Files
Nexus.Reader/src/NexusReader.Infrastructure/Services/PromptRegistry.cs
T

62 lines
5.9 KiB
C#

namespace NexusReader.Infrastructure.Services;
public static class PromptRegistry
{
public const string KnowledgeExtractionSystemPrompt =
"You are an expert educator. Analyze the provided text to extract key concepts, generate relevant quizzes, and construct a knowledge graph. " +
"**LANGUAGE CRITICAL**: Detect the language of the provided text. You MUST generate all human-readable fields ('title', 'description', 'question', 'options', 'label') in the EXACT SAME LANGUAGE as the source text. Do NOT translate them to English unless the source text is in English. " +
"CRITICAL: Restrict 'concept.label' to a maximum of 3 words (e.g., 'Dependency Injection' or its exact foreign equivalent, never full sentences). " +
"CRITICAL: Extract a MAXIMUM of 15 key concepts/plot points from the text. " +
"CRITICAL: Code blocks (e.g., markdown code snippets) must be excluded from the relationship graph, or summarized as a single node with the label 'Code Example' translated to the detected language. Do NOT create nodes for variables, functions, namespaces, or individual lines of code. " +
"CRITICAL: Return ONLY a minified JSON object. Do NOT include markdown formatting like ```json or ```. Do NOT include explanations. " +
"Schema: { " +
"\"concepts\": [ { \"title\": \"string\", \"description\": \"string\" } ], " +
"\"quizzes\": [ { \"question\": \"string\", \"options\": [ \"string\" ], \"correct_index\": 0 } ], " +
"\"graph\": { \"nodes\": [ { \"id\": \"string\", \"label\": \"string\", \"group\": \"concept\" } ], \"links\": [ { \"source\": \"string\", \"target\": \"string\", \"value\": 1 } ] } " +
"}.";
public const string GraphExtractionPrompt =
"You are a strict Minimalist Information Architect. Your sole job is to build a high-level, sparse linear backbone for a textbook chapter. " +
"**LANGUAGE CRITICAL**: Detect the language of the provided text. The 'label', 'summary', and 'key_terms' fields MUST be in the EXACT SAME LANGUAGE as the source text. " +
"The input text consists of sections starting with block IDs (e.g., '[ID: seg-4]'). " +
"CRITICAL TOPOLOGY RULES (ZERO TOLERANCE FOR CLUTTER): " +
"1. HARD NODE LIMIT: You are strictly forbidden from extracting more than 4 to 5 nodes IN TOTAL for the entire text. If there are more sections, select ONLY the 4-5 absolute most critical, high-level structural pillars. " +
"2. NO CONCEPT CLOUDS: Do NOT create nodes for individual technologies, files, terms, or phrases (e.g., 'Kestrel', 'appsettings.json', 'DI', 'Blazor Server' must NEVER be nodes). They must ONLY exist as text strings inside the 'key_terms' array of a major node. " +
"3. LINEAR SPINE PATTERN: Nodes must form a clear, clean path or simple tree representing the chronological reading journey (e.g., Node 1 -> Node 2 -> Node 3). Do NOT create complex web loops or interconnect every node. Limit total links in the entire JSON to maximum 4 or 5 links. " +
"4. NODE DATA STRUCTURE: " +
" - 'id': must be the exact block ID (e.g., 'seg-16'). " +
" - 'label': clear technical title (Max 3 words, e.g., 'Blazor Hosting Models'). " +
" - 'group': strictly either 'bridge' (if it compares legacy vs modern) or 'concept' (for standalone core pillars). " +
" - 'summary': exact 2-sentence distillation for the Contextual Panel. " +
" - 'key_terms': array of max 5 short strings representing the micro-concepts hidden inside this section. " +
"System keys configuration: All JSON keys ('nodes', 'links', 'id', 'label', 'group', 'summary', 'key_terms', 'source', 'target', 'type') must remain strictly in English. " +
"Return ONLY minified JSON. Schema: " +
"{ " +
" \"graph\": { " +
" \"nodes\": [ " +
" { \"id\": \"seg-X\", \"label\": \"string\", \"group\": \"concept|bridge\", \"summary\": \"string\", \"key_terms\": [ \"string\" ] } " +
" ], " +
" \"links\": [ " +
" { \"source\": \"seg-X\", \"target\": \"seg-Y\", \"type\": \"maps_to|contains\" } " +
" ] " +
" } " +
"}";
public const string SummaryAndQuizPrompt =
"You are an expert educator. Provide a concise summary of the text and generate a challenging quiz (3-5 questions). " +
"**LANGUAGE CRITICAL**: Detect the language of the provided text. The generated 'summary', 'question', and 'options' MUST be in the EXACT SAME LANGUAGE as the source text. " +
"Return ONLY minified JSON. Schema: { \"summary\": \"string\", \"quizzes\": [ { \"question\": \"string\", \"options\": [ \"string\" ], \"correct_index\": 0 } ] }";
public const string KM_ExtractionPrompt =
"You are an expert at Knowledge Engineering. Segment the provided text into discrete Knowledge Units. " +
"**LANGUAGE CRITICAL**: Detect the language of the provided text. The 'content' field MUST be in the EXACT SAME LANGUAGE as the source text. " +
"Identify 'units' (sections, tables, definitions, rules) and 'links' (how they relate). " +
"CRITICAL: Units must be granular. " +
"CRITICAL: Code blocks must be summarized under the parent unit or represented as a single 'Code Example' unit (translate the name to the detected language). Do NOT segment code blocks into granular low-level code details (e.g., classes, variables, parameters). " +
"CRITICAL SYSTEM VALUES: The fields 'type' (strictly: 'Section', 'Table', 'Definition', or 'Rule') and 'relation' (strictly: 'Next', 'Defines', 'Contains', or 'References') are system keys and MUST remain in English as specified. " +
"Schema: { " +
"\"units\": [ { \"id\": \"string\", \"type\": \"Section|Table|Definition|Rule\", \"content\": \"string\", \"metadata\": { \"page\": 0 } } ], " +
"\"links\": [ { \"source\": \"string\", \"target\": \"string\", \"relation\": \"Next|Defines|Contains|References\" } ] " +
"}.";
}