hamtaa-texttools 1.1.17__tar.gz → 1.1.19__tar.gz

{hamtaa_texttools-1.1.17/hamtaa_texttools.egg-info → hamtaa_texttools-1.1.19}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hamtaa-texttools
-Version: 1.1.17
+Version: 1.1.19
 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
@@ -61,10 +61,40 @@ 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 
 - **`run_custom()`** - Allows users to define a custom tool with an arbitrary BaseModel
 
 ---
 
+## 📊 Tool Quality Tiers
+
+| Status | Meaning | Use in Production? |
+|--------|---------|-------------------|
+| **✅ Production** | Evaluated, tested, stable. | **Yes** - ready for reliable use. |
+| **🧪 Experimental** | Added to the package but **not fully evaluated**. Functional, but quality may vary. | **Use with caution** - outputs not yet validated. |
+
+### Current Status
+**Production Tools:**
+- `categorize()` (list mode)
+- `extract_keywords()`
+- `extract_entities()`
+- `is_question()`
+- `text_to_question()`
+- `merge_questions()`
+- `rewrite()`
+- `subject_to_question()`
+- `summarize()`
+- `run_custom()` (fine in most cases)
+
+**Experimental Tools:**
+- `categorize()` (tree mode)
+- `translate()`
+- `propositionize()`
+- `check_fact()`
+- `run_custom()` (not evaluated in all scenarios)
+
+---
+
 ## ⚙️ `with_analysis`, `logprobs`, `output_lang`, `user_prompt`, `temperature`, `validator` and `priority` parameters
 
 TextTools provides several optional flags to customize LLM behavior:

{hamtaa_texttools-1.1.17 → hamtaa_texttools-1.1.19}/README.md

@@ -26,10 +26,40 @@ 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 
 - **`run_custom()`** - Allows users to define a custom tool with an arbitrary BaseModel
 
 ---
 
+## 📊 Tool Quality Tiers
+
+| Status | Meaning | Use in Production? |
+|--------|---------|-------------------|
+| **✅ Production** | Evaluated, tested, stable. | **Yes** - ready for reliable use. |
+| **🧪 Experimental** | Added to the package but **not fully evaluated**. Functional, but quality may vary. | **Use with caution** - outputs not yet validated. |
+
+### Current Status
+**Production Tools:**
+- `categorize()` (list mode)
+- `extract_keywords()`
+- `extract_entities()`
+- `is_question()`
+- `text_to_question()`
+- `merge_questions()`
+- `rewrite()`
+- `subject_to_question()`
+- `summarize()`
+- `run_custom()` (fine in most cases)
+
+**Experimental Tools:**
+- `categorize()` (tree mode)
+- `translate()`
+- `propositionize()`
+- `check_fact()`
+- `run_custom()` (not evaluated in all scenarios)
+
+---
+
 ## ⚙️ `with_analysis`, `logprobs`, `output_lang`, `user_prompt`, `temperature`, `validator` and `priority` parameters
 
 TextTools provides several optional flags to customize LLM behavior:

{hamtaa_texttools-1.1.17 → hamtaa_texttools-1.1.19/hamtaa_texttools.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hamtaa-texttools
-Version: 1.1.17
+Version: 1.1.19
 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
@@ -61,10 +61,40 @@ 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 
 - **`run_custom()`** - Allows users to define a custom tool with an arbitrary BaseModel
 
 ---
 
+## 📊 Tool Quality Tiers
+
+| Status | Meaning | Use in Production? |
+|--------|---------|-------------------|
+| **✅ Production** | Evaluated, tested, stable. | **Yes** - ready for reliable use. |
+| **🧪 Experimental** | Added to the package but **not fully evaluated**. Functional, but quality may vary. | **Use with caution** - outputs not yet validated. |
+
+### Current Status
+**Production Tools:**
+- `categorize()` (list mode)
+- `extract_keywords()`
+- `extract_entities()`
+- `is_question()`
+- `text_to_question()`
+- `merge_questions()`
+- `rewrite()`
+- `subject_to_question()`
+- `summarize()`
+- `run_custom()` (fine in most cases)
+
+**Experimental Tools:**
+- `categorize()` (tree mode)
+- `translate()`
+- `propositionize()`
+- `check_fact()`
+- `run_custom()` (not evaluated in all scenarios)
+
+---
+
 ## ⚙️ `with_analysis`, `logprobs`, `output_lang`, `user_prompt`, `temperature`, `validator` and `priority` parameters
 
 TextTools provides several optional flags to customize LLM behavior:

{hamtaa_texttools-1.1.17 → hamtaa_texttools-1.1.19}/hamtaa_texttools.egg-info/SOURCES.txt

@@ -15,9 +15,16 @@ texttools/batch/batch_config.py
 texttools/batch/batch_runner.py
 texttools/batch/internals/batch_manager.py
 texttools/batch/internals/utils.py
+texttools/internals/async_operator.py
+texttools/internals/exceptions.py
+texttools/internals/formatters.py
+texttools/internals/models.py
+texttools/internals/operator_utils.py
+texttools/internals/prompt_loader.py
+texttools/internals/sync_operator.py
 texttools/prompts/README.md
 texttools/prompts/categorize.yaml
-texttools/prompts/detect_entity.yaml
+texttools/prompts/check_fact.yaml
 texttools/prompts/extract_entities.yaml
 texttools/prompts/extract_keywords.yaml
 texttools/prompts/is_question.yaml
@@ -30,10 +37,4 @@ texttools/prompts/summarize.yaml
 texttools/prompts/text_to_question.yaml
 texttools/prompts/translate.yaml
 texttools/tools/async_tools.py
-texttools/tools/sync_tools.py
-texttools/tools/internals/async_operator.py
-texttools/tools/internals/formatters.py
-texttools/tools/internals/models.py
-texttools/tools/internals/operator_utils.py
-texttools/tools/internals/prompt_loader.py
-texttools/tools/internals/sync_operator.py
+texttools/tools/sync_tools.py

{hamtaa_texttools-1.1.17 → hamtaa_texttools-1.1.19}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hamtaa-texttools"
-version = "1.1.17"
+version = "1.1.19"
 authors = [
   { name = "Tohidi", email = "the.mohammad.tohidi@gmail.com" },
   { name = "Montazer", email = "montazerh82@gmail.com" },

{hamtaa_texttools-1.1.17 → hamtaa_texttools-1.1.19}/tests/test_all_async_tools.py

@@ -21,7 +21,10 @@ t = AsyncTheTool(client=client, model=MODEL)
 
 async def main():
     category_task = t.categorize(
-        "سلام حالت چطوره؟", categories=["هیچکدام", "دینی", "فلسفه"]
+        "سلام حالت چطوره؟",
+        categories=["هیچکدام", "دینی", "فلسفه"],
+        logprobs=True,
+        top_logprobs=-1,
     )
     keywords_task = t.extract_keywords("Tomorrow, we will be dead by the car crash")
     entities_task = t.extract_entities("We will be dead by the car crash")
@@ -40,7 +43,11 @@ async def main():
     questions_task = t.subject_to_question("Friendship", 3)
     summary_task = t.summarize("Tomorrow, we will be dead by the car crash")
     translation_task = t.translate("سلام حالت چطوره؟", target_language="English")
-    propositionize_task = t.propositionize("جنگ جهانی دوم در سال ۱۹۳۹ آغاز شد و آلمان به لهستان حمله کرد.", output_lang="Persian")
+    propositionize_task = t.propositionize(
+        "جنگ جهانی دوم در سال ۱۹۳۹ آغاز شد و آلمان به لهستان حمله کرد.",
+        output_lang="Persian",
+    )
+    check_fact_task = t.check_fact(text="امام نهم در ایران به خاک سپرده شد", source_text="حرم مطهر امام رضا علیه السلام در مشهد مقدس هست")
     (
         category,
         keywords,
@@ -53,6 +60,7 @@ async def main():
         summary,
         translation,
         propositionize,
+        check_fact,
     ) = await asyncio.gather(
         category_task,
         keywords_task,
@@ -65,6 +73,7 @@ async def main():
         summary_task,
         translation_task,
         propositionize_task,
+        check_fact_task,
     )
 
     for tool_output in (
@@ -79,6 +88,7 @@ async def main():
         summary,
         translation,
         propositionize,
+        check_fact,
     ):
         print(repr(tool_output))
 

{hamtaa_texttools-1.1.17 → hamtaa_texttools-1.1.19}/tests/test_all_tools.py

@@ -19,7 +19,12 @@ client = OpenAI(base_url=BASE_URL, api_key=API_KEY)
 t = TheTool(client=client, model=MODEL)
 
 # Categorizer: list mode
-category = t.categorize("سلام حالت چطوره؟", categories=["هیچکدام", "دینی", "فلسفه"])
+category = t.categorize(
+    "سلام حالت چطوره؟",
+    categories=["هیچکدام", "دینی", "فلسفه"],
+    logprobs=True,
+    top_logprobs=-1,
+)
 print(repr(category))
 
 # Categorizer: tree mode
@@ -46,7 +51,7 @@ keywords = t.extract_keywords(
 print(repr(keywords))
 
 # NER Extractor
-entities = t.extract_entities("We will be dead by the car crash")
+entities = t.extract_entities("We will be dead by the car crash", with_analysis=True)
 print(repr(entities))
 
 
@@ -85,9 +90,20 @@ translation = t.translate("سلام حالت چطوره؟", target_language="Eng
 print(repr(translation))
 
 # propositionize
-propositionize = t.propositionize("جنگ جهانی دوم در سال ۱۹۳۹ آغاز شد و آلمان به لهستان حمله کرد.", output_lang="Persian")
+propositionize = t.propositionize(
+    "جنگ جهانی دوم در سال ۱۹۳۹ آغاز شد و آلمان به لهستان حمله کرد.",
+    output_lang="Persian",
+)
 print(repr(propositionize))
 
+# check_fact
+check_fact = t.check_fact(
+    text="امام نهم در ایران به خاک سپرده شد",
+    source_text="حرم مطهر امام رضا علیه السلام در مشهد مقدس هست",
+)
+print(repr(check_fact))
+
+
 # Custom tool
 class Student(BaseModel):
     result: list[dict[str, str]]

{hamtaa_texttools-1.1.17 → hamtaa_texttools-1.1.19}/tests/test_output_validation.py

@@ -29,7 +29,7 @@ question = t.text_to_question(
     "زندگی",
     output_lang="Persian",
     validator=validate,
-    max_validation_retries=5,
+    max_validation_retries=0,
     temperature=1.0,
 )
-print(question)
+print(repr(question))

{hamtaa_texttools-1.1.17 → hamtaa_texttools-1.1.19}/texttools/__init__.py

@@ -2,6 +2,6 @@ from .batch.batch_runner import BatchJobRunner
 from .batch.batch_config import BatchConfig
 from .tools.sync_tools import TheTool
 from .tools.async_tools import AsyncTheTool
-from .tools.internals.models import CategoryTree
+from .internals.models import CategoryTree
 
 __all__ = ["TheTool", "AsyncTheTool", "BatchJobRunner", "BatchConfig", "CategoryTree"]

{hamtaa_texttools-1.1.17 → hamtaa_texttools-1.1.19}/texttools/batch/batch_runner.py

@@ -11,7 +11,8 @@ from pydantic import BaseModel
 
 from texttools.batch.internals.batch_manager import BatchManager
 from texttools.batch.batch_config import BatchConfig
-from texttools.tools.internals.models import StrOutput
+from texttools.internals.models import StrOutput
+from texttools.internals.exceptions import TextToolsError, ConfigurationError
 
 # Base Model type for output models
 T = TypeVar("T", bound=BaseModel)
@@ -27,22 +28,26 @@ class BatchJobRunner:
     def __init__(
         self, config: BatchConfig = BatchConfig(), output_model: Type[T] = StrOutput
     ):
-        self._config = config
-        self._system_prompt = config.system_prompt
-        self._job_name = config.job_name
-        self._input_data_path = config.input_data_path
-        self._output_data_filename = config.output_data_filename
-        self._model = config.model
-        self._output_model = output_model
-        self._manager = self._init_manager()
-        self._data = self._load_data()
-        self._parts: list[list[dict[str, Any]]] = []
-        # Map part index to job name
-        self._part_idx_to_job_name: dict[int, str] = {}
-        # Track retry attempts per part
-        self._part_attempts: dict[int, int] = {}
-        self._partition_data()
-        Path(self._config.BASE_OUTPUT_DIR).mkdir(parents=True, exist_ok=True)
+        try:
+            self._config = config
+            self._system_prompt = config.system_prompt
+            self._job_name = config.job_name
+            self._input_data_path = config.input_data_path
+            self._output_data_filename = config.output_data_filename
+            self._model = config.model
+            self._output_model = output_model
+            self._manager = self._init_manager()
+            self._data = self._load_data()
+            self._parts: list[list[dict[str, Any]]] = []
+            # Map part index to job name
+            self._part_idx_to_job_name: dict[int, str] = {}
+            # Track retry attempts per part
+            self._part_attempts: dict[int, int] = {}
+            self._partition_data()
+            Path(self._config.BASE_OUTPUT_DIR).mkdir(parents=True, exist_ok=True)
+
+        except Exception as e:
+            raise ConfigurationError(f"Batch runner initialization failed: {e}")
 
     def _init_manager(self) -> BatchManager:
         load_dotenv()
@@ -162,56 +167,62 @@ class BatchJobRunner:
 
         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())
-        logger.info(f"Pending parts: {sorted(pending_parts)}")
-        # Polling loop
-        while pending_parts:
-            finished_this_round: list[int] = []
-            for part_idx in list(pending_parts):
-                job_name = self._part_idx_to_job_name[part_idx]
-                status = self._manager.check_status(job_name=job_name)
-                logger.info(f"Status for {job_name}: {status}")
-                if status == "completed":
-                    logger.info(
-                        f"Job completed. Fetching results for part {part_idx + 1}..."
-                    )
-                    output_data, log = self._manager.fetch_results(
-                        job_name=job_name, remove_cache=False
-                    )
-                    output_data = self._config.import_function(output_data)
-                    self._save_results(output_data, log, part_idx)
-                    logger.info(f"Fetched and saved results for part {part_idx + 1}.")
-                    finished_this_round.append(part_idx)
-                elif status == "failed":
-                    attempt = self._part_attempts.get(part_idx, 0) + 1
-                    self._part_attempts[part_idx] = attempt
-                    if attempt <= self._config.max_retries:
+        try:
+            # Submit all jobs up-front for concurrent execution
+            self._submit_all_jobs()
+            pending_parts: set[int] = set(self._part_idx_to_job_name.keys())
+            logger.info(f"Pending parts: {sorted(pending_parts)}")
+            # Polling loop
+            while pending_parts:
+                finished_this_round: list[int] = []
+                for part_idx in list(pending_parts):
+                    job_name = self._part_idx_to_job_name[part_idx]
+                    status = self._manager.check_status(job_name=job_name)
+                    logger.info(f"Status for {job_name}: {status}")
+                    if status == "completed":
                         logger.info(
-                            f"Job {job_name} failed (attempt {attempt}). Retrying after short backoff..."
+                            f"Job completed. Fetching results for part {part_idx + 1}..."
                         )
-                        self._manager._clear_state(job_name)
-                        time.sleep(10)
-                        payload = self._to_manager_payload(self._parts[part_idx])
-                        new_job_name = (
-                            f"{self._job_name}_part_{part_idx + 1}_retry_{attempt}"
+                        output_data, log = self._manager.fetch_results(
+                            job_name=job_name, remove_cache=False
                         )
-                        self._manager.start(payload, job_name=new_job_name)
-                        self._part_idx_to_job_name[part_idx] = new_job_name
-                    else:
+                        output_data = self._config.import_function(output_data)
+                        self._save_results(output_data, log, part_idx)
                         logger.info(
-                            f"Job {job_name} failed after {attempt - 1} retries. Marking as failed."
+                            f"Fetched and saved results for part {part_idx + 1}."
                         )
                         finished_this_round.append(part_idx)
-                else:
-                    # Still running or queued
-                    continue
-            # Remove finished parts
-            for part_idx in finished_this_round:
-                pending_parts.discard(part_idx)
-            if pending_parts:
-                logger.info(
-                    f"Waiting {self._config.poll_interval_seconds}s before next status check for parts: {sorted(pending_parts)}"
-                )
-                time.sleep(self._config.poll_interval_seconds)
+                    elif status == "failed":
+                        attempt = self._part_attempts.get(part_idx, 0) + 1
+                        self._part_attempts[part_idx] = attempt
+                        if attempt <= self._config.max_retries:
+                            logger.info(
+                                f"Job {job_name} failed (attempt {attempt}). Retrying after short backoff..."
+                            )
+                            self._manager._clear_state(job_name)
+                            time.sleep(10)
+                            payload = self._to_manager_payload(self._parts[part_idx])
+                            new_job_name = (
+                                f"{self._job_name}_part_{part_idx + 1}_retry_{attempt}"
+                            )
+                            self._manager.start(payload, job_name=new_job_name)
+                            self._part_idx_to_job_name[part_idx] = new_job_name
+                        else:
+                            logger.info(
+                                f"Job {job_name} failed after {attempt - 1} retries. Marking as failed."
+                            )
+                            finished_this_round.append(part_idx)
+                    else:
+                        # Still running or queued
+                        continue
+                # Remove finished parts
+                for part_idx in finished_this_round:
+                    pending_parts.discard(part_idx)
+                if pending_parts:
+                    logger.info(
+                        f"Waiting {self._config.poll_interval_seconds}s before next status check for parts: {sorted(pending_parts)}"
+                    )
+                    time.sleep(self._config.poll_interval_seconds)
+
+        except Exception as e:
+            raise TextToolsError(f"Batch job execution failed: {e}")