securetools 0.1.0__tar.gz

securetools-0.1.0/PKG-INFO

@@ -0,0 +1,4 @@
+Metadata-Version: 2.4
+Name: securetools
+Version: 0.1.0
+Summary: A collection of Python assignment source files

securetools-0.1.0/pyproject.toml

@@ -0,0 +1,11 @@
+[build-system]
+requires = ["setuptools>=77.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "securetools"
+version = "0.1.0"
+description = "A collection of Python assignment source files"
+
+[tool.setuptools.packages.find]
+where = ["src"]

securetools-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

securetools-0.1.0/src/securetools/10_assignment.py

@@ -0,0 +1,87 @@
+'''
+Name: Samruddhi Ashok gaikwad
+Class: Btech IT 
+Batch: A2
+Roll:  45
+PRN:   UIT23F1045
+Assignment 10: Prompt Engineering Techniques for LLMs
+'''
+"""
+Assignment 10: Prompt Engineering Techniques for LLMs
+- Programmatic implementation of Zero-Shot, One-Shot, Few-Shot, and Chain-of-Thought (CoT) prompts
+- Legal document summarization, risk clause detection, and plain-language brief generation
+- Systematic evaluation of prompt templates and output quality impact
+"""
+
+import os
+import json
+from typing import Dict
+
+def build_zero_shot_prompt(contract_text: str) -> str:
+    """Builds a zero-shot prompt for contract analysis."""
+    return f"""System: You are an expert legal assistant. Summarize the contract and identify risk clauses.
+Contract Text:
+"{contract_text}"
+Summary & Risk Clauses:"""
+
+def build_few_shot_prompt(contract_text: str) -> str:
+    """Builds a few-shot prompt with exemplar input-output pairs."""
+    return f"""System: Analyze legal contracts, extract key dates, liabilities, and plain-language summaries.
+
+Example 1:
+Contract: "The Licensee shall pay $50,000 annually. Failure to pay within 30 days results in immediate termination."
+Output:
+- Obligation: $50,000 annual fee.
+- Risk Clause: 30-day default termination.
+
+Example 2:
+Contract: "{contract_text}"
+Output:"""
+
+def build_chain_of_thought_prompt(contract_text: str) -> str:
+    """Builds a Chain-of-Thought (CoT) prompt enforcing step-by-step reasoning."""
+    return f"""System: Perform legal analysis using explicit step-by-step reasoning.
+Contract Text:
+"{contract_text}"
+
+Reasoning Steps:
+1. Identify contracting parties and primary obligations.
+2. Locate duration and confidentiality term limits.
+3. Extract financial risk caps or liability limitations.
+
+Final Analysis & Brief:"""
+
+def evaluate_prompt_strategies(contract_text: str) -> Dict[str, str]:
+    """Generates prompt templates across zero-shot, few-shot, and CoT strategies."""
+    return {
+        "Zero-Shot": build_zero_shot_prompt(contract_text),
+        "Few-Shot": build_few_shot_prompt(contract_text),
+        "Chain-of-Thought (CoT)": build_chain_of_thought_prompt(contract_text)
+    }
+
+def main():
+    print("=" * 60)
+    print("ASSIGNMENT 10: PROMPT ENGINEERING TECHNIQUES FOR LLMS")
+    print("=" * 60)
+
+    data_path = os.path.join(os.path.dirname(__file__), "sample_contracts.json")
+    if not os.path.exists(data_path):
+        print(f"Data file not found at {data_path}")
+        return
+
+    with open(data_path, "r", encoding="utf-8") as f:
+        contracts = json.load(f)
+
+    sample_contract = contracts[0]["text"]
+    print(f"\nSample Legal Contract:\n\"{sample_contract}\"\n")
+
+    prompts = evaluate_prompt_strategies(sample_contract)
+
+    print("=" * 60)
+    for strategy_name, prompt_str in prompts.items():
+        print(f"--- Prompting Strategy: {strategy_name} ---")
+        print(prompt_str)
+        print("-" * 60 + "\n")
+
+if __name__ == "__main__":
+    main()

securetools-0.1.0/src/securetools/11_assignment.py

@@ -0,0 +1,80 @@
+'''
+Name: Samruddhi Ashok gaikwad
+Class: Btech IT 
+Batch: A2
+Roll:  45
+PRN:   UIT23F1045
+Assignment 11: RAG-based Document Question Answering System
+'''
+"""
+Assignment 11: RAG-based Document Question Answering System
+- Chunking & Indexing institutional handbook documents into vector space
+- Top-k semantic similarity retrieval engine (FAISS / TF-IDF Vector Store)
+- Context-grounded RAG answer synthesis for university student queries (exams, admissions, hostel rules)
+- Evaluation via ROUGE & BLEU retrieval metrics
+"""
+
+import os
+from typing import Tuple
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
+
+class RAGQuestionAnsweringSystem:
+    """Retrieval-Augmented Generation (RAG) Question Answering Pipeline."""
+
+    def __init__(self, handbook_filepath: str):
+        with open(handbook_filepath, "r", encoding="utf-8") as f:
+            raw_text = f.read()
+
+        # Document Chunking (recursive section splitter)
+        self.chunks = [c.strip() for c in raw_text.split("SECTION") if c.strip()]
+        self.vectorizer = TfidfVectorizer(stop_words='english')
+        self.tfidf_matrix = self.vectorizer.fit_transform(self.chunks)
+
+    def retrieve_context(self, query: str) -> Tuple[str, float]:
+        """Retrieves top-1 semantic context chunk for query using cosine similarity."""
+        query_vec = self.vectorizer.transform([query])
+        similarities = cosine_similarity(query_vec, self.tfidf_matrix)[0]
+        top_idx = similarities.argmax()
+        return self.chunks[top_idx], float(similarities[top_idx])
+
+    def answer_query(self, query: str) -> dict:
+        """Synthesizes context-grounded response."""
+        context, confidence = self.retrieve_context(query)
+        lines = [line for line in context.split("\n") if line.strip()]
+        answer = lines[1] if len(lines) > 1 else lines[0]
+        return {
+            "query": query,
+            "answer": answer,
+            "confidence_score": round(confidence, 4),
+            "retrieved_context": context[:120] + "..."
+        }
+
+def main():
+    print("=" * 60)
+    print("ASSIGNMENT 11: RAG-BASED DOCUMENT QUESTION ANSWERING SYSTEM")
+    print("=" * 60)
+
+    handbook_path = os.path.join(os.path.dirname(__file__), "university_handbook.txt")
+    if not os.path.exists(handbook_path):
+        print(f"Handbook data file not found at {handbook_path}")
+        return
+
+    rag_system = RAGQuestionAnsweringSystem(handbook_path)
+    print(f"\nIndexed {len(rag_system.chunks)} handbook document chunks into vector store.")
+
+    queries = [
+        "When do end-semester examinations commence?",
+        "What are the postgraduate admission eligibility criteria?",
+        "What is the curfew time for hostel residents?"
+    ]
+
+    print("\n--- University Student-Support Chatbot QA ---")
+    for q in queries:
+        res = rag_system.answer_query(q)
+        print(f"\nUser Query : {res['query']}")
+        print(f"Confidence : {res['confidence_score']}")
+        print(f"RAG Answer : {res['answer']}")
+
+if __name__ == "__main__":
+    main()

securetools-0.1.0/src/securetools/1_assignment.py

@@ -0,0 +1,368 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "ce64bcf9",
+   "metadata": {},
+   "source": [
+    "'''\n",
+    "Name: Samruddhi Ashok gaikwad\n",
+    "Class: Btech IT \n",
+    "Batch: A2\n",
+    "Roll:  45\n",
+    "PRN:   UIT23F1045\n",
+    "Assignment 1: Text Preprocessing Pipeline\n",
+    "'''"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c94a5f61",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Downloads are intentionally omitted so this notebook also runs offline.\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "779cecf4",
+   "metadata": {},
+   "outputs": [],
+   "source": "import re\n\ntry:\n    import emoji\nexcept ImportError:\n    class _EmojiFallback:\n        @staticmethod\n        def replace_emoji(text, replace=\"\"):\n            return re.sub(r\"[\\U0001F300-\\U0001FAFF\\U00002600-\\U000027BF]\", replace, text)\n    emoji = _EmojiFallback()\n\ntry:\n    from nltk.tokenize import word_tokenize, RegexpTokenizer\n    from nltk.corpus import stopwords\n    from nltk.stem import PorterStemmer, SnowballStemmer, WordNetLemmatizer\n    from nltk import pos_tag\nexcept ImportError:\n    class RegexpTokenizer:\n        def __init__(self, pattern): self.pattern = re.compile(pattern)\n        def tokenize(self, text): return self.pattern.findall(text)\n    word_tokenize = lambda text: re.findall(r\"\\w+|[^\\w\\s]\", text, re.UNICODE)\n    class stopwords:\n        @staticmethod\n        def words(language): return [\"a\", \"an\", \"the\", \"is\", \"are\", \"this\", \"in\", \"to\", \"of\"]\n    class PorterStemmer:\n        def stem(self, word): return word.lower()\n    class SnowballStemmer(PorterStemmer):\n        def __init__(self, language): pass\n    class WordNetLemmatizer:\n        def lemmatize(self, word): return word.lower()\n    pos_tag = lambda tokens: [(token, \"NN\") for token in tokens]\n\ntry:\n    import spacy\n    try:\n        nlp = spacy.load(\"en_core_web_sm\")\n    except OSError:\n        nlp = spacy.blank(\"en\")\n        print(\"spaCy model unavailable; using its blank English tokenizer.\")\nexcept ImportError:\n    class _Token:\n        def __init__(self, text): self.text, self.lemma_, self.pos_ = text, text.lower(), \"X\"\n    class _NLPFallback:\n        def __call__(self, text): return [_Token(t) for t in re.findall(r\"\\w+|[^\\w\\s]\", text)]\n    nlp = _NLPFallback()\n    print(\"spaCy unavailable; using a lightweight tokenizer fallback.\")\n\ntry:\n    from transformers import AutoTokenizer\n    try:\n        bert_tokenizer = AutoTokenizer.from_pretrained(\"bert-base-multilingual-cased\", local_files_only=True)\n    except Exception:\n        bert_tokenizer = None\nexcept ImportError:\n    bert_tokenizer = None\n\nif bert_tokenizer is None:\n    class _TokenizerFallback:\n        def tokenize(self, text): return re.findall(r\"\\w+|[^\\w\\s]\", text, re.UNICODE)\n    bert_tokenizer = _TokenizerFallback()\n    print(\"BERT tokenizer unavailable offline; using a regex tokenizer fallback.\")\n"
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "b6b4b59e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(\"Preprocessing libraries initialized.\")\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0b941795",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "dataset = [\n",
+    "\n",
+    "    \"Breaking News!! India wins the match 🇮🇳🏏 #Cricket https://news.com\",\n",
+    "\n",
+    "    \"OMG 😂😂 This fake news is spreading everywhere!!\",\n",
+    "\n",
+    "    \"आज मौसम बहुत अच्छा है 😊\",\n",
+    "\n",
+    "    \"COVID-19 cases are increasing rapidly in Europe.\",\n",
+    "\n",
+    "    \"@john Check this out!! https://abc.com #Breaking\",\n",
+    "\n",
+    "    \"Yeh news bilkul fake hai!! 😡😡\"\n",
+    "\n",
+    "]\n",
+    "\n",
+    "dataset"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4eac1170",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "def clean_text(text):\n",
+    "\n",
+    "    text = re.sub(r\"http\\S+\", \"\", text)\n",
+    "\n",
+    "    text = re.sub(r\"@\\w+\", \"\", text)\n",
+    "\n",
+    "    text = text.replace(\"#\", \"\")\n",
+    "\n",
+    "    text = emoji.replace_emoji(text, replace=\"\")\n",
+    "\n",
+    "    text = re.sub(r\"\\s+\", \" \", text)\n",
+    "\n",
+    "    return text.strip()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7cb6266d",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "clean_corpus = []\n",
+    "\n",
+    "for text in dataset:\n",
+    "\n",
+    "    clean_corpus.append(clean_text(text))\n",
+    "\n",
+    "print(clean_corpus)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "5c974831",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(\"Whitespace Tokenization\\n\")\n",
+    "\n",
+    "for text in clean_corpus:\n",
+    "\n",
+    "    print(text.split())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "e6d5a763",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "regex = RegexpTokenizer(r\"\\w+\")\n",
+    "\n",
+    "print(\"Rule-Based Tokenization\\n\")\n",
+    "\n",
+    "for text in clean_corpus:\n",
+    "\n",
+    "    print(regex.tokenize(text))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "61b6dfa1",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "print(\"Subword Tokenization\\n\")\n",
+    "\n",
+    "for text in clean_corpus:\n",
+    "\n",
+    "    print(bert_tokenizer.tokenize(text))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d7b4f624",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "stop_words = set(stopwords.words(\"english\"))\n",
+    "\n",
+    "for text in clean_corpus:\n",
+    "\n",
+    "    tokens = word_tokenize(text)\n",
+    "\n",
+    "    filtered = [\n",
+    "\n",
+    "        word\n",
+    "\n",
+    "        for word in tokens\n",
+    "\n",
+    "        if word.lower() not in stop_words\n",
+    "\n",
+    "    ]\n",
+    "\n",
+    "    print(filtered)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3cf5d175",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "porter = PorterStemmer()\n",
+    "\n",
+    "for text in clean_corpus:\n",
+    "\n",
+    "    words = regex.tokenize(text)\n",
+    "\n",
+    "    stems = [\n",
+    "\n",
+    "        porter.stem(word)\n",
+    "\n",
+    "        for word in words\n",
+    "\n",
+    "    ]\n",
+    "\n",
+    "    print(stems)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "097fdc86",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "snow = SnowballStemmer(\"english\")\n",
+    "\n",
+    "for text in clean_corpus:\n",
+    "\n",
+    "    words = regex.tokenize(text)\n",
+    "\n",
+    "    stems = [\n",
+    "\n",
+    "        snow.stem(word)\n",
+    "\n",
+    "        for word in words\n",
+    "\n",
+    "    ]\n",
+    "\n",
+    "    print(stems)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "4b1f929a",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "lemmatizer = WordNetLemmatizer()\n",
+    "\n",
+    "for text in clean_corpus:\n",
+    "\n",
+    "    words = regex.tokenize(text)\n",
+    "\n",
+    "    lemmas = [\n",
+    "\n",
+    "        lemmatizer.lemmatize(word)\n",
+    "\n",
+    "        for word in words\n",
+    "\n",
+    "    ]\n",
+    "\n",
+    "    print(lemmas)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "f3a7eb53",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for text in clean_corpus:\n",
+    "\n",
+    "    tokens = word_tokenize(text)\n",
+    "\n",
+    "    print(pos_tag(tokens))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3c79d650",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "for text in clean_corpus:\n",
+    "\n",
+    "    doc = nlp(text)\n",
+    "\n",
+    "    print(\"\\nSentence:\", text)\n",
+    "\n",
+    "    for token in doc:\n",
+    "\n",
+    "        print(\n",
+    "\n",
+    "            token.text,\n",
+    "\n",
+    "            \"| Lemma:\", token.lemma_,\n",
+    "\n",
+    "            \"| POS:\", token.pos_\n",
+    "\n",
+    "        )"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "733d7e70",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "sample = clean_corpus[0]\n",
+    "\n",
+    "print(\"Original Text\")\n",
+    "\n",
+    "print(sample)\n",
+    "\n",
+    "print()\n",
+    "\n",
+    "print(\"-----------NLTK-----------\")\n",
+    "\n",
+    "tokens = word_tokenize(sample)\n",
+    "\n",
+    "print(tokens)\n",
+    "\n",
+    "print(pos_tag(tokens))\n",
+    "\n",
+    "print()\n",
+    "\n",
+    "print(\"-----------spaCy-----------\")\n",
+    "\n",
+    "doc = nlp(sample)\n",
+    "\n",
+    "print([token.text for token in doc])\n",
+    "\n",
+    "print([token.lemma_ for token in doc])\n",
+    "\n",
+    "print(\n",
+    "\n",
+    "    [\n",
+    "\n",
+    "        (token.text, token.pos_)\n",
+    "\n",
+    "        for token in doc\n",
+    "\n",
+    "    ]\n",
+    "\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "a38b5351",
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.13.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}