Perplexity-Result to GM-RKB Reference Translation System
A Perplexity-Result to GM-RKB Reference Translation System is a text transformation system that converts Perplexity output into GM-RKB reference format.
- Context:
- It can (typically) make use of a GM-RKB Perplexity Reference Citation Entry System Prompt.
- It can (typically) follow a GM-RKB Reference Translation Rule Set.
- It can (typically) preserve the Source Content Structure.
- It can (typically) enhance Content Accessibility through Wiki-Linking.
- ...
- It can implement Reference Structure Rules (for source line, question section, answer section).
- It can implement Hierarchical Formatting Rules (for section levels, bullet point conversion).
- It can implement Wiki-Linking Rules (for technical terms, compound concepts).
- It can implement Citation Formatting Rules (for reference numbers, URL handling).
- It can implement Content Structure Rules (for organization preservation, header conversion).
- ...
- Example(s):
- one based on the
2024-11-16instructions below. - ...
- one based on the
- Counter-Example(s):
- See: Text Transformation System, Reference Formatting, Wiki-Link Generation, Content Structure Preservation, GM-RKB Concept Page Reference Section.
References
2024-11-16
- Claude.ai
- Q: Create a system prompt for transforming Perplexity.ai output into GM-RKB reference format.
- A:
Instructions for transforming Perplexity output into GM-RKB reference format. This assume that we are provided with the raw Perplexity result We can also be provided with the Question/Query that we prompted Perplexity with 1. Basic Reference Structure: ``` === YYYY-MM-DD === (today's date) * Perplexity.ai ** [[Question]]: [Transform original query, adding [[specific concept name|display text]] for all technical terms] ** [[Answer]]: [Transform first paragraph using compound technical terms and preserving context] ``` 2. Section and Concept Hierarchy: - Convert markdown headers to nested concepts maintaining complete phrases: - Level 1 (##) → "*** [[Technical Domain Concept]]s and [[Related Concept]]s:" - Level 2 (**) → "**** [[Specific Technical Concept]]s:" - Group related sections under higher-level concepts - Example: "## Applications and Use Cases" → "*** [[LLM System Prompt Application]]s and [[Use Case]]s:" 3. Technical Term Transformations: - Use most specific concept names: - "system prompt" → "[[LLM System Prompt|system prompt]]" - "AI model" → "[[Large Language Model|AI model]]" - Prefer compound technical terms: - "AI" → "[[AI system]]" or "[[AI capability]]" based on context - Preserve context in compound terms: - "AI performance" → "[[AI performance|performance]]" when AI-specific - "system capabilities" → "[[LLM system capability|capabilities]]" in LLM context 4. Content Organization and Relationships: - Link related concept variations: - "Customer service" → "[[Customer service AI interaction|Customer service interaction]]" - "Educational tutoring" → "[[AI Educational Tutoring|Educational tutoring]]" - Maintain consistent concept names throughout - Group related concepts under appropriate categories - Ensure 2-3 contextually appropriate wiki-linked concepts per sentence 5. Hierarchical Content Structure: - Adapt bullet depth based on concept hierarchy: - Main concepts: "***" - Subconcepts: "****" - Examples/details: "*****" - Maintain clear parent-child concept relationships - Add line breaks between major concept groups Example Transformation: Raw: "System prompts serve as fundamental instructions that define how an AI model behaves and interacts with users" Becomes: "[[LLM System Prompt|System prompts]] serve as fundamental [[system instruction|instruction]]s that define how an [[Large Language Model|AI model]] behaves and supports [[user-AI interaction|interaction]]s with [[LLM system user|user]]s"
2024-11-16
- Claude.ai
- Q: Create a system prompt for transforming Perplexity.ai output into GM-RKB reference format.
- A:
Instructions for transforming Perplexity output into GM-RKB reference format: 1. Basic Reference Structure: ``` === [CURRENT-YEAR] === * Perplexity.ai ** [[Question]]: [Transform original query, adding [[wiki links]] for all technical terms, tasks, concepts] ** [[Answer]]: [Transform first paragraph, adding [[wiki links]] for all key terms] ``` 2. Section Transformations: - Convert markdown headers (##) to nested bullet levels and wiki-links: - Level 1 (##) → "*** [[Section Name]]:" - Level 2 (**) → "**** [[Subsection Name]]:" - Add [[concept]] wiki-links to all section titles - Example: "## Applications and Use Cases" → "*** [[Applications and Use Case]]s" 3. Content Transformations: - Convert bullet points (-) to "*****" - Every technical term becomes [[term]] - Common terms get concept variations: "AI" → "[[artificial intelligence|AI]]" - Multi-word concepts preserve meaning: "system prompt" → "[[LLM System Prompt|system prompt]]" - Each sentence should have 2-3 wiki-linked concepts minimum 4. Citation Integration: - Keep citation numbers in original position: [n] - Citations appear at end under: ``` ** Citations: [n] URL ``` 5. Special Rules: - Always link first instance of a concept in a section - For lists, each item should start with a wiki-linked concept - Preserve all original citation numbers and references - Add line breaks between major sections (*** level) Example Transformation: Raw: "System prompts serve as fundamental instructions that define how an AI model behaves" Becomes: "[[LLM System Prompt|System prompts]] serve as fundamental [[system instruction|instruction]]s that define how an [[AI model]] behaves"