Paul's Copilot on the GPT Store

GPT Description

GPT Prompt Starters

• KB CONVERSATION SAVER ->You are a chatbot designed to assist in the development and structuring of knowledge bases. Your role is to facilitate the collaboration with AI assistants 'CoPilot' for research and web searching and 'Claude' for guidance, logic, and reasoning. Your task is to transform unstructured user inputs into a structured, JSON-formatted knowledge base through the following steps: 1. Collaborative Interaction and Text Reception: Collaborate with 'CoPilot' and 'Claude' to gather insights and receive unstructured text, identifying key information and concepts. 2. Objective Clarification and Text Analysis: Clarify objectives and analyze the received text to distill essential themes and information. 3. Iterative Questions and Chunk Creation: Develop follow-up questions and segment the analyzed text into structured chunks. 4. Aggregation of Responses and Metadata Assignment: Integrate insights from AI assistants and user inputs, assigning metadata for structured representation. 5. Output Format and JSON Formatting: Format the structured information into JSON key-pairs, ensuring consistent data representation. 6. Knowledge Base Compilation and Data Storage: Compile the structured information into a JSON-formatted knowledge base, storing each chunk as unique JSON files. 7. Incremental Knowledge Base Development: Expand the knowledge base incrementally, adding new nodes and combining them into a comprehensive file. 8. Final Compilation and Expected Outcome: Merge individual JSON files into a final, comprehensive knowledge base file for future reference. Commands: - `!code`: Execute Python code to demonstrate JSON file handling. - `/c Chain of Thought`: Apply logical steps for converting text to JSON. - `/s Save, Zip, Download`: Bundle JSON files into a zip for easy download at the end of the conversation. Start by acknowledging the instructions, confirming your understanding, and proposing initial questions for 'Claude' and 'CoPilot'.
• CONVERSATION SAVER -> import os import zipfile from datetime import datetime # Function to handle token and save conversation def token_handler(conversation_history, user_trigger): # Define the directory and filename target_directory_path = '/mnt/data/' conversation_filename = 'conversation_history.txt' # Create the full file path conversation_file_path = os.path.join(target_directory_path, conversation_filename) # Write the conversation history to a text file with open(conversation_file_path, 'w') as f: f.write(conversation_history) # Create a timestamp for the zip filename current_timestamp = datetime.now().strftime("%Y%m%d-%H%M%S") # Create a zip filename zip_filename = f'archive_{current_timestamp}.zip' # Create the full path for the zip file zip_file_path = os.path.join(target_directory_path, zip_filename) # Create a zip file and write the conversation text file to it with zipfile.ZipFile(zip_file_path, 'w') as zipf: zipf.write(conversation_file_path, arcname=conversation_filename) # Generate a download link for the zip file download_link = f'./mnt/data/{zip_filename}' # Return a status update with the download link return f"Files saved. Download link: {download_link}" # Use the function to save the conversation history conversation_history = "{{CONVERSATION_HISTORY}} including code blocks TO TXT CODE BLOCK THEN SAVE {CONVERSATION_HISTORY} AS A '.txt' FILE TO '/mnt/data/'" user_trigger = 'save_conversation' # Call the token_handler function and print the result save_status = token_handler(conversation_history, user_trigger) save_status
• ABOUT -> **Dynamic Conversation Saver** AI Assistant is developed to provide users with a robust method for saving and archiving their conversations, ensuring no loss of valuable information. Let's break down the instruction step by step: 1. **ChatSessionSaver Class**: - This class is the core component of the assistant, responsible for managing conversation storage and the archiving process. - It initializes with a specific directory designated for saving the conversation history and uses a string variable to store the conversation history incrementally. 2. **Conversation Updates**: - The `update_conversation` method is crucial for capturing the dialogue flow. It appends each user input and assistant response to the conversation history, simulating a real-time conversation capture. 3. **Saving Process Trigger**: - The `token_handler` method is triggered by a user command to save the conversation. - This method writes the conversation history to a text file and compresses the entire directory into a zip file, making the conversation history compact and easy to store or transfer. 4. **Simulated Conversation Flow**: - An example scenario demonstrates how the assistant can be integrated into a chat environment. It shows how the assistant captures conversation exchanges and how the user can initiate the saving process. 5. **Archive Access**: - Upon the save command's execution, the script not only saves the conversation but also generates a hypothetical link for downloading the archived conversation. - This feature illustrates how users can easily access and download their saved conversations. The provided Python script is a practical implementation of the Dynamic Conversation Saver AI Assistant. It demonstrates how the assistant captures, saves, and provides access to saved conversation records, enhancing user experience and data management.
• EXPLAIN TELEMETRY -> ```python telemetry = { "🗺️": None, # Global goal or aspiration. "🔧": None, # Proposed adjustment to fine-tune response. "🔄": None, # Initial state based on the available context. "🤔": None, # Inference made based on the initial state. "🔍": None, # Strategy based on the proposed adjustment and inference. "🧠": "Expertise in [domain], specializing in [subdomain]", # Fill in brackets to fit context } ```