hamtaa-texttools 1.1.20__py3-none-any.whl → 1.1.21__py3-none-any.whl

{hamtaa_texttools-1.1.20.dist-info → hamtaa_texttools-1.1.21.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hamtaa-texttools
-Version: 1.1.20
+Version: 1.1.21
 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>, Zareshahi <a.zareshahi1377@gmail.com>
 License: MIT License
@@ -50,7 +50,7 @@ It provides ready-to-use utilities for **translation, question detection, keywor
 TextTools provides a rich collection of high-level NLP utilities,
 Each tool is designed to work with structured outputs (JSON / Pydantic).
 
-- **`categorize()`** - Classifies text into given categories (You have to create a category tree)
+- **`categorize()`** - Classifies text into given categories
 - **`extract_keywords()`** - Extracts keywords from text
 - **`extract_entities()`** - Named Entity Recognition (NER) system
 - **`is_question()`** - Binary detection of whether input is a question
@@ -61,7 +61,7 @@ Each tool is designed to work with structured outputs (JSON / Pydantic).
 - **`summarize()`** - Text summarization
 - **`translate()`** - Text translation between languages
 - **`propositionize()`** - Convert text to atomic independence meaningful sentences 
-- **`check_fact()`** - Check a statement is relevant to source text or not 
+- **`check_fact()`** - Check whether a statement is relevant to the source text
 - **`run_custom()`** - Allows users to define a custom tool with an arbitrary BaseModel
 
 ---
@@ -125,11 +125,12 @@ TextTools provides several optional flags to customize LLM behavior:
 Every tool of `TextTools` returns a `ToolOutput` object which is a BaseModel with attributes:
 - **`result: Any`** → The output of LLM
 - **`analysis: str`** → The reasoning step before generating the final output
-- **`logprobs: list`** → Token-level probabilities for the generated output 
-- **`process: str`** → The tool name which processed the input
-- **`processed_at: datetime`** → The process time
-- **`execution_time: float`** → The execution time (seconds)
+- **`logprobs: list`** → Token-level probabilities for the generated output
 - **`errors: list[str]`** → Any error that have occured during calling LLM
+- **`ToolOutputMetadata`** →
+    - **`tool_name: str`** → The tool name which processed the input
+    - **`processed_at: datetime`** → The process time
+    - **`execution_time: float`** → The execution time (seconds)
 
 **Note:** You can use `repr(ToolOutput)` to see details of your ToolOutput.
 
@@ -224,26 +225,6 @@ Use **TextTools** when you need to:
 
 ---
 
-## 🔍 Logging
-
-TextTools uses Python's standard `logging` module. The library's default logger level is `WARNING`, so if you want to modify it, follow instructions:
-
-
-```python
-import logging
-
-# Default: warnings and errors only
-logging.basicConfig(level=logging.WARNING)
-
-# Debug everything (verbose)
-logging.basicConfig(level=logging.DEBUG)
-
-# Complete silence
-logging.basicConfig(level=logging.CRITICAL)
-```
-
----
-
 ## 📚 Batch Processing
 
 Process large datasets efficiently using OpenAI's batch API.

hamtaa_texttools-1.1.21.dist-info/RECORD

@@ -0,0 +1,32 @@
+hamtaa_texttools-1.1.21.dist-info/licenses/LICENSE,sha256=Hb2YOBKy2MJQLnyLrX37B4ZVuac8eaIcE71SvVIMOLg,1082
+texttools/__init__.py,sha256=CmCS9dEvO6061GiJ8A7gD3UAhCWHTkaID9q3Krlyq_o,311
+texttools/batch/batch_config.py,sha256=scWYQBDuaTj8-b2x_a33Zu-zxm7eqEf5FFoquD-Sv94,1029
+texttools/batch/batch_manager.py,sha256=6HfsexU0PHGGBH7HKReZ-CQxaQI9DXYKAPsFXxovb_I,8740
+texttools/batch/batch_runner.py,sha256=fmoq7yxtEdvfLbEhcx95ma-lgrL-ZdI2EgxmEfVcKtE,10016
+texttools/internals/async_operator.py,sha256=sKMYEy7jEcsXpwnBkA18PFubkM-TXZrBH3QwF7l-wSg,7054
+texttools/internals/exceptions.py,sha256=h_yp_5i_5IfmqTBQ4S6ZOISrrliJBQ3HTEAjwJXrplk,495
+texttools/internals/models.py,sha256=9uoCAe2TLrSzyS9lMJja5orPAYaCvVL1zoCb6FNdkfs,4541
+texttools/internals/operator_utils.py,sha256=eLY2OjYQ3jT-50nx3I8gzuVzgGpMi52f5oB3cnFyxko,1864
+texttools/internals/prompt_loader.py,sha256=yYXDD4YYG2zohGPAmvZwmv5f6xV_RSl5yOrObTh9w7I,3352
+texttools/internals/sync_operator.py,sha256=IG3CXfGmv4PdFlAQ4AZcKuBAqPJdkIAK4mVw77zLbqI,6959
+texttools/internals/text_to_chunks.py,sha256=vY3odhgCZK4E44k_SGlLoSiKkdN0ib6-lQAsPcplAHA,3843
+texttools/prompts/README.md,sha256=ztajRJcmFLhyrUF0_qmOXaCwGsTGCFabfMjch2LAJG0,1375
+texttools/prompts/categorize.yaml,sha256=016b1uGtbKXEwB8_2_bBgVuUelBlu_rgT85XK_c3Yv0,1219
+texttools/prompts/check_fact.yaml,sha256=gQqacCXqUEx3u2FRwhFSZHvhyWGwsYuJd1nIJyhpu7Q,700
+texttools/prompts/extract_entities.yaml,sha256=DN8lZjvzCjotODnHFkWIAxFvmVvoeSs-hDKdN1L6bec,608
+texttools/prompts/extract_keywords.yaml,sha256=GoeApi9SUCLZgs18H2-2BxZiKQ3lHptMPesgq3cluqU,3171
+texttools/prompts/is_question.yaml,sha256=w5qF-z05h62YVs-0x2b2ySlHDKIhukFC9pibnvNM0vc,469
+texttools/prompts/merge_questions.yaml,sha256=f6bHEx54jJ8hnb8iDBUCxXeGdGwRFmuu7vOkVWdaIkM,1788
+texttools/prompts/propositionize.yaml,sha256=agZKQY-NmeJD86DGjmd-paIuazf82bczIGadgzSP5Vs,1378
+texttools/prompts/rewrite.yaml,sha256=h6x8aXcW8oRxEbp466eak0y-LCkUOKf-mJ-vNVp5j5M,5386
+texttools/prompts/run_custom.yaml,sha256=IETY9H0wPGWIIzcnupfbwwKQblwZrbYAxB754W9MhgU,125
+texttools/prompts/subject_to_question.yaml,sha256=TfVmZ6gDgaHRqJWCVkFlKpuJczpMvJTo4XLWPaq5zic,1145
+texttools/prompts/summarize.yaml,sha256=CKx4vjhHbGus1TdjDz_oc0bNEQtq7zfHsZkV2WeYHDU,457
+texttools/prompts/text_to_question.yaml,sha256=mnArBoYu7gpGHriaU2-Aw5SixB2ZIgoHMt99PnTPKD0,1003
+texttools/prompts/translate.yaml,sha256=ew9RERAVSzg0cvxAinNwTSFIaOIjdwIsekbUsgAuNgo,632
+texttools/tools/async_tools.py,sha256=VU3cqqCPILsyjRiG84w8kCw3iDSuFbI6S3VjExXZwFQ,44635
+texttools/tools/sync_tools.py,sha256=2cqcosMYR6LHuYw32WFR-drvqQ-t7Q9_2rUBDOeYzho,44441
+hamtaa_texttools-1.1.21.dist-info/METADATA,sha256=lExdE6uMFSs_wqUSElOyktjpHpZx4RY-cUH6azF-IYA,10183
+hamtaa_texttools-1.1.21.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+hamtaa_texttools-1.1.21.dist-info/top_level.txt,sha256=5Mh0jIxxZ5rOXHGJ6Mp-JPKviywwN0MYuH0xk5bEWqE,10
+hamtaa_texttools-1.1.21.dist-info/RECORD,,

texttools/batch/batch_config.py

@@ -1,7 +1,20 @@
 from dataclasses import dataclass
 from collections.abc import Callable
 
-from texttools.batch.internals.utils import import_data, export_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},...]
+    """
+    return data
+
+
+def import_data(data) -> object:
+    """
+    Takes the output and adds and aggregates it to the original structure.
+    """
+    return data
 
 
 @dataclass

texttools/batch/batch_runner.py

@@ -9,7 +9,7 @@ from dotenv import load_dotenv
 from openai import OpenAI
 from pydantic import BaseModel
 
-from texttools.batch.internals.batch_manager import BatchManager
+from texttools.batch.batch_manager import BatchManager
 from texttools.batch.batch_config import BatchConfig
 from texttools.internals.models import Str
 from texttools.internals.exceptions import TextToolsError, ConfigurationError

texttools/internals/async_operator.py

@@ -1,11 +1,10 @@
 from typing import TypeVar, Type
 from collections.abc import Callable
-import logging
 
 from openai import AsyncOpenAI
 from pydantic import BaseModel
 
-from texttools.internals.models import ToolOutput
+from texttools.internals.models import OperatorOutput
 from texttools.internals.operator_utils import OperatorUtils
 from texttools.internals.prompt_loader import PromptLoader
 from texttools.internals.exceptions import (
@@ -18,35 +17,23 @@ from texttools.internals.exceptions import (
 # Base Model type for output models
 T = TypeVar("T", bound=BaseModel)
 
-logger = logging.getLogger("texttools.async_operator")
-
 
 class AsyncOperator:
     """
-    Core engine for running text-processing operations with an LLM (Async).
-
-    It wires together:
-    - `PromptLoader` → loads YAML prompt templates.
-    - `UserMergeFormatter` → applies formatting to messages (e.g., merging).
-    - AsyncOpenAI client → executes completions/parsed completions.
+    Core engine for running text-processing operations with an LLM.
     """
 
     def __init__(self, client: AsyncOpenAI, model: str):
         self._client = client
         self._model = model
 
-    async def _analyze(self, prompt_configs: dict[str, str], temperature: float) -> str:
-        """
-        Calls OpenAI API for analysis using the configured prompt template.
-        Returns the analyzed content as a string.
-        """
+    async def _analyze_completion(self, analyze_prompt: str, temperature: float) -> str:
         try:
-            analyze_prompt = prompt_configs["analyze_template"]
-
             if not analyze_prompt:
                 raise PromptError("Analyze template is empty")
 
-            analyze_message = [OperatorUtils.build_user_message(analyze_prompt)]
+            analyze_message = OperatorUtils.build_user_message(analyze_prompt)
+
             completion = await self._client.chat.completions.create(
                 model=self._model,
                 messages=analyze_message,
@@ -61,7 +48,7 @@ class AsyncOperator:
             if not analysis:
                 raise LLMError("Empty analysis response")
 
-            return analysis.strip()
+            return analysis
 
         except Exception as e:
             if isinstance(e, (PromptError, LLMError)):
@@ -70,21 +57,23 @@ class AsyncOperator:
 
     async def _parse_completion(
         self,
-        message: list[dict[str, str]],
+        main_prompt: str,
         output_model: Type[T],
         temperature: float,
-        logprobs: bool = False,
-        top_logprobs: int = 3,
-        priority: int | None = 0,
+        logprobs: bool,
+        top_logprobs: int,
+        priority: int,
     ) -> tuple[T, object]:
         """
         Parses a chat completion using OpenAI's structured output format.
         Returns both the parsed object and the raw completion for logprobs.
         """
         try:
+            main_message = OperatorUtils.build_user_message(main_prompt)
+
             request_kwargs = {
                 "model": self._model,
-                "messages": message,
+                "messages": main_message,
                 "response_format": output_model,
                 "temperature": temperature,
             }
@@ -92,8 +81,10 @@ class AsyncOperator:
             if logprobs:
                 request_kwargs["logprobs"] = True
                 request_kwargs["top_logprobs"] = top_logprobs
+
             if priority:
                 request_kwargs["extra_body"] = {"priority": priority}
+
             completion = await self._client.beta.chat.completions.parse(
                 **request_kwargs
             )
@@ -122,24 +113,22 @@ class AsyncOperator:
         user_prompt: str | None,
         temperature: float,
         logprobs: bool,
-        top_logprobs: int | None,
+        top_logprobs: int,
         validator: Callable[[object], bool] | None,
         max_validation_retries: int | None,
+        priority: int,
         # Internal parameters
         prompt_file: str,
         output_model: Type[T],
         mode: str | None,
-        priority: int | None = 0,
         **extra_kwargs,
-    ) -> ToolOutput:
+    ) -> OperatorOutput:
         """
-        Execute the LLM pipeline with the given input text. (Async)
+        Execute the LLM pipeline with the given input text. (Sync)
         """
         try:
             prompt_loader = PromptLoader()
-            output = ToolOutput()
 
-            # Prompt configs contain two keys: main_template and analyze template, both are string
             prompt_configs = prompt_loader.load(
                 prompt_file=prompt_file,
                 text=text.strip(),
@@ -147,47 +136,32 @@ class AsyncOperator:
                 **extra_kwargs,
             )
 
-            messages = []
+            main_prompt = ""
+            analysis = ""
 
             if with_analysis:
-                analysis = await self._analyze(prompt_configs, temperature)
-                messages.append(
-                    OperatorUtils.build_user_message(
-                        f"Based on this analysis: {analysis}"
-                    )
+                analysis = await self._analyze_completion(
+                    prompt_configs["analyze_template"], temperature
                 )
+                main_prompt += f"Based on this analysis:\n{analysis}\n"
 
             if output_lang:
-                messages.append(
-                    OperatorUtils.build_user_message(
-                        f"Respond only in the {output_lang} language."
-                    )
-                )
+                main_prompt += f"Respond only in the {output_lang} language.\n"
 
             if user_prompt:
-                messages.append(
-                    OperatorUtils.build_user_message(
-                        f"Consider this instruction {user_prompt}"
-                    )
-                )
-
-            messages.append(
-                OperatorUtils.build_user_message(prompt_configs["main_template"])
-            )
+                main_prompt += f"Consider this instruction {user_prompt}\n"
 
-            messages = OperatorUtils.user_merge_format(messages)
+            main_prompt += prompt_configs["main_template"]
 
             if logprobs and (not isinstance(top_logprobs, int) or top_logprobs < 2):
                 raise ValueError("top_logprobs should be an integer greater than 1")
 
             parsed, completion = await self._parse_completion(
-                messages, output_model, temperature, logprobs, top_logprobs, priority
+                main_prompt, output_model, temperature, logprobs, top_logprobs, priority
             )
 
-            output.result = parsed.result
-
             # Retry logic if validation fails
-            if validator and not validator(output.result):
+            if validator and not validator(parsed.result):
                 if (
                     not isinstance(max_validation_retries, int)
                     or max_validation_retries < 1
@@ -197,17 +171,13 @@ class AsyncOperator:
                     )
 
                 succeeded = False
-                for attempt in range(max_validation_retries):
-                    logger.warning(
-                        f"Validation failed, retrying for the {attempt + 1} time."
-                    )
-
-                    # Generate new temperature for retry
+                for _ in range(max_validation_retries):
+                    # Generate a new temperature to retry
                     retry_temperature = OperatorUtils.get_retry_temp(temperature)
 
                     try:
                         parsed, completion = await self._parse_completion(
-                            messages,
+                            main_prompt,
                             output_model,
                             retry_temperature,
                             logprobs,
@@ -215,30 +185,26 @@ class AsyncOperator:
                             priority=priority,
                         )
 
-                        output.result = parsed.result
-
                         # Check if retry was successful
-                        if validator(output.result):
+                        if validator(parsed.result):
                             succeeded = True
                             break
 
-                    except LLMError as e:
-                        logger.error(f"Retry attempt {attempt + 1} failed: {e}")
+                    except LLMError:
+                        pass
 
                 if not succeeded:
-                    raise ValidationError(
-                        f"Validation failed after {max_validation_retries} retries"
-                    )
-
-            if logprobs:
-                output.logprobs = OperatorUtils.extract_logprobs(completion)
-
-            if with_analysis:
-                output.analysis = analysis
-
-            output.process = prompt_file[:-5]
+                    raise ValidationError("Validation failed after all retries")
+
+            operator_output = OperatorOutput(
+                result=parsed.result,
+                analysis=analysis if with_analysis else None,
+                logprobs=OperatorUtils.extract_logprobs(completion)
+                if logprobs
+                else None,
+            )
 
-            return output
+            return operator_output
 
         except (PromptError, LLMError, ValidationError):
             raise

texttools/internals/models.py

@@ -1,25 +1,39 @@
+from __future__ import annotations
+
 from datetime import datetime
-from typing import Type, Literal
+from typing import Type, Literal, Any
 
 from pydantic import BaseModel, Field, create_model
 
 
-class ToolOutput(BaseModel):
-    result: object = None
-    logprobs: list[dict[str, object]] = []
-    analysis: str = ""
-    process: str | None = None
-    processed_at: datetime = datetime.now()
+class ToolOutputMetadata(BaseModel):
+    tool_name: str
+    processed_at: datetime = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
     execution_time: float | None = None
+
+
+class ToolOutput(BaseModel):
+    result: Any = None
+    analysis: str | None = None
+    logprobs: list[dict[str, Any]] | None = None
     errors: list[str] = []
+    metadata: ToolOutputMetadata | None = None
 
     def __repr__(self) -> str:
-        return f"""
-        ToolOutput(process='{self.process}', result_type='{type(self.result)}', 
-        result='{self.result}', analysis='{self.analysis}', 
-        logprobs='{self.logprobs}', errors='{self.errors}', 
-        processed_at='{self.processed_at}', execution_time='{self.execution_time}'
-        """
+        base = f"""ToolOutput(result='{self.result}', result_type='{type(self.result)}', analysis='{self.analysis}', logprobs='{self.logprobs}', errors='{self.errors}'"""
+
+        if self.metadata:
+            base += f""", tool_name='{self.metadata.tool_name}', 
+            processed_at='{self.metadata.processed_at}', execution_time='{self.metadata.execution_time}'
+            """
+
+        return base
+
+
+class OperatorOutput(BaseModel):
+    result: Any
+    analysis: str | None
+    logprobs: list[dict[str, Any]] | None
 
 
 class Str(BaseModel):
@@ -53,114 +67,69 @@ class ReasonListStr(BaseModel):
     )
 
 
-class Node(BaseModel):
-    node_id: int
-    name: str
-    level: int
-    parent_id: int | None
-    description: str
+class Node:
+    def __init__(self, name: str, description: str, level: int, parent: Node | None):
+        self.name = name
+        self.description = description
+        self.level = level
+        self.parent = parent
+        self.children = {}
 
 
 class CategoryTree:
-    def __init__(self, tree_name):
-        self._root = Node(
-            node_id=0, name=tree_name, level=0, parent_id=None, description="Root node"
-        )
-        self._all_nodes: list[Node] = [self._root]
-        self._new_id = 1
-
-    def get_all_nodes(self) -> list[Node]:
+    def __init__(self):
+        self._root = Node(name="root", description="root", level=0, parent=None)
+        self._all_nodes = {"root": self._root}
+
+    def get_all_nodes(self) -> dict[str, Node]:
         return self._all_nodes
 
     def get_level_count(self) -> int:
-        return max([item.level for item in self._all_nodes])
-
-    def get_node(self, identifier: int | str) -> Node | None:
-        if isinstance(identifier, str):
-            for node in self.get_all_nodes():
-                if node.name == identifier:
-                    return node
-            return None
-        elif isinstance(identifier, int):
-            for node in self.get_all_nodes():
-                if node.node_id == identifier:
-                    return node
-            return None
-        else:
-            return None
-
-    def get_children(self, parent_node: Node) -> list[Node] | None:
-        children = [
-            node
-            for node in self.get_all_nodes()
-            if parent_node.node_id == node.parent_id
-        ]
-        return children if children else None
+        return max(node.level for node in self._all_nodes.values())
+
+    def get_node(self, name: str) -> Node | None:
+        return self._all_nodes.get(name)
 
     def add_node(
         self,
-        node_name: str,
-        parent_name: str | None = None,
+        name: str,
+        parent_name: str,
         description: str | None = None,
     ) -> None:
-        if self.get_node(node_name):
-            raise ValueError(f"{node_name} has been chosen for another category before")
-
-        if parent_name:
-            parent_node = self.get_node(parent_name)
-            if not parent_node:
-                raise ValueError(f"Parent category '{parent_name}' not found")
-            parent_id = parent_node.node_id
-            level = parent_node.level + 1
-        else:
-            level = 1
-            parent_id = 0
+        if self.get_node(name):
+            raise ValueError(f"Cannot add {name} category twice")
+
+        parent = self.get_node(parent_name)
+
+        if not parent:
+            raise ValueError(f"Parent category '{parent_name}' not found")
 
         node_data = {
-            "node_id": self._new_id,
-            "name": node_name,
-            "level": level,
-            "parent_id": parent_id,
+            "name": name,
             "description": description if description else "No description provided",
+            "level": parent.level + 1,
+            "parent": parent,
         }
 
-        self._all_nodes.append(Node(**node_data))
-        self._new_id += 1
-
-    def remove_node(self, identifier: int | str) -> None:
-        node = self.get_node(identifier)
-
-        if node:
-            # Remove node's children recursively
-            children = self.get_children(node)
-
-            if not children:
-                self._all_nodes.remove(node)
-                return
-
-            for child in children:
-                self.remove_node(child.name)
-
-            self._all_nodes.remove(node)
-        else:
-            raise ValueError(f"Node with identifier: '{identifier}' not found.")
-
-    def dump_tree(self) -> dict:
-        def build_dict(node: Node) -> dict:
-            children = [
-                build_dict(child)
-                for child in self._all_nodes
-                if child.parent_id == node.node_id
-            ]
-            return {
-                "node_id": node.node_id,
-                "name": node.name,
-                "level": node.level,
-                "parent_id": node.parent_id,
-                "children": children,
-            }
-
-        return {"category_tree": build_dict(self._root)["children"]}
+        new_node = Node(**node_data)
+        parent.children[name] = new_node
+        self._all_nodes[name] = new_node
+
+    def remove_node(self, name: str) -> None:
+        if name == "root":
+            raise ValueError("Cannot remove the root node")
+
+        node = self.get_node(name)
+        if not node:
+            raise ValueError(f"Category: '{name}' not found")
+
+        for child_name in list(node.children.keys()):
+            self.remove_node(child_name)
+
+        if node.parent:
+            del node.parent.children[name]
+
+        del self._all_nodes[name]
 
 
 # This function is needed to create CategorizerOutput with dynamic categories

texttools/internals/operator_utils.py

@@ -5,8 +5,8 @@ import random
 
 class OperatorUtils:
     @staticmethod
-    def build_user_message(prompt: str) -> dict[str, str]:
-        return {"role": "user", "content": prompt}
+    def build_user_message(prompt: str) -> list[dict[str, str]]:
+        return [{"role": "user", "content": prompt}]
 
     @staticmethod
     def extract_logprobs(completion: dict) -> list[dict]:
@@ -52,27 +52,3 @@ class OperatorUtils:
         new_temp = base_temp + delta_temp
 
         return max(0.0, min(new_temp, 1.5))
-
-    @staticmethod
-    def user_merge_format(messages: list[dict[str, str]]) -> list[dict[str, str]]:
-        """
-        Merges consecutive user messages into a single message, separated by newlines.
-
-        This is useful for condensing a multi-turn user input into a single
-        message for the LLM. Assistant and system messages are left unchanged and
-        act as separators between user message groups.
-        """
-        merged = []
-
-        for message in messages:
-            role, content = message["role"], message["content"].strip()
-
-            # Merge with previous user turn
-            if merged and role == "user" and merged[-1]["role"] == "user":
-                merged[-1]["content"] += "\n" + content
-
-            # Otherwise, start a new turn
-            else:
-                merged.append({"role": role, "content": content})
-
-        return merged