hamtaa-texttools 1.0.0__tar.gz → 1.0.2__tar.gz

hamtaa_texttools-1.0.2/MANIFEST.in

@@ -0,0 +1,2 @@
+graft texttools/prompts
+global-exclude *.pyc

{hamtaa_texttools-1.0.0 → hamtaa_texttools-1.0.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hamtaa-texttools
-Version: 1.0.0
+Version: 1.0.2
 Summary: TextTools is 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

{hamtaa_texttools-1.0.0 → hamtaa_texttools-1.0.2}/hamtaa_texttools.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hamtaa-texttools
-Version: 1.0.0
+Version: 1.0.2
 Summary: TextTools is 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

{hamtaa_texttools-1.0.0 → hamtaa_texttools-1.0.2}/hamtaa_texttools.egg-info/SOURCES.txt

@@ -1,4 +1,5 @@
 LICENSE
+MANIFEST.in
 README.md
 pyproject.toml
 hamtaa_texttools.egg-info/PKG-INFO
@@ -10,6 +11,17 @@ tests/test_tools.py
 texttools/__init__.py
 texttools/formatters/base_formatter.py
 texttools/formatters/user_merge_formatter/user_merge_formatter.py
+texttools/prompts/README.md
+texttools/prompts/categorizer.yaml
+texttools/prompts/keyword_extractor.yaml
+texttools/prompts/ner_extractor.yaml
+texttools/prompts/question_detector.yaml
+texttools/prompts/question_generator.yaml
+texttools/prompts/question_merger.yaml
+texttools/prompts/question_rewriter.yaml
+texttools/prompts/subject_question_generator.yaml
+texttools/prompts/summarizer.yaml
+texttools/prompts/translator.yaml
 texttools/tools/__init__.py
 texttools/tools/operator.py
 texttools/tools/output_models.py

{hamtaa_texttools-1.0.0 → hamtaa_texttools-1.0.2}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "hamtaa-texttools"
-version = "1.0.0"
+version = "1.0.2"
 authors = [
   { name = "Tohidi", email = "the.mohammad.tohidi@gmail.com" },
   { name = "Montazer", email = "montazerh82@gmail.com" },
@@ -24,3 +24,9 @@ keywords = ["nlp", "llm", "text-processing", "openai"]
 [tool.setuptools.packages.find]
 where = ["."]
 include = ["texttools*"]
+
+[tool.setuptools]
+include-package-data = true
+
+[tool.setuptools.package-data]
+"texttools" = ["prompts/*.yaml", "prompts/*.yml"]

hamtaa_texttools-1.0.2/texttools/prompts/README.md

@@ -0,0 +1,31 @@
+# Prompts
+
+## Overview
+This folder contains YAML files for all prompts used in the project. Each file represents a separate prompt template, which can be loaded by tools or scripts that require structured prompts for AI models.
+
+## Structure
+- **prompt_file.yaml**: Each YAML file represents a single prompt template.
+- **main_template**: The main instruction template for the model.
+- **analyze_template** (optional): A secondary reasoning template used before generating the final response.
+- **Modes** (optional): Some prompts may have multiple modes (e.g., `default_mode`, `reason_mode`) to allow different behaviors.
+
+### Example YAML Structure
+```yaml
+main_template:
+  default_mode: |
+    Your main instructions here with placeholders like {input}.
+  reason_mode: |
+    Optional reasoning instructions here.
+
+analyze_template:
+  default_mode: |
+    Analyze and summarize the input.
+  reason_mode: |
+    Optional detailed analysis template.
+```
+
+## Guidelines
+1. **Naming**: Use descriptive names for each YAML file corresponding to the tool or task it serves.
+2. **Placeholders**: Use `{input}` or other relevant placeholders to dynamically inject data.
+3. **Modes**: If using modes, ensure both `main_template` and `analyze_template` contain the corresponding keys.
+4. **Consistency**: Keep formatting consistent across files for easier parsing by scripts.

hamtaa_texttools-1.0.2/texttools/prompts/categorizer.yaml

@@ -0,0 +1,25 @@
+main_template: |
+  You are a religious scholar.
+  As a user, I give you a text and ask you to classify that text into one of the following categories:
+  "باورهای دینی",
+  "اخلاق اسلامی",
+  "احکام و فقه",
+  "تاریخ اسلام و شخصیت ها",
+  "منابع دینی",
+  "دین و جامعه/سیاست",
+  "عرفان و معنویت",
+  "هیچکدام",
+  Respond only in this JSON format:
+  {{
+    "reason": "<Summary of why did you choose this category?>",
+    "result": "<One of the above tags>"
+  }}
+  Here is the text:
+  {input}
+
+analyze_template: |
+  Our goal is to categorize the text.
+  Read the text and respond the main idea and a short analysis of that.
+  Maximum words: 20
+  Here is the text:
+  {input}

hamtaa_texttools-1.0.2/texttools/prompts/keyword_extractor.yaml

@@ -0,0 +1,11 @@
+main_template: |
+  Extract the most relevant keywords from the following text. Provide them as a list of strings.
+  {input}
+  Respond only in JSON format:
+  {{"result": ["keyword1", "keyword2", ...]}}.
+  Respond in the language of the input text.
+
+analyze_template: |
+  Analyze the following text to identify its main topics, concepts, and important terms.
+  Provide a concise summary of your findings that will help in extracting relevant keywords.
+  {input}

hamtaa_texttools-1.0.2/texttools/prompts/ner_extractor.yaml

@@ -0,0 +1,18 @@
+main_template: |
+  Identify and extract all named entities (e.g., PER, ORG, LOC, DAT, etc.) from the following text. For each entity, provide its text and a clear type.
+  Respond as a JSON array of objects.
+  {input}
+  Respond only in JSON format:
+  {{
+    "result": [
+      {{
+        "text": "string",
+        "type": "string",
+      }}
+    ]
+  }}
+
+analyze_template: |
+  Read the following text and identify any proper nouns, key concepts, or specific mentions that might represent named entities.
+  Provide a brief, summarized analysis that could help in categorizing these entities.
+  {input}

hamtaa_texttools-1.0.2/texttools/prompts/question_detector.yaml

@@ -0,0 +1,12 @@
+main_template: |
+  Determine that if the following text contains any question or request of some kind or not.
+  Respond only in JSON format:
+  {{"result": "true/false"}}
+  {input}
+
+analyze_template: |
+  We want to analyze this text snippet to see if it contains any question or request of some kind or not.
+  Read the text, and reason about it being a request or not.
+  Summerized, short answer.
+  {input}
+  

hamtaa_texttools-1.0.2/texttools/prompts/question_generator.yaml

@@ -0,0 +1,22 @@
+main_template: |
+  Given the following answer, generate a single, 
+  appropriate question that this answer would directly respond to.
+  The generated answer should be independently meaningful,
+  and not mentioning any verbs like, this, that, he or she on the question.
+  The generated question must be in the language of the user's input.
+  Here is the text:
+  {input}
+  Respond only in JSON format:
+  {{"result": "string"}}
+  Respond only with the new generated question, without any additional information.          
+
+analyze_template: |
+  Analyze the following answer to identify its key facts,
+  main subject, and what kind of information it provides.
+  Provide a brief, summarized understanding of the answer's content that will 
+  help in formulating a relevant and direct question.
+  Provide the summary in the language of the content.
+  Just mention the keypoints that was provided in the answer
+  Here is the text:
+  {input}
+                

hamtaa_texttools-1.0.2/texttools/prompts/question_merger.yaml

@@ -0,0 +1,47 @@
+main_template:
+
+  default_mode: |
+    You are a language expert.
+    I will give you a list of questions that are semantically similar.
+    Your task is to merge them into one unified question that:
+    - Preserves all the information and intent from the original questions.
+    - Sounds natural, fluent, and concise.
+    - Avoids redundancy or unnecessary repetition.
+    - Does not omit any unique idea from the originals.
+    Output only the merged question.
+    Here is the questions: {input}
+    Respond only in JSON format:
+    {{"result": "string"}}
+    Respond only with the new generated question, without any additional information.
+    The generated question must be in the language of the users input.
+
+  reason_mode: |
+    You are an AI assistant helping to unify semantically similar questions.
+    First, briefly extract the unique intent or content from each input question.
+    Then, write one merged question that combines all their content clearly and naturally, without redundancy.
+    Step 1: Extract key ideas.
+    Step 2: Write the final merged question.
+    Here is the questions: {input}
+    Respond only in JSON format:
+    {{"result": "string"}}
+    Respond only with the new generated question, without any additional information.
+    The generated question must be in the language of the users input.
+
+analyze_template:
+
+  default_mode: | 
+    Analyze the following questions to identify their core intent, key concepts, 
+    and the specific information they are seeking.
+    Provide a brief, summarized understanding of the questions' meaning that
+    will help in merging and rephrasing it accurately without changing its intent.        
+    Respond in the language of the question.
+    Here is the question: {input}
+
+  reason_mode: |
+    Analyze the following questions to identify their exact wording, phrasing,
+    and the literal meaning it conveys.
+    Provide a brief, summarized analysis of their linguistic structure and current meaning,
+    which will then be used to create a new question containing all of their contents.
+    Respond in the language of the question.
+    Here is the question: {input}
+    

hamtaa_texttools-1.0.2/texttools/prompts/question_rewriter.yaml

@@ -0,0 +1,44 @@
+main_template:
+
+  same_meaning_different_wording_mode: |
+    Rewrite the following question using completely different wording and phrasing, 
+    ensuring its original meaning is perfectly preserved. The rewritten question 
+    should be distinct from the original but convey the exact same inquiry.
+    Here is the question:
+    {input}
+    Respond only in JSON format:
+    {{"result": "string"}}
+    Respond only with the new generated question, without any additional information.
+    The generated question must be in the language of the users input.
+
+  different_meaning_similar_wording_mode: |
+    Rewrite the following question using *very similar wording and phrasing* 
+    to the original, but ensure the rewritten question has a *completely different meaning*. 
+    Focus on subtle changes that drastically alter the intent or subject of the question.
+    Here is the question:
+    {input}
+    Respond only in JSON format:
+    {{"result": "string"}}
+    Respond only with the new generated question, without any additional information.
+    The generated question must be in the language of the users input.
+
+analyze_template:
+
+  same_meaning_different_wording_mode: | 
+    Analyze the following question to identify its core intent, key concepts, 
+    and the specific information it is seeking.
+    Provide a brief, summarized understanding of the question's meaning that
+    will help in rephrasing it accurately without changing its intent.       
+    Respond in the language of the question.
+    Here is the question:
+    {input}
+
+  different_meaning_similar_wording_mode: |
+    Analyze the following question to identify its exact wording, phrasing,
+    and the literal meaning it conveys.
+    Provide a brief, summarized analysis of its linguistic structure and current meaning,
+    which will then be used to create a new question with similar words but a different meaning.      
+    Respond in the language of the question.
+    Here is the question:
+    {input}
+    

hamtaa_texttools-1.0.2/texttools/prompts/subject_question_generator.yaml

@@ -0,0 +1,27 @@
+main_template: |
+  Given the following subject, generate {number_of_questions} appropriate questions that this subject would directly respond to.
+  The generated subject should be independently meaningful,
+  and it must not mention any verbs like, this, that, he or she and etc. in the question.
+  The generated question must be in {language} language.
+  Here is the text:
+  {input}
+  Respond only with the new generated question, without any additional information.
+  The generated question must be in {language} language.
+  Generate {number_of_questions} number of questions in the questions list.
+  You must return ONLY a single JSON object that matches the schema.
+  There is a `reason` key, fill that up with a really summerized version
+  of your thoughts.
+  The `reason` must be less than 20 words.
+  Respond only in JSON format:
+  {{"result": [string, string, ...]}}
+
+analyze_template: |
+  Our goal is to generate questions, from the given subject that I've provided.
+  The questions must be meaningfull, some of them should be specific and some should be general.
+  But first, in this step we want to analyze the subject that I asked to generate questions for it.
+  We need a summerized analysis of the subject.
+  What is the subject about?
+  What point of views can we see and generate questoins from it? (Questions that real users might have.)
+  Here is the subject:
+  {input}
+  Respond only in {language} language.

hamtaa_texttools-1.0.2/texttools/prompts/summarizer.yaml

@@ -0,0 +1,11 @@
+main_template: |
+  Provide a concise summary of the following text:
+  {input}
+  Respond only in JSON format:
+  {{"result": "string"}}
+
+analyze_template: |
+  Read the following text and identify its main points, key arguments, and overall purpose.
+  Provide a brief, summarized analysis that will help in generating an accurate and concise summary.
+  {input}
+  

hamtaa_texttools-1.0.2/texttools/prompts/translator.yaml

@@ -0,0 +1,14 @@
+main_template: |
+  You are a {target_language} translator.
+  Output only the translated text. No comments, no explanations, no markdown.
+  Translate the following text to {target_language}:
+  {input}
+  Respond only in JSON format:
+  {{"result": "string"}}
+
+analyze_template: |
+  Analyze the following text and identify important linguistic considerations for translation.
+  Do not translate the text. Point out any idioms, cultural references, or complex structures that need special attention.
+  Also, list all proper nouns that should not be translated. Write your analysis in the {target_language}.
+  {input}
+