@superlinked/sie-chroma 0.1.9 → 0.2.0

package/dist/index.cjs

@@ -72,17 +72,7 @@ var SIEEmbeddingFunction = class {
       outputTypes: ["dense"]
     };
     const results = await this.client.encode(this.model, items, options);
-    return results.map((result) => this.extractDense(result));
-  }
-  /**
-   * Extract dense embedding from encode result.
-   */
-  extractDense(result) {
-    const dense = result.dense;
-    if (!dense) {
-      throw new Error("Encode result missing dense embedding");
-    }
-    return (0, import_sie_sdk.toNumberArray)(dense);
+    return results.map((result) => (0, import_sie_sdk.denseEmbedding)(result));
   }
   /**
    * Close the underlying client connection.
@@ -136,7 +126,7 @@ var SIESparseEmbeddingFunction = class {
       outputTypes: ["sparse"]
     };
     const results = await this.client.encode(this.model, items, options);
-    return results.map((result) => this.extractSparse(result));
+    return results.map((result) => (0, import_sie_sdk.sparseEmbedding)(result));
   }
   /**
    * Generate sparse embeddings as dict format (token_id -> weight).
@@ -160,19 +150,6 @@ var SIESparseEmbeddingFunction = class {
       return dict;
     });
   }
-  /**
-   * Extract sparse embedding from encode result.
-   */
-  extractSparse(result) {
-    const sparse = result.sparse;
-    if (!sparse) {
-      return { indices: [], values: [] };
-    }
-    return {
-      indices: (0, import_sie_sdk.toNumberArray)(sparse.indices),
-      values: (0, import_sie_sdk.toNumberArray)(sparse.values)
-    };
-  }
   /**
    * Close the underlying client connection.
    */

package/dist/index.cjs.map

@@ -1 +1 @@
-{"version":3,"sources":["../src/index.ts"],"sourcesContent":["/**\n * SIE embedding functions for ChromaDB.\n *\n * Provides custom embedding functions that use SIE for generating embeddings:\n * - SIEEmbeddingFunction: Dense embeddings for standard Chroma collections\n *\n * @example\n * ```typescript\n * import { ChromaClient } from \"chromadb\";\n * import { SIEEmbeddingFunction } from \"@superlinked/sie-chroma\";\n *\n * const client = new ChromaClient();\n * const embeddingFunction = new SIEEmbeddingFunction({\n *   baseUrl: \"http://localhost:8080\",\n *   model: \"BAAI/bge-m3\",\n * });\n *\n * const collection = await client.createCollection({\n *   name: \"my_collection\",\n *   embeddingFunction,\n * });\n *\n * await collection.add({\n *   ids: [\"doc1\", \"doc2\"],\n *   documents: [\"Hello world\", \"Goodbye world\"],\n * });\n * ```\n */\n\nimport {\n  type EncodeOptions,\n  type EncodeResult,\n  SIEClient,\n  type SIEClientOptions,\n  toNumberArray,\n} from \"@superlinked/sie-sdk\";\nimport type { IEmbeddingFunction } from \"chromadb\";\n\n/**\n * Configuration options for SIEEmbeddingFunction.\n */\nexport interface SIEEmbeddingFunctionOptions {\n  /**\n   * URL of the SIE server.\n   * @default \"http://localhost:8080\"\n   */\n  baseUrl?: string;\n\n  /**\n   * Model name/ID to use for encoding.\n   * @default \"BAAI/bge-m3\"\n   */\n  model?: string;\n\n  /**\n   * Optional pre-configured SIEClient instance.\n   */\n  client?: SIEClient;\n\n  /**\n   * Target GPU type for routing (e.g., \"l4\", \"a100-80gb\").\n   */\n  gpu?: string;\n\n  /**\n   * Request timeout in milliseconds.\n   * @default 180000 (3 minutes)\n   */\n  timeout?: number;\n}\n\n/**\n * Embedding function using SIE for ChromaDB collections.\n *\n * This class implements ChromaDB's IEmbeddingFunction interface,\n * allowing SIE to generate embeddings for document storage and retrieval.\n *\n * @example\n * ```typescript\n * import { ChromaClient } from \"chromadb\";\n * import { SIEEmbeddingFunction } from \"@superlinked/sie-chroma\";\n *\n * const embeddingFunction = new SIEEmbeddingFunction({\n *   baseUrl: \"http://localhost:8080\",\n *   model: \"BAAI/bge-m3\",\n * });\n *\n * const client = new ChromaClient();\n * const collection = await client.createCollection({\n *   name: \"my_collection\",\n *   embeddingFunction,\n * });\n *\n * // Add documents (embeddings generated automatically)\n * await collection.add({\n *   ids: [\"doc1\", \"doc2\"],\n *   documents: [\"First document\", \"Second document\"],\n * });\n *\n * // Query (query embedding generated automatically)\n * const results = await collection.query({\n *   queryTexts: [\"search query\"],\n *   nResults: 5,\n * });\n * ```\n */\nexport class SIEEmbeddingFunction implements IEmbeddingFunction {\n  private readonly model: string;\n  private _client: SIEClient | undefined;\n  private readonly baseUrl: string;\n  private readonly clientOptions: SIEClientOptions;\n\n  constructor(options: SIEEmbeddingFunctionOptions = {}) {\n    const {\n      baseUrl = \"http://localhost:8080\",\n      model = \"BAAI/bge-m3\",\n      client,\n      gpu,\n      timeout = 180_000,\n    } = options;\n\n    this.baseUrl = baseUrl;\n    this.model = model;\n    this._client = client;\n    this.clientOptions = {\n      timeout,\n      gpu,\n    };\n  }\n\n  /**\n   * Get or create the SIEClient.\n   */\n  private get client(): SIEClient {\n    if (!this._client) {\n      this._client = new SIEClient(this.baseUrl, this.clientOptions);\n    }\n    return this._client;\n  }\n\n  /**\n   * Generate embeddings for documents.\n   *\n   * This method is called by ChromaDB when adding documents or querying.\n   *\n   * @param texts - Array of document texts to embed.\n   * @returns Array of embedding vectors.\n   */\n  async generate(texts: string[]): Promise<number[][]> {\n    if (texts.length === 0) {\n      return [];\n    }\n\n    const items = texts.map((text) => ({ text }));\n    const options: EncodeOptions = {\n      outputTypes: [\"dense\"],\n    };\n\n    const results = await this.client.encode(this.model, items, options);\n    return (results as EncodeResult[]).map((result) => this.extractDense(result));\n  }\n\n  /**\n   * Extract dense embedding from encode result.\n   */\n  private extractDense(result: EncodeResult): number[] {\n    const dense = result.dense;\n    if (!dense) {\n      throw new Error(\"Encode result missing dense embedding\");\n    }\n    return toNumberArray(dense);\n  }\n\n  /**\n   * Close the underlying client connection.\n   */\n  async close(): Promise<void> {\n    if (this._client) {\n      await this._client.close();\n    }\n  }\n}\n\n/**\n * Sparse embedding representation for ChromaDB hybrid search.\n */\nexport interface SparseEmbedding {\n  indices: number[];\n  values: number[];\n}\n\n/**\n * Configuration options for SIESparseEmbeddingFunction.\n */\nexport interface SIESparseEmbeddingFunctionOptions {\n  /**\n   * URL of the SIE server.\n   * @default \"http://localhost:8080\"\n   */\n  baseUrl?: string;\n\n  /**\n   * Model name/ID to use for encoding. Must support sparse output.\n   * @default \"BAAI/bge-m3\"\n   */\n  model?: string;\n\n  /**\n   * Target GPU type for routing (e.g., \"l4\", \"a100-80gb\").\n   */\n  gpu?: string;\n\n  /**\n   * Request timeout in milliseconds.\n   * @default 180000 (3 minutes)\n   */\n  timeout?: number;\n}\n\n/**\n * Sparse embedding function using SIE for ChromaDB hybrid search.\n *\n * Generates sparse embeddings that can be used with ChromaDB's hybrid\n * search capabilities. Returns embeddings as {indices, values} pairs.\n *\n * @example\n * ```typescript\n * import { SIESparseEmbeddingFunction } from \"@superlinked/sie-chroma\";\n *\n * const sparseEf = new SIESparseEmbeddingFunction({\n *   baseUrl: \"http://localhost:8080\",\n *   model: \"BAAI/bge-m3\",\n * });\n *\n * const embeddings = await sparseEf.generate([\"Hello world\"]);\n * console.log(embeddings[0].indices); // [1, 5, 10, ...]\n * console.log(embeddings[0].values);  // [0.5, 0.3, 0.2, ...]\n * ```\n */\nexport class SIESparseEmbeddingFunction {\n  private readonly model: string;\n  private _client: SIEClient | undefined;\n  private readonly baseUrl: string;\n  private readonly clientOptions: SIEClientOptions;\n\n  constructor(options: SIESparseEmbeddingFunctionOptions = {}) {\n    const {\n      baseUrl = \"http://localhost:8080\",\n      model = \"BAAI/bge-m3\",\n      gpu,\n      timeout = 180_000,\n    } = options;\n\n    this.baseUrl = baseUrl;\n    this.model = model;\n    this.clientOptions = {\n      timeout,\n      gpu,\n    };\n  }\n\n  /**\n   * Get or create the SIEClient.\n   */\n  private get client(): SIEClient {\n    if (!this._client) {\n      this._client = new SIEClient(this.baseUrl, this.clientOptions);\n    }\n    return this._client;\n  }\n\n  /**\n   * Generate sparse embeddings for documents.\n   *\n   * @param texts - Array of document texts to embed.\n   * @returns Array of sparse embeddings with indices and values.\n   */\n  async generate(texts: string[]): Promise<SparseEmbedding[]> {\n    if (texts.length === 0) {\n      return [];\n    }\n\n    const items = texts.map((text) => ({ text }));\n    const options: EncodeOptions = {\n      outputTypes: [\"sparse\"],\n    };\n\n    const results = await this.client.encode(this.model, items, options);\n    return (results as EncodeResult[]).map((result) => this.extractSparse(result));\n  }\n\n  /**\n   * Generate sparse embeddings as dict format (token_id -> weight).\n   *\n   * This format is compatible with some ChromaDB hybrid search configurations.\n   *\n   * @param texts - Array of document texts to embed.\n   * @returns Array of sparse embeddings as {[tokenId]: weight} dicts.\n   */\n  async generateAsDict(texts: string[]): Promise<Record<number, number>[]> {\n    const embeddings = await this.generate(texts);\n    return embeddings.map((emb) => {\n      const dict: Record<number, number> = {};\n      for (let i = 0; i < emb.indices.length; i++) {\n        const idx = emb.indices[i];\n        const val = emb.values[i];\n        if (idx !== undefined && val !== undefined) {\n          dict[idx] = val;\n        }\n      }\n      return dict;\n    });\n  }\n\n  /**\n   * Extract sparse embedding from encode result.\n   */\n  private extractSparse(result: EncodeResult): SparseEmbedding {\n    const sparse = result.sparse;\n    if (!sparse) {\n      return { indices: [], values: [] };\n    }\n\n    return {\n      indices: toNumberArray(sparse.indices),\n      values: toNumberArray(sparse.values),\n    };\n  }\n\n  /**\n   * Close the underlying client connection.\n   */\n  async close(): Promise<void> {\n    if (this._client) {\n      await this._client.close();\n    }\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AA6BA,qBAMO;AAuEA,IAAM,uBAAN,MAAyD;AAAA,EAC7C;AAAA,EACT;AAAA,EACS;AAAA,EACA;AAAA,EAEjB,YAAY,UAAuC,CAAC,GAAG;AACrD,UAAM;AAAA,MACJ,UAAU;AAAA,MACV,QAAQ;AAAA,MACR;AAAA,MACA;AAAA,MACA,UAAU;AAAA,IACZ,IAAI;AAEJ,SAAK,UAAU;AACf,SAAK,QAAQ;AACb,SAAK,UAAU;AACf,SAAK,gBAAgB;AAAA,MACnB;AAAA,MACA;AAAA,IACF;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,IAAY,SAAoB;AAC9B,QAAI,CAAC,KAAK,SAAS;AACjB,WAAK,UAAU,IAAI,yBAAU,KAAK,SAAS,KAAK,aAAa;AAAA,IAC/D;AACA,WAAO,KAAK;AAAA,EACd;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAUA,MAAM,SAAS,OAAsC;AACnD,QAAI,MAAM,WAAW,GAAG;AACtB,aAAO,CAAC;AAAA,IACV;AAEA,UAAM,QAAQ,MAAM,IAAI,CAAC,UAAU,EAAE,KAAK,EAAE;AAC5C,UAAM,UAAyB;AAAA,MAC7B,aAAa,CAAC,OAAO;AAAA,IACvB;AAEA,UAAM,UAAU,MAAM,KAAK,OAAO,OAAO,KAAK,OAAO,OAAO,OAAO;AACnE,WAAQ,QAA2B,IAAI,CAAC,WAAW,KAAK,aAAa,MAAM,CAAC;AAAA,EAC9E;AAAA;AAAA;AAAA;AAAA,EAKQ,aAAa,QAAgC;AACnD,UAAM,QAAQ,OAAO;AACrB,QAAI,CAAC,OAAO;AACV,YAAM,IAAI,MAAM,uCAAuC;AAAA,IACzD;AACA,eAAO,8BAAc,KAAK;AAAA,EAC5B;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,QAAuB;AAC3B,QAAI,KAAK,SAAS;AAChB,YAAM,KAAK,QAAQ,MAAM;AAAA,IAC3B;AAAA,EACF;AACF;AA0DO,IAAM,6BAAN,MAAiC;AAAA,EACrB;AAAA,EACT;AAAA,EACS;AAAA,EACA;AAAA,EAEjB,YAAY,UAA6C,CAAC,GAAG;AAC3D,UAAM;AAAA,MACJ,UAAU;AAAA,MACV,QAAQ;AAAA,MACR;AAAA,MACA,UAAU;AAAA,IACZ,IAAI;AAEJ,SAAK,UAAU;AACf,SAAK,QAAQ;AACb,SAAK,gBAAgB;AAAA,MACnB;AAAA,MACA;AAAA,IACF;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,IAAY,SAAoB;AAC9B,QAAI,CAAC,KAAK,SAAS;AACjB,WAAK,UAAU,IAAI,yBAAU,KAAK,SAAS,KAAK,aAAa;AAAA,IAC/D;AACA,WAAO,KAAK;AAAA,EACd;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQA,MAAM,SAAS,OAA6C;AAC1D,QAAI,MAAM,WAAW,GAAG;AACtB,aAAO,CAAC;AAAA,IACV;AAEA,UAAM,QAAQ,MAAM,IAAI,CAAC,UAAU,EAAE,KAAK,EAAE;AAC5C,UAAM,UAAyB;AAAA,MAC7B,aAAa,CAAC,QAAQ;AAAA,IACxB;AAEA,UAAM,UAAU,MAAM,KAAK,OAAO,OAAO,KAAK,OAAO,OAAO,OAAO;AACnE,WAAQ,QAA2B,IAAI,CAAC,WAAW,KAAK,cAAc,MAAM,CAAC;AAAA,EAC/E;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAUA,MAAM,eAAe,OAAoD;AACvE,UAAM,aAAa,MAAM,KAAK,SAAS,KAAK;AAC5C,WAAO,WAAW,IAAI,CAAC,QAAQ;AAC7B,YAAM,OAA+B,CAAC;AACtC,eAAS,IAAI,GAAG,IAAI,IAAI,QAAQ,QAAQ,KAAK;AAC3C,cAAM,MAAM,IAAI,QAAQ,CAAC;AACzB,cAAM,MAAM,IAAI,OAAO,CAAC;AACxB,YAAI,QAAQ,UAAa,QAAQ,QAAW;AAC1C,eAAK,GAAG,IAAI;AAAA,QACd;AAAA,MACF;AACA,aAAO;AAAA,IACT,CAAC;AAAA,EACH;AAAA;AAAA;AAAA;AAAA,EAKQ,cAAc,QAAuC;AAC3D,UAAM,SAAS,OAAO;AACtB,QAAI,CAAC,QAAQ;AACX,aAAO,EAAE,SAAS,CAAC,GAAG,QAAQ,CAAC,EAAE;AAAA,IACnC;AAEA,WAAO;AAAA,MACL,aAAS,8BAAc,OAAO,OAAO;AAAA,MACrC,YAAQ,8BAAc,OAAO,MAAM;AAAA,IACrC;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,QAAuB;AAC3B,QAAI,KAAK,SAAS;AAChB,YAAM,KAAK,QAAQ,MAAM;AAAA,IAC3B;AAAA,EACF;AACF;","names":[]}
+{"version":3,"sources":["../src/index.ts"],"sourcesContent":["/**\n * SIE embedding functions for ChromaDB.\n *\n * Provides custom embedding functions that use SIE for generating embeddings:\n * - SIEEmbeddingFunction: Dense embeddings for standard Chroma collections\n *\n * @example\n * ```typescript\n * import { ChromaClient } from \"chromadb\";\n * import { SIEEmbeddingFunction } from \"@superlinked/sie-chroma\";\n *\n * const client = new ChromaClient();\n * const embeddingFunction = new SIEEmbeddingFunction({\n *   baseUrl: \"http://localhost:8080\",\n *   model: \"BAAI/bge-m3\",\n * });\n *\n * const collection = await client.createCollection({\n *   name: \"my_collection\",\n *   embeddingFunction,\n * });\n *\n * await collection.add({\n *   ids: [\"doc1\", \"doc2\"],\n *   documents: [\"Hello world\", \"Goodbye world\"],\n * });\n * ```\n */\n\nimport {\n  type EncodeOptions,\n  type EncodeResult,\n  SIEClient,\n  type SIEClientOptions,\n  denseEmbedding,\n  sparseEmbedding,\n} from \"@superlinked/sie-sdk\";\nimport type { IEmbeddingFunction } from \"chromadb\";\n\n/**\n * Configuration options for SIEEmbeddingFunction.\n */\nexport interface SIEEmbeddingFunctionOptions {\n  /**\n   * URL of the SIE server.\n   * @default \"http://localhost:8080\"\n   */\n  baseUrl?: string;\n\n  /**\n   * Model name/ID to use for encoding.\n   * @default \"BAAI/bge-m3\"\n   */\n  model?: string;\n\n  /**\n   * Optional pre-configured SIEClient instance.\n   */\n  client?: SIEClient;\n\n  /**\n   * Target GPU type for routing (e.g., \"l4\", \"a100-80gb\").\n   */\n  gpu?: string;\n\n  /**\n   * Request timeout in milliseconds.\n   * @default 180000 (3 minutes)\n   */\n  timeout?: number;\n}\n\n/**\n * Embedding function using SIE for ChromaDB collections.\n *\n * This class implements ChromaDB's IEmbeddingFunction interface,\n * allowing SIE to generate embeddings for document storage and retrieval.\n *\n * @example\n * ```typescript\n * import { ChromaClient } from \"chromadb\";\n * import { SIEEmbeddingFunction } from \"@superlinked/sie-chroma\";\n *\n * const embeddingFunction = new SIEEmbeddingFunction({\n *   baseUrl: \"http://localhost:8080\",\n *   model: \"BAAI/bge-m3\",\n * });\n *\n * const client = new ChromaClient();\n * const collection = await client.createCollection({\n *   name: \"my_collection\",\n *   embeddingFunction,\n * });\n *\n * // Add documents (embeddings generated automatically)\n * await collection.add({\n *   ids: [\"doc1\", \"doc2\"],\n *   documents: [\"First document\", \"Second document\"],\n * });\n *\n * // Query (query embedding generated automatically)\n * const results = await collection.query({\n *   queryTexts: [\"search query\"],\n *   nResults: 5,\n * });\n * ```\n */\nexport class SIEEmbeddingFunction implements IEmbeddingFunction {\n  private readonly model: string;\n  private _client: SIEClient | undefined;\n  private readonly baseUrl: string;\n  private readonly clientOptions: SIEClientOptions;\n\n  constructor(options: SIEEmbeddingFunctionOptions = {}) {\n    const {\n      baseUrl = \"http://localhost:8080\",\n      model = \"BAAI/bge-m3\",\n      client,\n      gpu,\n      timeout = 180_000,\n    } = options;\n\n    this.baseUrl = baseUrl;\n    this.model = model;\n    this._client = client;\n    this.clientOptions = {\n      timeout,\n      gpu,\n    };\n  }\n\n  /**\n   * Get or create the SIEClient.\n   */\n  private get client(): SIEClient {\n    if (!this._client) {\n      this._client = new SIEClient(this.baseUrl, this.clientOptions);\n    }\n    return this._client;\n  }\n\n  /**\n   * Generate embeddings for documents.\n   *\n   * This method is called by ChromaDB when adding documents or querying.\n   *\n   * @param texts - Array of document texts to embed.\n   * @returns Array of embedding vectors.\n   */\n  async generate(texts: string[]): Promise<number[][]> {\n    if (texts.length === 0) {\n      return [];\n    }\n\n    const items = texts.map((text) => ({ text }));\n    const options: EncodeOptions = {\n      outputTypes: [\"dense\"],\n    };\n\n    const results = await this.client.encode(this.model, items, options);\n    return (results as EncodeResult[]).map((result) => denseEmbedding(result));\n  }\n\n  /**\n   * Close the underlying client connection.\n   */\n  async close(): Promise<void> {\n    if (this._client) {\n      await this._client.close();\n    }\n  }\n}\n\n/**\n * Sparse embedding representation for ChromaDB hybrid search.\n */\nexport interface SparseEmbedding {\n  indices: number[];\n  values: number[];\n}\n\n/**\n * Configuration options for SIESparseEmbeddingFunction.\n */\nexport interface SIESparseEmbeddingFunctionOptions {\n  /**\n   * URL of the SIE server.\n   * @default \"http://localhost:8080\"\n   */\n  baseUrl?: string;\n\n  /**\n   * Model name/ID to use for encoding. Must support sparse output.\n   * @default \"BAAI/bge-m3\"\n   */\n  model?: string;\n\n  /**\n   * Target GPU type for routing (e.g., \"l4\", \"a100-80gb\").\n   */\n  gpu?: string;\n\n  /**\n   * Request timeout in milliseconds.\n   * @default 180000 (3 minutes)\n   */\n  timeout?: number;\n}\n\n/**\n * Sparse embedding function using SIE for ChromaDB hybrid search.\n *\n * Generates sparse embeddings that can be used with ChromaDB's hybrid\n * search capabilities. Returns embeddings as {indices, values} pairs.\n *\n * @example\n * ```typescript\n * import { SIESparseEmbeddingFunction } from \"@superlinked/sie-chroma\";\n *\n * const sparseEf = new SIESparseEmbeddingFunction({\n *   baseUrl: \"http://localhost:8080\",\n *   model: \"BAAI/bge-m3\",\n * });\n *\n * const embeddings = await sparseEf.generate([\"Hello world\"]);\n * console.log(embeddings[0].indices); // [1, 5, 10, ...]\n * console.log(embeddings[0].values);  // [0.5, 0.3, 0.2, ...]\n * ```\n */\nexport class SIESparseEmbeddingFunction {\n  private readonly model: string;\n  private _client: SIEClient | undefined;\n  private readonly baseUrl: string;\n  private readonly clientOptions: SIEClientOptions;\n\n  constructor(options: SIESparseEmbeddingFunctionOptions = {}) {\n    const {\n      baseUrl = \"http://localhost:8080\",\n      model = \"BAAI/bge-m3\",\n      gpu,\n      timeout = 180_000,\n    } = options;\n\n    this.baseUrl = baseUrl;\n    this.model = model;\n    this.clientOptions = {\n      timeout,\n      gpu,\n    };\n  }\n\n  /**\n   * Get or create the SIEClient.\n   */\n  private get client(): SIEClient {\n    if (!this._client) {\n      this._client = new SIEClient(this.baseUrl, this.clientOptions);\n    }\n    return this._client;\n  }\n\n  /**\n   * Generate sparse embeddings for documents.\n   *\n   * @param texts - Array of document texts to embed.\n   * @returns Array of sparse embeddings with indices and values.\n   */\n  async generate(texts: string[]): Promise<SparseEmbedding[]> {\n    if (texts.length === 0) {\n      return [];\n    }\n\n    const items = texts.map((text) => ({ text }));\n    const options: EncodeOptions = {\n      outputTypes: [\"sparse\"],\n    };\n\n    const results = await this.client.encode(this.model, items, options);\n    return (results as EncodeResult[]).map((result) => sparseEmbedding(result));\n  }\n\n  /**\n   * Generate sparse embeddings as dict format (token_id -> weight).\n   *\n   * This format is compatible with some ChromaDB hybrid search configurations.\n   *\n   * @param texts - Array of document texts to embed.\n   * @returns Array of sparse embeddings as {[tokenId]: weight} dicts.\n   */\n  async generateAsDict(texts: string[]): Promise<Record<number, number>[]> {\n    const embeddings = await this.generate(texts);\n    return embeddings.map((emb) => {\n      const dict: Record<number, number> = {};\n      for (let i = 0; i < emb.indices.length; i++) {\n        const idx = emb.indices[i];\n        const val = emb.values[i];\n        if (idx !== undefined && val !== undefined) {\n          dict[idx] = val;\n        }\n      }\n      return dict;\n    });\n  }\n\n  /**\n   * Close the underlying client connection.\n   */\n  async close(): Promise<void> {\n    if (this._client) {\n      await this._client.close();\n    }\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AA6BA,qBAOO;AAuEA,IAAM,uBAAN,MAAyD;AAAA,EAC7C;AAAA,EACT;AAAA,EACS;AAAA,EACA;AAAA,EAEjB,YAAY,UAAuC,CAAC,GAAG;AACrD,UAAM;AAAA,MACJ,UAAU;AAAA,MACV,QAAQ;AAAA,MACR;AAAA,MACA;AAAA,MACA,UAAU;AAAA,IACZ,IAAI;AAEJ,SAAK,UAAU;AACf,SAAK,QAAQ;AACb,SAAK,UAAU;AACf,SAAK,gBAAgB;AAAA,MACnB;AAAA,MACA;AAAA,IACF;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,IAAY,SAAoB;AAC9B,QAAI,CAAC,KAAK,SAAS;AACjB,WAAK,UAAU,IAAI,yBAAU,KAAK,SAAS,KAAK,aAAa;AAAA,IAC/D;AACA,WAAO,KAAK;AAAA,EACd;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAUA,MAAM,SAAS,OAAsC;AACnD,QAAI,MAAM,WAAW,GAAG;AACtB,aAAO,CAAC;AAAA,IACV;AAEA,UAAM,QAAQ,MAAM,IAAI,CAAC,UAAU,EAAE,KAAK,EAAE;AAC5C,UAAM,UAAyB;AAAA,MAC7B,aAAa,CAAC,OAAO;AAAA,IACvB;AAEA,UAAM,UAAU,MAAM,KAAK,OAAO,OAAO,KAAK,OAAO,OAAO,OAAO;AACnE,WAAQ,QAA2B,IAAI,CAAC,eAAW,+BAAe,MAAM,CAAC;AAAA,EAC3E;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,QAAuB;AAC3B,QAAI,KAAK,SAAS;AAChB,YAAM,KAAK,QAAQ,MAAM;AAAA,IAC3B;AAAA,EACF;AACF;AA0DO,IAAM,6BAAN,MAAiC;AAAA,EACrB;AAAA,EACT;AAAA,EACS;AAAA,EACA;AAAA,EAEjB,YAAY,UAA6C,CAAC,GAAG;AAC3D,UAAM;AAAA,MACJ,UAAU;AAAA,MACV,QAAQ;AAAA,MACR;AAAA,MACA,UAAU;AAAA,IACZ,IAAI;AAEJ,SAAK,UAAU;AACf,SAAK,QAAQ;AACb,SAAK,gBAAgB;AAAA,MACnB;AAAA,MACA;AAAA,IACF;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,IAAY,SAAoB;AAC9B,QAAI,CAAC,KAAK,SAAS;AACjB,WAAK,UAAU,IAAI,yBAAU,KAAK,SAAS,KAAK,aAAa;AAAA,IAC/D;AACA,WAAO,KAAK;AAAA,EACd;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQA,MAAM,SAAS,OAA6C;AAC1D,QAAI,MAAM,WAAW,GAAG;AACtB,aAAO,CAAC;AAAA,IACV;AAEA,UAAM,QAAQ,MAAM,IAAI,CAAC,UAAU,EAAE,KAAK,EAAE;AAC5C,UAAM,UAAyB;AAAA,MAC7B,aAAa,CAAC,QAAQ;AAAA,IACxB;AAEA,UAAM,UAAU,MAAM,KAAK,OAAO,OAAO,KAAK,OAAO,OAAO,OAAO;AACnE,WAAQ,QAA2B,IAAI,CAAC,eAAW,gCAAgB,MAAM,CAAC;AAAA,EAC5E;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAUA,MAAM,eAAe,OAAoD;AACvE,UAAM,aAAa,MAAM,KAAK,SAAS,KAAK;AAC5C,WAAO,WAAW,IAAI,CAAC,QAAQ;AAC7B,YAAM,OAA+B,CAAC;AACtC,eAAS,IAAI,GAAG,IAAI,IAAI,QAAQ,QAAQ,KAAK;AAC3C,cAAM,MAAM,IAAI,QAAQ,CAAC;AACzB,cAAM,MAAM,IAAI,OAAO,CAAC;AACxB,YAAI,QAAQ,UAAa,QAAQ,QAAW;AAC1C,eAAK,GAAG,IAAI;AAAA,QACd;AAAA,MACF;AACA,aAAO;AAAA,IACT,CAAC;AAAA,EACH;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,QAAuB;AAC3B,QAAI,KAAK,SAAS;AAChB,YAAM,KAAK,QAAQ,MAAM;AAAA,IAC3B;AAAA,EACF;AACF;","names":[]}

package/dist/index.d.cts

@@ -112,10 +112,6 @@ declare class SIEEmbeddingFunction implements IEmbeddingFunction {
      * @returns Array of embedding vectors.
      */
     generate(texts: string[]): Promise<number[][]>;
-    /**
-     * Extract dense embedding from encode result.
-     */
-    private extractDense;
     /**
      * Close the underlying client connection.
      */
@@ -198,10 +194,6 @@ declare class SIESparseEmbeddingFunction {
      * @returns Array of sparse embeddings as {[tokenId]: weight} dicts.
      */
     generateAsDict(texts: string[]): Promise<Record<number, number>[]>;
-    /**
-     * Extract sparse embedding from encode result.
-     */
-    private extractSparse;
     /**
      * Close the underlying client connection.
      */

package/dist/index.d.ts

@@ -112,10 +112,6 @@ declare class SIEEmbeddingFunction implements IEmbeddingFunction {
      * @returns Array of embedding vectors.
      */
     generate(texts: string[]): Promise<number[][]>;
-    /**
-     * Extract dense embedding from encode result.
-     */
-    private extractDense;
     /**
      * Close the underlying client connection.
      */
@@ -198,10 +194,6 @@ declare class SIESparseEmbeddingFunction {
      * @returns Array of sparse embeddings as {[tokenId]: weight} dicts.
      */
     generateAsDict(texts: string[]): Promise<Record<number, number>[]>;
-    /**
-     * Extract sparse embedding from encode result.
-     */
-    private extractSparse;
     /**
      * Close the underlying client connection.
      */

package/dist/index.js

@@ -1,7 +1,8 @@
 // src/index.ts
 import {
   SIEClient,
-  toNumberArray
+  denseEmbedding,
+  sparseEmbedding
 } from "@superlinked/sie-sdk";
 var SIEEmbeddingFunction = class {
   model;
@@ -50,17 +51,7 @@ var SIEEmbeddingFunction = class {
       outputTypes: ["dense"]
     };
     const results = await this.client.encode(this.model, items, options);
-    return results.map((result) => this.extractDense(result));
-  }
-  /**
-   * Extract dense embedding from encode result.
-   */
-  extractDense(result) {
-    const dense = result.dense;
-    if (!dense) {
-      throw new Error("Encode result missing dense embedding");
-    }
-    return toNumberArray(dense);
+    return results.map((result) => denseEmbedding(result));
   }
   /**
    * Close the underlying client connection.
@@ -114,7 +105,7 @@ var SIESparseEmbeddingFunction = class {
       outputTypes: ["sparse"]
     };
     const results = await this.client.encode(this.model, items, options);
-    return results.map((result) => this.extractSparse(result));
+    return results.map((result) => sparseEmbedding(result));
   }
   /**
    * Generate sparse embeddings as dict format (token_id -> weight).
@@ -138,19 +129,6 @@ var SIESparseEmbeddingFunction = class {
       return dict;
     });
   }
-  /**
-   * Extract sparse embedding from encode result.
-   */
-  extractSparse(result) {
-    const sparse = result.sparse;
-    if (!sparse) {
-      return { indices: [], values: [] };
-    }
-    return {
-      indices: toNumberArray(sparse.indices),
-      values: toNumberArray(sparse.values)
-    };
-  }
   /**
    * Close the underlying client connection.
    */

package/dist/index.js.map

@@ -1 +1 @@
-{"version":3,"sources":["../src/index.ts"],"sourcesContent":["/**\n * SIE embedding functions for ChromaDB.\n *\n * Provides custom embedding functions that use SIE for generating embeddings:\n * - SIEEmbeddingFunction: Dense embeddings for standard Chroma collections\n *\n * @example\n * ```typescript\n * import { ChromaClient } from \"chromadb\";\n * import { SIEEmbeddingFunction } from \"@superlinked/sie-chroma\";\n *\n * const client = new ChromaClient();\n * const embeddingFunction = new SIEEmbeddingFunction({\n *   baseUrl: \"http://localhost:8080\",\n *   model: \"BAAI/bge-m3\",\n * });\n *\n * const collection = await client.createCollection({\n *   name: \"my_collection\",\n *   embeddingFunction,\n * });\n *\n * await collection.add({\n *   ids: [\"doc1\", \"doc2\"],\n *   documents: [\"Hello world\", \"Goodbye world\"],\n * });\n * ```\n */\n\nimport {\n  type EncodeOptions,\n  type EncodeResult,\n  SIEClient,\n  type SIEClientOptions,\n  toNumberArray,\n} from \"@superlinked/sie-sdk\";\nimport type { IEmbeddingFunction } from \"chromadb\";\n\n/**\n * Configuration options for SIEEmbeddingFunction.\n */\nexport interface SIEEmbeddingFunctionOptions {\n  /**\n   * URL of the SIE server.\n   * @default \"http://localhost:8080\"\n   */\n  baseUrl?: string;\n\n  /**\n   * Model name/ID to use for encoding.\n   * @default \"BAAI/bge-m3\"\n   */\n  model?: string;\n\n  /**\n   * Optional pre-configured SIEClient instance.\n   */\n  client?: SIEClient;\n\n  /**\n   * Target GPU type for routing (e.g., \"l4\", \"a100-80gb\").\n   */\n  gpu?: string;\n\n  /**\n   * Request timeout in milliseconds.\n   * @default 180000 (3 minutes)\n   */\n  timeout?: number;\n}\n\n/**\n * Embedding function using SIE for ChromaDB collections.\n *\n * This class implements ChromaDB's IEmbeddingFunction interface,\n * allowing SIE to generate embeddings for document storage and retrieval.\n *\n * @example\n * ```typescript\n * import { ChromaClient } from \"chromadb\";\n * import { SIEEmbeddingFunction } from \"@superlinked/sie-chroma\";\n *\n * const embeddingFunction = new SIEEmbeddingFunction({\n *   baseUrl: \"http://localhost:8080\",\n *   model: \"BAAI/bge-m3\",\n * });\n *\n * const client = new ChromaClient();\n * const collection = await client.createCollection({\n *   name: \"my_collection\",\n *   embeddingFunction,\n * });\n *\n * // Add documents (embeddings generated automatically)\n * await collection.add({\n *   ids: [\"doc1\", \"doc2\"],\n *   documents: [\"First document\", \"Second document\"],\n * });\n *\n * // Query (query embedding generated automatically)\n * const results = await collection.query({\n *   queryTexts: [\"search query\"],\n *   nResults: 5,\n * });\n * ```\n */\nexport class SIEEmbeddingFunction implements IEmbeddingFunction {\n  private readonly model: string;\n  private _client: SIEClient | undefined;\n  private readonly baseUrl: string;\n  private readonly clientOptions: SIEClientOptions;\n\n  constructor(options: SIEEmbeddingFunctionOptions = {}) {\n    const {\n      baseUrl = \"http://localhost:8080\",\n      model = \"BAAI/bge-m3\",\n      client,\n      gpu,\n      timeout = 180_000,\n    } = options;\n\n    this.baseUrl = baseUrl;\n    this.model = model;\n    this._client = client;\n    this.clientOptions = {\n      timeout,\n      gpu,\n    };\n  }\n\n  /**\n   * Get or create the SIEClient.\n   */\n  private get client(): SIEClient {\n    if (!this._client) {\n      this._client = new SIEClient(this.baseUrl, this.clientOptions);\n    }\n    return this._client;\n  }\n\n  /**\n   * Generate embeddings for documents.\n   *\n   * This method is called by ChromaDB when adding documents or querying.\n   *\n   * @param texts - Array of document texts to embed.\n   * @returns Array of embedding vectors.\n   */\n  async generate(texts: string[]): Promise<number[][]> {\n    if (texts.length === 0) {\n      return [];\n    }\n\n    const items = texts.map((text) => ({ text }));\n    const options: EncodeOptions = {\n      outputTypes: [\"dense\"],\n    };\n\n    const results = await this.client.encode(this.model, items, options);\n    return (results as EncodeResult[]).map((result) => this.extractDense(result));\n  }\n\n  /**\n   * Extract dense embedding from encode result.\n   */\n  private extractDense(result: EncodeResult): number[] {\n    const dense = result.dense;\n    if (!dense) {\n      throw new Error(\"Encode result missing dense embedding\");\n    }\n    return toNumberArray(dense);\n  }\n\n  /**\n   * Close the underlying client connection.\n   */\n  async close(): Promise<void> {\n    if (this._client) {\n      await this._client.close();\n    }\n  }\n}\n\n/**\n * Sparse embedding representation for ChromaDB hybrid search.\n */\nexport interface SparseEmbedding {\n  indices: number[];\n  values: number[];\n}\n\n/**\n * Configuration options for SIESparseEmbeddingFunction.\n */\nexport interface SIESparseEmbeddingFunctionOptions {\n  /**\n   * URL of the SIE server.\n   * @default \"http://localhost:8080\"\n   */\n  baseUrl?: string;\n\n  /**\n   * Model name/ID to use for encoding. Must support sparse output.\n   * @default \"BAAI/bge-m3\"\n   */\n  model?: string;\n\n  /**\n   * Target GPU type for routing (e.g., \"l4\", \"a100-80gb\").\n   */\n  gpu?: string;\n\n  /**\n   * Request timeout in milliseconds.\n   * @default 180000 (3 minutes)\n   */\n  timeout?: number;\n}\n\n/**\n * Sparse embedding function using SIE for ChromaDB hybrid search.\n *\n * Generates sparse embeddings that can be used with ChromaDB's hybrid\n * search capabilities. Returns embeddings as {indices, values} pairs.\n *\n * @example\n * ```typescript\n * import { SIESparseEmbeddingFunction } from \"@superlinked/sie-chroma\";\n *\n * const sparseEf = new SIESparseEmbeddingFunction({\n *   baseUrl: \"http://localhost:8080\",\n *   model: \"BAAI/bge-m3\",\n * });\n *\n * const embeddings = await sparseEf.generate([\"Hello world\"]);\n * console.log(embeddings[0].indices); // [1, 5, 10, ...]\n * console.log(embeddings[0].values);  // [0.5, 0.3, 0.2, ...]\n * ```\n */\nexport class SIESparseEmbeddingFunction {\n  private readonly model: string;\n  private _client: SIEClient | undefined;\n  private readonly baseUrl: string;\n  private readonly clientOptions: SIEClientOptions;\n\n  constructor(options: SIESparseEmbeddingFunctionOptions = {}) {\n    const {\n      baseUrl = \"http://localhost:8080\",\n      model = \"BAAI/bge-m3\",\n      gpu,\n      timeout = 180_000,\n    } = options;\n\n    this.baseUrl = baseUrl;\n    this.model = model;\n    this.clientOptions = {\n      timeout,\n      gpu,\n    };\n  }\n\n  /**\n   * Get or create the SIEClient.\n   */\n  private get client(): SIEClient {\n    if (!this._client) {\n      this._client = new SIEClient(this.baseUrl, this.clientOptions);\n    }\n    return this._client;\n  }\n\n  /**\n   * Generate sparse embeddings for documents.\n   *\n   * @param texts - Array of document texts to embed.\n   * @returns Array of sparse embeddings with indices and values.\n   */\n  async generate(texts: string[]): Promise<SparseEmbedding[]> {\n    if (texts.length === 0) {\n      return [];\n    }\n\n    const items = texts.map((text) => ({ text }));\n    const options: EncodeOptions = {\n      outputTypes: [\"sparse\"],\n    };\n\n    const results = await this.client.encode(this.model, items, options);\n    return (results as EncodeResult[]).map((result) => this.extractSparse(result));\n  }\n\n  /**\n   * Generate sparse embeddings as dict format (token_id -> weight).\n   *\n   * This format is compatible with some ChromaDB hybrid search configurations.\n   *\n   * @param texts - Array of document texts to embed.\n   * @returns Array of sparse embeddings as {[tokenId]: weight} dicts.\n   */\n  async generateAsDict(texts: string[]): Promise<Record<number, number>[]> {\n    const embeddings = await this.generate(texts);\n    return embeddings.map((emb) => {\n      const dict: Record<number, number> = {};\n      for (let i = 0; i < emb.indices.length; i++) {\n        const idx = emb.indices[i];\n        const val = emb.values[i];\n        if (idx !== undefined && val !== undefined) {\n          dict[idx] = val;\n        }\n      }\n      return dict;\n    });\n  }\n\n  /**\n   * Extract sparse embedding from encode result.\n   */\n  private extractSparse(result: EncodeResult): SparseEmbedding {\n    const sparse = result.sparse;\n    if (!sparse) {\n      return { indices: [], values: [] };\n    }\n\n    return {\n      indices: toNumberArray(sparse.indices),\n      values: toNumberArray(sparse.values),\n    };\n  }\n\n  /**\n   * Close the underlying client connection.\n   */\n  async close(): Promise<void> {\n    if (this._client) {\n      await this._client.close();\n    }\n  }\n}\n"],"mappings":";AA6BA;AAAA,EAGE;AAAA,EAEA;AAAA,OACK;AAuEA,IAAM,uBAAN,MAAyD;AAAA,EAC7C;AAAA,EACT;AAAA,EACS;AAAA,EACA;AAAA,EAEjB,YAAY,UAAuC,CAAC,GAAG;AACrD,UAAM;AAAA,MACJ,UAAU;AAAA,MACV,QAAQ;AAAA,MACR;AAAA,MACA;AAAA,MACA,UAAU;AAAA,IACZ,IAAI;AAEJ,SAAK,UAAU;AACf,SAAK,QAAQ;AACb,SAAK,UAAU;AACf,SAAK,gBAAgB;AAAA,MACnB;AAAA,MACA;AAAA,IACF;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,IAAY,SAAoB;AAC9B,QAAI,CAAC,KAAK,SAAS;AACjB,WAAK,UAAU,IAAI,UAAU,KAAK,SAAS,KAAK,aAAa;AAAA,IAC/D;AACA,WAAO,KAAK;AAAA,EACd;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAUA,MAAM,SAAS,OAAsC;AACnD,QAAI,MAAM,WAAW,GAAG;AACtB,aAAO,CAAC;AAAA,IACV;AAEA,UAAM,QAAQ,MAAM,IAAI,CAAC,UAAU,EAAE,KAAK,EAAE;AAC5C,UAAM,UAAyB;AAAA,MAC7B,aAAa,CAAC,OAAO;AAAA,IACvB;AAEA,UAAM,UAAU,MAAM,KAAK,OAAO,OAAO,KAAK,OAAO,OAAO,OAAO;AACnE,WAAQ,QAA2B,IAAI,CAAC,WAAW,KAAK,aAAa,MAAM,CAAC;AAAA,EAC9E;AAAA;AAAA;AAAA;AAAA,EAKQ,aAAa,QAAgC;AACnD,UAAM,QAAQ,OAAO;AACrB,QAAI,CAAC,OAAO;AACV,YAAM,IAAI,MAAM,uCAAuC;AAAA,IACzD;AACA,WAAO,cAAc,KAAK;AAAA,EAC5B;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,QAAuB;AAC3B,QAAI,KAAK,SAAS;AAChB,YAAM,KAAK,QAAQ,MAAM;AAAA,IAC3B;AAAA,EACF;AACF;AA0DO,IAAM,6BAAN,MAAiC;AAAA,EACrB;AAAA,EACT;AAAA,EACS;AAAA,EACA;AAAA,EAEjB,YAAY,UAA6C,CAAC,GAAG;AAC3D,UAAM;AAAA,MACJ,UAAU;AAAA,MACV,QAAQ;AAAA,MACR;AAAA,MACA,UAAU;AAAA,IACZ,IAAI;AAEJ,SAAK,UAAU;AACf,SAAK,QAAQ;AACb,SAAK,gBAAgB;AAAA,MACnB;AAAA,MACA;AAAA,IACF;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,IAAY,SAAoB;AAC9B,QAAI,CAAC,KAAK,SAAS;AACjB,WAAK,UAAU,IAAI,UAAU,KAAK,SAAS,KAAK,aAAa;AAAA,IAC/D;AACA,WAAO,KAAK;AAAA,EACd;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQA,MAAM,SAAS,OAA6C;AAC1D,QAAI,MAAM,WAAW,GAAG;AACtB,aAAO,CAAC;AAAA,IACV;AAEA,UAAM,QAAQ,MAAM,IAAI,CAAC,UAAU,EAAE,KAAK,EAAE;AAC5C,UAAM,UAAyB;AAAA,MAC7B,aAAa,CAAC,QAAQ;AAAA,IACxB;AAEA,UAAM,UAAU,MAAM,KAAK,OAAO,OAAO,KAAK,OAAO,OAAO,OAAO;AACnE,WAAQ,QAA2B,IAAI,CAAC,WAAW,KAAK,cAAc,MAAM,CAAC;AAAA,EAC/E;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAUA,MAAM,eAAe,OAAoD;AACvE,UAAM,aAAa,MAAM,KAAK,SAAS,KAAK;AAC5C,WAAO,WAAW,IAAI,CAAC,QAAQ;AAC7B,YAAM,OAA+B,CAAC;AACtC,eAAS,IAAI,GAAG,IAAI,IAAI,QAAQ,QAAQ,KAAK;AAC3C,cAAM,MAAM,IAAI,QAAQ,CAAC;AACzB,cAAM,MAAM,IAAI,OAAO,CAAC;AACxB,YAAI,QAAQ,UAAa,QAAQ,QAAW;AAC1C,eAAK,GAAG,IAAI;AAAA,QACd;AAAA,MACF;AACA,aAAO;AAAA,IACT,CAAC;AAAA,EACH;AAAA;AAAA;AAAA;AAAA,EAKQ,cAAc,QAAuC;AAC3D,UAAM,SAAS,OAAO;AACtB,QAAI,CAAC,QAAQ;AACX,aAAO,EAAE,SAAS,CAAC,GAAG,QAAQ,CAAC,EAAE;AAAA,IACnC;AAEA,WAAO;AAAA,MACL,SAAS,cAAc,OAAO,OAAO;AAAA,MACrC,QAAQ,cAAc,OAAO,MAAM;AAAA,IACrC;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,QAAuB;AAC3B,QAAI,KAAK,SAAS;AAChB,YAAM,KAAK,QAAQ,MAAM;AAAA,IAC3B;AAAA,EACF;AACF;","names":[]}
+{"version":3,"sources":["../src/index.ts"],"sourcesContent":["/**\n * SIE embedding functions for ChromaDB.\n *\n * Provides custom embedding functions that use SIE for generating embeddings:\n * - SIEEmbeddingFunction: Dense embeddings for standard Chroma collections\n *\n * @example\n * ```typescript\n * import { ChromaClient } from \"chromadb\";\n * import { SIEEmbeddingFunction } from \"@superlinked/sie-chroma\";\n *\n * const client = new ChromaClient();\n * const embeddingFunction = new SIEEmbeddingFunction({\n *   baseUrl: \"http://localhost:8080\",\n *   model: \"BAAI/bge-m3\",\n * });\n *\n * const collection = await client.createCollection({\n *   name: \"my_collection\",\n *   embeddingFunction,\n * });\n *\n * await collection.add({\n *   ids: [\"doc1\", \"doc2\"],\n *   documents: [\"Hello world\", \"Goodbye world\"],\n * });\n * ```\n */\n\nimport {\n  type EncodeOptions,\n  type EncodeResult,\n  SIEClient,\n  type SIEClientOptions,\n  denseEmbedding,\n  sparseEmbedding,\n} from \"@superlinked/sie-sdk\";\nimport type { IEmbeddingFunction } from \"chromadb\";\n\n/**\n * Configuration options for SIEEmbeddingFunction.\n */\nexport interface SIEEmbeddingFunctionOptions {\n  /**\n   * URL of the SIE server.\n   * @default \"http://localhost:8080\"\n   */\n  baseUrl?: string;\n\n  /**\n   * Model name/ID to use for encoding.\n   * @default \"BAAI/bge-m3\"\n   */\n  model?: string;\n\n  /**\n   * Optional pre-configured SIEClient instance.\n   */\n  client?: SIEClient;\n\n  /**\n   * Target GPU type for routing (e.g., \"l4\", \"a100-80gb\").\n   */\n  gpu?: string;\n\n  /**\n   * Request timeout in milliseconds.\n   * @default 180000 (3 minutes)\n   */\n  timeout?: number;\n}\n\n/**\n * Embedding function using SIE for ChromaDB collections.\n *\n * This class implements ChromaDB's IEmbeddingFunction interface,\n * allowing SIE to generate embeddings for document storage and retrieval.\n *\n * @example\n * ```typescript\n * import { ChromaClient } from \"chromadb\";\n * import { SIEEmbeddingFunction } from \"@superlinked/sie-chroma\";\n *\n * const embeddingFunction = new SIEEmbeddingFunction({\n *   baseUrl: \"http://localhost:8080\",\n *   model: \"BAAI/bge-m3\",\n * });\n *\n * const client = new ChromaClient();\n * const collection = await client.createCollection({\n *   name: \"my_collection\",\n *   embeddingFunction,\n * });\n *\n * // Add documents (embeddings generated automatically)\n * await collection.add({\n *   ids: [\"doc1\", \"doc2\"],\n *   documents: [\"First document\", \"Second document\"],\n * });\n *\n * // Query (query embedding generated automatically)\n * const results = await collection.query({\n *   queryTexts: [\"search query\"],\n *   nResults: 5,\n * });\n * ```\n */\nexport class SIEEmbeddingFunction implements IEmbeddingFunction {\n  private readonly model: string;\n  private _client: SIEClient | undefined;\n  private readonly baseUrl: string;\n  private readonly clientOptions: SIEClientOptions;\n\n  constructor(options: SIEEmbeddingFunctionOptions = {}) {\n    const {\n      baseUrl = \"http://localhost:8080\",\n      model = \"BAAI/bge-m3\",\n      client,\n      gpu,\n      timeout = 180_000,\n    } = options;\n\n    this.baseUrl = baseUrl;\n    this.model = model;\n    this._client = client;\n    this.clientOptions = {\n      timeout,\n      gpu,\n    };\n  }\n\n  /**\n   * Get or create the SIEClient.\n   */\n  private get client(): SIEClient {\n    if (!this._client) {\n      this._client = new SIEClient(this.baseUrl, this.clientOptions);\n    }\n    return this._client;\n  }\n\n  /**\n   * Generate embeddings for documents.\n   *\n   * This method is called by ChromaDB when adding documents or querying.\n   *\n   * @param texts - Array of document texts to embed.\n   * @returns Array of embedding vectors.\n   */\n  async generate(texts: string[]): Promise<number[][]> {\n    if (texts.length === 0) {\n      return [];\n    }\n\n    const items = texts.map((text) => ({ text }));\n    const options: EncodeOptions = {\n      outputTypes: [\"dense\"],\n    };\n\n    const results = await this.client.encode(this.model, items, options);\n    return (results as EncodeResult[]).map((result) => denseEmbedding(result));\n  }\n\n  /**\n   * Close the underlying client connection.\n   */\n  async close(): Promise<void> {\n    if (this._client) {\n      await this._client.close();\n    }\n  }\n}\n\n/**\n * Sparse embedding representation for ChromaDB hybrid search.\n */\nexport interface SparseEmbedding {\n  indices: number[];\n  values: number[];\n}\n\n/**\n * Configuration options for SIESparseEmbeddingFunction.\n */\nexport interface SIESparseEmbeddingFunctionOptions {\n  /**\n   * URL of the SIE server.\n   * @default \"http://localhost:8080\"\n   */\n  baseUrl?: string;\n\n  /**\n   * Model name/ID to use for encoding. Must support sparse output.\n   * @default \"BAAI/bge-m3\"\n   */\n  model?: string;\n\n  /**\n   * Target GPU type for routing (e.g., \"l4\", \"a100-80gb\").\n   */\n  gpu?: string;\n\n  /**\n   * Request timeout in milliseconds.\n   * @default 180000 (3 minutes)\n   */\n  timeout?: number;\n}\n\n/**\n * Sparse embedding function using SIE for ChromaDB hybrid search.\n *\n * Generates sparse embeddings that can be used with ChromaDB's hybrid\n * search capabilities. Returns embeddings as {indices, values} pairs.\n *\n * @example\n * ```typescript\n * import { SIESparseEmbeddingFunction } from \"@superlinked/sie-chroma\";\n *\n * const sparseEf = new SIESparseEmbeddingFunction({\n *   baseUrl: \"http://localhost:8080\",\n *   model: \"BAAI/bge-m3\",\n * });\n *\n * const embeddings = await sparseEf.generate([\"Hello world\"]);\n * console.log(embeddings[0].indices); // [1, 5, 10, ...]\n * console.log(embeddings[0].values);  // [0.5, 0.3, 0.2, ...]\n * ```\n */\nexport class SIESparseEmbeddingFunction {\n  private readonly model: string;\n  private _client: SIEClient | undefined;\n  private readonly baseUrl: string;\n  private readonly clientOptions: SIEClientOptions;\n\n  constructor(options: SIESparseEmbeddingFunctionOptions = {}) {\n    const {\n      baseUrl = \"http://localhost:8080\",\n      model = \"BAAI/bge-m3\",\n      gpu,\n      timeout = 180_000,\n    } = options;\n\n    this.baseUrl = baseUrl;\n    this.model = model;\n    this.clientOptions = {\n      timeout,\n      gpu,\n    };\n  }\n\n  /**\n   * Get or create the SIEClient.\n   */\n  private get client(): SIEClient {\n    if (!this._client) {\n      this._client = new SIEClient(this.baseUrl, this.clientOptions);\n    }\n    return this._client;\n  }\n\n  /**\n   * Generate sparse embeddings for documents.\n   *\n   * @param texts - Array of document texts to embed.\n   * @returns Array of sparse embeddings with indices and values.\n   */\n  async generate(texts: string[]): Promise<SparseEmbedding[]> {\n    if (texts.length === 0) {\n      return [];\n    }\n\n    const items = texts.map((text) => ({ text }));\n    const options: EncodeOptions = {\n      outputTypes: [\"sparse\"],\n    };\n\n    const results = await this.client.encode(this.model, items, options);\n    return (results as EncodeResult[]).map((result) => sparseEmbedding(result));\n  }\n\n  /**\n   * Generate sparse embeddings as dict format (token_id -> weight).\n   *\n   * This format is compatible with some ChromaDB hybrid search configurations.\n   *\n   * @param texts - Array of document texts to embed.\n   * @returns Array of sparse embeddings as {[tokenId]: weight} dicts.\n   */\n  async generateAsDict(texts: string[]): Promise<Record<number, number>[]> {\n    const embeddings = await this.generate(texts);\n    return embeddings.map((emb) => {\n      const dict: Record<number, number> = {};\n      for (let i = 0; i < emb.indices.length; i++) {\n        const idx = emb.indices[i];\n        const val = emb.values[i];\n        if (idx !== undefined && val !== undefined) {\n          dict[idx] = val;\n        }\n      }\n      return dict;\n    });\n  }\n\n  /**\n   * Close the underlying client connection.\n   */\n  async close(): Promise<void> {\n    if (this._client) {\n      await this._client.close();\n    }\n  }\n}\n"],"mappings":";AA6BA;AAAA,EAGE;AAAA,EAEA;AAAA,EACA;AAAA,OACK;AAuEA,IAAM,uBAAN,MAAyD;AAAA,EAC7C;AAAA,EACT;AAAA,EACS;AAAA,EACA;AAAA,EAEjB,YAAY,UAAuC,CAAC,GAAG;AACrD,UAAM;AAAA,MACJ,UAAU;AAAA,MACV,QAAQ;AAAA,MACR;AAAA,MACA;AAAA,MACA,UAAU;AAAA,IACZ,IAAI;AAEJ,SAAK,UAAU;AACf,SAAK,QAAQ;AACb,SAAK,UAAU;AACf,SAAK,gBAAgB;AAAA,MACnB;AAAA,MACA;AAAA,IACF;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,IAAY,SAAoB;AAC9B,QAAI,CAAC,KAAK,SAAS;AACjB,WAAK,UAAU,IAAI,UAAU,KAAK,SAAS,KAAK,aAAa;AAAA,IAC/D;AACA,WAAO,KAAK;AAAA,EACd;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAUA,MAAM,SAAS,OAAsC;AACnD,QAAI,MAAM,WAAW,GAAG;AACtB,aAAO,CAAC;AAAA,IACV;AAEA,UAAM,QAAQ,MAAM,IAAI,CAAC,UAAU,EAAE,KAAK,EAAE;AAC5C,UAAM,UAAyB;AAAA,MAC7B,aAAa,CAAC,OAAO;AAAA,IACvB;AAEA,UAAM,UAAU,MAAM,KAAK,OAAO,OAAO,KAAK,OAAO,OAAO,OAAO;AACnE,WAAQ,QAA2B,IAAI,CAAC,WAAW,eAAe,MAAM,CAAC;AAAA,EAC3E;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,QAAuB;AAC3B,QAAI,KAAK,SAAS;AAChB,YAAM,KAAK,QAAQ,MAAM;AAAA,IAC3B;AAAA,EACF;AACF;AA0DO,IAAM,6BAAN,MAAiC;AAAA,EACrB;AAAA,EACT;AAAA,EACS;AAAA,EACA;AAAA,EAEjB,YAAY,UAA6C,CAAC,GAAG;AAC3D,UAAM;AAAA,MACJ,UAAU;AAAA,MACV,QAAQ;AAAA,MACR;AAAA,MACA,UAAU;AAAA,IACZ,IAAI;AAEJ,SAAK,UAAU;AACf,SAAK,QAAQ;AACb,SAAK,gBAAgB;AAAA,MACnB;AAAA,MACA;AAAA,IACF;AAAA,EACF;AAAA;AAAA;AAAA;AAAA,EAKA,IAAY,SAAoB;AAC9B,QAAI,CAAC,KAAK,SAAS;AACjB,WAAK,UAAU,IAAI,UAAU,KAAK,SAAS,KAAK,aAAa;AAAA,IAC/D;AACA,WAAO,KAAK;AAAA,EACd;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAQA,MAAM,SAAS,OAA6C;AAC1D,QAAI,MAAM,WAAW,GAAG;AACtB,aAAO,CAAC;AAAA,IACV;AAEA,UAAM,QAAQ,MAAM,IAAI,CAAC,UAAU,EAAE,KAAK,EAAE;AAC5C,UAAM,UAAyB;AAAA,MAC7B,aAAa,CAAC,QAAQ;AAAA,IACxB;AAEA,UAAM,UAAU,MAAM,KAAK,OAAO,OAAO,KAAK,OAAO,OAAO,OAAO;AACnE,WAAQ,QAA2B,IAAI,CAAC,WAAW,gBAAgB,MAAM,CAAC;AAAA,EAC5E;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA;AAAA,EAUA,MAAM,eAAe,OAAoD;AACvE,UAAM,aAAa,MAAM,KAAK,SAAS,KAAK;AAC5C,WAAO,WAAW,IAAI,CAAC,QAAQ;AAC7B,YAAM,OAA+B,CAAC;AACtC,eAAS,IAAI,GAAG,IAAI,IAAI,QAAQ,QAAQ,KAAK;AAC3C,cAAM,MAAM,IAAI,QAAQ,CAAC;AACzB,cAAM,MAAM,IAAI,OAAO,CAAC;AACxB,YAAI,QAAQ,UAAa,QAAQ,QAAW;AAC1C,eAAK,GAAG,IAAI;AAAA,QACd;AAAA,MACF;AACA,aAAO;AAAA,IACT,CAAC;AAAA,EACH;AAAA;AAAA;AAAA;AAAA,EAKA,MAAM,QAAuB;AAC3B,QAAI,KAAK,SAAS;AAChB,YAAM,KAAK,QAAQ,MAAM;AAAA,IAC3B;AAAA,EACF;AACF;","names":[]}

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@superlinked/sie-chroma",
-  "version": "0.1.9",
+  "version": "0.2.0",
   "description": "SIE embedding function for ChromaDB",
   "type": "module",
   "main": "./dist/index.cjs",
@@ -17,7 +17,7 @@
     "dist"
   ],
   "dependencies": {
-    "@superlinked/sie-sdk": "0.1.9"
+    "@superlinked/sie-sdk": "0.2.0"
   },
   "peerDependencies": {
     "chromadb": ">=1.9.0"