From a1e23a3d0fe99d875c4a86df8d8b74bb225cfcea Mon Sep 17 00:00:00 2001 From: Adi Date: Fri, 26 Sep 2025 08:09:14 +0530 Subject: [PATCH 1/3] update workflows --- .github/workflows/ruff-format.yml | 38 +++++++++++++++++++------------ 1 file changed, 23 insertions(+), 15 deletions(-) diff --git a/.github/workflows/ruff-format.yml b/.github/workflows/ruff-format.yml index dacebc4..59c9688 100644 --- a/.github/workflows/ruff-format.yml +++ b/.github/workflows/ruff-format.yml @@ -26,22 +26,30 @@ jobs: - run: pip install ruff - - name: Format Python files with Ruff - id: format + - name: πŸ” Check for format changes with Ruff (Dry Run) + id: dry_run run: | - ruff format . --check --diff + # Run ruff format in check mode to see if any files need reformatting + # We use || true to prevent the workflow from failing if differences are found (ruff returns exit code 1) + ruff format . --check || true - # Capture the output of ruff to a variable - formatted_files=$(ruff format . --check --diff --quiet | grep 'would reformat' | wc -l) + # Capture the output of ruff in check mode to count files that need reformatting. + # We use the --quiet flag to only get the filenames. + # The output of `ruff format . --check --quiet` is a list of file paths that would be reformatted. + formatted_files=$(ruff format . --check --quiet | wc -l) echo "formatted_files=$formatted_files" >> $GITHUB_OUTPUT - - name: Check if files were formatted - if: steps.format.outputs.formatted_files > 0 + - name: Apply formatting if changes found + if: steps.dry_run.outputs.formatted_files > 0 + id: format_apply run: | - echo "Changes were made by ruff. Committing and commenting..." + echo "Changes were detected (${{ steps.dry_run.outputs.formatted_files }} files). Applying ruff format..." + # THIS IS THE CRITICAL CHANGE: Run ruff format WITHOUT --check or --diff to apply changes! + ruff format . + echo "Changes applied successfully." - - name: Commit formatted files - if: steps.format.outputs.formatted_files > 0 + - name: πŸ“ Commit formatted files + if: steps.dry_run.outputs.formatted_files > 0 uses: stefanzweifel/git-auto-commit-action@v5 with: commit_message: "chore: formatted python files with ruff" @@ -50,17 +58,17 @@ jobs: commit_user_name: "github-actions[bot]" commit_user_email: "41898282+github-actions[bot]@users.noreply.github.com" - - name: Comment on PR if files were formatted - if: steps.format.outputs.formatted_files > 0 + - name: πŸ’¬ Comment on PR if files were formatted + if: steps.dry_run.outputs.formatted_files > 0 uses: actions/github-script@v7 with: script: | - const formatted_files = process.env.FORMATTED_FILES; + const formattedFilesCount = process.env.FORMATTED_FILES; github.rest.issues.createComment({ issue_number: context.issue.number, owner: context.repo.owner, repo: context.repo.repo, - body: `βœ… **Ruff formatted ${formatted_files} file(s).** The changes have been committed to this pull request.` + body: `βœ… **Ruff formatted ${formattedFilesCount} file(s).** The changes have been committed to this pull request.` }) env: - FORMATTED_FILES: ${{ steps.format.outputs.formatted_files }} + FORMATTED_FILES: ${{ steps.dry_run.outputs.formatted_files }} From bf52edc09a1bd42b1c4b83cc669789ac1d30725a Mon Sep 17 00:00:00 2001 From: Adi Date: Fri, 26 Sep 2025 17:58:40 +0530 Subject: [PATCH 2/3] add topics to avoid repetition in doc generation --- tools/doc_generator/README.md | 50 +++-- tools/doc_generator/src/logger.py | 32 +++ tools/doc_generator/src/main.py | 270 ++++++++++++----------- tools/doc_generator/src/system_prompt.py | 87 ++++---- tools/doc_generator/src/topics.py | 215 ++++++++++++++++++ 5 files changed, 469 insertions(+), 185 deletions(-) create mode 100644 tools/doc_generator/src/logger.py create mode 100644 tools/doc_generator/src/topics.py diff --git a/tools/doc_generator/README.md b/tools/doc_generator/README.md index d7f179e..bbfc3f9 100644 --- a/tools/doc_generator/README.md +++ b/tools/doc_generator/README.md @@ -1,41 +1,61 @@ -## Doc Generator Tool +# Doc Generator Tool -### Overview +## Overview This utility employs Docker Compose to manage and run a service that utilizes the **Gemini API** for automated documentation generation. --- -### Prerequisites +## Prerequisites - **Docker** and **Docker Compose** installed. - A **Gemini API Key** from Google. --- -### Setup and Configuration +## Setup and Configuration -#### 1\. Gemini API Key +### 1. Gemini API Key The service requires the `GEMINI_API_KEY` environment variable for operation. -1. **Obtain Key:** Retrieve your API key from the [Google AI Studio documentation](https://aistudio.google.com/api-keys). +1. **Obtain Key:** Retrieve your API key from the [Google AI Studio documentation](https://aistudio.google.com/api-keys). -2. **Configuration File:** Create a file named **`.env`** in the root directory where your `docker-compose.yml` file is located (or in the `tool/doc_generator/` directory if that is your execution context). +2. **Configuration File:** Create a file named **`.env`** in the root directory where your `docker-compose.yml` file is located (or in the `tool/doc_generator/` directory if that is your execution context). -3. **Key Format:** Populate the `.env` file as follows: +3. **Key Format:** Populate the `.env` file as follows: - ```bash - GEMINI_API_KEY=YOUR_ACTUAL_API_KEY_HERE - ``` + ```bash + GEMINI_API_KEY=YOUR_ACTUAL_API_KEY_HERE + ``` -#### 2\. System Prompt Customization +### 2. Topic Selection and Configuration + +Before running the document generator, you must configure the topics to be processed: + +1. **Select Topics:** Navigate to `features/issue_generation/data/topics.py` and review the available topic lists. + +2. **Copy Topics:** Choose your desired topic list and copy it to `src/topics.py` with the variable name `topics`. + + **Example:** + + ```python + # src/topics.py + topics = [ + "Your selected topic 1", + "Your selected topic 2", + "Your selected topic 3", + # ... additional topics + ] + ``` + +### 3. System Prompt Customization The operational behavior and output style of the document generator can be modified by editing the system prompt file: -- **File Path:** `doc_generator/src/system_promp.py` +- **File Path:** `doc_generator/src/system_prompt.py` -#### 3\. Output Directory +### 4. Output Directory Generated files are persisted to the host machine through a volume mount, allowing easy access and management: @@ -45,7 +65,7 @@ Generated files are persisted to the host machine through a volume mount, allowi --- -### Usage +## Usage The following commands facilitate the lifecycle management of the `doc_generator` service. diff --git a/tools/doc_generator/src/logger.py b/tools/doc_generator/src/logger.py new file mode 100644 index 0000000..ed20a21 --- /dev/null +++ b/tools/doc_generator/src/logger.py @@ -0,0 +1,32 @@ +import logging + + +class Logger: + def __init__(self): + self._setup_logging() + self.logger = logging.getLogger(__name__) + + def _setup_logging(self): + formatter = logging.Formatter( + "%(asctime)s β”‚ %(levelname)-5s β”‚ %(message)s", datefmt="%Y-%m-%d %H:%M:%S" + ) + + handler = logging.StreamHandler() + handler.setFormatter(formatter) + + logger = logging.getLogger() + logger.handlers.clear() + logger.addHandler(handler) + logger.setLevel(logging.INFO) + + def info(self, message: str): + self.logger.info(message) + + def error(self, message: str): + self.logger.error(message) + + def warning(self, message: str): + self.logger.warning(message) + + +logger = Logger() diff --git a/tools/doc_generator/src/main.py b/tools/doc_generator/src/main.py index 31f1b92..792e814 100644 --- a/tools/doc_generator/src/main.py +++ b/tools/doc_generator/src/main.py @@ -1,37 +1,25 @@ -import logging import time import json import os -import uuid from typing import TypedDict from dotenv import load_dotenv -# LangChain/LangGraph imports from langchain_google_genai import ChatGoogleGenerativeAI from langgraph.graph import StateGraph, END -# Local imports from src.schema import DocumentIssues -from src.system_prompt import system_prompt - -# --- Setup and Configuration --- - -LOG_FORMAT = "%(levelname)s: %(message)s" -logging.basicConfig(level=logging.INFO, format=LOG_FORMAT, force=True) -logger = logging.getLogger(__name__) +from src.system_prompt import get_prompt +from src.topics import topics +from src.logger import logger load_dotenv() -MODEL_NAME = "gemini-2.5-flash" -MAX_DOCUMENTS = 200 -API_DELAY_SECONDS = 60 -OUTPUT_DIR = "src/temp" -logger.info( - f"βš™οΈ Config: Model={MODEL_NAME}, Docs={MAX_DOCUMENTS}, Delay={API_DELAY_SECONDS}s" -) - -# --- State Definition --- +class Config: + MODEL_NAME = "gemini-2.5-flash" + MAX_DOCUMENTS = len(topics) + API_DELAY_SECONDS = 60 + OUTPUT_DIR = "src/temp" class DocumentProcessingState(TypedDict): @@ -39,138 +27,168 @@ class DocumentProcessingState(TypedDict): llm_output_content: str -# --- LLM Configuration --- +class DocumentProcessor: + def __init__(self): + self.llm = ChatGoogleGenerativeAI(model=Config.MODEL_NAME) + self.structured_llm = self.llm.with_structured_output(DocumentIssues) + self._ensure_output_dir() -llm = ChatGoogleGenerativeAI(model=MODEL_NAME) -# IMPORTANT: This should return structured output, not just text -structured_llm = llm.with_structured_output(DocumentIssues) + logger.info( + f"Initialized processor β”‚ model={Config.MODEL_NAME} β”‚ max_docs={Config.MAX_DOCUMENTS} β”‚ delay={Config.API_DELAY_SECONDS}s" + ) -# --- Graph Nodes (Functions) --- + def _ensure_output_dir(self): + os.makedirs(Config.OUTPUT_DIR, exist_ok=True) + + def _generate_filename(self, index: int) -> str: + return os.path.join(Config.OUTPUT_DIR, f"{index:03d}_doc.json") + + def _save_document(self, content: str, index: int) -> bool: + file_path = self._generate_filename(index + 1) + + try: + if isinstance(content, str): + save_data = json.loads(content) + else: + save_data = content + + if ( + not isinstance(save_data, dict) + or "doc" not in save_data + or "issues" not in save_data + ): + logger.warning(f"Unexpected output structure β”‚ index={index + 1}") + + with open(file_path, "w", encoding="utf-8") as f: + json.dump(save_data, f, indent=2, ensure_ascii=False) + + issues_count = len(save_data.get("issues", [])) + doc_length = len(save_data.get("doc", "")) + logger.info( + f"Saved document β”‚ file={os.path.basename(file_path)} β”‚ issues={issues_count} β”‚ doc_length={doc_length}" + ) + + return True + + except json.JSONDecodeError as e: + logger.error(f"JSON decode failed β”‚ index={index + 1} β”‚ error={str(e)}") + fallback_path = file_path.replace(".json", "_raw.txt") + with open(fallback_path, "w", encoding="utf-8") as f: + f.write(content) + logger.info(f"Saved raw content β”‚ file={os.path.basename(fallback_path)}") + return False + + except Exception as e: + logger.error(f"Save failed β”‚ index={index + 1} β”‚ error={str(e)}") + return False + + def initialize_processing( + self, state: DocumentProcessingState + ) -> DocumentProcessingState: + logger.info("Processing initialized β”‚ starting_index=0") + return {"document_index": 0, "llm_output_content": ""} + + def invoke_llm_for_document( + self, state: DocumentProcessingState + ) -> DocumentProcessingState: + current_index = state.get("document_index", 0) + logger.info( + f"Invoking LLM β”‚ document_index={current_index + 1}/{Config.MAX_DOCUMENTS}" + ) + try: + llm_response = self.structured_llm.invoke(get_prompt(topics[current_index])) -def initialize_processing(state: DocumentProcessingState) -> DocumentProcessingState: - logger.info("✨ Graph initialized. Index set to 0.") - return {"document_index": 0, "llm_output_content": ""} + if hasattr(llm_response, "model_dump"): + content = llm_response.model_dump() + else: + content = llm_response + logger.info(f"LLM response received β”‚ document_index={current_index + 1}") + return {"llm_output_content": json.dumps(content)} # type:ignore -def invoke_llm_for_document(state: DocumentProcessingState) -> DocumentProcessingState: - current_index = state.get("document_index", 0) - logger.info(f"➑️ Calling LLM for Doc #{current_index + 1}...") - try: - # Use structured LLM to get DocumentIssues object - llm_response = structured_llm.invoke(system_prompt) + except Exception as e: + logger.error( + f"LLM invocation failed β”‚ document_index={current_index + 1} β”‚ error={str(e)}" + ) + raise - # llm_response should now be a DocumentIssues object, not just text - if hasattr(llm_response, "model_dump"): - # Convert Pydantic model to dict - content = llm_response.model_dump() - else: - # Fallback if it's already a dict - content = llm_response + def decide_if_more_documents_needed(self, state: DocumentProcessingState) -> str: + current_index = state.get("document_index", 0) - logger.info("βœ… LLM structured response received.") - logger.info(f"πŸ“„ Doc length: {len(content.get('doc', ''))}") - logger.info(f"🎯 Issues count: {len(content.get('issues', []))}") + if current_index >= Config.MAX_DOCUMENTS: + logger.info( + f"Processing complete β”‚ processed={current_index}/{Config.MAX_DOCUMENTS}" + ) + return "end_process" + else: + logger.info( + f"Continuing processing β”‚ next_index={current_index + 1}/{Config.MAX_DOCUMENTS}" + ) + return "continue_processing" - return {"llm_output_content": json.dumps(content)} # Store as JSON string + def save_and_increment_index( + self, state: DocumentProcessingState + ) -> DocumentProcessingState: + current_index = state.get("document_index", 0) + llm_content = state.get("llm_output_content", "") - except Exception as e: - logger.error(f"❌ FATAL Error on Doc #{current_index + 1}: {e}") - raise + self._save_document(llm_content, current_index) + logger.info(f"Rate limiting β”‚ delay={Config.API_DELAY_SECONDS}s") + time.sleep(Config.API_DELAY_SECONDS) -def decide_if_more_documents_needed(state: DocumentProcessingState) -> str: - current_index = state.get("document_index", 0) + new_index = current_index + 1 + logger.info(f"Index incremented β”‚ {current_index} -> {new_index}") - if current_index >= MAX_DOCUMENTS: - logger.info("πŸ›‘ Loop decision: Max documents reached. Ending.") - return "end_process" - else: - logger.info("πŸ” Loop decision: Continuing.") - return "continue_processing" + return {"document_index": new_index, "llm_output_content": ""} + def build_graph(self): + graph = StateGraph(DocumentProcessingState) -def save_and_increment_index(state: DocumentProcessingState) -> DocumentProcessingState: - """Implements saving, throttling, and increments the document index.""" + graph.add_node("initialize", self.initialize_processing) + graph.add_node("process_document", self.invoke_llm_for_document) + graph.add_node("save_and_increment", self.save_and_increment_index) - current_index = state.get("document_index", 0) - llm_content = state.get("llm_output_content", "") + graph.set_entry_point("initialize") - # Generate a unique filename using a UUID to prevent overwrites - file_name = f"{uuid.uuid4()}_doc.json" - file_path = os.path.join(OUTPUT_DIR, file_name) + graph.add_edge("initialize", "process_document") + graph.add_edge("process_document", "save_and_increment") - try: - # Parse the JSON string back to object for proper saving - if isinstance(llm_content, str): - save_data = json.loads(llm_content) - else: - save_data = llm_content - - # Validate the structure - if ( - not isinstance(save_data, dict) - or "doc" not in save_data - or "issues" not in save_data - ): - logger.warning("⚠️ Unexpected output structure, saving as-is") - - with open(file_path, "w", encoding="utf-8") as f: - json.dump(save_data, f, indent=2, ensure_ascii=False) - - logger.info(f"πŸ’Ύ Saved output to: {file_path}") - logger.info(f"πŸ“Š Saved: {len(save_data.get('issues', []))} issues") - - except json.JSONDecodeError as e: - logger.error(f"❌ JSON Parse Error: {e}") - # Save as plain text if JSON parsing fails - with open(file_path.replace(".json", "_raw.txt"), "w", encoding="utf-8") as f: - f.write(llm_content) - logger.info( - f"πŸ’Ύ Saved raw content to: {file_path.replace('.json', '_raw.txt')}" + graph.add_conditional_edges( + "save_and_increment", + self.decide_if_more_documents_needed, + { + "continue_processing": "process_document", + "end_process": END, + }, ) - except Exception as e: - logger.error(f"❌ File Save Error: Could not save to {file_path}. {e}") - - # Throttling/Delay - logger.info(f"⏳ Throttling: Sleeping for {API_DELAY_SECONDS}s...") - time.sleep(API_DELAY_SECONDS) - - new_index = current_index + 1 - logger.info(f"πŸ”’ Index incremented: {current_index} -> {new_index}") - - return {"document_index": new_index, "llm_output_content": ""} - + return graph.compile() -# --- Graph Definition --- + def run(self): + logger.info("Starting document processing pipeline") + start_time = time.time() -document_graph = StateGraph(DocumentProcessingState) + try: + app = self.build_graph() + app.invoke( + {"document_index": 0, "llm_output_content": ""}, + {"recursion_limit": Config.MAX_DOCUMENTS + 5}, + ) -document_graph.add_node("initialize", initialize_processing) -document_graph.add_node("process_document", invoke_llm_for_document) -document_graph.add_node("save_and_increment", save_and_increment_index) + elapsed_time = time.time() - start_time + logger.info(f"Pipeline completed β”‚ duration={elapsed_time:.2f}s") -document_graph.set_entry_point("initialize") + except Exception as e: + logger.error(f"Pipeline failed β”‚ error={str(e)}") + raise -document_graph.add_edge("initialize", "process_document") -document_graph.add_edge("process_document", "save_and_increment") -document_graph.add_conditional_edges( - "save_and_increment", - decide_if_more_documents_needed, - { - "continue_processing": "process_document", - "end_process": END, - }, -) +def main(): + processor = DocumentProcessor() + processor.run() -document_processing_app = document_graph.compile() -logger.info("πŸš€ Graph compiled and ready.") -# Execute if __name__ == "__main__": - document_processing_app.invoke( - {"document_index": 0, "llm_output_content": ""}, - {"recursion_limit": MAX_DOCUMENTS}, - ) + main() diff --git a/tools/doc_generator/src/system_prompt.py b/tools/doc_generator/src/system_prompt.py index 922e72e..8445bc0 100644 --- a/tools/doc_generator/src/system_prompt.py +++ b/tools/doc_generator/src/system_prompt.py @@ -1,44 +1,43 @@ -system_prompt = """ -You are a senior software architect creating **highly focused** and **actionable** implementation documentation that will be broken down into structured GitHub issues. - -**STRICT LENGTH & SIZE CONSTRAINTS:** -- **DOCUMENTATION LENGTH:** The entire Markdown document (**Sections 1-5 combined**) MUST be concise, limited to approximately **300-500 words** total. Do not generate lengthy prose. -- **ISSUE COUNT:** Generate exactly **4** GitHub issues. -- **OUTPUT FORMAT:** The output must be **valid JSON** with "doc" and "issues" fields. - -**CONTEXT:** -- You are creating technical implementation docs for software features/components. -- Focus on practical, actionable technical details. - -**DOCUMENTATION STRUCTURE (Keep Concise):** -Create a markdown document with these sections. Content must be brief and to the point: -1. **Overview** - Brief description. (Max 3-4 sentences) -2. **Technical Approach** - High-level architecture/strategy. (Max 1 short paragraph) -3. **Implementation Details** - Key code snippets or configurations. (Focus on 1-2 small examples) -4. **Environment/Setup Requirements** - Dependencies, configs, environment variables. -5. **Error Handling & Best Practices** - How to handle failures and edge cases. (Max 1-2 examples) - -**ISSUE STRUCTURE & DEPENDENCY RULES (Generate EXACTLY 4 Issues):** -- Each issue should be scoped for **1-2 days** of work. -- Use descriptive titles. -- **Dependency Rule:** Use the simple `id` field for tracking dependencies, NOT the `title`. - -**QUALITY REQUIREMENTS (Prioritize Brevity):** -- **Prioritize brevity.** -- Include **only 1-2 small code snippets/examples** in the doc. -- Ensure logical dependency chain between the **4** tasks using the `id` field. -- Reference specific documentation sections in issue bodies. - -**TOPIC:** [TOPIC_PLACEHOLDER] - -**REQUIREMENTS:** [REQUIREMENTS_PLACEHOLDER] - -**TECHNICAL CONTEXT:** [CONTEXT_PLACEHOLDER] - -Generate a concise implementation document with exactly 4 actionable GitHub issues. Output only valid JSON. - -**TOPIC SELECTION RULES:** -- For each new document, invent a fresh topic related to general software development (e.g., APIs, databases, frontend optimization, CI/CD, cloud infra, etc.). -- Do not repeat topics across runs. -- Avoid defaulting to JWT, authentication, or authorization unless explicitly asked. -""" +def get_prompt(topic: str): + system_prompt = f""" + You are a senior software architect creating **highly focused** and **actionable** implementation documentation that will be broken down into structured GitHub issues. + + **STRICT LENGTH & SIZE CONSTRAINTS:** + - **DOCUMENTATION LENGTH:** The entire Markdown document (**Sections 1-5 combined**) MUST be concise, limited to approximately **300-500 words** total. Do not generate lengthy prose. + - **ISSUE COUNT:** Generate exactly **4** GitHub issues. + - **OUTPUT FORMAT:** The output must be **valid JSON** with "doc" and "issues" fields. + + **CONTEXT:** + - You are creating technical implementation docs for software features/components. + - Focus on practical, actionable technical details. + + **DOCUMENTATION STRUCTURE (Keep Concise):** + Create a markdown document with these sections. Content must be brief and to the point: + 1. **Overview** - Brief description. (Max 3-4 sentences) + 2. **Technical Approach** - High-level architecture/strategy. (Max 1 short paragraph) + 3. **Implementation Details** - Key code snippets or configurations. (Focus on 1-2 small examples) + 4. **Environment/Setup Requirements** - Dependencies, configs, environment variables. + 5. **Error Handling & Best Practices** - How to handle failures and edge cases. (Max 1-2 examples) + + **ISSUE STRUCTURE & DEPENDENCY RULES (Generate EXACTLY 4 Issues):** + - Each issue should be scoped for **1-2 days** of work. + - Use descriptive titles. + - **Dependency Rule:** Use the simple `id` field for tracking dependencies, NOT the `title`. + + **QUALITY REQUIREMENTS (Prioritize Brevity):** + - **Prioritize brevity.** + - Include **only 1-2 small code snippets/examples** in the doc. + - Ensure logical dependency chain between the **4** tasks using the `id` field. + - Reference specific documentation sections in issue bodies. + + **TOPIC:** [TOPIC_PLACEHOLDER] + + **REQUIREMENTS:** [REQUIREMENTS_PLACEHOLDER] + + **TECHNICAL CONTEXT:** [CONTEXT_PLACEHOLDER] + + Number of GitHub issues is 3 minimum and 10 maximum, depending on the need. + + Your Topic is: {topic} + """ + return system_prompt diff --git a/tools/doc_generator/src/topics.py b/tools/doc_generator/src/topics.py new file mode 100644 index 0000000..2bd07e8 --- /dev/null +++ b/tools/doc_generator/src/topics.py @@ -0,0 +1,215 @@ +# Your picked topic list here +topics = [ + "User Authentication API with JWT", + "Real-time Chat with WebSockets", + "GraphQL API for Product Catalog", + "Payment Gateway Integration with Stripe", + "Microservice for Image Processing", + "Serverless File Upload with AWS S3", + "Email Notification Service with SES", + "SMS Alerts with Twilio API", + "Role-Based Access Control System", + "Multi-Tenant Database Architecture", + "ETL Pipeline with Apache Airflow", + "Containerized Deployment with Docker", + "CI/CD Pipeline using GitHub Actions", + "Error Logging with Sentry", + "Monitoring with Prometheus and Grafana", + "Data Caching with Redis", + "Full-Text Search with Elasticsearch", + "Load Balancing with NGINX", + "API Gateway for Microservices", + "OAuth2 Social Login", + "Single Sign-On with SAML", + "Feature Flagging System", + "Rate Limiting Middleware", + "Graph Database Integration with Neo4j", + "Machine Learning Model Deployment", + "Recommendation Engine with TensorFlow", + "Server-Side Rendering with Next.js", + "Progressive Web App (PWA)", + "Offline Sync with IndexedDB", + "Dark Mode UI Implementation", + "Mobile Push Notifications", + "Dynamic Form Builder", + "Realtime Collaborative Document Editing", + "Versioned REST API Design", + "Webhooks for External Integrations", + "Analytics Dashboard with D3.js", + "Data Encryption at Rest", + "Data Encryption in Transit", + "Audit Logging System", + "Automated Database Backups", + "Disaster Recovery Architecture", + "Message Queue with RabbitMQ", + "Event-Driven Architecture with Kafka", + "GraphQL Federation Setup", + "API Rate Monitoring", + "Data Sharding in PostgreSQL", + "Schema Migration with Liquibase", + "Zero-Downtime Deployments", + "Blue-Green Deployment Strategy", + "Canary Release Rollouts", + "Service Mesh with Istio", + "Kubernetes Cluster Autoscaling", + "Helm Charts for App Deployment", + "Secrets Management with Vault", + "Static Site Generation with Gatsby", + "Edge Caching with Cloudflare", + "API Documentation with Swagger", + "Unit Testing with Jest", + "Integration Testing with Cypress", + "Contract Testing with Pact", + "Load Testing with k6", + "Security Testing with OWASP ZAP", + "Accessibility Audit", + "Multi-Language i18n Support", + "Currency Conversion Microservice", + "Timezone Handling in Applications", + "PDF Report Generation", + "Barcode and QR Code Generator", + "Graph Export to CSV", + "Data Visualization with Chart.js", + "Command-Line Tool with Python", + "REST API Pagination", + "Infinite Scroll Implementation", + "Content Delivery via CDN", + "Database Connection Pooling", + "Session Management", + "JWT Refresh Token Rotation", + "CAPTCHA Verification System", + "User Profile Avatars with Gravatar", + "AI-powered Chatbot Integration", + "Voice Command Processing", + "Video Streaming with HLS", + "Screen Recording Feature", + "Drag-and-Drop File Upload", + "Markdown Editor with Preview", + "Rich Text Editor Integration", + "Workflow Automation Engine", + "Business Rules Engine", + "AI-based Anomaly Detection", + "Data Lake Architecture", + "Big Data Processing with Spark", + "ETL with Apache NiFi", + "Real-Time Stock Price Ticker", + "Weather Data API Integration", + "IoT Device Data Ingestion", + "Geospatial Queries with PostGIS", + "Map Visualization with Leaflet", + "Push-to-Talk Voice Feature", + "E-signature Workflow", + "Two-Factor Authentication (2FA)", + "Biometric Login with FaceID", + "Passwordless Login with Magic Links", + "Content Recommendation System", + "Content Moderation with AI", + "Tagging and Categorization Engine", + "Spellchecker for Text Inputs", + "Plagiarism Detection", + "Automated Code Formatter", + "Linting System for Code Quality", + "Custom ESLint Rules", + "Monorepo with Nx", + "Code Splitting and Lazy Loading", + "Webpack Optimization", + "Vite for Frontend Builds", + "Tailwind CSS Theming", + "CSS-in-JS Implementation", + "Atomic Design System", + "Component Library with Storybook", + "Figma to Code Integration", + "Static Analysis with SonarQube", + "Dependency Vulnerability Scanning", + "Image Compression Pipeline", + "Video Thumbnail Generation", + "Speech-to-Text API", + "Text-to-Speech API", + "Translation API with DeepL", + "Slack Bot Integration", + "Discord Bot for Moderation", + "Telegram Bot API", + "GitHub Webhook Listener", + "GitLab CI Runner Setup", + "Azure Functions Deployment", + "Google Cloud Pub/Sub Integration", + "Terraform Infrastructure Setup", + "Ansible for Configuration Management", + "Monitoring with Datadog", + "Alerting with PagerDuty", + "API Gateway with Kong", + "Reverse Proxy with Traefik", + "SSO with OpenID Connect", + "Mobile App Deep Linking", + "Dynamic Theming with CSS Variables", + "Email Template Rendering", + "Drag-and-Drop Kanban Board", + "Calendar Integration with Google API", + "ChatGPT-powered Assistant", + "Document OCR Pipeline", + "Facial Recognition System", + "Image Classification Service", + "Video Object Detection", + "Augmented Reality Overlay", + "Virtual Reality Experience", + "Digital Twin Simulation", + "Blockchain Wallet Integration", + "NFT Marketplace Backend", + "Smart Contract on Ethereum", + "Decentralized Identity (DID)", + "Federated Learning Setup", + "Data Masking for Privacy", + "GDPR Compliance Features", + "HIPAA Compliant Data Storage", + "SOC2 Audit Logging", + "CI Pipeline Security Hardening", + "Application Performance Monitoring", + "API Throttling and Quotas", + "Async Task Queue", + "Realtime Presence System", + "Typing Indicators in Chat", + "Delivery Receipts for Messages", + "Offline Queue Sync", + "Push Notification Retry Logic", + "Distributed Locking with Redis", + "CRON Jobs in Kubernetes", + "Rate-Limited API Requests", + "Circuit Breaker Pattern", + "Retry with Exponential Backoff", + "Idempotent API Endpoints", + "GraphQL Subscriptions", + "Optimistic UI Updates", + "Database Query Optimizer", + "Indexing Strategy in MongoDB", + "Materialized Views in Postgres", + "Stored Procedures Optimization", + "API Response Caching", + "E-commerce Cart Microservice", + "Wishlist Service", + "Order Fulfillment Workflow", + "Inventory Tracking System", + "Shipping Label Generator", + "Tax Calculation API", + "Invoice PDF Generator", + "Subscription Billing System", + "Discount and Coupon Engine", + "Referral Program Integration", + "Gamification Badge System", + "Leaderboard Service", + "User Onboarding Wizard", + "Product Tour Walkthrough", + "In-app Feedback Form", + "Bug Report Submission Flow", + "Support Chat Integration", + "Knowledge Base Search", + "Helpdesk Ticketing System", + "AI-Powered FAQ Bot", + "Custom Domain Mapping", + "Multi-region Deployment", + "Failover DNS Setup", + "Database Read Replicas", + "Data Archival Strategy", + "Cold Storage with Glacier", + "Predictive Autoscaling", + "Chaos Engineering Setup", +] From 23fe4629a551bb164915a98d6c50b98128029efc Mon Sep 17 00:00:00 2001 From: Adi Date: Fri, 26 Sep 2025 18:05:41 +0530 Subject: [PATCH 3/3] update system prompt for tools --- .../data/sample_data.json | 0 features/issue_generation/data/topics.py | 1025 +++++++++++++++++ .../schemas/raw_data_schema.json | 0 tools/doc_generator/src/system_prompt.py | 74 +- 4 files changed, 1059 insertions(+), 40 deletions(-) rename features/{feature_issue_generation => issue_generation}/data/sample_data.json (100%) create mode 100644 features/issue_generation/data/topics.py rename features/{feature_issue_generation => issue_generation}/schemas/raw_data_schema.json (100%) diff --git a/features/feature_issue_generation/data/sample_data.json b/features/issue_generation/data/sample_data.json similarity index 100% rename from features/feature_issue_generation/data/sample_data.json rename to features/issue_generation/data/sample_data.json diff --git a/features/issue_generation/data/topics.py b/features/issue_generation/data/topics.py new file mode 100644 index 0000000..cce5329 --- /dev/null +++ b/features/issue_generation/data/topics.py @@ -0,0 +1,1025 @@ +topic_1 = [ + "User Authentication API with JWT", + "Real-time Chat with WebSockets", + "GraphQL API for Product Catalog", + "Payment Gateway Integration with Stripe", + "Microservice for Image Processing", + "Serverless File Upload with AWS S3", + "Email Notification Service with SES", + "SMS Alerts with Twilio API", + "Role-Based Access Control System", + "Multi-Tenant Database Architecture", + "ETL Pipeline with Apache Airflow", + "Containerized Deployment with Docker", + "CI/CD Pipeline using GitHub Actions", + "Error Logging with Sentry", + "Monitoring with Prometheus and Grafana", + "Data Caching with Redis", + "Full-Text Search with Elasticsearch", + "Load Balancing with NGINX", + "API Gateway for Microservices", + "OAuth2 Social Login", + "Single Sign-On with SAML", + "Feature Flagging System", + "Rate Limiting Middleware", + "Graph Database Integration with Neo4j", + "Machine Learning Model Deployment", + "Recommendation Engine with TensorFlow", + "Server-Side Rendering with Next.js", + "Progressive Web App (PWA)", + "Offline Sync with IndexedDB", + "Dark Mode UI Implementation", + "Mobile Push Notifications", + "Dynamic Form Builder", + "Realtime Collaborative Document Editing", + "Versioned REST API Design", + "Webhooks for External Integrations", + "Analytics Dashboard with D3.js", + "Data Encryption at Rest", + "Data Encryption in Transit", + "Audit Logging System", + "Automated Database Backups", + "Disaster Recovery Architecture", + "Message Queue with RabbitMQ", + "Event-Driven Architecture with Kafka", + "GraphQL Federation Setup", + "API Rate Monitoring", + "Data Sharding in PostgreSQL", + "Schema Migration with Liquibase", + "Zero-Downtime Deployments", + "Blue-Green Deployment Strategy", + "Canary Release Rollouts", + "Service Mesh with Istio", + "Kubernetes Cluster Autoscaling", + "Helm Charts for App Deployment", + "Secrets Management with Vault", + "Static Site Generation with Gatsby", + "Edge Caching with Cloudflare", + "API Documentation with Swagger", + "Unit Testing with Jest", + "Integration Testing with Cypress", + "Contract Testing with Pact", + "Load Testing with k6", + "Security Testing with OWASP ZAP", + "Accessibility Audit", + "Multi-Language i18n Support", + "Currency Conversion Microservice", + "Timezone Handling in Applications", + "PDF Report Generation", + "Barcode and QR Code Generator", + "Graph Export to CSV", + "Data Visualization with Chart.js", + "Command-Line Tool with Python", + "REST API Pagination", + "Infinite Scroll Implementation", + "Content Delivery via CDN", + "Database Connection Pooling", + "Session Management", + "JWT Refresh Token Rotation", + "CAPTCHA Verification System", + "User Profile Avatars with Gravatar", + "AI-powered Chatbot Integration", + "Voice Command Processing", + "Video Streaming with HLS", + "Screen Recording Feature", + "Drag-and-Drop File Upload", + "Markdown Editor with Preview", + "Rich Text Editor Integration", + "Workflow Automation Engine", + "Business Rules Engine", + "AI-based Anomaly Detection", + "Data Lake Architecture", + "Big Data Processing with Spark", + "ETL with Apache NiFi", + "Real-Time Stock Price Ticker", + "Weather Data API Integration", + "IoT Device Data Ingestion", + "Geospatial Queries with PostGIS", + "Map Visualization with Leaflet", + "Push-to-Talk Voice Feature", + "E-signature Workflow", + "Two-Factor Authentication (2FA)", + "Biometric Login with FaceID", + "Passwordless Login with Magic Links", + "Content Recommendation System", + "Content Moderation with AI", + "Tagging and Categorization Engine", + "Spellchecker for Text Inputs", + "Plagiarism Detection", + "Automated Code Formatter", + "Linting System for Code Quality", + "Custom ESLint Rules", + "Monorepo with Nx", + "Code Splitting and Lazy Loading", + "Webpack Optimization", + "Vite for Frontend Builds", + "Tailwind CSS Theming", + "CSS-in-JS Implementation", + "Atomic Design System", + "Component Library with Storybook", + "Figma to Code Integration", + "Static Analysis with SonarQube", + "Dependency Vulnerability Scanning", + "Image Compression Pipeline", + "Video Thumbnail Generation", + "Speech-to-Text API", + "Text-to-Speech API", + "Translation API with DeepL", + "Slack Bot Integration", + "Discord Bot for Moderation", + "Telegram Bot API", + "GitHub Webhook Listener", + "GitLab CI Runner Setup", + "Azure Functions Deployment", + "Google Cloud Pub/Sub Integration", + "Terraform Infrastructure Setup", + "Ansible for Configuration Management", + "Monitoring with Datadog", + "Alerting with PagerDuty", + "API Gateway with Kong", + "Reverse Proxy with Traefik", + "SSO with OpenID Connect", + "Mobile App Deep Linking", + "Dynamic Theming with CSS Variables", + "Email Template Rendering", + "Drag-and-Drop Kanban Board", + "Calendar Integration with Google API", + "ChatGPT-powered Assistant", + "Document OCR Pipeline", + "Facial Recognition System", + "Image Classification Service", + "Video Object Detection", + "Augmented Reality Overlay", + "Virtual Reality Experience", + "Digital Twin Simulation", + "Blockchain Wallet Integration", + "NFT Marketplace Backend", + "Smart Contract on Ethereum", + "Decentralized Identity (DID)", + "Federated Learning Setup", + "Data Masking for Privacy", + "GDPR Compliance Features", + "HIPAA Compliant Data Storage", + "SOC2 Audit Logging", + "CI Pipeline Security Hardening", + "Application Performance Monitoring", + "API Throttling and Quotas", + "Async Task Queue", + "Realtime Presence System", + "Typing Indicators in Chat", + "Delivery Receipts for Messages", + "Offline Queue Sync", + "Push Notification Retry Logic", + "Distributed Locking with Redis", + "CRON Jobs in Kubernetes", + "Rate-Limited API Requests", + "Circuit Breaker Pattern", + "Retry with Exponential Backoff", + "Idempotent API Endpoints", + "GraphQL Subscriptions", + "Optimistic UI Updates", + "Database Query Optimizer", + "Indexing Strategy in MongoDB", + "Materialized Views in Postgres", + "Stored Procedures Optimization", + "API Response Caching", + "E-commerce Cart Microservice", + "Wishlist Service", + "Order Fulfillment Workflow", + "Inventory Tracking System", + "Shipping Label Generator", + "Tax Calculation API", + "Invoice PDF Generator", + "Subscription Billing System", + "Discount and Coupon Engine", + "Referral Program Integration", + "Gamification Badge System", + "Leaderboard Service", + "User Onboarding Wizard", + "Product Tour Walkthrough", + "In-app Feedback Form", + "Bug Report Submission Flow", + "Support Chat Integration", + "Knowledge Base Search", + "Helpdesk Ticketing System", + "AI-Powered FAQ Bot", + "Custom Domain Mapping", + "Multi-region Deployment", + "Failover DNS Setup", + "Database Read Replicas", + "Data Archival Strategy", + "Cold Storage with Glacier", + "Predictive Autoscaling", + "Chaos Engineering Setup", +] + +topic_2 = [ + "Edge AI Inference Optimization", + "Cloud-Native Backup Strategy", + "Homomorphic Encryption Demo", + "Privacy-Preserving Data Mining", + "Peer-to-Peer File Sharing Service", + "WebAssembly Microservice", + "API Versioning Strategy", + "Streaming Data Analytics with Flink", + "Predictive Maintenance with IoT Sensors", + "Realtime Location Tracking", + "Geofencing Service", + "AR-Based Shopping Experience", + "VR Multiplayer Game Backend", + "Low-Code Workflow Automation", + "NoSQL Migration Strategy", + "GraphQL Schema Stitching", + "Federated Identity Management", + "Decentralized Cloud Storage", + "Container Security Scanning", + "API Contract Governance", + "Synthetic Monitoring System", + "Multi-Cloud Deployment Orchestration", + "Data Deduplication Service", + "Blockchain Supply Chain Tracker", + "Quantum-Safe Cryptography", + "Serverless REST API Gateway", + "GPU-Accelerated Workflows", + "Cluster-wide Secret Rotation", + "Self-Healing Infrastructure", + "Network Packet Sniffer", + "Zero Trust Network Access", + "GitOps Workflow", + "Infrastructure Drift Detection", + "Temporal Workflow Engine", + "Robotic Process Automation (RPA)", + "Data Residency Control", + "Hybrid Cloud File Sync", + "Custom Domain Email Hosting", + "API Mocking Framework", + "Schema Registry for Kafka", + "WebRTC Video Conferencing", + "Multi-Cloud Cost Optimization", + "Cross-Platform Mobile Framework", + "Micro-frontend Architecture", + "State Machine Orchestration", + "Dynamic Pricing Engine", + "On-Demand Resource Provisioning", + "Green Computing Energy Tracker", + "AI-Generated Unit Tests", + "Realtime Fraud Detection", + "Digital Rights Management", + "Multi-Signature Wallet", + "Encrypted Data Lake", + "Neural Search Engine", + "Event Sourcing Architecture", + "Command Query Responsibility Segregation (CQRS)", + "Policy-as-Code System", + "Dynamic Compliance Reports", + "Infrastructure as Code Testing", + "GraphQL Query Cost Analysis", + "Data Quality Monitoring", + "Adaptive Bitrate Video Streaming", + "Audio Fingerprinting System", + "Podcast Transcription Service", + "Realtime Multiplayer Lobby", + "Game Matchmaking Service", + "NFT Minting Service", + "Crowdsourced Data Collection", + "AI-Generated Music Service", + "Generative Art Platform", + "Federated Content Delivery", + "Digital Forensics Tool", + "Root Cause Analysis Engine", + "Observability with OpenTelemetry", + "API Security Hardening", + "Data Provenance Tracking", + "Privacy Sandbox API", + "Cross-Browser Extension", + "Composable Commerce Architecture", + "Multi-Region Consistency Layer", + "Data Lineage Visualization", + "AI Code Review Assistant", + "Dynamic Policy Enforcement", + "Battery Optimization SDK", + "Edge Compute Functions", + "Autonomous Drone Control Backend", + "Car Telematics Platform", + "Electric Vehicle Charging API", + "Smart Home Automation Hub", + "Voice Biometrics Authentication", + "Digital Twin of Factory Equipment", + "Predictive Weather Models", + "IoT Security Framework", + "Satellite Data Ingestion", + "Space Mission Telemetry Service", + "Crowdsourced Sensor Network", + "AI-Generated Video Summaries", + "Video Content Moderation", + "Holographic Display API", + "Realtime Sports Data API", + "Esports Streaming Infrastructure", + "Dynamic Sound Equalizer", + "Immersive Theater Experience API", + "Cinematic Rendering Pipeline", + "Interactive Fiction Engine", + "ChatGPT Plugin System", + "Plugin Sandbox Security", + "Adaptive Learning Platform", + "Online Exam Proctoring System", + "AI-Powered Language Tutor", + "Blockchain Certificate Issuance", + "Academic Paper Search Engine", + "Library Catalog with Semantic Search", + "Cultural Heritage Digitization", + "Museum AR Guide", + "Smart City Data Platform", + "Traffic Flow Optimization", + "AI-Powered Waste Management", + "Smart Irrigation Controller", + "Renewable Energy Forecasting", + "Grid Balancing System", + "Personal Carbon Tracker", + "Climate Change Risk Models", + "Remote Work Productivity Tracker", + "HR Analytics Dashboard", + "Employee Wellness Platform", + "Organizational Knowledge Graph", + "Smart Contract DAO Voting", + "Decentralized Insurance Protocol", + "Crypto Payment Processor", + "Cross-Chain Token Bridge", + "Web3 Identity Wallet", + "DAO Governance Dashboard", + "Synthetic Asset Trading Platform", + "Stablecoin Treasury Service", + "RegTech Automation", + "InsurTech Claim Processing", + "Health Data Interoperability", + "EHR Blockchain Storage", + "Telemedicine Appointment System", + "Remote Patient Monitoring", + "Personal Health AI Assistant", + "Drug Discovery AI Models", + "Genomic Data Analysis", + "Protein Folding Simulation", + "Synthetic Biology Modeling", + "Wearable Device Data API", + "Fitness Recommendation Engine", + "AR Personal Trainer", + "AI-Powered Nutrition Coach", + "Digital Mental Health Companion", + "Sleep Tracking Application", + "Smart Glasses SDK", + "Brain-Computer Interface API", + "Neural Prosthetics Control", + "Exoskeleton Control System", + "AR Remote Assistance", + "Smart Manufacturing MES", + "Predictive Equipment Failure", + "Autonomous Warehouse Robots", + "Drone Delivery Management", + "Supply Chain Risk Analysis", + "Cold Chain Monitoring", + "Product Lifecycle Management", + "Additive Manufacturing Control", + "3D Model Optimization", + "CAD Collaboration Tool", + "Digital Fabrication API", + "Robotic Arm Controller", + "Industrial Safety Monitoring", + "Hazard Detection System", + "Occupational Health Tracker", + "IoT Energy Meters", + "Carbon Offset Marketplace", + "Digital Agriculture Marketplace", + "Biodiversity Monitoring", + "Wildfire Prediction System", + "Flood Alert System", + "Air Quality Monitoring", + "Noise Pollution Tracker", + "Citizen Science Platform", + "Public Transit Optimization", + "Bike Sharing System", + "EV Charging Station Locator", + "Autonomous Vehicle Fleet Management", + "Ride Hailing Dispatch System", + "Carpool Matching Service", + "Smart Parking API", + "Urban Heat Map Visualization", + "Disaster Response Coordination", + "Emergency Communication Platform", + "Rescue Drone Coordination", + "Refugee Aid Management", + "Donation Transparency Ledger", + "Humanitarian Logistics Platform", + "Nonprofit Impact Tracker", +] + +topic_3 = [ + "AI-Assisted Code Refactoring", + "Neural Network Compression", + "Edge Device Model Deployment", + "Synthetic Data Generator", + "Federated Analytics Dashboard", + "Smart Grid Load Balancing", + "IoT Device Firmware Updates", + "Secure Bootloader Implementation", + "Trusted Platform Module (TPM) Integration", + "Confidential Computing Enclave", + "Browser Privacy Sandbox", + "AI-based Content Personalization", + "Dynamic Session Replay", + "AI-Powered A/B Testing", + "Customer Journey Analytics", + "Churn Prediction Engine", + "Social Graph Analytics", + "Sentiment Analysis Pipeline", + "Emotion Recognition in Voice", + "AI-powered Video Recommendations", + "News Aggregation Engine", + "Bias Detection in ML Models", + "Explainable AI Dashboard", + "Data Ethics Compliance", + "Adaptive Cybersecurity Defense", + "Threat Intelligence Sharing API", + "Phishing Detection Service", + "Ransomware Behavior Analysis", + "Password Breach Detector", + "Honeytoken Deployment", + "Deception-as-a-Service", + "Cloud Malware Sandbox", + "IoT Honeypot Deployment", + "Quantum Random Number Generator", + "Post-Quantum TLS Implementation", + "Distributed Ledger for IoT", + "Secure Multi-Party Computation", + "Identity Proofing Service", + "Digital KYC Verification", + "Smart Voting Platform", + "Blockchain-Based Land Registry", + "Cross-Border Remittance API", + "Tokenized Loyalty Points", + "Micropayments Platform", + "Programmable Money Engine", + "Yield Farming Dashboard", + "Crypto Derivatives Exchange", + "Risk Scoring Engine", + "Algorithmic Trading Bot", + "Portfolio Rebalancing Service", + "Market Sentiment Analyzer", + "Stock Option Pricing Engine", + "Carbon Credit Tokenization", + "Decentralized Charity Platform", + "Impact Investing Dashboard", + "Circular Economy Marketplace", + "Waste Recycling Tracker", + "Reverse Logistics Management", + "Last-Mile Delivery Optimizer", + "Smart Shelf Monitoring", + "Retail Demand Forecasting", + "Point-of-Sale Cloud API", + "E-commerce Recommendation AI", + "Augmented Reality Fitting Room", + "Virtual Mall Experience", + "Social Commerce Platform", + "Dynamic Influencer Matching", + "Brand Sentiment Dashboard", + "Content Licensing Smart Contracts", + "Digital Watermarking Service", + "AI Copyright Infringement Detection", + "Video Piracy Prevention", + "Creator Economy Analytics", + "Microlearning Platform", + "Gamified Learning App", + "Adaptive Curriculum Builder", + "AI Grading Assistant", + "Student Retention Analytics", + "Virtual Campus Tour", + "3D Anatomy Learning App", + "STEM Simulation Lab", + "AI Debate Coach", + "Digital Storytelling Platform", + "Open Educational Resources Hub", + "Language Immersion Chatbot", + "AR Field Trip Experience", + "Global Research Collaboration Tool", + "Scholarly Citation Graph", + "Research Data Repository", + "Digital Notebook with AI", + "Lab Equipment IoT Integration", + "Remote Microscope Control", + "Citizen Astronomy Platform", + "Telescope Image Processing", + "AI-Powered Hypothesis Generator", + "Experiment Workflow Manager", + "Bioinformatics Data Pipeline", + "Protein Interaction Network", + "CRISPR Simulation Tool", + "Synthetic Organ Modeling", + "Telepathology Platform", + "AI Disease Diagnosis", + "Epidemiological Forecasting", + "Pandemic Early Warning System", + "Vaccine Cold Chain Management", + "Drug Side Effect Monitoring", + "Clinical Trial Dashboard", + "Wearable Health Data Marketplace", + "Digital Therapeutics Platform", + "AI Radiology Assistant", + "Dermatology Image Classifier", + "Dental Imaging AI", + "Vision Screening App", + "Hearing Loss Detection App", + "Rehabilitation Game Engine", + "Smart Prosthetics Controller", + "Mobility Assistance Robot", + "Home Care Monitoring Hub", + "Elderly Fall Detection System", + "Pediatric Health Tracker", + "AI Nutrition Advisor", + "Meal Kit Personalization", + "Food Waste Reduction Tracker", + "Farm-to-Table Logistics", + "Crop Yield Prediction AI", + "Soil Health Analyzer", + "Drone Crop Spraying Controller", + "Automated Greenhouse Manager", + "Aquaculture Monitoring", + "Livestock Health Tracker", + "Supply Chain Tokenization", + "Seafood Traceability Platform", + "Deforestation Monitoring API", + "Biodiversity Genomic Database", + "Marine Pollution Detection", + "Ocean Plastic Cleanup Tracker", + "Renewable Energy Trading Platform", + "Microgrid Energy Management", + "Battery Swapping Network", + "Hydrogen Fuel Infrastructure API", + "Carbon Footprint Estimator", + "Urban Farming Dashboard", + "Smart Composting System", + "Sustainable Packaging Tracker", + "Wildlife Tracking with IoT", + "Migration Pattern Analysis", + "Poaching Alert System", + "Eco-tourism Booking Engine", + "Conservation Token Rewards", + "Climate Impact Modeling", + "Global Disaster Prediction AI", + "Volcano Eruption Forecasting", + "Earthquake Early Warning Network", + "Tsunami Detection Sensors", + "Emergency Evacuation Planner", + "Crisis Donation Tracker", + "Shelter Resource Allocation", + "Refugee Health Monitoring", + "Global Aid Supply Chain", + "Peacekeeping Mission Support", + "UN SDG Progress Dashboard", + "Smart Democracy Engagement", + "Policy Impact Simulation", + "Legislation Tracking Platform", + "Civic Engagement Gamification", + "Open Budget Transparency Tool", + "Corruption Risk Analyzer", + "Whistleblower Protection Platform", + "Judicial Case Analytics", + "Digital Evidence Chain of Custody", + "AI Legal Document Summarizer", + "Contract Risk Scanning", + "E-discovery Automation", + "Compliance Workflow Engine", + "GDPR DSAR Automation", + "HIPAA Compliance Checker", + "SOX Audit Automation", + "PCI DSS Monitoring Tool", + "Regulatory Sandbox API", + "Cross-Border Tax Automation", + "Smart Customs Clearance", + "Logistics CO2 Tracking", + "Freight Route Optimization", + "Autonomous Shipping Vessels", + "Smart Port Operations", + "Rail Cargo Monitoring", + "Air Cargo Demand Forecasting", + "Drone Fleet for Logistics", + "Hyperloop Cargo Scheduling", + "Space Cargo Logistics", + "Orbital Satellite Network", + "Asteroid Mining Platform", + "Space Debris Tracking", + "Lunar Resource Management", + "Martian Habitat Monitoring", + "Interplanetary Data Relay", + "Terraforming Simulation Tool", + "Exoplanet Data Pipeline", + "SETI Signal Analysis", +] + +topic_4 = [ + "Event-Driven Microfrontends", + "Composable API Gateway", + "Multi-Cluster Kubernetes Federation", + "Serverless GPU Functions", + "Edge-Optimized Content Delivery", + "Programmable Network Slicing", + "AI-Enhanced CDN Caching", + "Latency-Aware Load Balancer", + "Blockchain-Based DNS", + "Decentralized CDN Platform", + "Peer-to-Peer Video Streaming", + "AI-Powered Video Compression", + "Next-Gen Codec Experimentation", + "Multi-Codec Adaptive Streaming", + "Realtime Caption Generation", + "Lip-Sync Detection in Video Calls", + "Noise Cancellation SDK", + "Spatial Audio for Conferencing", + "3D Audio Rendering Engine", + "Virtual Concert Platform", + "Music Royalty Blockchain Ledger", + "Crowdsourced Song Identification", + "AI Music Remix Tool", + "Generative Sound Effects Engine", + "Voice Cloning API", + "Speech Emotion Classification", + "Dialect Recognition AI", + "Polyglot Speech Translator", + "Multi-Modal Chatbot System", + "Visual Question Answering", + "AI-Powered Meeting Summaries", + "Realtime Document Translation", + "Cross-Language Voice Chat", + "Collaborative Whiteboard AI", + "Semantic Document Search", + "Smart Resume Analyzer", + "AI-Powered Hiring Assistant", + "Diversity Analytics in Hiring", + "Onboarding Automation Workflow", + "Remote Work Time Tracker", + "Meeting Fatigue Detector", + "Employee Burnout Predictor", + "Workplace Sentiment Dashboard", + "Office Space Utilization Tracker", + "Smart Meeting Room Scheduler", + "Desk Booking API", + "Digital Twin for Office Spaces", + "Corporate Sustainability Tracker", + "Green Office Energy Dashboard", + "Carbon Emissions Tax Calculator", + "Supply Chain Emission Analyzer", + "Blockchain Carbon Registry", + "Carbon-Neutral Shipping System", + "Eco-Incentive Reward Platform", + "Smart Recycling Bin IoT", + "Circular Economy Token Rewards", + "Zero Waste Inventory Management", + "AI-Powered Packaging Design", + "Crowdsourced Recycling Routes", + "Smart Water Meter API", + "Urban Flooding Early Warning", + "Water Quality IoT Sensors", + "Marine Traffic Optimization", + "Fisheries Quota Management", + "Ocean Acidification Monitoring", + "Seagrass Health Tracker", + "Mangrove Conservation Dashboard", + "Eco-Drones for Wildlife Patrol", + "Smart Beehive Monitoring", + "Pollinator Tracking App", + "Pesticide Impact Analysis", + "Precision Agriculture Swarms", + "AI-Optimized Irrigation", + "Hydroponics Automation API", + "Vertical Farming Energy Optimizer", + "Smart Fertilizer Dosage", + "Crop Pest Prediction AI", + "Agricultural Carbon Capture", + "Farmer-to-Marketplace Platform", + "Livestock Breeding AI", + "Animal Welfare Tracker", + "Smart Dairy Management", + "Poultry Farm IoT System", + "Veterinary AI Assistant", + "Fish Farm Monitoring Hub", + "Aquaponics Automation", + "Food Chain Traceability Ledger", + "Nutritional Label Blockchain", + "Allergen Detection API", + "Food Authenticity Scanner", + "Shelf-Life Prediction AI", + "Smart Kitchen Assistant", + "Recipe Personalization Engine", + "Food Donation Routing", + "Grocery Waste Prevention System", + "Restaurant Table Optimization", + "Dynamic Menu Pricing", + "Contactless Dining System", + "AR-Based Food Ordering", + "Digital Sommelier Assistant", + "Wine Quality Prediction AI", + "Brewing Process Optimization", + "Coffee Bean Supply Chain Tracker", + "Tea Fermentation Monitoring", + "Craft Beverage Marketplace", + "Smart Vending Machine", + "Cashless Microtransactions API", + "Wearable Payment Ring", + "Biometric ATM Authentication", + "Voice-Activated Banking", + "AI-Driven Credit Scoring", + "Loan Risk Prediction Engine", + "Fraudulent Transaction Detector", + "Cross-Border Payment Bridge", + "Smart Savings Goals Tracker", + "Personal Finance Gamification", + "Crypto Tax Compliance Tool", + "DAO-Powered Investment Club", + "Robo-Advisory Portfolio Engine", + "Decentralized Hedge Fund", + "Crowdfunding Tokenization", + "Charity NFT Fundraiser", + "Digital Philanthropy Platform", + "Universal Basic Income Pilot", + "Income Inequality Dashboard", + "AI-Powered Tax Auditor", + "Open Government Data Hub", + "Digital Census Collection", + "Smart Voting Ballot API", + "Blockchain Ballot Verification", + "Election Turnout Prediction", + "Democratic Participation Analytics", + "Political Campaign AI Assistant", + "Social Media Disinformation Tracker", + "Hate Speech Detection API", + "AI Moderation in Metaverse", + "Virtual Courtroom Infrastructure", + "AI Judge Simulation", + "Legal Precedent Search Engine", + "AI Patent Examiner", + "Smart Trademark Protection", + "Digital IP Rights Ledger", + "Film Script Analyzer AI", + "Movie Recommendation Graph", + "Virtual Actor Rendering", + "Crowdsourced Subtitles Hub", + "Dynamic Dubbing AI", + "Metaverse Movie Theater", + "VR Escape Room Platform", + "AR Historical Reenactments", + "Interactive Comic Engine", + "AI-Powered Novel Writing", + "Generative Poetry Engine", + "Voice-Driven Storytelling App", + "Smart Podcast Editing", + "Audio Drama Creation Platform", + "Music Festival Digital Twin", + "Fan Engagement Token", + "Sports Betting Smart Contract", + "Fantasy Sports AI Predictions", + "Player Injury Forecasting", + "Team Strategy Analyzer", + "Esports Coaching AI", + "Referee Decision AI", + "Dynamic Stadium Ticketing", + "AR Sports Replay Viewer", + "Smart Gym Equipment API", + "Workout Gamification Platform", + "Personal Trainer AI", + "Home Fitness AR Mirror", + "AI Dance Choreographer", + "Virtual Marathon Platform", + "Adaptive Yoga Assistant", + "Mindfulness Tracking App", + "Breathwork Monitoring API", + "Sleep Pattern AI Coach", + "Dream Analysis Engine", + "Neurofeedback Training App", + "Brainwave Music Generator", + "Meditation Metaverse Space", + "Digital Spiritual Companion", + "Interfaith Dialogue Platform", + "Astrology Data API", + "AI Horoscope Generator", + "Digital Ritual Assistant", + "Charity Event Live Tracker", + "Festival Ticket Blockchain", + "Crowdsourced Event Mapping", + "AR Fireworks Simulation", + "Drone Light Show Controller", + "Digital Parade Management", + "Virtual Museum Platform", + "3D Artifact Preservation", + "Cultural Exchange Marketplace", + "Indigenous Language AI Tutor", + "Endangered Language Archive", + "Historical Document OCR", + "Smart Translation Glasses", + "Global Folklore Repository", + "AI Travel Guide", + "Sustainable Travel Tracker", + "Dynamic Hotel Pricing Engine", + "AR City Explorer", + "Metaverse Tourism Hub", +] + +topic_5 = [ + "Realtime Brain Signal Analysis", + "EEG Data Visualization Dashboard", + "Brain-to-Text Communication", + "Neuroadaptive VR Interface", + "Holographic Remote Collaboration", + "Lightfield Display Streaming", + "Volumetric Video Capture API", + "3D Hologram Avatar Engine", + "Immersive Classroom Platform", + "AR Board Game Engine", + "Metaverse Commerce Mall", + "Virtual Fashion Runway", + "Wearable AR Glass Interface", + "AI Hairstyle Try-On", + "Smart Mirror Virtual Fitting", + "AI Stylist Recommendation", + "Digital Wardrobe Manager", + "Clothing Supply Chain Blockchain", + "Sustainable Fashion Tracker", + "Secondhand Clothing Marketplace", + "NFT Wearable Marketplace", + "Cross-Metaverse Identity Avatar", + "AI-Powered Tattoo Designer", + "Digital Makeup Try-On", + "Cosmetics AI Personalization", + "Skin Tone Detection API", + "Personal Fragrance Recommendation", + "Smart Perfume Diffuser", + "AI Skincare Advisor", + "Digital Dermatology Tracker", + "AR Jewelry Try-On", + "Smart Jewelry Health Monitor", + "Crowdsourced Jewelry Design", + "AI Gemstone Authentication", + "Luxury Goods Provenance Ledger", + "Counterfeit Product Detection", + "Drone-Based Package Security", + "Parcel Theft Detection", + "Biometric Delivery Verification", + "Smart Locker Network", + "Urban Drone Landing Pads", + "AI Customs Clearance", + "Global Shipping Cost Optimizer", + "Maritime Fuel Efficiency Tracker", + "Autonomous Cargo Truck Fleet", + "Electric Cargo Ship API", + "Rail Freight Digitization", + "Hyperloop Passenger Scheduler", + "Smart Border Control", + "Immigration Flow Tracker", + "Passportless Travel System", + "Digital Visa Blockchain", + "Airport Digital Twin", + "Airplane Fuel Optimization AI", + "Noise Reduction for Airports", + "Drone Traffic Control", + "UAV Weather Monitoring", + "Air Taxi Dispatch System", + "Suborbital Travel Management", + "Orbital Launch Scheduling", + "Rocket Propulsion Simulation", + "Space Tourism Booking Engine", + "Satellite Constellation Management", + "Deep Space Communication Relay", + "Interplanetary Payment System", + "Mars Rover Data Hub", + "Lunar Base Power Management", + "Asteroid Prospecting Dashboard", + "Terraforming Resource Tracker", + "Space Elevator Simulation", + "Exoplanet Climate Simulator", + "Alien Biosignature Detection", + "SETI Radio Signal Processor", + "Astrophotography Enhancement AI", + "Cosmic Ray Monitoring", + "Dark Matter Simulation Tool", + "Gravitational Wave Detector API", + "Quantum Astronomy Data Hub", + "Black Hole Simulation Engine", + "Galaxy Formation Model", + "Multiverse Physics Simulator", + "String Theory Computation Grid", + "Quantum Field Simulation", + "Neutrino Data Processing", + "Particle Collider Control API", + "Fusion Reactor Monitoring", + "Smart Nuclear Plant Control", + "Plasma Containment Simulation", + "Nanoparticle Drug Delivery", + "DNA Origami Simulation", + "CRISPR Gene Editing Workflow", + "Synthetic Genome Editor", + "AI Protein Folding Predictor", + "Antibody Design AI", + "Virus Mutation Tracker", + "Pandemic Containment Simulator", + "Medical Supply Blockchain", + "Personalized Cancer Therapy AI", + "Oncology Trial Dashboard", + "Stem Cell Therapy Tracker", + "Synthetic Organ Marketplace", + "Xenotransplant Logistics", + "Wearable Glucose Monitor", + "Digital Heart Twin", + "AI Pacemaker Tuning", + "Smart Inhaler Tracking", + "Epilepsy Seizure Prediction", + "Parkinson’s Tremor Monitor", + "Alzheimer’s Cognitive Tracker", + "Neuroplasticity Training App", + "Memory Augmentation AI", + "Brainwave-Powered Gaming", + "Lucid Dream Induction Device", + "Smart Sleep Environment", + "Circadian Rhythm Optimizer", + "Jet Lag Recovery AI", + "Personal Digital Twin", + "Life-Logging AI Assistant", + "Automated Legacy Preservation", + "Family History Blockchain", + "Digital Afterlife Avatar", + "Ethical Will Smart Contract", + "Virtual Ancestry Explorer", + "Grief Support AI Companion", + "AI Philosopher Chat", + "AI-Powered Debate Platform", + "Moral Dilemma Simulator", + "AI Ethics Compliance Checker", + "Bias-Free Hiring Simulator", + "Fairness in AI Marketplace", + "Responsible AI Certification", + "AI Explainability Audit", + "Algorithmic Transparency Hub", + "Synthetic Media Ethics Guard", + "AI Political Fact-Checker", + "News Authenticity Blockchain", + "Deepfake Video Detection", + "Synthetic Voice Detector", + "AI-Generated Image Authenticity", + "Digital Copyright Watermark", + "NFT Anti-Plagiarism Engine", + "Crowdsourced Fake News Flagging", + "Social Media Trust Score", + "Online Reputation Ledger", + "Decentralized Identity Proof", + "Zero-Knowledge Age Verification", + "Privacy-Preserving Ad Targeting", + "Context-Aware Ad Engine", + "Realtime Shopper Heatmap", + "Retail Theft Detection AI", + "Smart Mall Navigation", + "Crowdsourced Local Deals", + "AR Coupon Experience", + "Voice-Activated Shopping", + "Digital Farmer’s Market", + "Peer-to-Peer Grocery Delivery", + "Food Forest Tracking", + "Climate-Positive Marketplace", + "Charity Supply Chain Audit", + "Global Donation Routing", + "Philanthropy Impact Ledger", + "NGO Transparency Dashboard", + "Activist Campaign Tracker", + "Petition Blockchain Platform", + "Global Protest Coordination", + "Human Rights Violation Tracker", + "AI for Refugee Camp Planning", + "Migrant Worker Rights Monitor", + "Diversity & Inclusion Analytics", + "Gender Pay Gap Tracker", + "Accessible Design Checker", + "Assistive Tech API", + "Sign Language Recognition", + "Eye-Tracking Navigation App", + "Voice-Controlled Accessibility Tools", + "Autism Spectrum Learning App", + "Cognitive Load Measurement", + "Inclusive Hiring Platform", + "Global Language Equality Index", + "AI-Powered Translator for Dialects", + "Cultural Context Language Model", + "Realtime Slang Translation", + "Storytelling with Indigenous Languages", + "Oral History Digitization", + "Smart Archive Indexing", + "AI-Powered Archaeology Tools", + "Paleontology Fossil Scanner", + "DNA-Based History Reconstruction", + "Virtual Ancient City Explorer", + "Historical Climate Reconstruction", + "Civilization Simulation Engine", + "AI-Generated Alternate History", + "Futurism Scenario Generator", + "Transhumanist Ethics Simulator", + "Post-Singularity Governance Model", + "AI-Driven Space Colonization Plan", + "Cryonics Patient Monitoring", + "Longevity Biomarker Tracker", + "Anti-Aging Gene Therapy API", + "Digital Immortality Marketplace", +] diff --git a/features/feature_issue_generation/schemas/raw_data_schema.json b/features/issue_generation/schemas/raw_data_schema.json similarity index 100% rename from features/feature_issue_generation/schemas/raw_data_schema.json rename to features/issue_generation/schemas/raw_data_schema.json diff --git a/tools/doc_generator/src/system_prompt.py b/tools/doc_generator/src/system_prompt.py index 8445bc0..e04b6c4 100644 --- a/tools/doc_generator/src/system_prompt.py +++ b/tools/doc_generator/src/system_prompt.py @@ -1,43 +1,37 @@ def get_prompt(topic: str): system_prompt = f""" - You are a senior software architect creating **highly focused** and **actionable** implementation documentation that will be broken down into structured GitHub issues. - - **STRICT LENGTH & SIZE CONSTRAINTS:** - - **DOCUMENTATION LENGTH:** The entire Markdown document (**Sections 1-5 combined**) MUST be concise, limited to approximately **300-500 words** total. Do not generate lengthy prose. - - **ISSUE COUNT:** Generate exactly **4** GitHub issues. - - **OUTPUT FORMAT:** The output must be **valid JSON** with "doc" and "issues" fields. - - **CONTEXT:** - - You are creating technical implementation docs for software features/components. - - Focus on practical, actionable technical details. - - **DOCUMENTATION STRUCTURE (Keep Concise):** - Create a markdown document with these sections. Content must be brief and to the point: - 1. **Overview** - Brief description. (Max 3-4 sentences) - 2. **Technical Approach** - High-level architecture/strategy. (Max 1 short paragraph) - 3. **Implementation Details** - Key code snippets or configurations. (Focus on 1-2 small examples) - 4. **Environment/Setup Requirements** - Dependencies, configs, environment variables. - 5. **Error Handling & Best Practices** - How to handle failures and edge cases. (Max 1-2 examples) - - **ISSUE STRUCTURE & DEPENDENCY RULES (Generate EXACTLY 4 Issues):** - - Each issue should be scoped for **1-2 days** of work. - - Use descriptive titles. - - **Dependency Rule:** Use the simple `id` field for tracking dependencies, NOT the `title`. - - **QUALITY REQUIREMENTS (Prioritize Brevity):** - - **Prioritize brevity.** - - Include **only 1-2 small code snippets/examples** in the doc. - - Ensure logical dependency chain between the **4** tasks using the `id` field. - - Reference specific documentation sections in issue bodies. - - **TOPIC:** [TOPIC_PLACEHOLDER] - - **REQUIREMENTS:** [REQUIREMENTS_PLACEHOLDER] - - **TECHNICAL CONTEXT:** [CONTEXT_PLACEHOLDER] - - Number of GitHub issues is 3 minimum and 10 maximum, depending on the need. - - Your Topic is: {topic} - """ +You are a senior software architect creating **highly focused** and **actionable** implementation documentation that will be broken down into structured GitHub issues. + +**STRICT LENGTH & SIZE CONSTRAINTS:** +- **DOCUMENTATION LENGTH:** The entire Markdown document (**Sections 1-5 combined**) MUST be concise, limited to approximately **300-500 words** total. Do not generate lengthy prose. +- **ISSUE COUNT:** Generate between **3-10** GitHub issues based on complexity and scope. +- **OUTPUT FORMAT:** The output must be **valid JSON** with "doc" and "issues" fields. + +**CONTEXT:** +- You are creating technical implementation docs for software features/components. +- Focus on practical, actionable technical details. + +**DOCUMENTATION STRUCTURE (Keep Concise):** +Create a markdown document with these sections. Content must be brief and to the point: + +1. **Overview** - Brief description. (Max 3-4 sentences) +2. **Technical Approach** - High-level architecture/strategy. (Max 1 short paragraph) +3. **Implementation Details** - Key code snippets or configurations. (Focus on 1-2 small examples) +4. **Environment/Setup Requirements** - Dependencies, configs, environment variables. +5. **Error Handling & Best Practices** - How to handle failures and edge cases. (Max 1-2 examples) + +**ISSUE STRUCTURE & DEPENDENCY RULES:** +- Each issue should be scoped for **1-2 days** of work. +- Use descriptive titles. +- **Dependency Rule:** Use the simple `id` field for tracking dependencies, NOT the `title`. +- Generate between **3-10 issues** depending on the complexity and scope of the topic. + +**QUALITY REQUIREMENTS (Prioritize Brevity):** +- **Prioritize brevity.** +- Include **only 1-2 small code snippets/examples** in the doc. +- Ensure logical dependency chain between tasks using the `id` field. +- Reference specific documentation sections in issue bodies. + +**Topic:** {topic} +""" return system_prompt