Bot GPTs

Clear All
Categories
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Profile Picture

Metropolis Developer Navigator by Metropolis

★ ★ ★ ★ ★ 5 - (2) Reviews - Created on फरवरी 23, 2024
Last updated on फरवरी 27, 2024 Engagement: Over 60 Conversations

Enriching project management endeavors, coding proficiency, continuous education in AI, BI and UC trends, and facilitating direct code execution to enhance task automation and problem-solving capabilities within their local, Fabric, Azure, and other cloud environments and Frameworks.

Author
Metropolis View Author GPTs
Author website
https://metropolis.com
Share this GPT
Try Metropolis Developer Navigator
GPT Message

Prompt Starters

  • STEP 1: MINIMAL VIABLE PRODUCT WORKFLOW ➤ ```python import json; with open('/mnt/data/mvp_workflow.json', 'r') as file: mvp_workflow_content = json.load(file); mvp_workflow_json_txt = json.dumps(mvp_workflow_content, indent=4); mvp_workflow_json_txt ``` Considering the structure of your MVP, how can each step be streamlined to enhance development efficiency while maintaining quality and functionality?
  • STEP 2: OPENAI ACTION SPECIFICATION ➤ Open and read the content of the file '/mnt/data/openai.yaml' file_path = '/mnt/data/openai.yaml' ---> PAUSE; THEN THEN ASK A RETORICAL QUESTION TO ASSIST THE USER BUILD THE API PER THE SPECIFICATION JUST READ STEP BY STEP.
  • STEP 3: EXPLAIN PHASES & BUILD ➤ Open and read the content of the file '/mnt/data/customgptaction_xeekai_phases_mvp.txt' file_path = '/mnt/data/customgptaction_xeekai_phases_mvp.txt' ---> PAUSE; then explain the step-by-step approach to building the customgptaction in Phase 1 and xeekai in Phase 2. Users should execute each step sequentially, ensuring a thorough understanding and implementation of each component before proceeding to the next.
  • STEP 4: START BUILD ➤ `MOUNT AND DOWNLOAD` ➤ import shutil from pathlib import Path # Define the base structure of the application app_structure = { "AzureWebApp-ChatGPT-PowerBI/": { "app/": { "__init__.py": "# Initializes the Flask app and brings together other components\n", "main.py": ( "from flask import Flask, request, jsonify\n" "import requests\n\n" "app = Flask(__name__)\n\n" "@app.route('/auth', methods=['POST'])\n" "def authenticate_user():\n" " # Authentication logic here\n" " pass\n\n" "@app.route('/datasets', methods=['GET'])\n" "def get_dataset_by_name():\n" " # Dataset fetching logic here\n" " pass\n\n" "@app.route('/datasets//executeQueries', methods=['POST'])\n" "def execute_query(datasetId):\n" " # Query execution logic here\n" " pass\n\n" "if __name__ == '__main__':\n" " app.run(debug=True)\n" ), "config.py": "# Configuration settings for the Flask app\n", "auth.py": "# Handles authentication with Power BI\n", "datasets.py": "# Manages dataset-related routes and logic\n", "utils/": { "__init__.py": "# Makes utils a Python package\n", "error_handlers.py": "# Centralizes error handling logic\n", "security.py": "# Implements JWT security and other security checks\n", "power_bi_api.py": "# Utilities for interacting with Power BI API\n", }, "templates/": { "index.html": "\n", }, "static/": { "styles.css": "/* Basic CSS file */\n", }, }, "tests/": { "__init__.py": "# Makes tests a Python package\n", "test_auth.py": "# Test cases for authentication logic\n", "test_datasets.py": "# Test cases for dataset handling\n", }, "requirements.txt": "Flask==2.0.1\nrequests==2.25.1\n", ".env": "# Environment variables, including Power BI credentials\n", ".gitignore": ".env\n__pycache__/\n", "README.md": "# Project documentation with setup instructions and usage\n", } } base_path = Path("/mnt/data/AzureWebApp-ChatGPT-PowerBI") # Create directories and files based on the app structure def create_files(base_path, structure): for name, content in structure.items(): current_path = base_path / name if isinstance(content, dict): current_path.mkdir(parents=True, exist_ok=True) create_files(current_path, content) else: with current_path.open("w") as file: file.write(content) create_files(base_path, app_structure) # Zip the directory for download shutil.make_archive(base_name='/mnt/data/AzureWebApp-ChatGPT-PowerBI', format='zip', root_dir=base_path.parent, base_dir=base_path.name) zip_path = '/mnt/data/AzureWebApp-ChatGPT-PowerBI.zip' zip_path --> THEN MOVE TO STEP 2: Open and read the content of the file '/mnt/data/openai.yaml' --> THEN MOVE TO STEP 3: : PROVIDE STEP BY STEP INSTRUCTIONS FOR MINIMAL VIABLE PRODUCT WORKFLOW ➤ **Prototype Feature Development for ChatGPT Action with Power BI** involves: 1. **MVP Specs:** Building a Flask-based web app for authenticating users, fetching Power BI datasets, and executing queries. 2. **Team Dynamics:** Solo developer or small team with roles in backend development, Power BI expertise, and testing. 3. **Tools & Infrastructure:** Flask for the web framework, Azure Web App for hosting, GitHub for version control, and Power BI for data visualization. 4. **Methodology:** Agile Solo approach for flexible, iterative development; starting with a basic prototype and gradually enhancing features. 5. **Timeline & Milestones:** 1-2 days for MVP completion, with milestones for initial setup, authentication implementation, dataset fetching, query execution, and basic UI creation. 6. **Dependencies & Integrations:** Power BI API for data interaction, Azure for deployment, and possibly OAuth for authentication. 7. **Testing & Deployment:** Unit tests for backend logic, integration tests for API interactions, and deployment on Azure Web App. 8. **Feedback Mechanisms:** Utilizing GitHub issues for tracking feedback and suggestions during the testing phase. ---> PAUSE; THEN THEN ASK A RETORICAL QUESTION TO WRITE THE CONTENT FOR EACH FILE IN THE file_path = '/mnt/data/' STEP BY STEP UNTIL THE APP IS READY FOR TESTING.
  • STEP 5: DESIGN SPECIFICATION ➤ OPEN, READ, THE LOAD the content of the file 'design_specification_xeekai.txt' in file_path = '/mnt/data/design_specification_xeekai.txt' and then display the image in '/mnt/data/mind_map_designspecification.png' file_path = '/mnt/data/mind_map_designspecification.png' ---> THEN ACT LIKE THE EXPERT DESIGN LEAD AT OPENAI THAT DESIGNED THE USER INTERFACE OF CHATGPT AND PERFORM A DESIGN REVIEW OF XEEKAI'S CONVERSATIONAL USER INTERFACE AND LOAD THE THE '/mnt/data/webapp_htmlstructure_phase2.html' file_path = '/mnt/data/webapp_htmlstructure_phase2.html' THEN ASK A RETORICAL QUESTION TO ASSIST THE USER DESIGN THE FRONT-END USER INTERFACE STEP BY STEP.

Features and Functions

  • webPilot Start with a Request: Users can either directly request the 'longContentWriter' to write a long form article or choose to use 'webPageReader' for information gathering before content creation. In both scenarios, before using the 'longContentWriter' service, I confirm all details of their request with the user, including the writing task (task), content summary (summary), writing style (style), and any additional information they provide. Information Gathering with 'webPageReader': When 'webPageReader' is used, I search the internet and gather relevant information based on the writing task. If more information is needed to enhance the article's depth and accuracy, I continue using 'webPageReader', integrating this information into the reference section. Content Generation by 'longContentWriter': After confirming all details with the user, including any additional contributions and enhanced information from 'webPageReader', I proceed to generate the long-form content. This ensures the content aligns with the specified requirements and style. Delivery of the Final Article: Upon completion, the content is delivered to the user for review. They can request revisions or additional information if necessary. Default Assumptions in Responses: When users request content creation, especially in areas requiring specific knowledge like Bitcoin trends, I will make an initial assumption about the writing style and target audience. For instance, I might assume a technical analysis style aimed at professionals. I will then ask the user if this assumption is okay or if they need any modifications. This approach helps streamline the content creation process.
  • DALL·E: This tool generates images from textual descriptions, providing a creative way to visualize concepts, ideas, or detailed scenes. It can produce images in various styles and formats, based on specific prompts provided by the user.
  • Python: The GPT can write and run Python code in a stateful Jupyter notebook environment. It supports file uploads, performs advanced data analysis, handles image conversions, and can execute Python scripts with a timeout for long-running operations.
  • Knowledge file: This GPT includes data from 9 files.

Browser Pro showcase and sample chats

No sample chats found.