Implement AI Leadership & Intelligence protocols (Model Registry, RAG Pipeline, NLQ)

.gitignore

@@ -41,6 +41,14 @@ temp/
 packages/*/dist/
 packages/*/*.tsbuildinfo
 
+# Example builds
+examples/*/dist/
+examples/*/*.d.ts
+examples/*/*.d.ts.map
+examples/*/*.js
+!examples/*/*.config.js
+!examples/*/*.config.ts
+
 # Next.js
 .next
 out/

content/docs/references/ai/ChunkingStrategy.mdx

@@ -0,0 +1,5 @@
+---
+title: ChunkingStrategy
+description: ChunkingStrategy Schema Reference
+---
+

content/docs/references/ai/DocumentChunk.mdx

@@ -0,0 +1,15 @@
+---
+title: DocumentChunk
+description: DocumentChunk Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **id** | `string` | ✅ | Unique chunk identifier |
+| **content** | `string` | ✅ | Chunk text content |
+| **embedding** | `number[]` | optional | Embedding vector |
+| **metadata** | `object` | ✅ |  |
+| **chunkIndex** | `integer` | ✅ | Chunk position in document |
+| **tokens** | `integer` | optional | Token count |

content/docs/references/ai/DocumentLoaderConfig.mdx

@@ -0,0 +1,18 @@
+---
+title: DocumentLoaderConfig
+description: DocumentLoaderConfig Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **type** | `Enum<'file' \| 'directory' \| 'url' \| 'api' \| 'database' \| 'custom'>` | ✅ |  |
+| **source** | `string` | ✅ | Source path, URL, or identifier |
+| **fileTypes** | `string[]` | optional | Accepted file extensions (e.g., [".pdf", ".md"]) |
+| **recursive** | `boolean` | optional | Process directories recursively |
+| **maxFileSize** | `integer` | optional | Maximum file size in bytes |
+| **excludePatterns** | `string[]` | optional | Patterns to exclude |
+| **extractImages** | `boolean` | optional | Extract text from images (OCR) |
+| **extractTables** | `boolean` | optional | Extract and format tables |
+| **loaderConfig** | `Record<string, any>` | optional | Custom loader-specific config |

content/docs/references/ai/DocumentMetadata.mdx

@@ -0,0 +1,19 @@
+---
+title: DocumentMetadata
+description: DocumentMetadata Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **source** | `string` | ✅ | Document source (file path, URL, etc.) |
+| **sourceType** | `Enum<'file' \| 'url' \| 'api' \| 'database' \| 'custom'>` | optional |  |
+| **title** | `string` | optional |  |
+| **author** | `string` | optional |  |
+| **createdAt** | `string` | optional | ISO timestamp |
+| **updatedAt** | `string` | optional | ISO timestamp |
+| **tags** | `string[]` | optional |  |
+| **category** | `string` | optional |  |
+| **language** | `string` | optional | Document language (ISO 639-1 code) |
+| **custom** | `Record<string, any>` | optional | Custom metadata fields |

content/docs/references/ai/EmbeddingModel.mdx

@@ -0,0 +1,16 @@
+---
+title: EmbeddingModel
+description: EmbeddingModel Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **provider** | `Enum<'openai' \| 'cohere' \| 'huggingface' \| 'azure_openai' \| 'local' \| 'custom'>` | ✅ |  |
+| **model** | `string` | ✅ | Model name (e.g., "text-embedding-3-large") |
+| **dimensions** | `integer` | ✅ | Embedding vector dimensions |
+| **maxTokens** | `integer` | optional | Maximum tokens per embedding |
+| **batchSize** | `integer` | optional | Batch size for embedding |
+| **endpoint** | `string` | optional | Custom endpoint URL |
+| **apiKey** | `string` | optional | API key or reference to secret |

content/docs/references/ai/Entity.mdx

@@ -0,0 +1,14 @@
+---
+title: Entity
+description: Entity Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **type** | `Enum<'object' \| 'field' \| 'value' \| 'operator' \| 'function' \| 'timeframe'>` | ✅ |  |
+| **text** | `string` | ✅ | Original text from query |
+| **value** | `any` | optional | Normalized value |
+| **confidence** | `number` | ✅ | Confidence score |
+| **span** | `any[]` | optional | Character span in query |

content/docs/references/ai/FieldSynonymConfig.mdx

@@ -0,0 +1,13 @@
+---
+title: FieldSynonymConfig
+description: FieldSynonymConfig Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **object** | `string` | ✅ | Object name |
+| **field** | `string` | ✅ | Field name |
+| **synonyms** | `string[]` | ✅ | Natural language synonyms |
+| **examples** | `string[]` | optional | Example queries using synonyms |

content/docs/references/ai/ModelCapability.mdx

@@ -0,0 +1,16 @@
+---
+title: ModelCapability
+description: ModelCapability Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **textGeneration** | `boolean` | optional | Supports text generation |
+| **textEmbedding** | `boolean` | optional | Supports text embedding |
+| **imageGeneration** | `boolean` | optional | Supports image generation |
+| **imageUnderstanding** | `boolean` | optional | Supports image understanding |
+| **functionCalling** | `boolean` | optional | Supports function calling |
+| **codeGeneration** | `boolean` | optional | Supports code generation |
+| **reasoning** | `boolean` | optional | Supports advanced reasoning |

content/docs/references/ai/ModelConfig.mdx

@@ -0,0 +1,23 @@
+---
+title: ModelConfig
+description: ModelConfig Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **id** | `string` | ✅ | Unique model identifier |
+| **name** | `string` | ✅ | Model display name |
+| **version** | `string` | ✅ | Model version (e.g., "gpt-4-turbo-2024-04-09") |
+| **provider** | `Enum<'openai' \| 'azure_openai' \| 'anthropic' \| 'google' \| 'cohere' \| 'huggingface' \| 'local' \| 'custom'>` | ✅ |  |
+| **capabilities** | `object` | ✅ |  |
+| **limits** | `object` | ✅ |  |
+| **pricing** | `object` | optional |  |
+| **endpoint** | `string` | optional | Custom API endpoint |
+| **apiKey** | `string` | optional | API key or reference to secret |
+| **region** | `string` | optional | Deployment region (e.g., "us-east-1") |
+| **description** | `string` | optional |  |
+| **tags** | `string[]` | optional | Tags for categorization |
+| **deprecated** | `boolean` | optional |  |
+| **recommendedFor** | `string[]` | optional | Use case recommendations |

content/docs/references/ai/ModelLimits.mdx

@@ -0,0 +1,13 @@
+---
+title: ModelLimits
+description: ModelLimits Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **maxTokens** | `integer` | ✅ | Maximum tokens per request |
+| **contextWindow** | `integer` | ✅ | Context window size |
+| **maxOutputTokens** | `integer` | optional | Maximum output tokens |
+| **rateLimit** | `object` | optional |  |

content/docs/references/ai/ModelPricing.mdx

@@ -0,0 +1,13 @@
+---
+title: ModelPricing
+description: ModelPricing Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **currency** | `string` | optional |  |
+| **inputCostPer1kTokens** | `number` | optional | Cost per 1K input tokens |
+| **outputCostPer1kTokens** | `number` | optional | Cost per 1K output tokens |
+| **embeddingCostPer1kTokens** | `number` | optional | Cost per 1K embedding tokens |

content/docs/references/ai/ModelProvider.mdx

@@ -0,0 +1,15 @@
+---
+title: ModelProvider
+description: ModelProvider Schema Reference
+---
+
+## Allowed Values
+
+* `openai`
+* `azure_openai`
+* `anthropic`
+* `google`
+* `cohere`
+* `huggingface`
+* `local`
+* `custom`

content/docs/references/ai/ModelRegistry.mdx

@@ -0,0 +1,14 @@
+---
+title: ModelRegistry
+description: ModelRegistry Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **name** | `string` | ✅ | Registry name |
+| **models** | `Record<string, object>` | ✅ | Model entries by ID |
+| **promptTemplates** | `Record<string, object>` | optional | Prompt templates by name |
+| **defaultModel** | `string` | optional | Default model ID |
+| **enableAutoFallback** | `boolean` | optional | Auto-fallback on errors |

content/docs/references/ai/ModelRegistryEntry.mdx

@@ -0,0 +1,14 @@
+---
+title: ModelRegistryEntry
+description: ModelRegistryEntry Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **model** | `object` | ✅ |  |
+| **status** | `Enum<'active' \| 'deprecated' \| 'experimental' \| 'disabled'>` | optional |  |
+| **priority** | `integer` | optional | Priority for model selection |
+| **fallbackModels** | `string[]` | optional | Fallback model IDs |
+| **healthCheck** | `object` | optional |  |

content/docs/references/ai/ModelSelectionCriteria.mdx

@@ -0,0 +1,15 @@
+---
+title: ModelSelectionCriteria
+description: ModelSelectionCriteria Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **capabilities** | `string[]` | optional | Required capabilities |
+| **maxCostPer1kTokens** | `number` | optional | Maximum acceptable cost |
+| **minContextWindow** | `number` | optional | Minimum context window size |
+| **provider** | `Enum<'openai' \| 'azure_openai' \| 'anthropic' \| 'google' \| 'cohere' \| 'huggingface' \| 'local' \| 'custom'>` | optional |  |
+| **tags** | `string[]` | optional |  |
+| **excludeDeprecated** | `boolean` | optional |  |

content/docs/references/ai/NLQAnalytics.mdx

@@ -0,0 +1,20 @@
+---
+title: NLQAnalytics
+description: NLQAnalytics Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **totalQueries** | `integer` | ✅ |  |
+| **successfulQueries** | `integer` | ✅ |  |
+| **failedQueries** | `integer` | ✅ |  |
+| **averageConfidence** | `number` | ✅ |  |
+| **intentDistribution** | `Record<string, integer>` | ✅ | Count by intent type |
+| **topQueries** | `object[]` | ✅ |  |
+| **averageParseTime** | `number` | ✅ | Average parse time in milliseconds |
+| **averageExecutionTime** | `number` | optional |  |
+| **lowConfidenceQueries** | `object[]` | ✅ |  |
+| **startDate** | `string` | ✅ | ISO timestamp |
+| **endDate** | `string` | ✅ | ISO timestamp |

content/docs/references/ai/NLQFieldMapping.mdx

@@ -0,0 +1,14 @@
+---
+title: NLQFieldMapping
+description: NLQFieldMapping Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **naturalLanguage** | `string` | ✅ | NL field name (e.g., "customer name") |
+| **objectField** | `string` | ✅ | Actual field name (e.g., "account.name") |
+| **object** | `string` | ✅ | Object name |
+| **field** | `string` | ✅ | Field name |
+| **confidence** | `number` | ✅ |  |

content/docs/references/ai/NLQModelConfig.mdx

@@ -0,0 +1,23 @@
+---
+title: NLQModelConfig
+description: NLQModelConfig Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **modelId** | `string` | ✅ | Model from registry |
+| **systemPrompt** | `string` | optional | System prompt override |
+| **includeSchema** | `boolean` | optional | Include object schema in prompt |
+| **includeExamples** | `boolean` | optional | Include examples in prompt |
+| **enableIntentDetection** | `boolean` | optional |  |
+| **intentThreshold** | `number` | optional |  |
+| **enableEntityRecognition** | `boolean` | optional |  |
+| **entityRecognitionModel** | `string` | optional |  |
+| **enableFuzzyMatching** | `boolean` | optional | Fuzzy match field names |
+| **fuzzyMatchThreshold** | `number` | optional |  |
+| **enableTimeframeDetection** | `boolean` | optional |  |
+| **defaultTimeframe** | `string` | optional | Default timeframe if not specified |
+| **enableCaching** | `boolean` | optional |  |
+| **cacheTTL** | `integer` | optional | Cache TTL in seconds |

content/docs/references/ai/NLQParseResult.mdx

@@ -0,0 +1,20 @@
+---
+title: NLQParseResult
+description: NLQParseResult Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **originalQuery** | `string` | ✅ |  |
+| **intent** | `Enum<'select' \| 'aggregate' \| 'filter' \| 'sort' \| 'compare' \| 'trend' \| 'insight' \| 'create' \| 'update' \| 'delete'>` | ✅ |  |
+| **intentConfidence** | `number` | ✅ |  |
+| **entities** | `object[]` | ✅ |  |
+| **targetObject** | `string` | optional | Primary object to query |
+| **fields** | `object[]` | optional |  |
+| **timeframe** | `object` | optional |  |
+| **ast** | `any` | optional | Generated ObjectQL AST |
+| **confidence** | `number` | ✅ | Overall confidence |
+| **ambiguities** | `object[]` | optional | Detected ambiguities requiring clarification |
+| **alternatives** | `object[]` | optional |  |

content/docs/references/ai/NLQRequest.mdx

@@ -0,0 +1,16 @@
+---
+title: NLQRequest
+description: NLQRequest Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **query** | `string` | ✅ | Natural language query |
+| **context** | `object` | optional |  |
+| **includeAlternatives** | `boolean` | optional | Include alternative interpretations |
+| **maxAlternatives** | `integer` | optional |  |
+| **minConfidence** | `number` | optional | Minimum confidence threshold |
+| **executeQuery** | `boolean` | optional | Execute query and return results |
+| **maxResults** | `integer` | optional | Maximum results to return |

content/docs/references/ai/NLQResponse.mdx

@@ -0,0 +1,15 @@
+---
+title: NLQResponse
+description: NLQResponse Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **parseResult** | `object` | ✅ |  |
+| **results** | `Record<string, any>[]` | optional | Query results |
+| **totalCount** | `integer` | optional |  |
+| **executionTime** | `number` | optional | Execution time in milliseconds |
+| **needsClarification** | `boolean` | ✅ | Whether query needs clarification |
+| **suggestions** | `string[]` | optional | Query refinement suggestions |

content/docs/references/ai/NLQTrainingExample.mdx

@@ -0,0 +1,17 @@
+---
+title: NLQTrainingExample
+description: NLQTrainingExample Schema Reference
+---
+
+## Properties
+
+| Property | Type | Required | Description |
+| :--- | :--- | :--- | :--- |
+| **query** | `string` | ✅ | Natural language query |
+| **context** | `object` | optional |  |
+| **expectedIntent** | `Enum<'select' \| 'aggregate' \| 'filter' \| 'sort' \| 'compare' \| 'trend' \| 'insight' \| 'create' \| 'update' \| 'delete'>` | ✅ |  |
+| **expectedObject** | `string` | optional |  |
+| **expectedAST** | `any` | optional | Expected ObjectQL AST |
+| **category** | `string` | optional | Example category |
+| **tags** | `string[]` | optional |  |
+| **notes** | `string` | optional |  |