{"version":3,"file":"azure_aisearch.cjs","names":["VectorStore","embeddings: EmbeddingsInterface","config: AzureAISearchConfig","AzureKeyCredential","SearchClient","SearchIndexClient","params: {\n ids?: string | string[];\n filter?: AzureAISearchFilterType;\n }","filter: AzureAISearchFilterType","docs: AzureAISearchDocument[]","deleteResults: IndexingResult[]","SearchIndexingBufferedSender","ids: string | string[]","docs: { id: string }[]","documents: Document[]","options?: AzureAISearchAddDocumentsOptions","embeddings: number[][]","vectors: number[][]","entities: AzureAISearchDocument[]","query: string","filter: this[\"FilterType\"] | undefined","queryVector?: number[]","docsWithScore: [Document, number][]","Document","query: number[]","k: number","filter?: this[\"FilterType\"]","options: MaxMarginalRelevanceSearchOptions","indexClient: SearchIndexClient","indexName: string","texts: string[]","metadatas: object[] | object","docs: Document[]","docs: Document[]"],"sources":["../../src/vectorstores/azure_aisearch.ts"],"sourcesContent":["import * as uuid from \"uuid\";\nimport {\n SearchClient,\n SearchIndexClient,\n AzureKeyCredential,\n IndexingResult,\n SearchIndex,\n SearchIndexingBufferedSender,\n VectorFilterMode,\n} from \"@azure/search-documents\";\nimport type { KeyCredential, TokenCredential } from \"@azure/core-auth\";\nimport {\n MaxMarginalRelevanceSearchOptions,\n VectorStore,\n} from \"@langchain/core/vectorstores\";\nimport type { EmbeddingsInterface } from \"@langchain/core/embeddings\";\nimport { Document } from \"@langchain/core/documents\";\nimport { maximalMarginalRelevance } from \"@langchain/core/utils/math\";\nimport { getEnvironmentVariable } from \"@langchain/core/utils/env\";\n\n/**\n * Azure AI Search query type.\n */\nexport const AzureAISearchQueryType = {\n /** Vector search. */\n Similarity: \"similarity\",\n /** Hybrid full text and vector search. */\n SimilarityHybrid: \"similarity_hybrid\",\n /** Hybrid full text and vector search with semantic ranking. */\n SemanticHybrid: \"semantic_hybrid\",\n} as const;\n\n/**\n * Azure AI Search query type.\n */\nexport type AzureAISearchQueryType =\n (typeof AzureAISearchQueryType)[keyof typeof AzureAISearchQueryType];\n\n/**\n * Azure AI Search settings.\n */\nexport interface AzureAISearchQueryOptions {\n readonly type?: AzureAISearchQueryType;\n readonly semanticConfigurationName?: string;\n}\n\n/**\n * Configuration options for the `AzureAISearchStore` constructor.\n */\nexport interface AzureAISearchConfig {\n readonly client?: SearchClient;\n readonly indexName?: string;\n readonly endpoint?: string;\n readonly key?: string;\n readonly credentials?: KeyCredential | TokenCredential;\n readonly search?: AzureAISearchQueryOptions;\n}\n\n/**\n * Azure AI Search options metadata schema.\n * If yout want to add custom data, use the attributes property.\n */\nexport type AzureAISearchDocumentMetadata = {\n source: string;\n attributes?: Array<{ key: string; value: string }>;\n embedding?: number[];\n};\n\n/**\n * Azure AI Search indexed document.\n */\nexport type AzureAISearchDocument = {\n id: string;\n content: string;\n content_vector: number[];\n metadata: AzureAISearchDocumentMetadata;\n};\n\n/**\n * Azure AI Search options for adding documents.\n */\nexport type AzureAISearchAddDocumentsOptions = {\n ids?: string[];\n};\n\n/**\n * Azure AI Search filter type.\n */\nexport type AzureAISearchFilterType = {\n /** OData filter. */\n filterExpression?: string;\n /** Determines whether or not filters are applied before or after the vector search is performed. */\n vectorFilterMode?: VectorFilterMode;\n /** Determines whether or not to include the embeddings in the search results. */\n includeEmbeddings?: boolean;\n};\n\nconst USER_AGENT_PREFIX = \"langchainjs-azure-aisearch\";\nconst DEFAULT_FIELD_ID = \"id\";\nconst DEFAULT_FIELD_CONTENT = \"content\";\nconst DEFAULT_FIELD_CONTENT_VECTOR = \"content_vector\";\nconst DEFAULT_FIELD_METADATA = \"metadata\";\nconst DEFAULT_FIELD_METADATA_SOURCE = \"source\";\nconst DEFAULT_FIELD_METADATA_ATTRS = \"attributes\";\n\n/**\n * Azure AI Search vector store.\n * To use this, you should have:\n * - the `@azure/search-documents` NPM package installed\n * - an endpoint and key to the Azure AI Search instance\n *\n * If you directly provide a `SearchClient` instance, you need to ensure that\n * an index has been created. When using and endpoint and key, the index will\n * be created automatically if it does not exist.\n */\nexport class AzureAISearchVectorStore extends VectorStore {\n declare FilterType: AzureAISearchFilterType;\n\n get lc_secrets(): { [key: string]: string } {\n return {\n endpoint: \"AZURE_AISEARCH_ENDPOINT\",\n key: \"AZURE_AISEARCH_KEY\",\n };\n }\n\n _vectorstoreType(): string {\n return \"azure_aisearch\";\n }\n\n private readonly initPromise: Promise;\n\n private readonly client: SearchClient;\n\n private readonly indexName: string;\n\n private readonly options: AzureAISearchQueryOptions;\n\n constructor(embeddings: EmbeddingsInterface, config: AzureAISearchConfig) {\n super(embeddings, config);\n\n const endpoint =\n config.endpoint ?? getEnvironmentVariable(\"AZURE_AISEARCH_ENDPOINT\");\n const key = config.key ?? getEnvironmentVariable(\"AZURE_AISEARCH_KEY\");\n let { credentials } = config;\n\n if (!config.client && (!endpoint || (!key && !credentials))) {\n throw new Error(\n \"Azure AI Search client or endpoint and key/credentials must be set.\"\n );\n }\n\n this.indexName = config.indexName ?? \"vectorsearch\";\n\n if (!config.client) {\n credentials ??= new AzureKeyCredential(key!);\n this.client = new SearchClient(endpoint!, this.indexName, credentials, {\n userAgentOptions: { userAgentPrefix: USER_AGENT_PREFIX },\n });\n const indexClient = new SearchIndexClient(endpoint!, credentials, {\n userAgentOptions: { userAgentPrefix: USER_AGENT_PREFIX },\n });\n\n // Start initialization, but don't wait for it to finish here\n this.initPromise = this.ensureIndexExists(indexClient).catch((error) => {\n console.error(\n \"Error during Azure AI Search index initialization:\",\n error\n );\n });\n } else {\n this.client = config.client;\n }\n\n this.options = config.search ?? {};\n this.embeddings = embeddings;\n }\n\n /**\n * Removes specified documents from the AzureAISearchVectorStore using IDs or a filter.\n * @param params Object that includes either an array of IDs or a filter for the data to be deleted.\n * @returns A promise that resolves when the documents have been removed.\n */\n async delete(params: {\n ids?: string | string[];\n filter?: AzureAISearchFilterType;\n }) {\n if (!params.ids && !params.filter) {\n throw new Error(\n `Azure AI Search delete requires either \"ids\" or \"filter\" to be set in the params object`\n );\n }\n\n await this.initPromise;\n\n if (params.ids) {\n await this.deleteById(params.ids);\n }\n if (params.filter) {\n await this.deleteMany(params.filter);\n }\n }\n\n /**\n * Removes specified documents from the AzureAISearchVectorStore using a filter.\n * @param filter Filter options to find documents to delete.\n * @returns A promise that resolves when the documents have been removed.\n */\n private async deleteMany(\n filter: AzureAISearchFilterType\n ): Promise {\n if (!filter.filterExpression) {\n throw new Error(\n `Azure AI Search deleteMany requires \"filterExpression\" to be set in the filter object`\n );\n }\n\n const { results } = await this.client.search(\"*\", {\n filter: filter.filterExpression,\n });\n\n const docs: AzureAISearchDocument[] = [];\n for await (const item of results) {\n docs.push(item.document);\n }\n\n const deleteResults: IndexingResult[] = [];\n const bufferedClient =\n new SearchIndexingBufferedSender(\n this.client,\n (entity) => entity.id\n );\n bufferedClient.on(\"batchSucceeded\", (response) => {\n deleteResults.push(...response.results);\n });\n bufferedClient.on(\"batchFailed\", (response) => {\n throw new Error(\n `Azure AI Search deleteDocuments batch failed: ${response}`\n );\n });\n\n await bufferedClient.deleteDocuments(docs);\n await bufferedClient.flush();\n await bufferedClient.dispose();\n\n return deleteResults;\n }\n\n /**\n * Removes specified documents from the AzureAISearchVectorStore.\n * @param ids IDs of the documents to be removed.\n * @returns A promise that resolves when the documents have been removed.\n */\n private async deleteById(ids: string | string[]): Promise {\n const docsIds = Array.isArray(ids) ? ids : [ids];\n const docs: { id: string }[] = docsIds.map((id) => ({ id }));\n\n const deleteResults: IndexingResult[] = [];\n const bufferedClient = new SearchIndexingBufferedSender<{ id: string }>(\n this.client,\n (entity) => entity.id\n );\n bufferedClient.on(\"batchSucceeded\", (response) => {\n deleteResults.push(...response.results);\n });\n bufferedClient.on(\"batchFailed\", (response) => {\n throw new Error(\n `Azure AI Search deleteDocuments batch failed: ${response}`\n );\n });\n\n await bufferedClient.deleteDocuments(docs);\n await bufferedClient.flush();\n await bufferedClient.dispose();\n\n return deleteResults;\n }\n\n /**\n * Adds documents to the AzureAISearchVectorStore.\n * @param documents The documents to add.\n * @param options Options for adding documents.\n * @returns A promise that resolves to the ids of the added documents.\n */\n async addDocuments(\n documents: Document[],\n options?: AzureAISearchAddDocumentsOptions\n ) {\n const texts = documents.map(({ pageContent }) => pageContent);\n const embeddings: number[][] = await this.embeddings.embedDocuments(texts);\n const results = await this.addVectors(embeddings, documents, options);\n\n return results;\n }\n\n /**\n * Adds vectors to the AzureAISearchVectorStore.\n * @param vectors Vectors to be added.\n * @param documents Corresponding documents to be added.\n * @param options Options for adding documents.\n * @returns A promise that resolves to the ids of the added documents.\n */\n async addVectors(\n vectors: number[][],\n documents: Document[],\n options?: AzureAISearchAddDocumentsOptions\n ): Promise {\n const ids = options?.ids ?? documents.map(() => uuid.v4());\n const entities: AzureAISearchDocument[] = documents.map((doc, idx) => ({\n id: ids[idx],\n content: doc.pageContent,\n content_vector: vectors[idx],\n metadata: {\n source: doc.metadata?.source,\n attributes: doc.metadata?.attributes ?? [],\n },\n }));\n\n await this.initPromise;\n\n const bufferedClient =\n new SearchIndexingBufferedSender(\n this.client,\n (entity) => entity.id\n );\n bufferedClient.on(\"batchFailed\", (response) => {\n throw new Error(\n `Azure AI Search uploadDocuments batch failed: ${response}`\n );\n });\n\n await bufferedClient.uploadDocuments(entities);\n await bufferedClient.flush();\n await bufferedClient.dispose();\n\n return ids;\n }\n\n /**\n * Performs a similarity search using query type specified in configuration.\n * If the query type is not specified, it defaults to similarity search.\n * @param query Query text for the similarity search.\n * @param k=4 Number of nearest neighbors to return.\n * @param filter Optional filter options for the documents.\n * @returns Promise that resolves to a list of documents.\n */\n async similaritySearch(\n query: string,\n k = 4,\n filter: this[\"FilterType\"] | undefined = undefined\n ): Promise {\n const results = await this.similaritySearchWithScore(query, k, filter);\n\n return results.map((result) => result[0]);\n }\n\n /**\n * Performs a similarity search using query type specified in configuration.\n * If the query type is not specified, it defaults to similarity hybrid search.\n * @param query Query text for the similarity search.\n * @param k=4 Number of nearest neighbors to return.\n * @param filter Optional filter options for the documents.\n * @returns Promise that resolves to a list of documents and their corresponding similarity scores.\n */\n async similaritySearchWithScore(\n query: string,\n k = 4,\n filter: this[\"FilterType\"] | undefined = undefined\n ): Promise<[Document, number][]> {\n const searchType =\n this.options.type ?? AzureAISearchQueryType.SimilarityHybrid;\n\n if (searchType === AzureAISearchQueryType.Similarity) {\n return this.similaritySearchVectorWithScore(\n await this.embeddings.embedQuery(query),\n k,\n filter\n );\n } else if (searchType === AzureAISearchQueryType.SimilarityHybrid) {\n return this.hybridSearchVectorWithScore(\n query,\n await this.embeddings.embedQuery(query),\n k,\n filter\n );\n } else if (searchType === AzureAISearchQueryType.SemanticHybrid) {\n return this.semanticHybridSearchVectorWithScore(\n query,\n await this.embeddings.embedQuery(query),\n k,\n filter\n );\n }\n\n throw new Error(`Unrecognized search type '${searchType}'`);\n }\n\n /**\n * Performs a hybrid search using query text.\n * @param query Query text for the similarity search.\n * @param queryVector Query vector for the similarity search.\n * If not provided, the query text will be embedded.\n * @param k=4 Number of nearest neighbors to return.\n * @param filter Optional filter options for the documents.\n * @returns Promise that resolves to a list of documents and their corresponding similarity scores.\n */\n async hybridSearchVectorWithScore(\n query: string,\n queryVector?: number[],\n k = 4,\n filter: this[\"FilterType\"] | undefined = undefined\n ): Promise<[Document, number][]> {\n const vector = queryVector ?? (await this.embeddings.embedQuery(query));\n\n await this.initPromise;\n const { results } = await this.client.search(query, {\n vectorSearchOptions: {\n queries: [\n {\n kind: \"vector\",\n vector,\n kNearestNeighborsCount: k,\n fields: [DEFAULT_FIELD_CONTENT_VECTOR],\n },\n ],\n filterMode: filter?.vectorFilterMode,\n },\n filter: filter?.filterExpression,\n top: k,\n });\n\n const docsWithScore: [Document, number][] = [];\n\n for await (const item of results) {\n const document = new Document({\n pageContent: item.document[DEFAULT_FIELD_CONTENT],\n metadata: {\n ...item.document[DEFAULT_FIELD_METADATA],\n },\n });\n if (filter?.includeEmbeddings) {\n document.metadata.embedding =\n item.document[DEFAULT_FIELD_CONTENT_VECTOR];\n }\n docsWithScore.push([document, item.score]);\n }\n\n return docsWithScore;\n }\n\n /**\n * Performs a hybrid search with semantic reranker using query text.\n * @param query Query text for the similarity search.\n * @param queryVector Query vector for the similarity search.\n * If not provided, the query text will be embedded.\n * @param k=4 Number of nearest neighbors to return.\n * @param filter Optional filter options for the documents.\n * @returns Promise that resolves to a list of documents and their corresponding similarity scores.\n */\n async semanticHybridSearchVectorWithScore(\n query: string,\n queryVector?: number[],\n k = 4,\n filter: this[\"FilterType\"] | undefined = undefined\n ): Promise<[Document, number][]> {\n const vector = queryVector ?? (await this.embeddings.embedQuery(query));\n\n await this.initPromise;\n const { results } = await this.client.search(query, {\n vectorSearchOptions: {\n queries: [\n {\n kind: \"vector\",\n vector,\n kNearestNeighborsCount: k,\n fields: [DEFAULT_FIELD_CONTENT_VECTOR],\n },\n ],\n filterMode: filter?.vectorFilterMode,\n },\n filter: filter?.filterExpression,\n top: k,\n queryType: \"semantic\",\n semanticSearchOptions: {\n configurationName:\n this.options.semanticConfigurationName ?? \"semantic-search-config\",\n },\n });\n\n const docsWithScore: [Document, number][] = [];\n\n for await (const item of results) {\n const document = new Document({\n pageContent: item.document[DEFAULT_FIELD_CONTENT],\n metadata: {\n ...item.document[DEFAULT_FIELD_METADATA],\n },\n });\n if (filter?.includeEmbeddings) {\n document.metadata.embedding =\n item.document[DEFAULT_FIELD_CONTENT_VECTOR];\n }\n docsWithScore.push([document, item.score]);\n }\n\n return docsWithScore;\n }\n\n /**\n * Performs a similarity search on the vectors stored in the collection.\n * @param queryVector Query vector for the similarity search.\n * @param k=4 Number of nearest neighbors to return.\n * @param filter Optional filter options for the documents.\n * @returns Promise that resolves to a list of documents and their corresponding similarity scores.\n */\n async similaritySearchVectorWithScore(\n query: number[],\n k: number,\n filter?: this[\"FilterType\"]\n ): Promise<[Document, number][]> {\n await this.initPromise;\n\n const { results } = await this.client.search(\"*\", {\n vectorSearchOptions: {\n queries: [\n {\n kind: \"vector\",\n vector: query,\n kNearestNeighborsCount: k,\n fields: [DEFAULT_FIELD_CONTENT_VECTOR],\n },\n ],\n filterMode: filter?.vectorFilterMode,\n },\n filter: filter?.filterExpression,\n });\n\n const docsWithScore: [Document, number][] = [];\n\n for await (const item of results) {\n const document = new Document({\n pageContent: item.document[DEFAULT_FIELD_CONTENT],\n metadata: {\n ...item.document[DEFAULT_FIELD_METADATA],\n },\n });\n if (filter?.includeEmbeddings) {\n document.metadata.embedding =\n item.document[DEFAULT_FIELD_CONTENT_VECTOR];\n }\n docsWithScore.push([document, item.score]);\n }\n\n return docsWithScore;\n }\n\n /**\n * Return documents selected using the maximal marginal relevance.\n * Maximal marginal relevance optimizes for similarity to the query AND\n * diversity among selected documents.\n * @param query Text to look up documents similar to.\n * @param options.k Number of documents to return.\n * @param options.fetchK=20 Number of documents to fetch before passing to\n * the MMR algorithm.\n * @param options.lambda=0.5 Number between 0 and 1 that determines the\n * degree of diversity among the results, where 0 corresponds to maximum\n * diversity and 1 to minimum diversity.\n * @returns List of documents selected by maximal marginal relevance.\n */\n async maxMarginalRelevanceSearch(\n query: string,\n options: MaxMarginalRelevanceSearchOptions\n ): Promise {\n const { k, fetchK = 20, lambda = 0.5 } = options;\n const includeEmbeddingsFlag = options.filter?.includeEmbeddings || false;\n\n const queryEmbedding = await this.embeddings.embedQuery(query);\n const docs = await this.similaritySearchVectorWithScore(\n queryEmbedding,\n fetchK,\n {\n ...options.filter,\n includeEmbeddings: true,\n }\n );\n const embeddingList = docs.map((doc) => doc[0].metadata.embedding);\n\n // Re-rank the results using MMR\n const mmrIndexes = maximalMarginalRelevance(\n queryEmbedding,\n embeddingList,\n lambda,\n k\n );\n\n return mmrIndexes.map((index) => {\n const doc = docs[index][0];\n\n // Remove embeddings if they were not requested originally\n if (!includeEmbeddingsFlag) {\n delete doc.metadata.embedding;\n }\n return doc;\n });\n }\n\n /**\n * Ensures that an index exists on the AzureAISearchVectorStore.\n * @param indexClient The Azure AI Search index client.\n * @returns A promise that resolves when the AzureAISearchVectorStore index has been initialized.\n * @protected\n */\n protected async ensureIndexExists(\n indexClient: SearchIndexClient\n ): Promise {\n try {\n await indexClient.getIndex(this.indexName);\n } catch {\n // Index does not exists, create it\n const searchIndex = await this.createSearchIndexDefinition(\n this.indexName\n );\n await indexClient.createIndex(searchIndex);\n }\n }\n\n /**\n * Prepares the search index definition for Azure AI Search.\n * @param indexName The name of the index.\n * @returns The SearchIndex object.\n * @protected\n */\n protected async createSearchIndexDefinition(\n indexName: string\n ): Promise {\n // Embed a test query to get the embedding dimensions\n const testEmbedding = await this.embeddings.embedQuery(\"test\");\n const embeddingDimensions = testEmbedding.length;\n return {\n name: indexName,\n vectorSearch: {\n algorithms: [\n {\n name: \"vector-search-algorithm\",\n kind: \"hnsw\",\n parameters: {\n m: 4,\n efSearch: 500,\n metric: \"cosine\",\n efConstruction: 400,\n },\n },\n ],\n profiles: [\n {\n name: \"vector-search-profile\",\n algorithmConfigurationName: \"vector-search-algorithm\",\n },\n ],\n },\n semanticSearch: {\n defaultConfigurationName: \"semantic-search-config\",\n configurations: [\n {\n name: \"semantic-search-config\",\n prioritizedFields: {\n contentFields: [\n {\n name: DEFAULT_FIELD_CONTENT,\n },\n ],\n keywordsFields: [\n {\n name: DEFAULT_FIELD_CONTENT,\n },\n ],\n },\n },\n ],\n },\n fields: [\n {\n name: DEFAULT_FIELD_ID,\n filterable: true,\n key: true,\n type: \"Edm.String\",\n },\n {\n name: DEFAULT_FIELD_CONTENT,\n searchable: true,\n filterable: true,\n type: \"Edm.String\",\n },\n {\n name: DEFAULT_FIELD_CONTENT_VECTOR,\n searchable: true,\n type: \"Collection(Edm.Single)\",\n vectorSearchDimensions: embeddingDimensions,\n vectorSearchProfileName: \"vector-search-profile\",\n },\n {\n name: DEFAULT_FIELD_METADATA,\n type: \"Edm.ComplexType\",\n fields: [\n {\n name: DEFAULT_FIELD_METADATA_SOURCE,\n type: \"Edm.String\",\n filterable: true,\n },\n {\n name: DEFAULT_FIELD_METADATA_ATTRS,\n type: \"Collection(Edm.ComplexType)\",\n fields: [\n {\n name: \"key\",\n type: \"Edm.String\",\n filterable: true,\n },\n {\n name: \"value\",\n type: \"Edm.String\",\n filterable: true,\n },\n ],\n },\n ],\n },\n ],\n };\n }\n\n /**\n * Static method to create an instance of AzureAISearchVectorStore from a\n * list of texts. It first converts the texts to vectors and then adds\n * them to the collection.\n * @param texts List of texts to be converted to vectors.\n * @param metadatas Metadata for the texts.\n * @param embeddings Embeddings to be used for conversion.\n * @param config Database configuration for Azure AI Search.\n * @returns Promise that resolves to a new instance of AzureAISearchVectorStore.\n */\n static async fromTexts(\n texts: string[],\n metadatas: object[] | object,\n embeddings: EmbeddingsInterface,\n config: AzureAISearchConfig\n ): Promise {\n const docs: Document[] = [];\n for (let i = 0; i < texts.length; i += 1) {\n const metadata = Array.isArray(metadatas) ? metadatas[i] : metadatas;\n const newDoc = new Document({\n pageContent: texts[i],\n metadata,\n });\n docs.push(newDoc);\n }\n return AzureAISearchVectorStore.fromDocuments(docs, embeddings, config);\n }\n\n /**\n * Static method to create an instance of AzureAISearchVectorStore from a\n * list of documents. It first converts the documents to vectors and then\n * adds them to the database.\n * @param docs List of documents to be converted to vectors.\n * @param embeddings Embeddings to be used for conversion.\n * @param config Database configuration for Azure AI Search.\n * @returns Promise that resolves to a new instance of AzureAISearchVectorStore.\n */\n static async fromDocuments(\n docs: Document[],\n embeddings: EmbeddingsInterface,\n config: AzureAISearchConfig,\n options?: AzureAISearchAddDocumentsOptions\n ): Promise {\n const instance = new this(embeddings, config);\n await instance.addDocuments(docs, options);\n return instance;\n }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;AAuBA,MAAa,yBAAyB;CAEpC,YAAY;CAEZ,kBAAkB;CAElB,gBAAgB;AACjB;AAmED,MAAM,oBAAoB;AAC1B,MAAM,mBAAmB;AACzB,MAAM,wBAAwB;AAC9B,MAAM,+BAA+B;AACrC,MAAM,yBAAyB;AAC/B,MAAM,gCAAgC;AACtC,MAAM,+BAA+B;;;;;;;;;;;AAYrC,IAAa,2BAAb,MAAa,iCAAiCA,0CAAY;CAGxD,IAAI,aAAwC;AAC1C,SAAO;GACL,UAAU;GACV,KAAK;EACN;CACF;CAED,mBAA2B;AACzB,SAAO;CACR;CAED,AAAiB;CAEjB,AAAiB;CAEjB,AAAiB;CAEjB,AAAiB;CAEjB,YAAYC,YAAiCC,QAA6B;EACxE,MAAM,YAAY,OAAO;EAEzB,MAAM,WACJ,OAAO,mEAAmC,0BAA0B;EACtE,MAAM,MAAM,OAAO,8DAA8B,qBAAqB;EACtE,IAAI,EAAE,aAAa,GAAG;AAEtB,MAAI,CAAC,OAAO,WAAW,CAAC,YAAa,CAAC,OAAO,CAAC,aAC5C,OAAM,IAAI,MACR;EAIJ,KAAK,YAAY,OAAO,aAAa;AAErC,MAAI,CAAC,OAAO,QAAQ;GAClB,gBAAgB,IAAIC,4CAAmB;GACvC,KAAK,SAAS,IAAIC,sCAAa,UAAW,KAAK,WAAW,aAAa,EACrE,kBAAkB,EAAE,iBAAiB,kBAAmB,EACzD;GACD,MAAM,cAAc,IAAIC,2CAAkB,UAAW,aAAa,EAChE,kBAAkB,EAAE,iBAAiB,kBAAmB,EACzD;GAGD,KAAK,cAAc,KAAK,kBAAkB,YAAY,CAAC,MAAM,CAAC,UAAU;IACtE,QAAQ,MACN,sDACA,MACD;GACF,EAAC;EACH,OACC,KAAK,SAAS,OAAO;EAGvB,KAAK,UAAU,OAAO,UAAU,CAAE;EAClC,KAAK,aAAa;CACnB;;;;;;CAOD,MAAM,OAAOC,QAGV;AACD,MAAI,CAAC,OAAO,OAAO,CAAC,OAAO,OACzB,OAAM,IAAI,MACR,CAAC,uFAAuF,CAAC;EAI7F,MAAM,KAAK;AAEX,MAAI,OAAO,KACT,MAAM,KAAK,WAAW,OAAO,IAAI;AAEnC,MAAI,OAAO,QACT,MAAM,KAAK,WAAW,OAAO,OAAO;CAEvC;;;;;;CAOD,MAAc,WACZC,QAC2B;AAC3B,MAAI,CAAC,OAAO,iBACV,OAAM,IAAI,MACR,CAAC,qFAAqF,CAAC;EAI3F,MAAM,EAAE,SAAS,GAAG,MAAM,KAAK,OAAO,OAAO,KAAK,EAChD,QAAQ,OAAO,iBAChB,EAAC;EAEF,MAAMC,OAAgC,CAAE;AACxC,aAAW,MAAM,QAAQ,SACvB,KAAK,KAAK,KAAK,SAAS;EAG1B,MAAMC,gBAAkC,CAAE;EAC1C,MAAM,iBACJ,IAAIC,sDACF,KAAK,QACL,CAAC,WAAW,OAAO;EAEvB,eAAe,GAAG,kBAAkB,CAAC,aAAa;GAChD,cAAc,KAAK,GAAG,SAAS,QAAQ;EACxC,EAAC;EACF,eAAe,GAAG,eAAe,CAAC,aAAa;AAC7C,SAAM,IAAI,MACR,CAAC,8CAA8C,EAAE,UAAU;EAE9D,EAAC;EAEF,MAAM,eAAe,gBAAgB,KAAK;EAC1C,MAAM,eAAe,OAAO;EAC5B,MAAM,eAAe,SAAS;AAE9B,SAAO;CACR;;;;;;CAOD,MAAc,WAAWC,KAAmD;EAC1E,MAAM,UAAU,MAAM,QAAQ,IAAI,GAAG,MAAM,CAAC,GAAI;EAChD,MAAMC,OAAyB,QAAQ,IAAI,CAAC,QAAQ,EAAE,GAAI,GAAE;EAE5D,MAAMH,gBAAkC,CAAE;EAC1C,MAAM,iBAAiB,IAAIC,sDACzB,KAAK,QACL,CAAC,WAAW,OAAO;EAErB,eAAe,GAAG,kBAAkB,CAAC,aAAa;GAChD,cAAc,KAAK,GAAG,SAAS,QAAQ;EACxC,EAAC;EACF,eAAe,GAAG,eAAe,CAAC,aAAa;AAC7C,SAAM,IAAI,MACR,CAAC,8CAA8C,EAAE,UAAU;EAE9D,EAAC;EAEF,MAAM,eAAe,gBAAgB,KAAK;EAC1C,MAAM,eAAe,OAAO;EAC5B,MAAM,eAAe,SAAS;AAE9B,SAAO;CACR;;;;;;;CAQD,MAAM,aACJG,WACAC,SACA;EACA,MAAM,QAAQ,UAAU,IAAI,CAAC,EAAE,aAAa,KAAK,YAAY;EAC7D,MAAMC,aAAyB,MAAM,KAAK,WAAW,eAAe,MAAM;EAC1E,MAAM,UAAU,MAAM,KAAK,WAAW,YAAY,WAAW,QAAQ;AAErE,SAAO;CACR;;;;;;;;CASD,MAAM,WACJC,SACAH,WACAC,SACmB;EACnB,MAAM,MAAM,SAAS,OAAO,UAAU,IAAI,MAAM,KAAK,IAAI,CAAC;EAC1D,MAAMG,WAAoC,UAAU,IAAI,CAAC,KAAK,SAAS;GACrE,IAAI,IAAI;GACR,SAAS,IAAI;GACb,gBAAgB,QAAQ;GACxB,UAAU;IACR,QAAQ,IAAI,UAAU;IACtB,YAAY,IAAI,UAAU,cAAc,CAAE;GAC3C;EACF,GAAE;EAEH,MAAM,KAAK;EAEX,MAAM,iBACJ,IAAIP,sDACF,KAAK,QACL,CAAC,WAAW,OAAO;EAEvB,eAAe,GAAG,eAAe,CAAC,aAAa;AAC7C,SAAM,IAAI,MACR,CAAC,8CAA8C,EAAE,UAAU;EAE9D,EAAC;EAEF,MAAM,eAAe,gBAAgB,SAAS;EAC9C,MAAM,eAAe,OAAO;EAC5B,MAAM,eAAe,SAAS;AAE9B,SAAO;CACR;;;;;;;;;CAUD,MAAM,iBACJQ,OACA,IAAI,GACJC,SAAyC,QACpB;EACrB,MAAM,UAAU,MAAM,KAAK,0BAA0B,OAAO,GAAG,OAAO;AAEtE,SAAO,QAAQ,IAAI,CAAC,WAAW,OAAO,GAAG;CAC1C;;;;;;;;;CAUD,MAAM,0BACJD,OACA,IAAI,GACJC,SAAyC,QACV;EAC/B,MAAM,aACJ,KAAK,QAAQ,QAAQ,uBAAuB;AAE9C,MAAI,eAAe,uBAAuB,WACxC,QAAO,KAAK,gCACV,MAAM,KAAK,WAAW,WAAW,MAAM,EACvC,GACA,OACD;WACQ,eAAe,uBAAuB,iBAC/C,QAAO,KAAK,4BACV,OACA,MAAM,KAAK,WAAW,WAAW,MAAM,EACvC,GACA,OACD;WACQ,eAAe,uBAAuB,eAC/C,QAAO,KAAK,oCACV,OACA,MAAM,KAAK,WAAW,WAAW,MAAM,EACvC,GACA,OACD;AAGH,QAAM,IAAI,MAAM,CAAC,0BAA0B,EAAE,WAAW,CAAC,CAAC;CAC3D;;;;;;;;;;CAWD,MAAM,4BACJD,OACAE,aACA,IAAI,GACJD,SAAyC,QACV;EAC/B,MAAM,SAAS,eAAgB,MAAM,KAAK,WAAW,WAAW,MAAM;EAEtE,MAAM,KAAK;EACX,MAAM,EAAE,SAAS,GAAG,MAAM,KAAK,OAAO,OAAO,OAAO;GAClD,qBAAqB;IACnB,SAAS,CACP;KACE,MAAM;KACN;KACA,wBAAwB;KACxB,QAAQ,CAAC,4BAA6B;IACvC,CACF;IACD,YAAY,QAAQ;GACrB;GACD,QAAQ,QAAQ;GAChB,KAAK;EACN,EAAC;EAEF,MAAME,gBAAsC,CAAE;AAE9C,aAAW,MAAM,QAAQ,SAAS;GAChC,MAAM,WAAW,IAAIC,oCAAwC;IAC3D,aAAa,KAAK,SAAS;IAC3B,UAAU,EACR,GAAG,KAAK,SAAS,wBAClB;GACF;AACD,OAAI,QAAQ,mBACV,SAAS,SAAS,YAChB,KAAK,SAAS;GAElB,cAAc,KAAK,CAAC,UAAU,KAAK,KAAM,EAAC;EAC3C;AAED,SAAO;CACR;;;;;;;;;;CAWD,MAAM,oCACJJ,OACAE,aACA,IAAI,GACJD,SAAyC,QACV;EAC/B,MAAM,SAAS,eAAgB,MAAM,KAAK,WAAW,WAAW,MAAM;EAEtE,MAAM,KAAK;EACX,MAAM,EAAE,SAAS,GAAG,MAAM,KAAK,OAAO,OAAO,OAAO;GAClD,qBAAqB;IACnB,SAAS,CACP;KACE,MAAM;KACN;KACA,wBAAwB;KACxB,QAAQ,CAAC,4BAA6B;IACvC,CACF;IACD,YAAY,QAAQ;GACrB;GACD,QAAQ,QAAQ;GAChB,KAAK;GACL,WAAW;GACX,uBAAuB,EACrB,mBACE,KAAK,QAAQ,6BAA6B,yBAC7C;EACF,EAAC;EAEF,MAAME,gBAAsC,CAAE;AAE9C,aAAW,MAAM,QAAQ,SAAS;GAChC,MAAM,WAAW,IAAIC,oCAAwC;IAC3D,aAAa,KAAK,SAAS;IAC3B,UAAU,EACR,GAAG,KAAK,SAAS,wBAClB;GACF;AACD,OAAI,QAAQ,mBACV,SAAS,SAAS,YAChB,KAAK,SAAS;GAElB,cAAc,KAAK,CAAC,UAAU,KAAK,KAAM,EAAC;EAC3C;AAED,SAAO;CACR;;;;;;;;CASD,MAAM,gCACJC,OACAC,GACAC,QAC+B;EAC/B,MAAM,KAAK;EAEX,MAAM,EAAE,SAAS,GAAG,MAAM,KAAK,OAAO,OAAO,KAAK;GAChD,qBAAqB;IACnB,SAAS,CACP;KACE,MAAM;KACN,QAAQ;KACR,wBAAwB;KACxB,QAAQ,CAAC,4BAA6B;IACvC,CACF;IACD,YAAY,QAAQ;GACrB;GACD,QAAQ,QAAQ;EACjB,EAAC;EAEF,MAAMJ,gBAAsC,CAAE;AAE9C,aAAW,MAAM,QAAQ,SAAS;GAChC,MAAM,WAAW,IAAIC,oCAAwC;IAC3D,aAAa,KAAK,SAAS;IAC3B,UAAU,EACR,GAAG,KAAK,SAAS,wBAClB;GACF;AACD,OAAI,QAAQ,mBACV,SAAS,SAAS,YAChB,KAAK,SAAS;GAElB,cAAc,KAAK,CAAC,UAAU,KAAK,KAAM,EAAC;EAC3C;AAED,SAAO;CACR;;;;;;;;;;;;;;CAeD,MAAM,2BACJJ,OACAQ,SACqB;EACrB,MAAM,EAAE,GAAG,SAAS,IAAI,SAAS,IAAK,GAAG;EACzC,MAAM,wBAAwB,QAAQ,QAAQ,qBAAqB;EAEnE,MAAM,iBAAiB,MAAM,KAAK,WAAW,WAAW,MAAM;EAC9D,MAAM,OAAO,MAAM,KAAK,gCACtB,gBACA,QACA;GACE,GAAG,QAAQ;GACX,mBAAmB;EACpB,EACF;EACD,MAAM,gBAAgB,KAAK,IAAI,CAAC,QAAQ,IAAI,GAAG,SAAS,UAAU;EAGlE,MAAM,uEACJ,gBACA,eACA,QACA,EACD;AAED,SAAO,WAAW,IAAI,CAAC,UAAU;GAC/B,MAAM,MAAM,KAAK,OAAO;AAGxB,OAAI,CAAC,uBACH,OAAO,IAAI,SAAS;AAEtB,UAAO;EACR,EAAC;CACH;;;;;;;CAQD,MAAgB,kBACdC,aACe;AACf,MAAI;GACF,MAAM,YAAY,SAAS,KAAK,UAAU;EAC3C,QAAO;GAEN,MAAM,cAAc,MAAM,KAAK,4BAC7B,KAAK,UACN;GACD,MAAM,YAAY,YAAY,YAAY;EAC3C;CACF;;;;;;;CAQD,MAAgB,4BACdC,WACsB;EAEtB,MAAM,gBAAgB,MAAM,KAAK,WAAW,WAAW,OAAO;EAC9D,MAAM,sBAAsB,cAAc;AAC1C,SAAO;GACL,MAAM;GACN,cAAc;IACZ,YAAY,CACV;KACE,MAAM;KACN,MAAM;KACN,YAAY;MACV,GAAG;MACH,UAAU;MACV,QAAQ;MACR,gBAAgB;KACjB;IACF,CACF;IACD,UAAU,CACR;KACE,MAAM;KACN,4BAA4B;IAC7B,CACF;GACF;GACD,gBAAgB;IACd,0BAA0B;IAC1B,gBAAgB,CACd;KACE,MAAM;KACN,mBAAmB;MACjB,eAAe,CACb,EACE,MAAM,sBACP,CACF;MACD,gBAAgB,CACd,EACE,MAAM,sBACP,CACF;KACF;IACF,CACF;GACF;GACD,QAAQ;IACN;KACE,MAAM;KACN,YAAY;KACZ,KAAK;KACL,MAAM;IACP;IACD;KACE,MAAM;KACN,YAAY;KACZ,YAAY;KACZ,MAAM;IACP;IACD;KACE,MAAM;KACN,YAAY;KACZ,MAAM;KACN,wBAAwB;KACxB,yBAAyB;IAC1B;IACD;KACE,MAAM;KACN,MAAM;KACN,QAAQ,CACN;MACE,MAAM;MACN,MAAM;MACN,YAAY;KACb,GACD;MACE,MAAM;MACN,MAAM;MACN,QAAQ,CACN;OACE,MAAM;OACN,MAAM;OACN,YAAY;MACb,GACD;OACE,MAAM;OACN,MAAM;OACN,YAAY;MACb,CACF;KACF,CACF;IACF;GACF;EACF;CACF;;;;;;;;;;;CAYD,aAAa,UACXC,OACAC,WACA7B,YACAC,QACmC;EACnC,MAAM6B,OAAkD,CAAE;AAC1D,OAAK,IAAI,IAAI,GAAG,IAAI,MAAM,QAAQ,KAAK,GAAG;GACxC,MAAM,WAAW,MAAM,QAAQ,UAAU,GAAG,UAAU,KAAK;GAC3D,MAAM,SAAS,IAAIT,oCAAS;IAC1B,aAAa,MAAM;IACnB;GACD;GACD,KAAK,KAAK,OAAO;EAClB;AACD,SAAO,yBAAyB,cAAc,MAAM,YAAY,OAAO;CACxE;;;;;;;;;;CAWD,aAAa,cACXU,MACA/B,YACAC,QACAY,SACmC;EACnC,MAAM,WAAW,IAAI,KAAK,YAAY;EACtC,MAAM,SAAS,aAAa,MAAM,QAAQ;AAC1C,SAAO;CACR;AACF"}