +252,3 @@ class BatchJobRunner:
                     f"Waiting {self.config.poll_interval_seconds}s before next status check for parts: {sorted(pending_parts)}"
                 )
                 time.sleep(self.config.poll_interval_seconds)
-
-    def _save_results(
-        self,
-        output_data: list[dict[str, Any]] | dict[str, Any],
-        log: list[Any],
-        part_idx: int,
-    ):
-        part_suffix = f"_part_{part_idx + 1}" if len(self.parts) > 1 else ""
-        result_path = (
-            Path(self.config.BASE_OUTPUT_DIR)
-            / f"{Path(self.output_data_filename).stem}{part_suffix}.json"
-        )
-        if not output_data:
-            logger.info("No output data to save. Skipping this part.")
-            return
-        else:
-            with open(result_path, "w", encoding="utf-8") as f:
-                json.dump(output_data, f, ensure_ascii=False, indent=4)
-        if log:
-            log_path = (
-                Path(self.config.BASE_OUTPUT_DIR)
-                / f"{Path(self.output_data_filename).stem}{part_suffix}_log.json"
-            )
-            with open(log_path, "w", encoding="utf-8") as f:
-                json.dump(log, f, ensure_ascii=False, indent=4)
-
-    def _result_exists(self, part_idx: int) -> bool:
-        part_suffix = f"_part_{part_idx + 1}" if len(self.parts) > 1 else ""
-        result_path = (
-            Path(self.config.BASE_OUTPUT_DIR)
-            / f"{Path(self.output_data_filename).stem}{part_suffix}.json"
-        )
-        return result_path.exists()
-
-
-if __name__ == "__main__":
-    logger.info("=== Batch Job Runner ===")
-    config = BatchConfig(
-        system_prompt="",
-        job_name="job_name",
-        input_data_path="Data.json",
-        output_data_filename="output",
-    )
-    runner = BatchJobRunner(config)
-    runner.run()

{hamtaa_texttools-1.1.3 → hamtaa_texttools-1.1.7}/texttools/tools/async_the_tool.py

@@ -1,4 +1,4 @@
-from typing import Literal, Any
+from typing import Literal, Any, Callable
 
 from openai import AsyncOpenAI
 
@@ -34,7 +34,7 @@ class AsyncTheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Categorize a text into a single Islamic studies domain category.
@@ -71,7 +71,7 @@ class AsyncTheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Extract salient keywords from text.
@@ -108,7 +108,7 @@ class AsyncTheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Perform Named Entity Recognition (NER) over the input text.
@@ -144,7 +144,7 @@ class AsyncTheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Detect if the input is phrased as a question.
@@ -181,7 +181,7 @@ class AsyncTheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Generate a single question from the given text.
@@ -219,7 +219,7 @@ class AsyncTheTool:
         logprobs: bool = False,
         top_logprobs: int | None = None,
         mode: Literal["default", "reason"] = "default",
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Merge multiple questions into a single unified question.
@@ -258,7 +258,7 @@ class AsyncTheTool:
         logprobs: bool = False,
         top_logprobs: int | None = None,
         mode: Literal["positive", "negative", "hard_negative"] = "positive",
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Rewrite a text with different modes.
@@ -296,7 +296,7 @@ class AsyncTheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Generate a list of questions about a subject.
@@ -334,7 +334,7 @@ class AsyncTheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Summarize the given subject text.
@@ -371,7 +371,7 @@ class AsyncTheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Translate text between languages.

{hamtaa_texttools-1.1.3 → hamtaa_texttools-1.1.7}/texttools/tools/internals/async_operator.py

@@ -1,4 +1,4 @@
-from typing import Any, TypeVar, Type, Literal
+from typing import Any, TypeVar, Type, Literal, Callable
 import logging
 
 from openai import AsyncOpenAI
@@ -12,8 +12,7 @@ from texttools.tools.internals.prompt_loader import PromptLoader
 # Base Model type for output models
 T = TypeVar("T", bound=BaseModel)
 
-logger = logging.getLogger("async_operator")
-logger.setLevel(logging.INFO)
+logger = logging.getLogger("texttools.async_operator")
 
 
 class AsyncOperator(BaseOperator):
@@ -115,7 +114,7 @@ class AsyncOperator(BaseOperator):
         temperature: float,
         logprobs: bool,
         top_logprobs: int | None,
-        validator: Any | None,
+        validator: Callable[[Any], bool] | None,
         # Internal parameters
         prompt_file: str,
         output_model: Type[T],
@@ -128,7 +127,7 @@ class AsyncOperator(BaseOperator):
         """
         prompt_loader = PromptLoader()
         formatter = Formatter()
-        output = ToolOutput(result="", analysis="", logprobs=[], errors=[])
+        output = ToolOutput()
 
         try:
             # Prompt configs contain two keys: main_template and analyze template, both are string
@@ -239,4 +238,5 @@ class AsyncOperator(BaseOperator):
 
         except Exception as e:
             logger.error(f"AsyncTheTool failed: {e}")
-            return output.errors.append(str(e))
+            output.errors.append(str(e))
+            return output

{hamtaa_texttools-1.1.3 → hamtaa_texttools-1.1.7}/texttools/tools/internals/base_operator.py

@@ -11,8 +11,7 @@ from openai import OpenAI, AsyncOpenAI
 # Base Model type for output models
 T = TypeVar("T", bound=BaseModel)
 
-logger = logging.getLogger("base_operator")
-logger.setLevel(logging.INFO)
+logger = logging.getLogger("texttools.base_operator")
 
 
 class BaseOperator:

{hamtaa_texttools-1.1.3 → hamtaa_texttools-1.1.7}/texttools/tools/internals/operator.py

@@ -1,4 +1,4 @@
-from typing import Any, TypeVar, Type, Literal
+from typing import Any, TypeVar, Type, Literal, Callable
 import logging
 
 from openai import OpenAI
@@ -12,8 +12,7 @@ from texttools.tools.internals.prompt_loader import PromptLoader
 # Base Model type for output models
 T = TypeVar("T", bound=BaseModel)
 
-logger = logging.getLogger("operator")
-logger.setLevel(logging.INFO)
+logger = logging.getLogger("texttools.operator")
 
 
 class Operator(BaseOperator):
@@ -115,7 +114,7 @@ class Operator(BaseOperator):
         temperature: float,
         logprobs: bool,
         top_logprobs: int | None,
-        validator: Any | None,
+        validator: Callable[[Any], bool] | None,
         # Internal parameters
         prompt_file: str,
         output_model: Type[T],
@@ -128,7 +127,7 @@ class Operator(BaseOperator):
         """
         prompt_loader = PromptLoader()
         formatter = Formatter()
-        output = ToolOutput(result="", analysis="", logprobs=[], errors=[])
+        output = ToolOutput()
 
         try:
             # Prompt configs contain two keys: main_template and analyze template, both are string
@@ -239,4 +238,5 @@ class Operator(BaseOperator):
 
         except Exception as e:
             logger.error(f"TheTool failed: {e}")
-            return output.errors.append(str(e))
+            output.errors.append(str(e))
+            return output

{hamtaa_texttools-1.1.3 → hamtaa_texttools-1.1.7}/texttools/tools/internals/output_models.py

@@ -4,10 +4,13 @@ from pydantic import BaseModel, Field
 
 
 class ToolOutput(BaseModel):
-    result: str
-    analysis: str
-    logprobs: list[dict[str, Any]]
-    errors: list[str]
+    result: Any = None
+    analysis: str = ""
+    logprobs: list[dict[str, Any]] = []
+    errors: list[str] = []
+
+    def __repr__(self) -> str:
+        return f"ToolOutput(result_type='{type(self.result)}', result='{self.result}', analysis='{self.analysis}', logprobs='{self.logprobs}', errors='{self.errors}'"
 
 
 class StrOutput(BaseModel):

{hamtaa_texttools-1.1.3 → hamtaa_texttools-1.1.7}/texttools/tools/the_tool.py

@@ -1,4 +1,4 @@
-from typing import Literal, Any
+from typing import Literal, Any, Callable
 
 from openai import OpenAI
 
@@ -32,7 +32,7 @@ class TheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Categorize a text into a single Islamic studies domain category.
@@ -69,7 +69,7 @@ class TheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Extract salient keywords from text.
@@ -106,7 +106,7 @@ class TheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Perform Named Entity Recognition (NER) over the input text.
@@ -142,7 +142,7 @@ class TheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Detect if the input is phrased as a question.
@@ -179,7 +179,7 @@ class TheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Generate a single question from the given text.
@@ -217,7 +217,7 @@ class TheTool:
         logprobs: bool = False,
         top_logprobs: int | None = None,
         mode: Literal["default", "reason"] = "default",
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Merge multiple questions into a single unified question.
@@ -256,7 +256,7 @@ class TheTool:
         logprobs: bool = False,
         top_logprobs: int | None = None,
         mode: Literal["positive", "negative", "hard_negative"] = "positive",
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Rewrite a text with different modes.
@@ -294,7 +294,7 @@ class TheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Generate a list of questions about a subject.
@@ -332,7 +332,7 @@ class TheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Summarize the given subject text.
@@ -369,7 +369,7 @@ class TheTool:
         temperature: float | None = 0.0,
         logprobs: bool = False,
         top_logprobs: int | None = None,
-        validator: Any | None = None,
+        validator: Callable[[Any], bool] | None = None,
     ) -> OutputModels.ToolOutput:
         """
         Translate text between languages.

hamtaa_texttools-1.1.3/texttools/__init__.py

@@ -1,9 +0,0 @@
-from .batch import BatchJobRunner, SimpleBatchManager
-from .tools import AsyncTheTool, TheTool
-
-__all__ = [
-    "TheTool",
-    "AsyncTheTool",
-    "SimpleBatchManager",
-    "BatchJobRunner",
-]

hamtaa_texttools-1.1.3/texttools/batch/__init__.py

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