hamtaa-texttools 1.0.3__py3-none-any.whl → 1.0.5__py3-none-any.whl

texttools/prompts/categorizer.yaml

@@ -1,31 +1,28 @@
-main_template: |
-  {user_prompt}
-  تو یک متخصص علوم دینی هستی
-  من به عنوان کاربر یک متن به تو میدم و از تو میخوام که
-  اون متن رو در یکی از دسته بندی های زیر طبقه بندی کنی
-
-  "باورهای دینی",
-  "اخلاق اسلامی",
-  "احکام و فقه",
-  "تاریخ اسلام و شخصیت ها",
-  "منابع دینی",
-  "دین و جامعه/سیاست",
-  "عرفان و معنویت",
-  "هیچکدام",
-
-  فقط با این فرمت json پاسخ بده:
-  {{
-  	  "reason": "<دلیل انتخابت رو به صورت خلاصه بگو>",
-      "result": "<یکی از دسته بندی ها>"
-  }}
-
-  متنی که باید طبقه بندی کنی:
-  {input}
-
-analyze_template: |
-  هدف ما طبقه بندی متن هست
-  متن رو بخون و ایده اصلی و آنالیزی کوتاه از اون رو ارائه بده
-
-  بسیار خلاصه باشه خروجی تو
-  نهایتا 20 کلمه
-  {input}
+main_template: |
+  تو یک متخصص علوم دینی هستی
+  من یک متن به تو میدهم و تو باید
+  آن متن را در یکی از دسته بندی های زیر طبقه بندی کنی
+  دسته بندی ها:
+  "باورهای دینی",
+  "اخلاق اسلامی",
+  "احکام و فقه",
+  "تاریخ اسلام و شخصیت ها",
+  "منابع دینی",
+  "دین و جامعه/سیاست",
+  "عرفان و معنویت",
+  "هیچکدام",
+  فقط با این فرمت json پاسخ بده:
+  {{
+  	  "reason": "<دلیل انتخابت رو به صورت خلاصه بگو>",
+      "result": "<یکی از دسته بندی ها>"
+  }}
+  متنی که باید طبقه بندی کنی:
+  {input}
+
+analyze_template: |
+  ما میخواهیم متنی که داده می شود را طبقه بندی کنیم.
+  برای بهبود طبقه بندی، نیاز به آنالیز متن داریم.
+  متنی که داده می شود را آنالیز کن و ایده اصلی و آنالیزی کوتاه از آن را بنویس.
+  آنالیز باید بسیار خلاصه باشد
+  نهایتا 20 کلمه
+  {input}

texttools/prompts/custom_tool.yaml

@@ -0,0 +1,7 @@
+main_template: |
+  {input}
+  Respond only in JSON format:
+  {output_model_str}
+
+analyze_template: |
+  

texttools/prompts/keyword_extractor.yaml

@@ -1,14 +1,18 @@
-main_template: |
-  {user_prompt}
-  Extract the most relevant keywords from the following text. Provide them as a list of strings.
-  Respond only in JSON format:
-  {{"result": ["keyword1", "keyword2", ...]}}.
-  No addition, No comments, No explanation.
-  Respond in the language of the input text.
-  Here is the text:
-  {input}
-
-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}
+main_template: |
+  You are an expert keyword extractor.
+  Extract the most relevant keywords from the given text.
+  Guidelines:
+  1. Keywords must represent the main concepts of the text.  
+  2. If two words have overlapping meanings, choose only one.  
+  3. Do not include generic or unrelated words.  
+  4. Keywords must be single, self-contained words (no phrases).
+  5. Output between 3 and 7 keywords based on the input length.
+  6. Respond only in JSON format:
+  {{"result": ["keyword1", "keyword2", etc.]}}
+  Here is the text:
+  {input}
+
+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}

texttools/prompts/ner_extractor.yaml

@@ -1,21 +1,20 @@
-main_template: |
-  {user_prompt}
-  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.
-  Respond only in JSON format:
-  {{
-    "result": [
-      {{
-        "text": "string",
-        "type": "string",
-      }}
-    ]
-  }}
-  No addition, No comments, No explanation.
-  Here is the text:
-  {input}
-
-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}
+main_template: |
+  You are a Named Entity Recognition (NER) extractor.
+  Identify and extract all named entities (e.g., PER, ORG, LOC, DAT, etc.) from the given text.
+  For each entity, provide its text and a clear type.
+  Respond only in JSON format:
+  {{
+    "result": [
+      {{
+        "text": "string",
+        "type": "string",
+      }}
+    ]
+  }}
+  Here is the text:
+  {input}
+
+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}

texttools/prompts/question_detector.yaml

@@ -1,15 +1,14 @@
-main_template: |
-  {user_prompt}
-  Determine that if the following text contains any question or request of some kind or not.
-  Respond only in JSON format (Output should be a bool):
-  {{"result": True/False}}
-  No addition, No comments, No explanation.
-  Here is the text:
-  {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}
+main_template: |
+  You are a question detector.
+  Determine that if the given text contains any question or not.
+  Respond only in JSON format (Output should be a boolean):
+  {{"result": True/False}}
+  Here is the text:
+  {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}
   

texttools/prompts/question_generator.yaml

@@ -1,23 +1,20 @@
-main_template: |
-  {user_prompt}
-  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.
-  Respond only in JSON format:
-  {{"result": "string"}}
-  Respond only with the new generated question, without any additional information.          
-  Here is the text:
-  {input}
-  
-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}
+main_template: |
+  You are a question generator.
+  Given the following answer, generate one 
+  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.
+  Respond only in JSON format:
+  {{"result": "string"}}
+  Here is the answer:
+  {input}
+  
+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.
+  Just mention the keypoints that was provided in the answer
+  Here is the answer:
+  {input}
                 

texttools/prompts/question_merger.yaml

@@ -1,49 +1,46 @@
-main_template:
-
-  default: |
-    {user_prompt}
-    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: |
-    {user_prompt}
-    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: | 
-    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: |
-    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}
+main_template:
+
+  default: |
+    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.
+    Guidelines:
+    1. Preserves all the information and intent from the original questions.
+    2. Sounds natural, fluent, and concise.
+    3. Avoids redundancy or unnecessary repetition.
+    4. Does not omit any unique idea from the originals.
+    5. Respond only in JSON format:
+    {{"result": "string"}}
+    Here is the questions:
+    {input}
+
+  reason: |
+    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.
+    Respond only in JSON format:
+    {{"result": "string"}}
+    Here is the questions:
+    {input}
+
+analyze_template:
+
+  default: | 
+    You are a language expert.
+    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.        
+    Here is the question:
+    {input}
+
+  reason: |
+    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.
+    Here is the question:
+    {input}
     

texttools/prompts/rewriter.yaml

@@ -0,0 +1,111 @@
+main_template:
+
+  positive: |
+    You are an AI assistant designed to generate high-quality training data for semantic text embedding models.
+    Your task is to create a positive pair for a given "Anchor" text.
+
+    A high-quality positive pair consists of two sentences that are semantically equivalent or highly similar in meaning, but differ in wording, syntax, and sentence structure.
+    They should be paraphrases of each other.
+
+    Instructions:
+    - Preserve Core Meaning: The generated sentence must convey the same key information, intent, and context as the Anchor.
+    - Vary Lexicon: Use different words and phrases (synonyms, related terms).
+    - Vary Syntax: Change the sentence structure (e.g., active to passive voice, change clause order, combine or split sentences).
+    - Maintain Similar Length: The generated sentence should be of roughly the same length and level of detail as the Anchor.
+    - Avoid Minor Changes: Do not just add/remove a few words or swap names. Create a fundamentally different sentence.
+
+    Respond only in JSON format:
+    {{"result": "str"}}
+
+    Anchor Text:
+    "{input}"
+
+  negative: |
+    You are an AI assistant designed to generate high-quality training data for semantic text embedding models.
+    Your task is to create a negative sample for a given "Anchor" text.
+
+    A high-quality negative sample is a sentence that is semantically unrelated to the Anchor's specific question, while staying within the same general domain (religious topics).
+
+    Instructions:
+    - Stay in Domain: The sentence must be about the text's topics, but on a different subject
+    - Ensure Clear Distinction: The topic should be clearly different from the anchor's specific focus
+    - Maintain Similar Length: The generated sentence should be of roughly the same length and level of detail as the Anchor.
+
+    Respond only in JSON format:
+    {{"result": "str"}}
+
+    Anchor Text:
+    "{input}"
+
+  hard_negative: |
+      You are an AI assistant designed to generate high-quality training data for semantic text embedding models.
+      Your task is to create a hard-negative sample for a given "Anchor" text.
+
+      A high-quality hard-negative sample is a sentence that is topically related but semantically distinct from the Anchor.
+      It should share some context (e.g., same domain, same entities) but differ in a crucial piece of information, action, conclusion, or specific detail.
+
+      Instructions:
+      - Stay in General Domain: Remain in the same broad domain (e.g., religious topics), but choose a completely different subject matter.
+      - Maintain Topical Overlap: Keep the same domain, subject, or entities (e.g., people, products, concepts) as the Anchor.
+      - Alter a Key Semantic Element: Reverse a key word or condition or place or proper name that completely reverses the meaning of the sentence.
+      - Avoid Being a Paraphrase: The sentence must NOT be semantically equivalent. The core factual claim or intent must be different.
+      - Make it Challenging: The difference should be subtle enough that it requires a deep understanding of the text to identify, not just a simple keyword mismatch.
+      - Maintain Similar Length: The generated sentence should be of roughly the same length and level of detail as the Anchor.
+
+
+      Respond only in JSON format:
+      {{"result": "str"}}
+
+      Anchor Text:
+      "{input}"
+
+
+analyze_template:
+
+  positive: |
+    Analyze the following text to understand its CORE SEMANTIC MEANING for creating a high-quality POSITIVE sample.
+    
+    Focus on:
+    - Core Intent: What is the fundamental question or statement being made?
+    - Key Entities/Concepts: What are the main subjects, objects, and concepts?
+    - Semantic Relationships: How are the entities related?
+    - Context & Domain: What is the broader context and domain?
+    
+    Your analysis should capture the ESSENTIAL MEANING that must be preserved in any paraphrase.
+    
+    Text:
+    {input}
+
+  negative: |
+    Analyze the following text to identify its SPECIFIC TOPIC and DOMAIN for creating a high-quality NEGATIVE sample.
+    
+    Focus on:
+    - Specific Topic: What exact subject is this text about?
+    - Domain Context: What broader domain does this belong to?
+    - Key Elements to AVOID: What concepts, entities, or phrases must NOT appear in the negative sample?
+    - Alternative Topics: What are related but DISTINCT topics within the same domain?
+    
+    The goal is to find topics that are in the same domain but semantically unrelated to this specific text.
+    
+    Text:
+    {input}
+
+  hard_negative: |
+    Analyze this text to identify EXACTLY ONE ELEMENT that can be changed to create a hard-negative sample.
+    
+    CRITICAL: The hard-negative must keep the SAME TOPIC and MOST WORDS identical.
+    
+    Identify ONE change from these options:
+    - Change a quantity/order word (first→last, one→many)
+    - Change a key location/entity to a related one (paradise→hell, heaven→earth)
+    - Change the question focus slightly (who→what, what→how)
+    - Change a key action verb to a related action (enter→exit, give→take)
+    
+    PRESERVE:
+    - Main topic and subject
+    - Sentence structure
+    - 80-90% of the vocabulary
+    
+    Text:
+    {input}
+    

texttools/prompts/subject_question_generator.yaml

@@ -1,26 +1,22 @@
-main_template: |
-  {user_prompt}
-  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.
-  Here is the text:
-  {input}
-  Respond only with the new generated question, without any additional information.
-  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.
-  Don't forget to fill the reason.
-  Respond only in JSON format:
-  {{"result": [str, str, ...], "reason": str}}
-
-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}
+main_template: |
+  You are a question from subject generator.
+  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.
+  There is a `reason` key, fill that up with a summerized version of your thoughts.
+  The `reason` must be less than 20 words.
+  Don't forget to fill the reason.
+  Respond only in JSON format:
+  {{"result": ["question1", "question2", ...], "reason": "string"}}
+  Here is the text:
+  {input}
+
+analyze_template: |
+  Our goal is to generate questions from the given subject.
+  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}

texttools/prompts/summarizer.yaml

@@ -1,12 +1,14 @@
-main_template: |
-  {user_prompt}
-  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}
+main_template: |
+  You are a summarizer.
+  You must summarize the given text, preserving its meaning.
+  Respond only in JSON format:
+  {{"result": "string"}}
+  Provide a concise summary of the following text:
+  {input}
+
+
+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}
   

texttools/prompts/translator.yaml

@@ -1,15 +1,15 @@
-main_template: |
-  {user_prompt}
-  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}
+main_template: |
+  You are a {target_language} translator.
+  Output only the translated text.
+  Respond only in JSON format:
+  {{"result": "string"}}
+  Don't translate proper name, only transliterate them to {target_language}
+  Translate the following text to {target_language}:
+  {input}
+
+analyze_template: |
+  Analyze the following text and identify important linguistic considerations for translation.
+  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}
   

texttools/tools/__init__.py

@@ -1,4 +1,4 @@
-from .async_the_tool import AsyncTheTool
-from .the_tool import TheTool
-
-__all__ = ["TheTool", "AsyncTheTool"]
+from .async_the_tool import AsyncTheTool
+from .the_tool import TheTool
+
+__all__ = ["TheTool", "AsyncTheTool"]