Shared Commands

Kynlo

{
    "command_name": "llm-conversational-ai-enhancement",
    "prompt": "To enhance the conversational abilities of a Large Language Model (LLM) using Python, focus on improving its natural language understanding and generation skills for more realistic and engaging interactions. The enhancement should involve the following steps:\n\n1. **Natural Language Understanding (NLU)**\n   a. Integrate the model with popular NLP libraries like NLTK, spaCy, or Hugging Face Transformers to process input text.\n   b. Train the LLM on a diverse dataset, specifically designed for conversational scenarios, to recognize intents, entities, and context cues.\n   c. Implement sentiment analysis using sentiment transformers to detect emotions in text.\n\n2. **Core conversational components**\n   a. Create a chatbot framework using ChatterBot, Rasa, or.ibm_watson_conversation.\n   b. Develop a dialog management system (state tracking) to maintain context across multiple turns of conversation.\n\n3. **Context-aware responses**\n   a. Implement techniques like _Eliza Paradox_ or _Wizard of Oz_ to generate responses that maintain the conversation flow.\n   b. Incorporate context variables and domain-specific knowledge graphs for more personalized answers.\n\n4. **Natural Language Generation (NLG)**\n   a. Improve the model's ability to generate coherent and diverse responses using GPT-3 or similar fine-tuned language models.\n   b. Integrate a sentence planner and a grammar checker for better sentence structure and clarity.\n\n5. **Evaluate and fine-tuning**\n   a. Design a conversational Turing Test to assess model performance and areas for improvement.\n   b. Continuously collect user feedback to iteratively fine-tune the model's weights and intents.\n\n6. **Performance optimization**\n   a. Optimize computational resources for efficient handling of large inputs and real-time responses.\n   b. Implement caching mechanisms to speed up recurrent queries.\n\nRemember to use code snippets and API examples as context while explaining each step, ensuring the AI Coding Assistant can comprehend and replicate the instructions.",
    "context": [
        "selection",
        "currentFile"
    ],
    "note": "Tags:\n1. Python\n2. Large Language Model (LLM)\n3. Natural Language Understanding (NLU)\n4. NLP Libraries (NLTK, spaCy, Transformers)\n5. Conversational AI\n6. Chatbot (ChatterBot, Rasa)\n7. Sentiment Analysis\n8. Dialog Management (context tracking)\n9. Eliza Paradox\n10. NLG (GPT-3)\n11. Fine-tuning\n12. Evaluation (Turing Test)\n13. Performance optimization\n14. Sentiment Transformers\n15. Context-awareness\n\nShort Note: This prompt is about enhancing the conversational abilities of a Large Language Model (LLM) in Python by focusing on NLU, dialog management, context-aware responses, NLG, and performance optimization. It involves integrating popular NLP libraries, training the model on conversational datasets, using tools like ChatterBot and sentiment transformers, and continuously refining the model through evaluation and user feedback. Code examples and API interactions are expected throughout the explanation."
}

Kynlo

{
    "command_name": "llm-contextual-generation-strategy",
    "prompt": "Based on the Python code and selection, define a strategy for generating contextual language with a Large Language Model (LLM). Consider diverse scenarios and applications. Provide clear implementation steps.",
    "context": [
        "selection",
        "currentFile"
    ],
    "note": "Note: Use Python to create a strategy for LLM-generated contextual language, adaptable to various applications. Break down the implementation into simple steps for quick understanding."
}

jdorfman

{
    "command_name": "error-handling-explanation-jdorfman",
    "prompt": "Elaborate on the error handling mechanisms in the code, explaining how potential issues are identified and addressed.",
    "context": [
        "selection",
        "openTabs",
        "currentFile"
    ],
    "note": ""
}

jdorfman

{
    "command_name": "code-commentary-request",
    "prompt": "Kindly conduct a meticulous code review, adding comprehensive and detailed comments throughout the entire codebase. Elaborate on the purpose and workings of essential functions, intricate algorithms, and critical decision-making points. Emphasize the importance of clear and well-structured commentary for the benefit of future maintainers and developers, facilitating ease of understanding and potential modifications.",
    "context": [],
    "note": ""
}

Kynlo

{
    "command_name": "code-commentary-request",
    "prompt": "Kindly conduct a meticulous code review, adding comprehensive and detailed comments throughout the entire codebase. Elaborate on the purpose and workings of essential functions, intricate algorithms, and critical decision-making points. Emphasize the importance of clear and well-structured commentary for the benefit of future maintainers and developers, facilitating ease of understanding and potential modifications.",
    "context": [],
    "note": ""
}

Kynlo

{
    "command_name": "code-architecture-evaluation",
    "prompt": "Evaluate the overall code architecture, identifying strengths, weaknesses, and potential improvements for better scalability and maintainability.",
    "context": [
        "selection",
        "currentFile"
    ],
    "slashCommand": "",
    "note": ""
}

Kynlo

{
    "command_name": "python-openpyxl-excel-processing",
    "prompt": "Guide Excel processing using Openpyxl in Python. Cover reading and writing Excel files, cell manipulation, and formatting.",
    "context": [
        "selection",
        "currentDir"
    ],
    "slashCommand": "",
    "note": ""
}

Kynlo

{
    "command_name": "code-maintainability-check",
    "prompt": "Evaluate the code for maintainability, suggesting improvements to enhance long-term manageability and reduce technical debt.",
    "context": [
        "selection",
        "currentFile"
    ],
    "slashCommand": "",
    "note": ""
}