@langchain/classic 1.0.40 → 1.0.42

package/dist/experimental/babyagi/agent.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"agent.cjs","names":["BaseChain","Document","TaskCreationChain","TaskPrioritizationChain","TaskExecutionChain"],"sources":["../../../src/experimental/babyagi/agent.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport type { VectorStoreInterface } from \"@langchain/core/vectorstores\";\nimport { Document } from \"@langchain/core/documents\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { BaseChain, ChainInputs } from \"../../chains/base.js\";\nimport { SerializedBaseChain } from \"../../chains/serde.js\";\nimport { Optional } from \"../../types/type-utils.js\";\nimport { TaskCreationChain } from \"./task_creation.js\";\nimport { TaskExecutionChain } from \"./task_execution.js\";\nimport { TaskPrioritizationChain } from \"./task_prioritization.js\";\n\n/**\n * Interface defining the structure of a task. A task has a `taskID` and a\n * `taskName`.\n */\nexport interface Task {\n  taskID: string;\n  taskName: string;\n}\n\n/**\n * Interface defining the structure of the inputs for the `BabyAGI` class.\n * It extends the `ChainInputs` interface, omitting the 'memory' and\n * 'callbackManager' properties, and adds properties specific to\n * `BabyAGI`.\n */\nexport interface BabyAGIInputs extends Omit<\n  ChainInputs,\n  \"memory\" | \"callbackManager\"\n> {\n  creationChain: BaseChain;\n  prioritizationChain: BaseChain;\n  executionChain: BaseChain;\n  vectorstore: VectorStoreInterface;\n  maxIterations?: number;\n}\n\n/**\n * Class responsible for managing tasks, including their creation,\n * prioritization, and execution. It uses three chains for these\n * operations: `creationChain`, `prioritizationChain`, and\n * `executionChain`.\n * @example\n * ```typescript\n * const babyAGI = BabyAGI.fromLLM({\n *   llm: new OpenAI({ temperature: 0 }),\n *   vectorstore: new MemoryVectorStore(new OpenAIEmbeddings()),\n *   maxIterations: 3,\n * });\n *\n * const result = await babyAGI.call({\n *   objective: \"Write a weather report for SF today\",\n * });\n * ```\n */\nexport class BabyAGI extends BaseChain implements BabyAGIInputs {\n  static lc_name() {\n    return \"BabyAGI\";\n  }\n\n  taskList: Task[];\n\n  creationChain: BaseChain;\n\n  prioritizationChain: BaseChain;\n\n  executionChain: BaseChain;\n\n  taskIDCounter: number;\n\n  vectorstore: VectorStoreInterface;\n\n  maxIterations: number;\n\n  constructor({\n    creationChain,\n    prioritizationChain,\n    executionChain,\n    vectorstore,\n    maxIterations = 100,\n    verbose,\n    callbacks,\n  }: BabyAGIInputs) {\n    super(undefined, verbose, callbacks);\n    this.taskList = [];\n    this.creationChain = creationChain;\n    this.prioritizationChain = prioritizationChain;\n    this.executionChain = executionChain;\n    this.taskIDCounter = 1;\n    this.vectorstore = vectorstore;\n    this.maxIterations = maxIterations;\n  }\n\n  _chainType() {\n    return \"BabyAGI\" as const;\n  }\n\n  get inputKeys() {\n    return [\"objective\", \"firstTask\"];\n  }\n\n  get outputKeys() {\n    return [];\n  }\n\n  /**\n   * Adds a task to the task list.\n   * @param task The task to be added.\n   * @returns Promise resolving to void.\n   */\n  async addTask(task: Task) {\n    this.taskList.push(task);\n  }\n\n  /**\n   * Prints the current task list to the console.\n   * @returns void\n   */\n  printTaskList() {\n    console.log(\"\\x1b[95m\\x1b[1m\\n*****TASK LIST*****\\n\\x1b[0m\\x1b[0m\");\n    for (const t of this.taskList) {\n      console.log(`${t.taskID}: ${t.taskName}`);\n    }\n  }\n\n  /**\n   * Prints the next task to the console.\n   * @param task The next task to be printed.\n   * @returns void\n   */\n  printNextTask(task: Task) {\n    console.log(\"\\x1b[92m\\x1b[1m\\n*****NEXT TASK*****\\n\\x1b[0m\\x1b[0m\");\n    console.log(`${task.taskID}: ${task.taskName}`);\n  }\n\n  /**\n   * Prints the result of a task to the console.\n   * @param result The result of the task.\n   * @returns void\n   */\n  printTaskResult(result: string) {\n    console.log(\"\\x1b[93m\\x1b[1m\\n*****TASK RESULT*****\\n\\x1b[0m\\x1b[0m\");\n    console.log(result.trim());\n  }\n\n  /**\n   * Generates the next tasks based on the result of the previous task, the\n   * task description, and the objective.\n   * @param result The result of the previous task.\n   * @param task_description The description of the task.\n   * @param objective The objective of the task.\n   * @param runManager Optional CallbackManagerForChainRun instance.\n   * @returns Promise resolving to an array of tasks without taskID.\n   */\n  async getNextTasks(\n    result: string,\n    task_description: string,\n    objective: string,\n    runManager?: CallbackManagerForChainRun\n  ): Promise<Optional<Task, \"taskID\">[]> {\n    const taskNames = this.taskList.map((t) => t.taskName);\n    const incomplete_tasks = taskNames.join(\", \");\n    const { [this.creationChain.outputKeys[0]]: text } =\n      await this.creationChain.call(\n        {\n          result,\n          task_description,\n          incomplete_tasks,\n          objective,\n        },\n        runManager?.getChild()\n      );\n    const newTasks = (text as string).split(\"\\n\");\n    return newTasks\n      .filter((taskName) => taskName.trim())\n      .map((taskName) => ({ taskName }));\n  }\n\n  /**\n   * Prioritizes the tasks based on the current task ID and the objective.\n   * @param thisTaskID The ID of the current task.\n   * @param objective The objective of the task.\n   * @param runManager Optional CallbackManagerForChainRun instance.\n   * @returns Promise resolving to an array of prioritized tasks.\n   */\n  async prioritizeTasks(\n    thisTaskID: number,\n    objective: string,\n    runManager?: CallbackManagerForChainRun\n  ) {\n    const taskNames = this.taskList.map((t) => t.taskName);\n    const nextTaskID = thisTaskID + 1;\n    const { [this.prioritizationChain.outputKeys[0]]: text } =\n      await this.prioritizationChain.call(\n        {\n          task_names: taskNames.join(\", \"),\n          next_task_id: String(nextTaskID),\n          objective,\n        },\n        runManager?.getChild()\n      );\n    const newTasks = (text as string).trim().split(\"\\n\");\n    const prioritizedTaskList = [];\n    for (const taskString of newTasks) {\n      const taskParts = taskString.trim().split(\".\", 2);\n      if (taskParts.length === 2) {\n        const taskID = taskParts[0].trim();\n        const taskName = taskParts[1].trim();\n        prioritizedTaskList.push({ taskID, taskName });\n      }\n    }\n    return prioritizedTaskList;\n  }\n\n  /**\n   * Retrieves the top tasks that are most similar to the given query.\n   * @param query The query to search for.\n   * @param k The number of top tasks to retrieve.\n   * @returns Promise resolving to an array of top tasks.\n   */\n  async getTopTasks(query: string, k = 5) {\n    const results = await this.vectorstore.similaritySearch(query, k);\n    if (!results) {\n      return [];\n    }\n    return results.map((item) => String(item.metadata.task));\n  }\n\n  /**\n   * Executes a task based on the objective and the task description.\n   * @param objective The objective of the task.\n   * @param task The task to be executed.\n   * @param runManager Optional CallbackManagerForChainRun instance.\n   * @returns Promise resolving to the result of the task execution as a string.\n   */\n  async executeTask(\n    objective: string,\n    task: string,\n    runManager?: CallbackManagerForChainRun\n  ) {\n    const context = await this.getTopTasks(objective);\n    const { [this.executionChain.outputKeys[0]]: text } =\n      await this.executionChain.call(\n        {\n          objective,\n          context: context.join(\"\\n\"),\n          task,\n        },\n        runManager?.getChild()\n      );\n    return text as string;\n  }\n\n  async _call(\n    { objective, firstTask = \"Make a todo list\" }: ChainValues,\n    runManager?: CallbackManagerForChainRun\n  ) {\n    this.taskList = [];\n    this.taskIDCounter = 1;\n    await this.addTask({ taskID: \"1\", taskName: firstTask });\n\n    let numIters = 0;\n    while (numIters < this.maxIterations && this.taskList.length > 0) {\n      this.printTaskList();\n\n      const task = this.taskList.shift()!;\n      this.printNextTask(task);\n\n      const result = await this.executeTask(\n        objective,\n        task.taskName,\n        runManager\n      );\n      const thisTaskID = parseInt(task.taskID, 10);\n      this.printTaskResult(result);\n\n      await this.vectorstore.addDocuments([\n        new Document({\n          pageContent: result,\n          metadata: { task: task.taskName },\n        }),\n      ]);\n\n      const newTasks = await this.getNextTasks(\n        result,\n        task.taskName,\n        objective,\n        runManager\n      );\n      for (const newTask of newTasks) {\n        this.taskIDCounter += 1;\n        newTask.taskID = this.taskIDCounter.toFixed();\n        await this.addTask(newTask as Task);\n      }\n      this.taskList = await this.prioritizeTasks(\n        thisTaskID,\n        objective,\n        runManager\n      );\n\n      numIters += 1;\n    }\n    return {};\n  }\n\n  serialize(): SerializedBaseChain {\n    throw new Error(\"Method not implemented.\");\n  }\n\n  /**\n   * Static method to create a new BabyAGI instance from a\n   * BaseLanguageModel.\n   * @param llm BaseLanguageModel instance used to generate a new BabyAGI instance.\n   * @param vectorstore VectorStore instance used to store and retrieve vectors.\n   * @param executionChain Optional BaseChain instance used to execute tasks.\n   * @param verbose Optional boolean indicating whether to log verbose output.\n   * @param callbacks Optional callbacks to be used during the execution of tasks.\n   * @param rest Optional additional parameters.\n   * @returns A new instance of BabyAGI.\n   */\n  static fromLLM({\n    llm,\n    vectorstore,\n    executionChain,\n    verbose,\n    callbacks,\n    ...rest\n  }: Optional<\n    BabyAGIInputs,\n    \"executionChain\" | \"creationChain\" | \"prioritizationChain\"\n  > & { llm: BaseLanguageModelInterface }) {\n    const creationChain = TaskCreationChain.fromLLM({\n      llm,\n      verbose,\n      callbacks,\n    });\n    const prioritizationChain = TaskPrioritizationChain.fromLLM({\n      llm,\n      verbose,\n      callbacks,\n    });\n    return new BabyAGI({\n      creationChain,\n      prioritizationChain,\n      executionChain:\n        executionChain ||\n        TaskExecutionChain.fromLLM({ llm, verbose, callbacks }),\n      vectorstore,\n      verbose,\n      callbacks,\n      ...rest,\n    });\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;AAwDA,IAAa,UAAb,MAAa,gBAAgBA,aAAAA,UAAmC;CAC9D,OAAO,UAAU;AACf,SAAO;;CAGT;CAEA;CAEA;CAEA;CAEA;CAEA;CAEA;CAEA,YAAY,EACV,eACA,qBACA,gBACA,aACA,gBAAgB,KAChB,SACA,aACgB;AAChB,QAAM,KAAA,GAAW,SAAS,UAAU;AACpC,OAAK,WAAW,EAAE;AAClB,OAAK,gBAAgB;AACrB,OAAK,sBAAsB;AAC3B,OAAK,iBAAiB;AACtB,OAAK,gBAAgB;AACrB,OAAK,cAAc;AACnB,OAAK,gBAAgB;;CAGvB,aAAa;AACX,SAAO;;CAGT,IAAI,YAAY;AACd,SAAO,CAAC,aAAa,YAAY;;CAGnC,IAAI,aAAa;AACf,SAAO,EAAE;;;;;;;CAQX,MAAM,QAAQ,MAAY;AACxB,OAAK,SAAS,KAAK,KAAK;;;;;;CAO1B,gBAAgB;AACd,UAAQ,IAAI,uDAAuD;AACnE,OAAK,MAAM,KAAK,KAAK,SACnB,SAAQ,IAAI,GAAG,EAAE,OAAO,IAAI,EAAE,WAAW;;;;;;;CAS7C,cAAc,MAAY;AACxB,UAAQ,IAAI,uDAAuD;AACnE,UAAQ,IAAI,GAAG,KAAK,OAAO,IAAI,KAAK,WAAW;;;;;;;CAQjD,gBAAgB,QAAgB;AAC9B,UAAQ,IAAI,yDAAyD;AACrE,UAAQ,IAAI,OAAO,MAAM,CAAC;;;;;;;;;;;CAY5B,MAAM,aACJ,QACA,kBACA,WACA,YACqC;EAErC,MAAM,mBADY,KAAK,SAAS,KAAK,MAAM,EAAE,SACX,CAAC,KAAK,KAAK;EAC7C,MAAM,GAAG,KAAK,cAAc,WAAW,KAAK,SAC1C,MAAM,KAAK,cAAc,KACvB;GACE;GACA;GACA;GACA;GACD,EACD,YAAY,UAAU,CACvB;AAEH,SADkB,KAAgB,MAAM,KACzB,CACZ,QAAQ,aAAa,SAAS,MAAM,CAAC,CACrC,KAAK,cAAc,EAAE,UAAU,EAAE;;;;;;;;;CAUtC,MAAM,gBACJ,YACA,WACA,YACA;EACA,MAAM,YAAY,KAAK,SAAS,KAAK,MAAM,EAAE,SAAS;EACtD,MAAM,aAAa,aAAa;EAChC,MAAM,GAAG,KAAK,oBAAoB,WAAW,KAAK,SAChD,MAAM,KAAK,oBAAoB,KAC7B;GACE,YAAY,UAAU,KAAK,KAAK;GAChC,cAAc,OAAO,WAAW;GAChC;GACD,EACD,YAAY,UAAU,CACvB;EACH,MAAM,WAAY,KAAgB,MAAM,CAAC,MAAM,KAAK;EACpD,MAAM,sBAAsB,EAAE;AAC9B,OAAK,MAAM,cAAc,UAAU;GACjC,MAAM,YAAY,WAAW,MAAM,CAAC,MAAM,KAAK,EAAE;AACjD,OAAI,UAAU,WAAW,GAAG;IAC1B,MAAM,SAAS,UAAU,GAAG,MAAM;IAClC,MAAM,WAAW,UAAU,GAAG,MAAM;AACpC,wBAAoB,KAAK;KAAE;KAAQ;KAAU,CAAC;;;AAGlD,SAAO;;;;;;;;CAST,MAAM,YAAY,OAAe,IAAI,GAAG;EACtC,MAAM,UAAU,MAAM,KAAK,YAAY,iBAAiB,OAAO,EAAE;AACjE,MAAI,CAAC,QACH,QAAO,EAAE;AAEX,SAAO,QAAQ,KAAK,SAAS,OAAO,KAAK,SAAS,KAAK,CAAC;;;;;;;;;CAU1D,MAAM,YACJ,WACA,MACA,YACA;EACA,MAAM,UAAU,MAAM,KAAK,YAAY,UAAU;EACjD,MAAM,GAAG,KAAK,eAAe,WAAW,KAAK,SAC3C,MAAM,KAAK,eAAe,KACxB;GACE;GACA,SAAS,QAAQ,KAAK,KAAK;GAC3B;GACD,EACD,YAAY,UAAU,CACvB;AACH,SAAO;;CAGT,MAAM,MACJ,EAAE,WAAW,YAAY,sBACzB,YACA;AACA,OAAK,WAAW,EAAE;AAClB,OAAK,gBAAgB;AACrB,QAAM,KAAK,QAAQ;GAAE,QAAQ;GAAK,UAAU;GAAW,CAAC;EAExD,IAAI,WAAW;AACf,SAAO,WAAW,KAAK,iBAAiB,KAAK,SAAS,SAAS,GAAG;AAChE,QAAK,eAAe;GAEpB,MAAM,OAAO,KAAK,SAAS,OAAO;AAClC,QAAK,cAAc,KAAK;GAExB,MAAM,SAAS,MAAM,KAAK,YACxB,WACA,KAAK,UACL,WACD;GACD,MAAM,aAAa,SAAS,KAAK,QAAQ,GAAG;AAC5C,QAAK,gBAAgB,OAAO;AAE5B,SAAM,KAAK,YAAY,aAAa,CAClC,IAAIC,0BAAAA,SAAS;IACX,aAAa;IACb,UAAU,EAAE,MAAM,KAAK,UAAU;IAClC,CAAC,CACH,CAAC;GAEF,MAAM,WAAW,MAAM,KAAK,aAC1B,QACA,KAAK,UACL,WACA,WACD;AACD,QAAK,MAAM,WAAW,UAAU;AAC9B,SAAK,iBAAiB;AACtB,YAAQ,SAAS,KAAK,cAAc,SAAS;AAC7C,UAAM,KAAK,QAAQ,QAAgB;;AAErC,QAAK,WAAW,MAAM,KAAK,gBACzB,YACA,WACA,WACD;AAED,eAAY;;AAEd,SAAO,EAAE;;CAGX,YAAiC;AAC/B,QAAM,IAAI,MAAM,0BAA0B;;;;;;;;;;;;;CAc5C,OAAO,QAAQ,EACb,KACA,aACA,gBACA,SACA,WACA,GAAG,QAIoC;AAWvC,SAAO,IAAI,QAAQ;GACjB,eAXoBC,sBAAAA,kBAAkB,QAAQ;IAC9C;IACA;IACA;IACD,CAOc;GACb,qBAP0BC,4BAAAA,wBAAwB,QAAQ;IAC1D;IACA;IACA;IACD,CAGoB;GACnB,gBACE,kBACAC,uBAAAA,mBAAmB,QAAQ;IAAE;IAAK;IAAS;IAAW,CAAC;GACzD;GACA;GACA;GACA,GAAG;GACJ,CAAC"}
+{"version":3,"file":"agent.cjs","names":["BaseChain","Document","TaskCreationChain","TaskPrioritizationChain","TaskExecutionChain"],"sources":["../../../src/experimental/babyagi/agent.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport type { VectorStoreInterface } from \"@langchain/core/vectorstores\";\nimport { Document } from \"@langchain/core/documents\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { BaseChain, ChainInputs } from \"../../chains/base.js\";\nimport { SerializedBaseChain } from \"../../chains/serde.js\";\nimport { Optional } from \"../../types/type-utils.js\";\nimport { TaskCreationChain } from \"./task_creation.js\";\nimport { TaskExecutionChain } from \"./task_execution.js\";\nimport { TaskPrioritizationChain } from \"./task_prioritization.js\";\n\n/**\n * Interface defining the structure of a task. A task has a `taskID` and a\n * `taskName`.\n */\nexport interface Task {\n  taskID: string;\n  taskName: string;\n}\n\n/**\n * Interface defining the structure of the inputs for the `BabyAGI` class.\n * It extends the `ChainInputs` interface, omitting the 'memory' and\n * 'callbackManager' properties, and adds properties specific to\n * `BabyAGI`.\n */\nexport interface BabyAGIInputs extends Omit<\n  ChainInputs,\n  \"memory\" | \"callbackManager\"\n> {\n  creationChain: BaseChain;\n  prioritizationChain: BaseChain;\n  executionChain: BaseChain;\n  vectorstore: VectorStoreInterface;\n  maxIterations?: number;\n}\n\n/**\n * Class responsible for managing tasks, including their creation,\n * prioritization, and execution. It uses three chains for these\n * operations: `creationChain`, `prioritizationChain`, and\n * `executionChain`.\n * @example\n * ```typescript\n * const babyAGI = BabyAGI.fromLLM({\n *   llm: new OpenAI({ temperature: 0 }),\n *   vectorstore: new MemoryVectorStore(new OpenAIEmbeddings()),\n *   maxIterations: 3,\n * });\n *\n * const result = await babyAGI.call({\n *   objective: \"Write a weather report for SF today\",\n * });\n * ```\n */\nexport class BabyAGI extends BaseChain implements BabyAGIInputs {\n  static lc_name() {\n    return \"BabyAGI\";\n  }\n\n  taskList: Task[];\n\n  creationChain: BaseChain;\n\n  prioritizationChain: BaseChain;\n\n  executionChain: BaseChain;\n\n  taskIDCounter: number;\n\n  vectorstore: VectorStoreInterface;\n\n  maxIterations: number;\n\n  constructor({\n    creationChain,\n    prioritizationChain,\n    executionChain,\n    vectorstore,\n    maxIterations = 100,\n    verbose,\n    callbacks,\n  }: BabyAGIInputs) {\n    super(undefined, verbose, callbacks);\n    this.taskList = [];\n    this.creationChain = creationChain;\n    this.prioritizationChain = prioritizationChain;\n    this.executionChain = executionChain;\n    this.taskIDCounter = 1;\n    this.vectorstore = vectorstore;\n    this.maxIterations = maxIterations;\n  }\n\n  _chainType() {\n    return \"BabyAGI\" as const;\n  }\n\n  get inputKeys() {\n    return [\"objective\", \"firstTask\"];\n  }\n\n  get outputKeys() {\n    return [];\n  }\n\n  /**\n   * Adds a task to the task list.\n   * @param task The task to be added.\n   * @returns Promise resolving to void.\n   */\n  async addTask(task: Task) {\n    this.taskList.push(task);\n  }\n\n  /**\n   * Prints the current task list to the console.\n   * @returns void\n   */\n  printTaskList() {\n    console.log(\"\\x1b[95m\\x1b[1m\\n*****TASK LIST*****\\n\\x1b[0m\\x1b[0m\");\n    for (const t of this.taskList) {\n      console.log(`${t.taskID}: ${t.taskName}`);\n    }\n  }\n\n  /**\n   * Prints the next task to the console.\n   * @param task The next task to be printed.\n   * @returns void\n   */\n  printNextTask(task: Task) {\n    console.log(\"\\x1b[92m\\x1b[1m\\n*****NEXT TASK*****\\n\\x1b[0m\\x1b[0m\");\n    console.log(`${task.taskID}: ${task.taskName}`);\n  }\n\n  /**\n   * Prints the result of a task to the console.\n   * @param result The result of the task.\n   * @returns void\n   */\n  printTaskResult(result: string) {\n    console.log(\"\\x1b[93m\\x1b[1m\\n*****TASK RESULT*****\\n\\x1b[0m\\x1b[0m\");\n    console.log(result.trim());\n  }\n\n  /**\n   * Generates the next tasks based on the result of the previous task, the\n   * task description, and the objective.\n   * @param result The result of the previous task.\n   * @param task_description The description of the task.\n   * @param objective The objective of the task.\n   * @param runManager Optional CallbackManagerForChainRun instance.\n   * @returns Promise resolving to an array of tasks without taskID.\n   */\n  async getNextTasks(\n    result: string,\n    task_description: string,\n    objective: string,\n    runManager?: CallbackManagerForChainRun\n  ): Promise<Optional<Task, \"taskID\">[]> {\n    const taskNames = this.taskList.map((t) => t.taskName);\n    const incomplete_tasks = taskNames.join(\", \");\n    const { [this.creationChain.outputKeys[0]]: text } =\n      await this.creationChain.call(\n        {\n          result,\n          task_description,\n          incomplete_tasks,\n          objective,\n        },\n        runManager?.getChild()\n      );\n    const newTasks = (text as string).split(\"\\n\");\n    return newTasks\n      .filter((taskName) => taskName.trim())\n      .map((taskName) => ({ taskName }));\n  }\n\n  /**\n   * Prioritizes the tasks based on the current task ID and the objective.\n   * @param thisTaskID The ID of the current task.\n   * @param objective The objective of the task.\n   * @param runManager Optional CallbackManagerForChainRun instance.\n   * @returns Promise resolving to an array of prioritized tasks.\n   */\n  async prioritizeTasks(\n    thisTaskID: number,\n    objective: string,\n    runManager?: CallbackManagerForChainRun\n  ) {\n    const taskNames = this.taskList.map((t) => t.taskName);\n    const nextTaskID = thisTaskID + 1;\n    const { [this.prioritizationChain.outputKeys[0]]: text } =\n      await this.prioritizationChain.call(\n        {\n          task_names: taskNames.join(\", \"),\n          next_task_id: String(nextTaskID),\n          objective,\n        },\n        runManager?.getChild()\n      );\n    const newTasks = (text as string).trim().split(\"\\n\");\n    const prioritizedTaskList = [];\n    for (const taskString of newTasks) {\n      const taskParts = taskString.trim().split(\".\", 2);\n      if (taskParts.length === 2) {\n        const taskID = taskParts[0].trim();\n        const taskName = taskParts[1].trim();\n        prioritizedTaskList.push({ taskID, taskName });\n      }\n    }\n    return prioritizedTaskList;\n  }\n\n  /**\n   * Retrieves the top tasks that are most similar to the given query.\n   * @param query The query to search for.\n   * @param k The number of top tasks to retrieve.\n   * @returns Promise resolving to an array of top tasks.\n   */\n  async getTopTasks(query: string, k = 5) {\n    const results = await this.vectorstore.similaritySearch(query, k);\n    if (!results) {\n      return [];\n    }\n    return results.map((item) => String(item.metadata.task));\n  }\n\n  /**\n   * Executes a task based on the objective and the task description.\n   * @param objective The objective of the task.\n   * @param task The task to be executed.\n   * @param runManager Optional CallbackManagerForChainRun instance.\n   * @returns Promise resolving to the result of the task execution as a string.\n   */\n  async executeTask(\n    objective: string,\n    task: string,\n    runManager?: CallbackManagerForChainRun\n  ) {\n    const context = await this.getTopTasks(objective);\n    const { [this.executionChain.outputKeys[0]]: text } =\n      await this.executionChain.call(\n        {\n          objective,\n          context: context.join(\"\\n\"),\n          task,\n        },\n        runManager?.getChild()\n      );\n    return text as string;\n  }\n\n  async _call(\n    { objective, firstTask = \"Make a todo list\" }: ChainValues,\n    runManager?: CallbackManagerForChainRun\n  ) {\n    this.taskList = [];\n    this.taskIDCounter = 1;\n    await this.addTask({ taskID: \"1\", taskName: firstTask });\n\n    let numIters = 0;\n    while (numIters < this.maxIterations && this.taskList.length > 0) {\n      this.printTaskList();\n\n      const task = this.taskList.shift()!;\n      this.printNextTask(task);\n\n      const result = await this.executeTask(\n        objective,\n        task.taskName,\n        runManager\n      );\n      const thisTaskID = parseInt(task.taskID, 10);\n      this.printTaskResult(result);\n\n      await this.vectorstore.addDocuments([\n        new Document({\n          pageContent: result,\n          metadata: { task: task.taskName },\n        }),\n      ]);\n\n      const newTasks = await this.getNextTasks(\n        result,\n        task.taskName,\n        objective,\n        runManager\n      );\n      for (const newTask of newTasks) {\n        this.taskIDCounter += 1;\n        newTask.taskID = this.taskIDCounter.toFixed();\n        await this.addTask(newTask as Task);\n      }\n      this.taskList = await this.prioritizeTasks(\n        thisTaskID,\n        objective,\n        runManager\n      );\n\n      numIters += 1;\n    }\n    return {};\n  }\n\n  serialize(): SerializedBaseChain {\n    throw new Error(\"Method not implemented.\");\n  }\n\n  /**\n   * Static method to create a new BabyAGI instance from a\n   * BaseLanguageModel.\n   * @param llm BaseLanguageModel instance used to generate a new BabyAGI instance.\n   * @param vectorstore VectorStore instance used to store and retrieve vectors.\n   * @param executionChain Optional BaseChain instance used to execute tasks.\n   * @param verbose Optional boolean indicating whether to log verbose output.\n   * @param callbacks Optional callbacks to be used during the execution of tasks.\n   * @param rest Optional additional parameters.\n   * @returns A new instance of BabyAGI.\n   */\n  static fromLLM({\n    llm,\n    vectorstore,\n    executionChain,\n    verbose,\n    callbacks,\n    ...rest\n  }: Optional<\n    BabyAGIInputs,\n    \"executionChain\" | \"creationChain\" | \"prioritizationChain\"\n  > & { llm: BaseLanguageModelInterface }) {\n    const creationChain = TaskCreationChain.fromLLM({\n      llm,\n      verbose,\n      callbacks,\n    });\n    const prioritizationChain = TaskPrioritizationChain.fromLLM({\n      llm,\n      verbose,\n      callbacks,\n    });\n    return new BabyAGI({\n      creationChain,\n      prioritizationChain,\n      executionChain:\n        executionChain ||\n        TaskExecutionChain.fromLLM({ llm, verbose, callbacks }),\n      vectorstore,\n      verbose,\n      callbacks,\n      ...rest,\n    });\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;AAwDA,IAAa,UAAb,MAAa,gBAAgBA,aAAAA,UAAmC;CAC9D,OAAO,UAAU;EACf,OAAO;CACT;CAEA;CAEA;CAEA;CAEA;CAEA;CAEA;CAEA;CAEA,YAAY,EACV,eACA,qBACA,gBACA,aACA,gBAAgB,KAChB,SACA,aACgB;EAChB,MAAM,KAAA,GAAW,SAAS,SAAS;EACnC,KAAK,WAAW,CAAC;EACjB,KAAK,gBAAgB;EACrB,KAAK,sBAAsB;EAC3B,KAAK,iBAAiB;EACtB,KAAK,gBAAgB;EACrB,KAAK,cAAc;EACnB,KAAK,gBAAgB;CACvB;CAEA,aAAa;EACX,OAAO;CACT;CAEA,IAAI,YAAY;EACd,OAAO,CAAC,aAAa,WAAW;CAClC;CAEA,IAAI,aAAa;EACf,OAAO,CAAC;CACV;;;;;;CAOA,MAAM,QAAQ,MAAY;EACxB,KAAK,SAAS,KAAK,IAAI;CACzB;;;;;CAMA,gBAAgB;EACd,QAAQ,IAAI,sDAAsD;EAClE,KAAK,MAAM,KAAK,KAAK,UACnB,QAAQ,IAAI,GAAG,EAAE,OAAO,IAAI,EAAE,UAAU;CAE5C;;;;;;CAOA,cAAc,MAAY;EACxB,QAAQ,IAAI,sDAAsD;EAClE,QAAQ,IAAI,GAAG,KAAK,OAAO,IAAI,KAAK,UAAU;CAChD;;;;;;CAOA,gBAAgB,QAAgB;EAC9B,QAAQ,IAAI,wDAAwD;EACpE,QAAQ,IAAI,OAAO,KAAK,CAAC;CAC3B;;;;;;;;;;CAWA,MAAM,aACJ,QACA,kBACA,WACA,YACqC;EAErC,MAAM,mBADY,KAAK,SAAS,KAAK,MAAM,EAAE,QACZ,CAAC,CAAC,KAAK,IAAI;EAC5C,MAAM,GAAG,KAAK,cAAc,WAAW,KAAK,SAC1C,MAAM,KAAK,cAAc,KACvB;GACE;GACA;GACA;GACA;EACF,GACA,YAAY,SAAS,CACvB;EAEF,OADkB,KAAgB,MAAM,IAC1B,CAAC,CACZ,QAAQ,aAAa,SAAS,KAAK,CAAC,CAAC,CACrC,KAAK,cAAc,EAAE,SAAS,EAAE;CACrC;;;;;;;;CASA,MAAM,gBACJ,YACA,WACA,YACA;EACA,MAAM,YAAY,KAAK,SAAS,KAAK,MAAM,EAAE,QAAQ;EACrD,MAAM,aAAa,aAAa;EAChC,MAAM,GAAG,KAAK,oBAAoB,WAAW,KAAK,SAChD,MAAM,KAAK,oBAAoB,KAC7B;GACE,YAAY,UAAU,KAAK,IAAI;GAC/B,cAAc,OAAO,UAAU;GAC/B;EACF,GACA,YAAY,SAAS,CACvB;EACF,MAAM,WAAY,KAAgB,KAAK,CAAC,CAAC,MAAM,IAAI;EACnD,MAAM,sBAAsB,CAAC;EAC7B,KAAK,MAAM,cAAc,UAAU;GACjC,MAAM,YAAY,WAAW,KAAK,CAAC,CAAC,MAAM,KAAK,CAAC;GAChD,IAAI,UAAU,WAAW,GAAG;IAC1B,MAAM,SAAS,UAAU,EAAE,CAAC,KAAK;IACjC,MAAM,WAAW,UAAU,EAAE,CAAC,KAAK;IACnC,oBAAoB,KAAK;KAAE;KAAQ;IAAS,CAAC;GAC/C;EACF;EACA,OAAO;CACT;;;;;;;CAQA,MAAM,YAAY,OAAe,IAAI,GAAG;EACtC,MAAM,UAAU,MAAM,KAAK,YAAY,iBAAiB,OAAO,CAAC;EAChE,IAAI,CAAC,SACH,OAAO,CAAC;EAEV,OAAO,QAAQ,KAAK,SAAS,OAAO,KAAK,SAAS,IAAI,CAAC;CACzD;;;;;;;;CASA,MAAM,YACJ,WACA,MACA,YACA;EACA,MAAM,UAAU,MAAM,KAAK,YAAY,SAAS;EAChD,MAAM,GAAG,KAAK,eAAe,WAAW,KAAK,SAC3C,MAAM,KAAK,eAAe,KACxB;GACE;GACA,SAAS,QAAQ,KAAK,IAAI;GAC1B;EACF,GACA,YAAY,SAAS,CACvB;EACF,OAAO;CACT;CAEA,MAAM,MACJ,EAAE,WAAW,YAAY,sBACzB,YACA;EACA,KAAK,WAAW,CAAC;EACjB,KAAK,gBAAgB;EACrB,MAAM,KAAK,QAAQ;GAAE,QAAQ;GAAK,UAAU;EAAU,CAAC;EAEvD,IAAI,WAAW;EACf,OAAO,WAAW,KAAK,iBAAiB,KAAK,SAAS,SAAS,GAAG;GAChE,KAAK,cAAc;GAEnB,MAAM,OAAO,KAAK,SAAS,MAAM;GACjC,KAAK,cAAc,IAAI;GAEvB,MAAM,SAAS,MAAM,KAAK,YACxB,WACA,KAAK,UACL,UACF;GACA,MAAM,aAAa,SAAS,KAAK,QAAQ,EAAE;GAC3C,KAAK,gBAAgB,MAAM;GAE3B,MAAM,KAAK,YAAY,aAAa,CAClC,IAAIC,0BAAAA,SAAS;IACX,aAAa;IACb,UAAU,EAAE,MAAM,KAAK,SAAS;GAClC,CAAC,CACH,CAAC;GAED,MAAM,WAAW,MAAM,KAAK,aAC1B,QACA,KAAK,UACL,WACA,UACF;GACA,KAAK,MAAM,WAAW,UAAU;IAC9B,KAAK,iBAAiB;IACtB,QAAQ,SAAS,KAAK,cAAc,QAAQ;IAC5C,MAAM,KAAK,QAAQ,OAAe;GACpC;GACA,KAAK,WAAW,MAAM,KAAK,gBACzB,YACA,WACA,UACF;GAEA,YAAY;EACd;EACA,OAAO,CAAC;CACV;CAEA,YAAiC;EAC/B,MAAM,IAAI,MAAM,yBAAyB;CAC3C;;;;;;;;;;;;CAaA,OAAO,QAAQ,EACb,KACA,aACA,gBACA,SACA,WACA,GAAG,QAIoC;EACvC,MAAM,gBAAgBC,sBAAAA,kBAAkB,QAAQ;GAC9C;GACA;GACA;EACF,CAAC;EACD,MAAM,sBAAsBC,4BAAAA,wBAAwB,QAAQ;GAC1D;GACA;GACA;EACF,CAAC;EACD,OAAO,IAAI,QAAQ;GACjB;GACA;GACA,gBACE,kBACAC,uBAAAA,mBAAmB,QAAQ;IAAE;IAAK;IAAS;GAAU,CAAC;GACxD;GACA;GACA;GACA,GAAG;EACL,CAAC;CACH;AACF"}

package/dist/experimental/babyagi/agent.d.cts

@@ -5,7 +5,6 @@ import { ChainValues } from "@langchain/core/utils/types";
 import { BaseLanguageModelInterface } from "@langchain/core/language_models/base";
 import { CallbackManagerForChainRun } from "@langchain/core/callbacks/manager";
 import { VectorStoreInterface } from "@langchain/core/vectorstores";
-
 //#region src/experimental/babyagi/agent.d.ts
 /**
  * Interface defining the structure of a task. A task has a `taskID` and a
@@ -55,15 +54,7 @@ declare class BabyAGI extends BaseChain implements BabyAGIInputs {
   taskIDCounter: number;
   vectorstore: VectorStoreInterface;
   maxIterations: number;
-  constructor({
-    creationChain,
-    prioritizationChain,
-    executionChain,
-    vectorstore,
-    maxIterations,
-    verbose,
-    callbacks
-  }: BabyAGIInputs);
+  constructor({ creationChain, prioritizationChain, executionChain, vectorstore, maxIterations, verbose, callbacks }: BabyAGIInputs);
   _chainType(): "BabyAGI";
   get inputKeys(): string[];
   get outputKeys(): never[];
@@ -126,10 +117,7 @@ declare class BabyAGI extends BaseChain implements BabyAGIInputs {
    * @returns Promise resolving to the result of the task execution as a string.
    */
   executeTask(objective: string, task: string, runManager?: CallbackManagerForChainRun): Promise<string>;
-  _call({
-    objective,
-    firstTask
-  }: ChainValues, runManager?: CallbackManagerForChainRun): Promise<{}>;
+  _call({ objective, firstTask }: ChainValues, runManager?: CallbackManagerForChainRun): Promise<{}>;
   serialize(): SerializedBaseChain;
   /**
    * Static method to create a new BabyAGI instance from a
@@ -142,14 +130,7 @@ declare class BabyAGI extends BaseChain implements BabyAGIInputs {
    * @param rest Optional additional parameters.
    * @returns A new instance of BabyAGI.
    */
-  static fromLLM({
-    llm,
-    vectorstore,
-    executionChain,
-    verbose,
-    callbacks,
-    ...rest
-  }: Optional<BabyAGIInputs, "executionChain" | "creationChain" | "prioritizationChain"> & {
+  static fromLLM({ llm, vectorstore, executionChain, verbose, callbacks, ...rest }: Optional<BabyAGIInputs, "executionChain" | "creationChain" | "prioritizationChain"> & {
     llm: BaseLanguageModelInterface;
   }): BabyAGI;
 }

package/dist/experimental/babyagi/agent.d.cts.map

@@ -1 +1 @@
-{"version":3,"file":"agent.d.cts","names":[],"sources":["../../../src/experimental/babyagi/agent.ts"],"mappings":";;;;;;;;;;;AAgBA;;UAAiB,IAAA;EACf,MAAA;EACA,QAAA;AAAA;;;;;;;UASe,aAAA,SAAsB,IAAA,CACrC,WAAA;EAGA,aAAA,EAAe,SAAA;EACf,mBAAA,EAAqB,SAAA;EACrB,cAAA,EAAgB,SAAA;EAChB,WAAA,EAAa,oBAAA;EACb,aAAA;AAAA;;;;;;;;;;;AAqBF;;;;;;;;cAAa,OAAA,SAAgB,SAAA,YAAqB,aAAA;EAAA,OACzC,OAAA,CAAA;EAIP,QAAA,EAAU,IAAA;EAEV,aAAA,EAAe,SAAA;EAEf,mBAAA,EAAqB,SAAA;EAErB,cAAA,EAAgB,SAAA;EAEhB,aAAA;EAEA,WAAA,EAAa,oBAAA;EAEb,aAAA;EAEA,WAAA,CAAA;IACE,aAAA;IACA,mBAAA;IACA,cAAA;IACA,WAAA;IACA,aAAA;IACA,OAAA;IACA;EAAA,GACC,aAAA;EAWH,UAAA,CAAA;EAAA,IAII,SAAA,CAAA;EAAA,IAIA,UAAA,CAAA;EA0DO;;;;;EAjDL,OAAA,CAAQ,IAAA,EAAM,IAAA,GAAI,OAAA;EAgIiB;;;;EAxHzC,aAAA,CAAA;EAyIyC;;;;;EA7HzC,aAAA,CAAc,IAAA,EAAM,IAAA;EAmMlB;;;;;EAzLF,eAAA,CAAgB,MAAA;EArFgC;;;;;;;;;EAmG1C,YAAA,CACJ,MAAA,UACA,gBAAA,UACA,SAAA,UACA,UAAA,GAAa,0BAAA,GACZ,OAAA,CAAQ,QAAA,CAAS,IAAA;EA/FpB;;;;;;;EAyHM,eAAA,CACJ,UAAA,UACA,SAAA,UACA,UAAA,GAAa,0BAAA,GAA0B,OAAA;;;;EAhHvC;;;;;;EAgJI,WAAA,CAAY,KAAA,UAAe,CAAA,YAAK,OAAA;EA7IpC;;;;;;;EA4JI,WAAA,CACJ,SAAA,UACA,IAAA,UACA,UAAA,GAAa,0BAAA,GAA0B,OAAA;EAenC,KAAA,CAAA;IACF,SAAA;IAAW;EAAA,GAAkC,WAAA,EAC/C,UAAA,GAAa,0BAAA,GAA0B,OAAA;EAkDzC,SAAA,CAAA,GAAa,mBAAA;EAnMO;;;;;;;;;;;EAAA,OAkNb,OAAA,CAAA;IACL,GAAA;IACA,WAAA;IACA,cAAA;IACA,OAAA;IACA,SAAA;IAAA,GACG;EAAA,GACF,QAAA,CACD,aAAA;IAEI,GAAA,EAAK,0BAAA;EAAA,IAA4B,OAAA;AAAA"}
+{"version":3,"file":"agent.d.cts","names":[],"sources":["../../../src/experimental/babyagi/agent.ts"],"mappings":";;;;;;;;;;;;UAgBiB;EACf;EACA;;;;;;;;UASe,sBAAsB,KACrC;EAGA,eAAe;EACf,qBAAqB;EACrB,gBAAgB;EAChB,aAAa;EACb;;;;;;;;;;;;;;;;;;;;cAqBW,gBAAgB,qBAAqB;SACzC;EAIP,UAAU;EAEV,eAAe;EAEf,qBAAqB;EAErB,gBAAgB;EAEhB;EAEA,aAAa;EAEb;EAEA,cACE,eACA,qBACA,gBACA,aACA,eACA,SACA,aACC;EAWH;MAII;MAIA;;;;;;EASE,QAAQ,MAAM,OAAI;;;;;EAQxB;;;;;;EAYA,cAAc,MAAM;;;;;;EAUpB,gBAAgB;;;;;;;;;;EAcV,aACJ,gBACA,0BACA,mBACA,aAAa,6BACZ,QAAQ,SAAS;;;;;;;;EA0Bd,gBACJ,oBACA,mBACA,aAAa,6BAA0B;;;;;;;;;;EAgCnC,YAAY,eAAe,aAAK;;;;;;;;EAehC,YACJ,mBACA,cACA,aAAa,6BAA0B;EAenC,QACF,WAAW,aAAkC,aAC/C,aAAa,6BAA0B;EAkDzC,aAAa;;;;;;;;;;;;SAeN,UACL,KACA,aACA,gBACA,SACA,cACG,QACF,SACD;IAEI,KAAK;MAA4B"}

package/dist/experimental/babyagi/agent.d.ts

@@ -5,7 +5,6 @@ import { BaseLanguageModelInterface } from "@langchain/core/language_models/base
 import { CallbackManagerForChainRun } from "@langchain/core/callbacks/manager";
 import { ChainValues } from "@langchain/core/utils/types";
 import { VectorStoreInterface } from "@langchain/core/vectorstores";
-
 //#region src/experimental/babyagi/agent.d.ts
 /**
  * Interface defining the structure of a task. A task has a `taskID` and a
@@ -55,15 +54,7 @@ declare class BabyAGI extends BaseChain implements BabyAGIInputs {
   taskIDCounter: number;
   vectorstore: VectorStoreInterface;
   maxIterations: number;
-  constructor({
-    creationChain,
-    prioritizationChain,
-    executionChain,
-    vectorstore,
-    maxIterations,
-    verbose,
-    callbacks
-  }: BabyAGIInputs);
+  constructor({ creationChain, prioritizationChain, executionChain, vectorstore, maxIterations, verbose, callbacks }: BabyAGIInputs);
   _chainType(): "BabyAGI";
   get inputKeys(): string[];
   get outputKeys(): never[];
@@ -126,10 +117,7 @@ declare class BabyAGI extends BaseChain implements BabyAGIInputs {
    * @returns Promise resolving to the result of the task execution as a string.
    */
   executeTask(objective: string, task: string, runManager?: CallbackManagerForChainRun): Promise<string>;
-  _call({
-    objective,
-    firstTask
-  }: ChainValues, runManager?: CallbackManagerForChainRun): Promise<{}>;
+  _call({ objective, firstTask }: ChainValues, runManager?: CallbackManagerForChainRun): Promise<{}>;
   serialize(): SerializedBaseChain;
   /**
    * Static method to create a new BabyAGI instance from a
@@ -142,14 +130,7 @@ declare class BabyAGI extends BaseChain implements BabyAGIInputs {
    * @param rest Optional additional parameters.
    * @returns A new instance of BabyAGI.
    */
-  static fromLLM({
-    llm,
-    vectorstore,
-    executionChain,
-    verbose,
-    callbacks,
-    ...rest
-  }: Optional<BabyAGIInputs, "executionChain" | "creationChain" | "prioritizationChain"> & {
+  static fromLLM({ llm, vectorstore, executionChain, verbose, callbacks, ...rest }: Optional<BabyAGIInputs, "executionChain" | "creationChain" | "prioritizationChain"> & {
     llm: BaseLanguageModelInterface;
   }): BabyAGI;
 }

package/dist/experimental/babyagi/agent.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"agent.d.ts","names":[],"sources":["../../../src/experimental/babyagi/agent.ts"],"mappings":";;;;;;;;;;;AAgBA;;UAAiB,IAAA;EACf,MAAA;EACA,QAAA;AAAA;;;;;;;UASe,aAAA,SAAsB,IAAA,CACrC,WAAA;EAGA,aAAA,EAAe,SAAA;EACf,mBAAA,EAAqB,SAAA;EACrB,cAAA,EAAgB,SAAA;EAChB,WAAA,EAAa,oBAAA;EACb,aAAA;AAAA;;;;;;;;;;;AAqBF;;;;;;;;cAAa,OAAA,SAAgB,SAAA,YAAqB,aAAA;EAAA,OACzC,OAAA,CAAA;EAIP,QAAA,EAAU,IAAA;EAEV,aAAA,EAAe,SAAA;EAEf,mBAAA,EAAqB,SAAA;EAErB,cAAA,EAAgB,SAAA;EAEhB,aAAA;EAEA,WAAA,EAAa,oBAAA;EAEb,aAAA;EAEA,WAAA,CAAA;IACE,aAAA;IACA,mBAAA;IACA,cAAA;IACA,WAAA;IACA,aAAA;IACA,OAAA;IACA;EAAA,GACC,aAAA;EAWH,UAAA,CAAA;EAAA,IAII,SAAA,CAAA;EAAA,IAIA,UAAA,CAAA;EA0DO;;;;;EAjDL,OAAA,CAAQ,IAAA,EAAM,IAAA,GAAI,OAAA;EAgIiB;;;;EAxHzC,aAAA,CAAA;EAyIyC;;;;;EA7HzC,aAAA,CAAc,IAAA,EAAM,IAAA;EAmMlB;;;;;EAzLF,eAAA,CAAgB,MAAA;EArFgC;;;;;;;;;EAmG1C,YAAA,CACJ,MAAA,UACA,gBAAA,UACA,SAAA,UACA,UAAA,GAAa,0BAAA,GACZ,OAAA,CAAQ,QAAA,CAAS,IAAA;EA/FpB;;;;;;;EAyHM,eAAA,CACJ,UAAA,UACA,SAAA,UACA,UAAA,GAAa,0BAAA,GAA0B,OAAA;;;;EAhHvC;;;;;;EAgJI,WAAA,CAAY,KAAA,UAAe,CAAA,YAAK,OAAA;EA7IpC;;;;;;;EA4JI,WAAA,CACJ,SAAA,UACA,IAAA,UACA,UAAA,GAAa,0BAAA,GAA0B,OAAA;EAenC,KAAA,CAAA;IACF,SAAA;IAAW;EAAA,GAAkC,WAAA,EAC/C,UAAA,GAAa,0BAAA,GAA0B,OAAA;EAkDzC,SAAA,CAAA,GAAa,mBAAA;EAnMO;;;;;;;;;;;EAAA,OAkNb,OAAA,CAAA;IACL,GAAA;IACA,WAAA;IACA,cAAA;IACA,OAAA;IACA,SAAA;IAAA,GACG;EAAA,GACF,QAAA,CACD,aAAA;IAEI,GAAA,EAAK,0BAAA;EAAA,IAA4B,OAAA;AAAA"}
+{"version":3,"file":"agent.d.ts","names":[],"sources":["../../../src/experimental/babyagi/agent.ts"],"mappings":";;;;;;;;;;;;UAgBiB;EACf;EACA;;;;;;;;UASe,sBAAsB,KACrC;EAGA,eAAe;EACf,qBAAqB;EACrB,gBAAgB;EAChB,aAAa;EACb;;;;;;;;;;;;;;;;;;;;cAqBW,gBAAgB,qBAAqB;SACzC;EAIP,UAAU;EAEV,eAAe;EAEf,qBAAqB;EAErB,gBAAgB;EAEhB;EAEA,aAAa;EAEb;EAEA,cACE,eACA,qBACA,gBACA,aACA,eACA,SACA,aACC;EAWH;MAII;MAIA;;;;;;EASE,QAAQ,MAAM,OAAI;;;;;EAQxB;;;;;;EAYA,cAAc,MAAM;;;;;;EAUpB,gBAAgB;;;;;;;;;;EAcV,aACJ,gBACA,0BACA,mBACA,aAAa,6BACZ,QAAQ,SAAS;;;;;;;;EA0Bd,gBACJ,oBACA,mBACA,aAAa,6BAA0B;;;;;;;;;;EAgCnC,YAAY,eAAe,aAAK;;;;;;;;EAehC,YACJ,mBACA,cACA,aAAa,6BAA0B;EAenC,QACF,WAAW,aAAkC,aAC/C,aAAa,6BAA0B;EAkDzC,aAAa;;;;;;;;;;;;SAeN,UACL,KACA,aACA,gBACA,SACA,cACG,QACF,SACD;IAEI,KAAK;MAA4B"}

package/dist/experimental/babyagi/agent.js

@@ -207,17 +207,19 @@ var BabyAGI = class BabyAGI extends BaseChain {
 	* @returns A new instance of BabyAGI.
 	*/
 	static fromLLM({ llm, vectorstore, executionChain, verbose, callbacks, ...rest }) {
+		const creationChain = TaskCreationChain.fromLLM({
+			llm,
+			verbose,
+			callbacks
+		});
+		const prioritizationChain = TaskPrioritizationChain.fromLLM({
+			llm,
+			verbose,
+			callbacks
+		});
 		return new BabyAGI({
-			creationChain: TaskCreationChain.fromLLM({
-				llm,
-				verbose,
-				callbacks
-			}),
-			prioritizationChain: TaskPrioritizationChain.fromLLM({
-				llm,
-				verbose,
-				callbacks
-			}),
+			creationChain,
+			prioritizationChain,
 			executionChain: executionChain || TaskExecutionChain.fromLLM({
 				llm,
 				verbose,

package/dist/experimental/babyagi/agent.js.map

@@ -1 +1 @@
-{"version":3,"file":"agent.js","names":[],"sources":["../../../src/experimental/babyagi/agent.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport type { VectorStoreInterface } from \"@langchain/core/vectorstores\";\nimport { Document } from \"@langchain/core/documents\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { BaseChain, ChainInputs } from \"../../chains/base.js\";\nimport { SerializedBaseChain } from \"../../chains/serde.js\";\nimport { Optional } from \"../../types/type-utils.js\";\nimport { TaskCreationChain } from \"./task_creation.js\";\nimport { TaskExecutionChain } from \"./task_execution.js\";\nimport { TaskPrioritizationChain } from \"./task_prioritization.js\";\n\n/**\n * Interface defining the structure of a task. A task has a `taskID` and a\n * `taskName`.\n */\nexport interface Task {\n  taskID: string;\n  taskName: string;\n}\n\n/**\n * Interface defining the structure of the inputs for the `BabyAGI` class.\n * It extends the `ChainInputs` interface, omitting the 'memory' and\n * 'callbackManager' properties, and adds properties specific to\n * `BabyAGI`.\n */\nexport interface BabyAGIInputs extends Omit<\n  ChainInputs,\n  \"memory\" | \"callbackManager\"\n> {\n  creationChain: BaseChain;\n  prioritizationChain: BaseChain;\n  executionChain: BaseChain;\n  vectorstore: VectorStoreInterface;\n  maxIterations?: number;\n}\n\n/**\n * Class responsible for managing tasks, including their creation,\n * prioritization, and execution. It uses three chains for these\n * operations: `creationChain`, `prioritizationChain`, and\n * `executionChain`.\n * @example\n * ```typescript\n * const babyAGI = BabyAGI.fromLLM({\n *   llm: new OpenAI({ temperature: 0 }),\n *   vectorstore: new MemoryVectorStore(new OpenAIEmbeddings()),\n *   maxIterations: 3,\n * });\n *\n * const result = await babyAGI.call({\n *   objective: \"Write a weather report for SF today\",\n * });\n * ```\n */\nexport class BabyAGI extends BaseChain implements BabyAGIInputs {\n  static lc_name() {\n    return \"BabyAGI\";\n  }\n\n  taskList: Task[];\n\n  creationChain: BaseChain;\n\n  prioritizationChain: BaseChain;\n\n  executionChain: BaseChain;\n\n  taskIDCounter: number;\n\n  vectorstore: VectorStoreInterface;\n\n  maxIterations: number;\n\n  constructor({\n    creationChain,\n    prioritizationChain,\n    executionChain,\n    vectorstore,\n    maxIterations = 100,\n    verbose,\n    callbacks,\n  }: BabyAGIInputs) {\n    super(undefined, verbose, callbacks);\n    this.taskList = [];\n    this.creationChain = creationChain;\n    this.prioritizationChain = prioritizationChain;\n    this.executionChain = executionChain;\n    this.taskIDCounter = 1;\n    this.vectorstore = vectorstore;\n    this.maxIterations = maxIterations;\n  }\n\n  _chainType() {\n    return \"BabyAGI\" as const;\n  }\n\n  get inputKeys() {\n    return [\"objective\", \"firstTask\"];\n  }\n\n  get outputKeys() {\n    return [];\n  }\n\n  /**\n   * Adds a task to the task list.\n   * @param task The task to be added.\n   * @returns Promise resolving to void.\n   */\n  async addTask(task: Task) {\n    this.taskList.push(task);\n  }\n\n  /**\n   * Prints the current task list to the console.\n   * @returns void\n   */\n  printTaskList() {\n    console.log(\"\\x1b[95m\\x1b[1m\\n*****TASK LIST*****\\n\\x1b[0m\\x1b[0m\");\n    for (const t of this.taskList) {\n      console.log(`${t.taskID}: ${t.taskName}`);\n    }\n  }\n\n  /**\n   * Prints the next task to the console.\n   * @param task The next task to be printed.\n   * @returns void\n   */\n  printNextTask(task: Task) {\n    console.log(\"\\x1b[92m\\x1b[1m\\n*****NEXT TASK*****\\n\\x1b[0m\\x1b[0m\");\n    console.log(`${task.taskID}: ${task.taskName}`);\n  }\n\n  /**\n   * Prints the result of a task to the console.\n   * @param result The result of the task.\n   * @returns void\n   */\n  printTaskResult(result: string) {\n    console.log(\"\\x1b[93m\\x1b[1m\\n*****TASK RESULT*****\\n\\x1b[0m\\x1b[0m\");\n    console.log(result.trim());\n  }\n\n  /**\n   * Generates the next tasks based on the result of the previous task, the\n   * task description, and the objective.\n   * @param result The result of the previous task.\n   * @param task_description The description of the task.\n   * @param objective The objective of the task.\n   * @param runManager Optional CallbackManagerForChainRun instance.\n   * @returns Promise resolving to an array of tasks without taskID.\n   */\n  async getNextTasks(\n    result: string,\n    task_description: string,\n    objective: string,\n    runManager?: CallbackManagerForChainRun\n  ): Promise<Optional<Task, \"taskID\">[]> {\n    const taskNames = this.taskList.map((t) => t.taskName);\n    const incomplete_tasks = taskNames.join(\", \");\n    const { [this.creationChain.outputKeys[0]]: text } =\n      await this.creationChain.call(\n        {\n          result,\n          task_description,\n          incomplete_tasks,\n          objective,\n        },\n        runManager?.getChild()\n      );\n    const newTasks = (text as string).split(\"\\n\");\n    return newTasks\n      .filter((taskName) => taskName.trim())\n      .map((taskName) => ({ taskName }));\n  }\n\n  /**\n   * Prioritizes the tasks based on the current task ID and the objective.\n   * @param thisTaskID The ID of the current task.\n   * @param objective The objective of the task.\n   * @param runManager Optional CallbackManagerForChainRun instance.\n   * @returns Promise resolving to an array of prioritized tasks.\n   */\n  async prioritizeTasks(\n    thisTaskID: number,\n    objective: string,\n    runManager?: CallbackManagerForChainRun\n  ) {\n    const taskNames = this.taskList.map((t) => t.taskName);\n    const nextTaskID = thisTaskID + 1;\n    const { [this.prioritizationChain.outputKeys[0]]: text } =\n      await this.prioritizationChain.call(\n        {\n          task_names: taskNames.join(\", \"),\n          next_task_id: String(nextTaskID),\n          objective,\n        },\n        runManager?.getChild()\n      );\n    const newTasks = (text as string).trim().split(\"\\n\");\n    const prioritizedTaskList = [];\n    for (const taskString of newTasks) {\n      const taskParts = taskString.trim().split(\".\", 2);\n      if (taskParts.length === 2) {\n        const taskID = taskParts[0].trim();\n        const taskName = taskParts[1].trim();\n        prioritizedTaskList.push({ taskID, taskName });\n      }\n    }\n    return prioritizedTaskList;\n  }\n\n  /**\n   * Retrieves the top tasks that are most similar to the given query.\n   * @param query The query to search for.\n   * @param k The number of top tasks to retrieve.\n   * @returns Promise resolving to an array of top tasks.\n   */\n  async getTopTasks(query: string, k = 5) {\n    const results = await this.vectorstore.similaritySearch(query, k);\n    if (!results) {\n      return [];\n    }\n    return results.map((item) => String(item.metadata.task));\n  }\n\n  /**\n   * Executes a task based on the objective and the task description.\n   * @param objective The objective of the task.\n   * @param task The task to be executed.\n   * @param runManager Optional CallbackManagerForChainRun instance.\n   * @returns Promise resolving to the result of the task execution as a string.\n   */\n  async executeTask(\n    objective: string,\n    task: string,\n    runManager?: CallbackManagerForChainRun\n  ) {\n    const context = await this.getTopTasks(objective);\n    const { [this.executionChain.outputKeys[0]]: text } =\n      await this.executionChain.call(\n        {\n          objective,\n          context: context.join(\"\\n\"),\n          task,\n        },\n        runManager?.getChild()\n      );\n    return text as string;\n  }\n\n  async _call(\n    { objective, firstTask = \"Make a todo list\" }: ChainValues,\n    runManager?: CallbackManagerForChainRun\n  ) {\n    this.taskList = [];\n    this.taskIDCounter = 1;\n    await this.addTask({ taskID: \"1\", taskName: firstTask });\n\n    let numIters = 0;\n    while (numIters < this.maxIterations && this.taskList.length > 0) {\n      this.printTaskList();\n\n      const task = this.taskList.shift()!;\n      this.printNextTask(task);\n\n      const result = await this.executeTask(\n        objective,\n        task.taskName,\n        runManager\n      );\n      const thisTaskID = parseInt(task.taskID, 10);\n      this.printTaskResult(result);\n\n      await this.vectorstore.addDocuments([\n        new Document({\n          pageContent: result,\n          metadata: { task: task.taskName },\n        }),\n      ]);\n\n      const newTasks = await this.getNextTasks(\n        result,\n        task.taskName,\n        objective,\n        runManager\n      );\n      for (const newTask of newTasks) {\n        this.taskIDCounter += 1;\n        newTask.taskID = this.taskIDCounter.toFixed();\n        await this.addTask(newTask as Task);\n      }\n      this.taskList = await this.prioritizeTasks(\n        thisTaskID,\n        objective,\n        runManager\n      );\n\n      numIters += 1;\n    }\n    return {};\n  }\n\n  serialize(): SerializedBaseChain {\n    throw new Error(\"Method not implemented.\");\n  }\n\n  /**\n   * Static method to create a new BabyAGI instance from a\n   * BaseLanguageModel.\n   * @param llm BaseLanguageModel instance used to generate a new BabyAGI instance.\n   * @param vectorstore VectorStore instance used to store and retrieve vectors.\n   * @param executionChain Optional BaseChain instance used to execute tasks.\n   * @param verbose Optional boolean indicating whether to log verbose output.\n   * @param callbacks Optional callbacks to be used during the execution of tasks.\n   * @param rest Optional additional parameters.\n   * @returns A new instance of BabyAGI.\n   */\n  static fromLLM({\n    llm,\n    vectorstore,\n    executionChain,\n    verbose,\n    callbacks,\n    ...rest\n  }: Optional<\n    BabyAGIInputs,\n    \"executionChain\" | \"creationChain\" | \"prioritizationChain\"\n  > & { llm: BaseLanguageModelInterface }) {\n    const creationChain = TaskCreationChain.fromLLM({\n      llm,\n      verbose,\n      callbacks,\n    });\n    const prioritizationChain = TaskPrioritizationChain.fromLLM({\n      llm,\n      verbose,\n      callbacks,\n    });\n    return new BabyAGI({\n      creationChain,\n      prioritizationChain,\n      executionChain:\n        executionChain ||\n        TaskExecutionChain.fromLLM({ llm, verbose, callbacks }),\n      vectorstore,\n      verbose,\n      callbacks,\n      ...rest,\n    });\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;AAwDA,IAAa,UAAb,MAAa,gBAAgB,UAAmC;CAC9D,OAAO,UAAU;AACf,SAAO;;CAGT;CAEA;CAEA;CAEA;CAEA;CAEA;CAEA;CAEA,YAAY,EACV,eACA,qBACA,gBACA,aACA,gBAAgB,KAChB,SACA,aACgB;AAChB,QAAM,KAAA,GAAW,SAAS,UAAU;AACpC,OAAK,WAAW,EAAE;AAClB,OAAK,gBAAgB;AACrB,OAAK,sBAAsB;AAC3B,OAAK,iBAAiB;AACtB,OAAK,gBAAgB;AACrB,OAAK,cAAc;AACnB,OAAK,gBAAgB;;CAGvB,aAAa;AACX,SAAO;;CAGT,IAAI,YAAY;AACd,SAAO,CAAC,aAAa,YAAY;;CAGnC,IAAI,aAAa;AACf,SAAO,EAAE;;;;;;;CAQX,MAAM,QAAQ,MAAY;AACxB,OAAK,SAAS,KAAK,KAAK;;;;;;CAO1B,gBAAgB;AACd,UAAQ,IAAI,uDAAuD;AACnE,OAAK,MAAM,KAAK,KAAK,SACnB,SAAQ,IAAI,GAAG,EAAE,OAAO,IAAI,EAAE,WAAW;;;;;;;CAS7C,cAAc,MAAY;AACxB,UAAQ,IAAI,uDAAuD;AACnE,UAAQ,IAAI,GAAG,KAAK,OAAO,IAAI,KAAK,WAAW;;;;;;;CAQjD,gBAAgB,QAAgB;AAC9B,UAAQ,IAAI,yDAAyD;AACrE,UAAQ,IAAI,OAAO,MAAM,CAAC;;;;;;;;;;;CAY5B,MAAM,aACJ,QACA,kBACA,WACA,YACqC;EAErC,MAAM,mBADY,KAAK,SAAS,KAAK,MAAM,EAAE,SACX,CAAC,KAAK,KAAK;EAC7C,MAAM,GAAG,KAAK,cAAc,WAAW,KAAK,SAC1C,MAAM,KAAK,cAAc,KACvB;GACE;GACA;GACA;GACA;GACD,EACD,YAAY,UAAU,CACvB;AAEH,SADkB,KAAgB,MAAM,KACzB,CACZ,QAAQ,aAAa,SAAS,MAAM,CAAC,CACrC,KAAK,cAAc,EAAE,UAAU,EAAE;;;;;;;;;CAUtC,MAAM,gBACJ,YACA,WACA,YACA;EACA,MAAM,YAAY,KAAK,SAAS,KAAK,MAAM,EAAE,SAAS;EACtD,MAAM,aAAa,aAAa;EAChC,MAAM,GAAG,KAAK,oBAAoB,WAAW,KAAK,SAChD,MAAM,KAAK,oBAAoB,KAC7B;GACE,YAAY,UAAU,KAAK,KAAK;GAChC,cAAc,OAAO,WAAW;GAChC;GACD,EACD,YAAY,UAAU,CACvB;EACH,MAAM,WAAY,KAAgB,MAAM,CAAC,MAAM,KAAK;EACpD,MAAM,sBAAsB,EAAE;AAC9B,OAAK,MAAM,cAAc,UAAU;GACjC,MAAM,YAAY,WAAW,MAAM,CAAC,MAAM,KAAK,EAAE;AACjD,OAAI,UAAU,WAAW,GAAG;IAC1B,MAAM,SAAS,UAAU,GAAG,MAAM;IAClC,MAAM,WAAW,UAAU,GAAG,MAAM;AACpC,wBAAoB,KAAK;KAAE;KAAQ;KAAU,CAAC;;;AAGlD,SAAO;;;;;;;;CAST,MAAM,YAAY,OAAe,IAAI,GAAG;EACtC,MAAM,UAAU,MAAM,KAAK,YAAY,iBAAiB,OAAO,EAAE;AACjE,MAAI,CAAC,QACH,QAAO,EAAE;AAEX,SAAO,QAAQ,KAAK,SAAS,OAAO,KAAK,SAAS,KAAK,CAAC;;;;;;;;;CAU1D,MAAM,YACJ,WACA,MACA,YACA;EACA,MAAM,UAAU,MAAM,KAAK,YAAY,UAAU;EACjD,MAAM,GAAG,KAAK,eAAe,WAAW,KAAK,SAC3C,MAAM,KAAK,eAAe,KACxB;GACE;GACA,SAAS,QAAQ,KAAK,KAAK;GAC3B;GACD,EACD,YAAY,UAAU,CACvB;AACH,SAAO;;CAGT,MAAM,MACJ,EAAE,WAAW,YAAY,sBACzB,YACA;AACA,OAAK,WAAW,EAAE;AAClB,OAAK,gBAAgB;AACrB,QAAM,KAAK,QAAQ;GAAE,QAAQ;GAAK,UAAU;GAAW,CAAC;EAExD,IAAI,WAAW;AACf,SAAO,WAAW,KAAK,iBAAiB,KAAK,SAAS,SAAS,GAAG;AAChE,QAAK,eAAe;GAEpB,MAAM,OAAO,KAAK,SAAS,OAAO;AAClC,QAAK,cAAc,KAAK;GAExB,MAAM,SAAS,MAAM,KAAK,YACxB,WACA,KAAK,UACL,WACD;GACD,MAAM,aAAa,SAAS,KAAK,QAAQ,GAAG;AAC5C,QAAK,gBAAgB,OAAO;AAE5B,SAAM,KAAK,YAAY,aAAa,CAClC,IAAI,SAAS;IACX,aAAa;IACb,UAAU,EAAE,MAAM,KAAK,UAAU;IAClC,CAAC,CACH,CAAC;GAEF,MAAM,WAAW,MAAM,KAAK,aAC1B,QACA,KAAK,UACL,WACA,WACD;AACD,QAAK,MAAM,WAAW,UAAU;AAC9B,SAAK,iBAAiB;AACtB,YAAQ,SAAS,KAAK,cAAc,SAAS;AAC7C,UAAM,KAAK,QAAQ,QAAgB;;AAErC,QAAK,WAAW,MAAM,KAAK,gBACzB,YACA,WACA,WACD;AAED,eAAY;;AAEd,SAAO,EAAE;;CAGX,YAAiC;AAC/B,QAAM,IAAI,MAAM,0BAA0B;;;;;;;;;;;;;CAc5C,OAAO,QAAQ,EACb,KACA,aACA,gBACA,SACA,WACA,GAAG,QAIoC;AAWvC,SAAO,IAAI,QAAQ;GACjB,eAXoB,kBAAkB,QAAQ;IAC9C;IACA;IACA;IACD,CAOc;GACb,qBAP0B,wBAAwB,QAAQ;IAC1D;IACA;IACA;IACD,CAGoB;GACnB,gBACE,kBACA,mBAAmB,QAAQ;IAAE;IAAK;IAAS;IAAW,CAAC;GACzD;GACA;GACA;GACA,GAAG;GACJ,CAAC"}
+{"version":3,"file":"agent.js","names":[],"sources":["../../../src/experimental/babyagi/agent.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport type { VectorStoreInterface } from \"@langchain/core/vectorstores\";\nimport { Document } from \"@langchain/core/documents\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { BaseChain, ChainInputs } from \"../../chains/base.js\";\nimport { SerializedBaseChain } from \"../../chains/serde.js\";\nimport { Optional } from \"../../types/type-utils.js\";\nimport { TaskCreationChain } from \"./task_creation.js\";\nimport { TaskExecutionChain } from \"./task_execution.js\";\nimport { TaskPrioritizationChain } from \"./task_prioritization.js\";\n\n/**\n * Interface defining the structure of a task. A task has a `taskID` and a\n * `taskName`.\n */\nexport interface Task {\n  taskID: string;\n  taskName: string;\n}\n\n/**\n * Interface defining the structure of the inputs for the `BabyAGI` class.\n * It extends the `ChainInputs` interface, omitting the 'memory' and\n * 'callbackManager' properties, and adds properties specific to\n * `BabyAGI`.\n */\nexport interface BabyAGIInputs extends Omit<\n  ChainInputs,\n  \"memory\" | \"callbackManager\"\n> {\n  creationChain: BaseChain;\n  prioritizationChain: BaseChain;\n  executionChain: BaseChain;\n  vectorstore: VectorStoreInterface;\n  maxIterations?: number;\n}\n\n/**\n * Class responsible for managing tasks, including their creation,\n * prioritization, and execution. It uses three chains for these\n * operations: `creationChain`, `prioritizationChain`, and\n * `executionChain`.\n * @example\n * ```typescript\n * const babyAGI = BabyAGI.fromLLM({\n *   llm: new OpenAI({ temperature: 0 }),\n *   vectorstore: new MemoryVectorStore(new OpenAIEmbeddings()),\n *   maxIterations: 3,\n * });\n *\n * const result = await babyAGI.call({\n *   objective: \"Write a weather report for SF today\",\n * });\n * ```\n */\nexport class BabyAGI extends BaseChain implements BabyAGIInputs {\n  static lc_name() {\n    return \"BabyAGI\";\n  }\n\n  taskList: Task[];\n\n  creationChain: BaseChain;\n\n  prioritizationChain: BaseChain;\n\n  executionChain: BaseChain;\n\n  taskIDCounter: number;\n\n  vectorstore: VectorStoreInterface;\n\n  maxIterations: number;\n\n  constructor({\n    creationChain,\n    prioritizationChain,\n    executionChain,\n    vectorstore,\n    maxIterations = 100,\n    verbose,\n    callbacks,\n  }: BabyAGIInputs) {\n    super(undefined, verbose, callbacks);\n    this.taskList = [];\n    this.creationChain = creationChain;\n    this.prioritizationChain = prioritizationChain;\n    this.executionChain = executionChain;\n    this.taskIDCounter = 1;\n    this.vectorstore = vectorstore;\n    this.maxIterations = maxIterations;\n  }\n\n  _chainType() {\n    return \"BabyAGI\" as const;\n  }\n\n  get inputKeys() {\n    return [\"objective\", \"firstTask\"];\n  }\n\n  get outputKeys() {\n    return [];\n  }\n\n  /**\n   * Adds a task to the task list.\n   * @param task The task to be added.\n   * @returns Promise resolving to void.\n   */\n  async addTask(task: Task) {\n    this.taskList.push(task);\n  }\n\n  /**\n   * Prints the current task list to the console.\n   * @returns void\n   */\n  printTaskList() {\n    console.log(\"\\x1b[95m\\x1b[1m\\n*****TASK LIST*****\\n\\x1b[0m\\x1b[0m\");\n    for (const t of this.taskList) {\n      console.log(`${t.taskID}: ${t.taskName}`);\n    }\n  }\n\n  /**\n   * Prints the next task to the console.\n   * @param task The next task to be printed.\n   * @returns void\n   */\n  printNextTask(task: Task) {\n    console.log(\"\\x1b[92m\\x1b[1m\\n*****NEXT TASK*****\\n\\x1b[0m\\x1b[0m\");\n    console.log(`${task.taskID}: ${task.taskName}`);\n  }\n\n  /**\n   * Prints the result of a task to the console.\n   * @param result The result of the task.\n   * @returns void\n   */\n  printTaskResult(result: string) {\n    console.log(\"\\x1b[93m\\x1b[1m\\n*****TASK RESULT*****\\n\\x1b[0m\\x1b[0m\");\n    console.log(result.trim());\n  }\n\n  /**\n   * Generates the next tasks based on the result of the previous task, the\n   * task description, and the objective.\n   * @param result The result of the previous task.\n   * @param task_description The description of the task.\n   * @param objective The objective of the task.\n   * @param runManager Optional CallbackManagerForChainRun instance.\n   * @returns Promise resolving to an array of tasks without taskID.\n   */\n  async getNextTasks(\n    result: string,\n    task_description: string,\n    objective: string,\n    runManager?: CallbackManagerForChainRun\n  ): Promise<Optional<Task, \"taskID\">[]> {\n    const taskNames = this.taskList.map((t) => t.taskName);\n    const incomplete_tasks = taskNames.join(\", \");\n    const { [this.creationChain.outputKeys[0]]: text } =\n      await this.creationChain.call(\n        {\n          result,\n          task_description,\n          incomplete_tasks,\n          objective,\n        },\n        runManager?.getChild()\n      );\n    const newTasks = (text as string).split(\"\\n\");\n    return newTasks\n      .filter((taskName) => taskName.trim())\n      .map((taskName) => ({ taskName }));\n  }\n\n  /**\n   * Prioritizes the tasks based on the current task ID and the objective.\n   * @param thisTaskID The ID of the current task.\n   * @param objective The objective of the task.\n   * @param runManager Optional CallbackManagerForChainRun instance.\n   * @returns Promise resolving to an array of prioritized tasks.\n   */\n  async prioritizeTasks(\n    thisTaskID: number,\n    objective: string,\n    runManager?: CallbackManagerForChainRun\n  ) {\n    const taskNames = this.taskList.map((t) => t.taskName);\n    const nextTaskID = thisTaskID + 1;\n    const { [this.prioritizationChain.outputKeys[0]]: text } =\n      await this.prioritizationChain.call(\n        {\n          task_names: taskNames.join(\", \"),\n          next_task_id: String(nextTaskID),\n          objective,\n        },\n        runManager?.getChild()\n      );\n    const newTasks = (text as string).trim().split(\"\\n\");\n    const prioritizedTaskList = [];\n    for (const taskString of newTasks) {\n      const taskParts = taskString.trim().split(\".\", 2);\n      if (taskParts.length === 2) {\n        const taskID = taskParts[0].trim();\n        const taskName = taskParts[1].trim();\n        prioritizedTaskList.push({ taskID, taskName });\n      }\n    }\n    return prioritizedTaskList;\n  }\n\n  /**\n   * Retrieves the top tasks that are most similar to the given query.\n   * @param query The query to search for.\n   * @param k The number of top tasks to retrieve.\n   * @returns Promise resolving to an array of top tasks.\n   */\n  async getTopTasks(query: string, k = 5) {\n    const results = await this.vectorstore.similaritySearch(query, k);\n    if (!results) {\n      return [];\n    }\n    return results.map((item) => String(item.metadata.task));\n  }\n\n  /**\n   * Executes a task based on the objective and the task description.\n   * @param objective The objective of the task.\n   * @param task The task to be executed.\n   * @param runManager Optional CallbackManagerForChainRun instance.\n   * @returns Promise resolving to the result of the task execution as a string.\n   */\n  async executeTask(\n    objective: string,\n    task: string,\n    runManager?: CallbackManagerForChainRun\n  ) {\n    const context = await this.getTopTasks(objective);\n    const { [this.executionChain.outputKeys[0]]: text } =\n      await this.executionChain.call(\n        {\n          objective,\n          context: context.join(\"\\n\"),\n          task,\n        },\n        runManager?.getChild()\n      );\n    return text as string;\n  }\n\n  async _call(\n    { objective, firstTask = \"Make a todo list\" }: ChainValues,\n    runManager?: CallbackManagerForChainRun\n  ) {\n    this.taskList = [];\n    this.taskIDCounter = 1;\n    await this.addTask({ taskID: \"1\", taskName: firstTask });\n\n    let numIters = 0;\n    while (numIters < this.maxIterations && this.taskList.length > 0) {\n      this.printTaskList();\n\n      const task = this.taskList.shift()!;\n      this.printNextTask(task);\n\n      const result = await this.executeTask(\n        objective,\n        task.taskName,\n        runManager\n      );\n      const thisTaskID = parseInt(task.taskID, 10);\n      this.printTaskResult(result);\n\n      await this.vectorstore.addDocuments([\n        new Document({\n          pageContent: result,\n          metadata: { task: task.taskName },\n        }),\n      ]);\n\n      const newTasks = await this.getNextTasks(\n        result,\n        task.taskName,\n        objective,\n        runManager\n      );\n      for (const newTask of newTasks) {\n        this.taskIDCounter += 1;\n        newTask.taskID = this.taskIDCounter.toFixed();\n        await this.addTask(newTask as Task);\n      }\n      this.taskList = await this.prioritizeTasks(\n        thisTaskID,\n        objective,\n        runManager\n      );\n\n      numIters += 1;\n    }\n    return {};\n  }\n\n  serialize(): SerializedBaseChain {\n    throw new Error(\"Method not implemented.\");\n  }\n\n  /**\n   * Static method to create a new BabyAGI instance from a\n   * BaseLanguageModel.\n   * @param llm BaseLanguageModel instance used to generate a new BabyAGI instance.\n   * @param vectorstore VectorStore instance used to store and retrieve vectors.\n   * @param executionChain Optional BaseChain instance used to execute tasks.\n   * @param verbose Optional boolean indicating whether to log verbose output.\n   * @param callbacks Optional callbacks to be used during the execution of tasks.\n   * @param rest Optional additional parameters.\n   * @returns A new instance of BabyAGI.\n   */\n  static fromLLM({\n    llm,\n    vectorstore,\n    executionChain,\n    verbose,\n    callbacks,\n    ...rest\n  }: Optional<\n    BabyAGIInputs,\n    \"executionChain\" | \"creationChain\" | \"prioritizationChain\"\n  > & { llm: BaseLanguageModelInterface }) {\n    const creationChain = TaskCreationChain.fromLLM({\n      llm,\n      verbose,\n      callbacks,\n    });\n    const prioritizationChain = TaskPrioritizationChain.fromLLM({\n      llm,\n      verbose,\n      callbacks,\n    });\n    return new BabyAGI({\n      creationChain,\n      prioritizationChain,\n      executionChain:\n        executionChain ||\n        TaskExecutionChain.fromLLM({ llm, verbose, callbacks }),\n      vectorstore,\n      verbose,\n      callbacks,\n      ...rest,\n    });\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;AAwDA,IAAa,UAAb,MAAa,gBAAgB,UAAmC;CAC9D,OAAO,UAAU;EACf,OAAO;CACT;CAEA;CAEA;CAEA;CAEA;CAEA;CAEA;CAEA;CAEA,YAAY,EACV,eACA,qBACA,gBACA,aACA,gBAAgB,KAChB,SACA,aACgB;EAChB,MAAM,KAAA,GAAW,SAAS,SAAS;EACnC,KAAK,WAAW,CAAC;EACjB,KAAK,gBAAgB;EACrB,KAAK,sBAAsB;EAC3B,KAAK,iBAAiB;EACtB,KAAK,gBAAgB;EACrB,KAAK,cAAc;EACnB,KAAK,gBAAgB;CACvB;CAEA,aAAa;EACX,OAAO;CACT;CAEA,IAAI,YAAY;EACd,OAAO,CAAC,aAAa,WAAW;CAClC;CAEA,IAAI,aAAa;EACf,OAAO,CAAC;CACV;;;;;;CAOA,MAAM,QAAQ,MAAY;EACxB,KAAK,SAAS,KAAK,IAAI;CACzB;;;;;CAMA,gBAAgB;EACd,QAAQ,IAAI,sDAAsD;EAClE,KAAK,MAAM,KAAK,KAAK,UACnB,QAAQ,IAAI,GAAG,EAAE,OAAO,IAAI,EAAE,UAAU;CAE5C;;;;;;CAOA,cAAc,MAAY;EACxB,QAAQ,IAAI,sDAAsD;EAClE,QAAQ,IAAI,GAAG,KAAK,OAAO,IAAI,KAAK,UAAU;CAChD;;;;;;CAOA,gBAAgB,QAAgB;EAC9B,QAAQ,IAAI,wDAAwD;EACpE,QAAQ,IAAI,OAAO,KAAK,CAAC;CAC3B;;;;;;;;;;CAWA,MAAM,aACJ,QACA,kBACA,WACA,YACqC;EAErC,MAAM,mBADY,KAAK,SAAS,KAAK,MAAM,EAAE,QACZ,CAAC,CAAC,KAAK,IAAI;EAC5C,MAAM,GAAG,KAAK,cAAc,WAAW,KAAK,SAC1C,MAAM,KAAK,cAAc,KACvB;GACE;GACA;GACA;GACA;EACF,GACA,YAAY,SAAS,CACvB;EAEF,OADkB,KAAgB,MAAM,IAC1B,CAAC,CACZ,QAAQ,aAAa,SAAS,KAAK,CAAC,CAAC,CACrC,KAAK,cAAc,EAAE,SAAS,EAAE;CACrC;;;;;;;;CASA,MAAM,gBACJ,YACA,WACA,YACA;EACA,MAAM,YAAY,KAAK,SAAS,KAAK,MAAM,EAAE,QAAQ;EACrD,MAAM,aAAa,aAAa;EAChC,MAAM,GAAG,KAAK,oBAAoB,WAAW,KAAK,SAChD,MAAM,KAAK,oBAAoB,KAC7B;GACE,YAAY,UAAU,KAAK,IAAI;GAC/B,cAAc,OAAO,UAAU;GAC/B;EACF,GACA,YAAY,SAAS,CACvB;EACF,MAAM,WAAY,KAAgB,KAAK,CAAC,CAAC,MAAM,IAAI;EACnD,MAAM,sBAAsB,CAAC;EAC7B,KAAK,MAAM,cAAc,UAAU;GACjC,MAAM,YAAY,WAAW,KAAK,CAAC,CAAC,MAAM,KAAK,CAAC;GAChD,IAAI,UAAU,WAAW,GAAG;IAC1B,MAAM,SAAS,UAAU,EAAE,CAAC,KAAK;IACjC,MAAM,WAAW,UAAU,EAAE,CAAC,KAAK;IACnC,oBAAoB,KAAK;KAAE;KAAQ;IAAS,CAAC;GAC/C;EACF;EACA,OAAO;CACT;;;;;;;CAQA,MAAM,YAAY,OAAe,IAAI,GAAG;EACtC,MAAM,UAAU,MAAM,KAAK,YAAY,iBAAiB,OAAO,CAAC;EAChE,IAAI,CAAC,SACH,OAAO,CAAC;EAEV,OAAO,QAAQ,KAAK,SAAS,OAAO,KAAK,SAAS,IAAI,CAAC;CACzD;;;;;;;;CASA,MAAM,YACJ,WACA,MACA,YACA;EACA,MAAM,UAAU,MAAM,KAAK,YAAY,SAAS;EAChD,MAAM,GAAG,KAAK,eAAe,WAAW,KAAK,SAC3C,MAAM,KAAK,eAAe,KACxB;GACE;GACA,SAAS,QAAQ,KAAK,IAAI;GAC1B;EACF,GACA,YAAY,SAAS,CACvB;EACF,OAAO;CACT;CAEA,MAAM,MACJ,EAAE,WAAW,YAAY,sBACzB,YACA;EACA,KAAK,WAAW,CAAC;EACjB,KAAK,gBAAgB;EACrB,MAAM,KAAK,QAAQ;GAAE,QAAQ;GAAK,UAAU;EAAU,CAAC;EAEvD,IAAI,WAAW;EACf,OAAO,WAAW,KAAK,iBAAiB,KAAK,SAAS,SAAS,GAAG;GAChE,KAAK,cAAc;GAEnB,MAAM,OAAO,KAAK,SAAS,MAAM;GACjC,KAAK,cAAc,IAAI;GAEvB,MAAM,SAAS,MAAM,KAAK,YACxB,WACA,KAAK,UACL,UACF;GACA,MAAM,aAAa,SAAS,KAAK,QAAQ,EAAE;GAC3C,KAAK,gBAAgB,MAAM;GAE3B,MAAM,KAAK,YAAY,aAAa,CAClC,IAAI,SAAS;IACX,aAAa;IACb,UAAU,EAAE,MAAM,KAAK,SAAS;GAClC,CAAC,CACH,CAAC;GAED,MAAM,WAAW,MAAM,KAAK,aAC1B,QACA,KAAK,UACL,WACA,UACF;GACA,KAAK,MAAM,WAAW,UAAU;IAC9B,KAAK,iBAAiB;IACtB,QAAQ,SAAS,KAAK,cAAc,QAAQ;IAC5C,MAAM,KAAK,QAAQ,OAAe;GACpC;GACA,KAAK,WAAW,MAAM,KAAK,gBACzB,YACA,WACA,UACF;GAEA,YAAY;EACd;EACA,OAAO,CAAC;CACV;CAEA,YAAiC;EAC/B,MAAM,IAAI,MAAM,yBAAyB;CAC3C;;;;;;;;;;;;CAaA,OAAO,QAAQ,EACb,KACA,aACA,gBACA,SACA,WACA,GAAG,QAIoC;EACvC,MAAM,gBAAgB,kBAAkB,QAAQ;GAC9C;GACA;GACA;EACF,CAAC;EACD,MAAM,sBAAsB,wBAAwB,QAAQ;GAC1D;GACA;GACA;EACF,CAAC;EACD,OAAO,IAAI,QAAQ;GACjB;GACA;GACA,gBACE,kBACA,mBAAmB,QAAQ;IAAE;IAAK;IAAS;GAAU,CAAC;GACxD;GACA;GACA;GACA,GAAG;EACL,CAAC;CACH;AACF"}

package/dist/experimental/babyagi/task_creation.cjs

@@ -1,4 +1,3 @@
-require("../../_virtual/_rolldown/runtime.cjs");
 const require_llm_chain = require("../../chains/llm_chain.cjs");
 let _langchain_core_prompts = require("@langchain/core/prompts");
 //#region src/experimental/babyagi/task_creation.ts
@@ -18,16 +17,17 @@ var TaskCreationChain = class TaskCreationChain extends require_llm_chain.LLMCha
 	* @returns A new instance of TaskCreationChain.
 	*/
 	static fromLLM(fields) {
+		const prompt = new _langchain_core_prompts.PromptTemplate({
+			template: "You are an task creation AI that uses the result of an execution agent to create new tasks with the following objective: {objective}, The last completed task has the result: {result}. This result was based on this task description: {task_description}. These are incomplete tasks: {incomplete_tasks}. Based on the result, create new tasks to be completed by the AI system that do not overlap with incomplete tasks. Return the tasks as an array.",
+			inputVariables: [
+				"result",
+				"task_description",
+				"incomplete_tasks",
+				"objective"
+			]
+		});
 		return new TaskCreationChain({
-			prompt: new _langchain_core_prompts.PromptTemplate({
-				template: "You are an task creation AI that uses the result of an execution agent to create new tasks with the following objective: {objective}, The last completed task has the result: {result}. This result was based on this task description: {task_description}. These are incomplete tasks: {incomplete_tasks}. Based on the result, create new tasks to be completed by the AI system that do not overlap with incomplete tasks. Return the tasks as an array.",
-				inputVariables: [
-					"result",
-					"task_description",
-					"incomplete_tasks",
-					"objective"
-				]
-			}),
+			prompt,
 			...fields
 		});
 	}

package/dist/experimental/babyagi/task_creation.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"task_creation.cjs","names":["LLMChain","PromptTemplate"],"sources":["../../../src/experimental/babyagi/task_creation.ts"],"sourcesContent":["import { PromptTemplate } from \"@langchain/core/prompts\";\nimport { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n\n/** Chain to generate tasks. */\nexport class TaskCreationChain extends LLMChain {\n  static lc_name() {\n    return \"TaskCreationChain\";\n  }\n\n  /**\n   * Creates a new TaskCreationChain instance. It takes an object of type\n   * LLMChainInput as input, omitting the 'prompt' field. It uses the\n   * PromptTemplate class to create a new prompt based on the task creation\n   * template and the input variables. The new TaskCreationChain instance is\n   * then created with this prompt and the remaining fields from the input\n   * object.\n   * @param fields An object of type LLMChainInput, omitting the 'prompt' field.\n   * @returns A new instance of TaskCreationChain.\n   */\n  static fromLLM(fields: Omit<LLMChainInput, \"prompt\">): LLMChain {\n    const taskCreationTemplate =\n      `You are an task creation AI that uses the result of an execution agent` +\n      ` to create new tasks with the following objective: {objective},` +\n      ` The last completed task has the result: {result}.` +\n      ` This result was based on this task description: {task_description}.` +\n      ` These are incomplete tasks: {incomplete_tasks}.` +\n      ` Based on the result, create new tasks to be completed` +\n      ` by the AI system that do not overlap with incomplete tasks.` +\n      ` Return the tasks as an array.`;\n    const prompt = new PromptTemplate({\n      template: taskCreationTemplate,\n      inputVariables: [\n        \"result\",\n        \"task_description\",\n        \"incomplete_tasks\",\n        \"objective\",\n      ],\n    });\n    return new TaskCreationChain({ prompt, ...fields });\n  }\n}\n"],"mappings":";;;;;AAIA,IAAa,oBAAb,MAAa,0BAA0BA,kBAAAA,SAAS;CAC9C,OAAO,UAAU;AACf,SAAO;;;;;;;;;;;;CAaT,OAAO,QAAQ,QAAiD;AAmB9D,SAAO,IAAI,kBAAkB;GAAE,QAAA,IATZC,wBAAAA,eAAe;IAChC,UAAU;IACV,gBAAgB;KACd;KACA;KACA;KACA;KACD;IACF,CACoC;GAAE,GAAG;GAAQ,CAAC"}
+{"version":3,"file":"task_creation.cjs","names":["LLMChain","PromptTemplate"],"sources":["../../../src/experimental/babyagi/task_creation.ts"],"sourcesContent":["import { PromptTemplate } from \"@langchain/core/prompts\";\nimport { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n\n/** Chain to generate tasks. */\nexport class TaskCreationChain extends LLMChain {\n  static lc_name() {\n    return \"TaskCreationChain\";\n  }\n\n  /**\n   * Creates a new TaskCreationChain instance. It takes an object of type\n   * LLMChainInput as input, omitting the 'prompt' field. It uses the\n   * PromptTemplate class to create a new prompt based on the task creation\n   * template and the input variables. The new TaskCreationChain instance is\n   * then created with this prompt and the remaining fields from the input\n   * object.\n   * @param fields An object of type LLMChainInput, omitting the 'prompt' field.\n   * @returns A new instance of TaskCreationChain.\n   */\n  static fromLLM(fields: Omit<LLMChainInput, \"prompt\">): LLMChain {\n    const taskCreationTemplate =\n      `You are an task creation AI that uses the result of an execution agent` +\n      ` to create new tasks with the following objective: {objective},` +\n      ` The last completed task has the result: {result}.` +\n      ` This result was based on this task description: {task_description}.` +\n      ` These are incomplete tasks: {incomplete_tasks}.` +\n      ` Based on the result, create new tasks to be completed` +\n      ` by the AI system that do not overlap with incomplete tasks.` +\n      ` Return the tasks as an array.`;\n    const prompt = new PromptTemplate({\n      template: taskCreationTemplate,\n      inputVariables: [\n        \"result\",\n        \"task_description\",\n        \"incomplete_tasks\",\n        \"objective\",\n      ],\n    });\n    return new TaskCreationChain({ prompt, ...fields });\n  }\n}\n"],"mappings":";;;;AAIA,IAAa,oBAAb,MAAa,0BAA0BA,kBAAAA,SAAS;CAC9C,OAAO,UAAU;EACf,OAAO;CACT;;;;;;;;;;;CAYA,OAAO,QAAQ,QAAiD;EAU9D,MAAM,SAAS,IAAIC,wBAAAA,eAAe;GAChC,UAAU;GACV,gBAAgB;IACd;IACA;IACA;IACA;GACF;EACF,CAAC;EACD,OAAO,IAAI,kBAAkB;GAAE;GAAQ,GAAG;EAAO,CAAC;CACpD;AACF"}

package/dist/experimental/babyagi/task_creation.d.cts

@@ -1,5 +1,4 @@
 import { LLMChain, LLMChainInput } from "../../chains/llm_chain.cjs";
-
 //#region src/experimental/babyagi/task_creation.d.ts
 /** Chain to generate tasks. */
 declare class TaskCreationChain extends LLMChain {

package/dist/experimental/babyagi/task_creation.d.cts.map

@@ -1 +1 @@
-{"version":3,"file":"task_creation.d.cts","names":[],"sources":["../../../src/experimental/babyagi/task_creation.ts"],"mappings":";;;;cAIa,iBAAA,SAA0B,QAAA;EAAA,OAC9B,OAAA,CAAA;EADsB;;;;;;;;;;EAAA,OAetB,OAAA,CAAQ,MAAA,EAAQ,IAAA,CAAK,aAAA,cAA2B,QAAA;AAAA"}
+{"version":3,"file":"task_creation.d.cts","names":[],"sources":["../../../src/experimental/babyagi/task_creation.ts"],"mappings":";;;cAIa,0BAA0B;SAC9B;;;;;;;;;;;SAcA,QAAQ,QAAQ,KAAK,2BAA2B"}

package/dist/experimental/babyagi/task_creation.d.ts

@@ -1,5 +1,4 @@
 import { LLMChain, LLMChainInput } from "../../chains/llm_chain.js";
-
 //#region src/experimental/babyagi/task_creation.d.ts
 /** Chain to generate tasks. */
 declare class TaskCreationChain extends LLMChain {

package/dist/experimental/babyagi/task_creation.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"task_creation.d.ts","names":[],"sources":["../../../src/experimental/babyagi/task_creation.ts"],"mappings":";;;;cAIa,iBAAA,SAA0B,QAAA;EAAA,OAC9B,OAAA,CAAA;EADsB;;;;;;;;;;EAAA,OAetB,OAAA,CAAQ,MAAA,EAAQ,IAAA,CAAK,aAAA,cAA2B,QAAA;AAAA"}
+{"version":3,"file":"task_creation.d.ts","names":[],"sources":["../../../src/experimental/babyagi/task_creation.ts"],"mappings":";;;cAIa,0BAA0B;SAC9B;;;;;;;;;;;SAcA,QAAQ,QAAQ,KAAK,2BAA2B"}

package/dist/experimental/babyagi/task_creation.js

@@ -17,16 +17,17 @@ var TaskCreationChain = class TaskCreationChain extends LLMChain {
 	* @returns A new instance of TaskCreationChain.
 	*/
 	static fromLLM(fields) {
+		const prompt = new PromptTemplate({
+			template: "You are an task creation AI that uses the result of an execution agent to create new tasks with the following objective: {objective}, The last completed task has the result: {result}. This result was based on this task description: {task_description}. These are incomplete tasks: {incomplete_tasks}. Based on the result, create new tasks to be completed by the AI system that do not overlap with incomplete tasks. Return the tasks as an array.",
+			inputVariables: [
+				"result",
+				"task_description",
+				"incomplete_tasks",
+				"objective"
+			]
+		});
 		return new TaskCreationChain({
-			prompt: new PromptTemplate({
-				template: "You are an task creation AI that uses the result of an execution agent to create new tasks with the following objective: {objective}, The last completed task has the result: {result}. This result was based on this task description: {task_description}. These are incomplete tasks: {incomplete_tasks}. Based on the result, create new tasks to be completed by the AI system that do not overlap with incomplete tasks. Return the tasks as an array.",
-				inputVariables: [
-					"result",
-					"task_description",
-					"incomplete_tasks",
-					"objective"
-				]
-			}),
+			prompt,
 			...fields
 		});
 	}

package/dist/experimental/babyagi/task_creation.js.map

@@ -1 +1 @@
-{"version":3,"file":"task_creation.js","names":[],"sources":["../../../src/experimental/babyagi/task_creation.ts"],"sourcesContent":["import { PromptTemplate } from \"@langchain/core/prompts\";\nimport { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n\n/** Chain to generate tasks. */\nexport class TaskCreationChain extends LLMChain {\n  static lc_name() {\n    return \"TaskCreationChain\";\n  }\n\n  /**\n   * Creates a new TaskCreationChain instance. It takes an object of type\n   * LLMChainInput as input, omitting the 'prompt' field. It uses the\n   * PromptTemplate class to create a new prompt based on the task creation\n   * template and the input variables. The new TaskCreationChain instance is\n   * then created with this prompt and the remaining fields from the input\n   * object.\n   * @param fields An object of type LLMChainInput, omitting the 'prompt' field.\n   * @returns A new instance of TaskCreationChain.\n   */\n  static fromLLM(fields: Omit<LLMChainInput, \"prompt\">): LLMChain {\n    const taskCreationTemplate =\n      `You are an task creation AI that uses the result of an execution agent` +\n      ` to create new tasks with the following objective: {objective},` +\n      ` The last completed task has the result: {result}.` +\n      ` This result was based on this task description: {task_description}.` +\n      ` These are incomplete tasks: {incomplete_tasks}.` +\n      ` Based on the result, create new tasks to be completed` +\n      ` by the AI system that do not overlap with incomplete tasks.` +\n      ` Return the tasks as an array.`;\n    const prompt = new PromptTemplate({\n      template: taskCreationTemplate,\n      inputVariables: [\n        \"result\",\n        \"task_description\",\n        \"incomplete_tasks\",\n        \"objective\",\n      ],\n    });\n    return new TaskCreationChain({ prompt, ...fields });\n  }\n}\n"],"mappings":";;;;AAIA,IAAa,oBAAb,MAAa,0BAA0B,SAAS;CAC9C,OAAO,UAAU;AACf,SAAO;;;;;;;;;;;;CAaT,OAAO,QAAQ,QAAiD;AAmB9D,SAAO,IAAI,kBAAkB;GAAE,QAAA,IATZ,eAAe;IAChC,UAAU;IACV,gBAAgB;KACd;KACA;KACA;KACA;KACD;IACF,CACoC;GAAE,GAAG;GAAQ,CAAC"}
+{"version":3,"file":"task_creation.js","names":[],"sources":["../../../src/experimental/babyagi/task_creation.ts"],"sourcesContent":["import { PromptTemplate } from \"@langchain/core/prompts\";\nimport { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n\n/** Chain to generate tasks. */\nexport class TaskCreationChain extends LLMChain {\n  static lc_name() {\n    return \"TaskCreationChain\";\n  }\n\n  /**\n   * Creates a new TaskCreationChain instance. It takes an object of type\n   * LLMChainInput as input, omitting the 'prompt' field. It uses the\n   * PromptTemplate class to create a new prompt based on the task creation\n   * template and the input variables. The new TaskCreationChain instance is\n   * then created with this prompt and the remaining fields from the input\n   * object.\n   * @param fields An object of type LLMChainInput, omitting the 'prompt' field.\n   * @returns A new instance of TaskCreationChain.\n   */\n  static fromLLM(fields: Omit<LLMChainInput, \"prompt\">): LLMChain {\n    const taskCreationTemplate =\n      `You are an task creation AI that uses the result of an execution agent` +\n      ` to create new tasks with the following objective: {objective},` +\n      ` The last completed task has the result: {result}.` +\n      ` This result was based on this task description: {task_description}.` +\n      ` These are incomplete tasks: {incomplete_tasks}.` +\n      ` Based on the result, create new tasks to be completed` +\n      ` by the AI system that do not overlap with incomplete tasks.` +\n      ` Return the tasks as an array.`;\n    const prompt = new PromptTemplate({\n      template: taskCreationTemplate,\n      inputVariables: [\n        \"result\",\n        \"task_description\",\n        \"incomplete_tasks\",\n        \"objective\",\n      ],\n    });\n    return new TaskCreationChain({ prompt, ...fields });\n  }\n}\n"],"mappings":";;;;AAIA,IAAa,oBAAb,MAAa,0BAA0B,SAAS;CAC9C,OAAO,UAAU;EACf,OAAO;CACT;;;;;;;;;;;CAYA,OAAO,QAAQ,QAAiD;EAU9D,MAAM,SAAS,IAAI,eAAe;GAChC,UAAU;GACV,gBAAgB;IACd;IACA;IACA;IACA;GACF;EACF,CAAC;EACD,OAAO,IAAI,kBAAkB;GAAE;GAAQ,GAAG;EAAO,CAAC;CACpD;AACF"}

package/dist/experimental/babyagi/task_execution.cjs

@@ -1,4 +1,3 @@
-require("../../_virtual/_rolldown/runtime.cjs");
 const require_llm_chain = require("../../chains/llm_chain.cjs");
 let _langchain_core_prompts = require("@langchain/core/prompts");
 //#region src/experimental/babyagi/task_execution.ts
@@ -17,15 +16,16 @@ var TaskExecutionChain = class TaskExecutionChain extends require_llm_chain.LLMC
 	* @returns An instance of LLMChain.
 	*/
 	static fromLLM(fields) {
+		const prompt = new _langchain_core_prompts.PromptTemplate({
+			template: "You are an AI who performs one task based on the following objective: {objective}.Take into account these previously completed tasks: {context}. Your task: {task}. Response:",
+			inputVariables: [
+				"objective",
+				"context",
+				"task"
+			]
+		});
 		return new TaskExecutionChain({
-			prompt: new _langchain_core_prompts.PromptTemplate({
-				template: "You are an AI who performs one task based on the following objective: {objective}.Take into account these previously completed tasks: {context}. Your task: {task}. Response:",
-				inputVariables: [
-					"objective",
-					"context",
-					"task"
-				]
-			}),
+			prompt,
 			...fields
 		});
 	}

package/dist/experimental/babyagi/task_execution.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"task_execution.cjs","names":["LLMChain","PromptTemplate"],"sources":["../../../src/experimental/babyagi/task_execution.ts"],"sourcesContent":["import { PromptTemplate } from \"@langchain/core/prompts\";\nimport { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n\n/** Chain to execute tasks. */\nexport class TaskExecutionChain extends LLMChain {\n  static lc_name() {\n    return \"TaskExecutionChain\";\n  }\n\n  /**\n   * A static factory method that creates an instance of TaskExecutionChain.\n   * It constructs a prompt template for task execution, which is then used\n   * to create a new instance of TaskExecutionChain. The prompt template\n   * instructs an AI to perform a task based on a given objective, taking\n   * into account previously completed tasks.\n   * @param fields An object of type LLMChainInput, excluding the \"prompt\" field.\n   * @returns An instance of LLMChain.\n   */\n  static fromLLM(fields: Omit<LLMChainInput, \"prompt\">): LLMChain {\n    const executionTemplate =\n      `You are an AI who performs one task based on the following objective: ` +\n      `{objective}.` +\n      `Take into account these previously completed tasks: {context}.` +\n      ` Your task: {task}. Response:`;\n    const prompt = new PromptTemplate({\n      template: executionTemplate,\n      inputVariables: [\"objective\", \"context\", \"task\"],\n    });\n    return new TaskExecutionChain({ prompt, ...fields });\n  }\n}\n"],"mappings":";;;;;AAIA,IAAa,qBAAb,MAAa,2BAA2BA,kBAAAA,SAAS;CAC/C,OAAO,UAAU;AACf,SAAO;;;;;;;;;;;CAYT,OAAO,QAAQ,QAAiD;AAU9D,SAAO,IAAI,mBAAmB;GAAE,QAAA,IAJbC,wBAAAA,eAAe;IAChC,UAAU;IACV,gBAAgB;KAAC;KAAa;KAAW;KAAO;IACjD,CACqC;GAAE,GAAG;GAAQ,CAAC"}
+{"version":3,"file":"task_execution.cjs","names":["LLMChain","PromptTemplate"],"sources":["../../../src/experimental/babyagi/task_execution.ts"],"sourcesContent":["import { PromptTemplate } from \"@langchain/core/prompts\";\nimport { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n\n/** Chain to execute tasks. */\nexport class TaskExecutionChain extends LLMChain {\n  static lc_name() {\n    return \"TaskExecutionChain\";\n  }\n\n  /**\n   * A static factory method that creates an instance of TaskExecutionChain.\n   * It constructs a prompt template for task execution, which is then used\n   * to create a new instance of TaskExecutionChain. The prompt template\n   * instructs an AI to perform a task based on a given objective, taking\n   * into account previously completed tasks.\n   * @param fields An object of type LLMChainInput, excluding the \"prompt\" field.\n   * @returns An instance of LLMChain.\n   */\n  static fromLLM(fields: Omit<LLMChainInput, \"prompt\">): LLMChain {\n    const executionTemplate =\n      `You are an AI who performs one task based on the following objective: ` +\n      `{objective}.` +\n      `Take into account these previously completed tasks: {context}.` +\n      ` Your task: {task}. Response:`;\n    const prompt = new PromptTemplate({\n      template: executionTemplate,\n      inputVariables: [\"objective\", \"context\", \"task\"],\n    });\n    return new TaskExecutionChain({ prompt, ...fields });\n  }\n}\n"],"mappings":";;;;AAIA,IAAa,qBAAb,MAAa,2BAA2BA,kBAAAA,SAAS;CAC/C,OAAO,UAAU;EACf,OAAO;CACT;;;;;;;;;;CAWA,OAAO,QAAQ,QAAiD;EAM9D,MAAM,SAAS,IAAIC,wBAAAA,eAAe;GAChC,UAAU;GACV,gBAAgB;IAAC;IAAa;IAAW;GAAM;EACjD,CAAC;EACD,OAAO,IAAI,mBAAmB;GAAE;GAAQ,GAAG;EAAO,CAAC;CACrD;AACF"}

package/dist/experimental/babyagi/task_execution.d.cts

@@ -1,5 +1,4 @@
 import { LLMChain, LLMChainInput } from "../../chains/llm_chain.cjs";
-
 //#region src/experimental/babyagi/task_execution.d.ts
 /** Chain to execute tasks. */
 declare class TaskExecutionChain extends LLMChain {

package/dist/experimental/babyagi/task_execution.d.cts.map

@@ -1 +1 @@
-{"version":3,"file":"task_execution.d.cts","names":[],"sources":["../../../src/experimental/babyagi/task_execution.ts"],"mappings":";;;;cAIa,kBAAA,SAA2B,QAAA;EAAA,OAC/B,OAAA,CAAA;EADuB;;;;;;;;;EAAA,OAcvB,OAAA,CAAQ,MAAA,EAAQ,IAAA,CAAK,aAAA,cAA2B,QAAA;AAAA"}
+{"version":3,"file":"task_execution.d.cts","names":[],"sources":["../../../src/experimental/babyagi/task_execution.ts"],"mappings":";;;cAIa,2BAA2B;SAC/B;;;;;;;;;;SAaA,QAAQ,QAAQ,KAAK,2BAA2B"}

package/dist/experimental/babyagi/task_execution.d.ts

@@ -1,5 +1,4 @@
 import { LLMChain, LLMChainInput } from "../../chains/llm_chain.js";
-
 //#region src/experimental/babyagi/task_execution.d.ts
 /** Chain to execute tasks. */
 declare class TaskExecutionChain extends LLMChain {

package/dist/experimental/babyagi/task_execution.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"task_execution.d.ts","names":[],"sources":["../../../src/experimental/babyagi/task_execution.ts"],"mappings":";;;;cAIa,kBAAA,SAA2B,QAAA;EAAA,OAC/B,OAAA,CAAA;EADuB;;;;;;;;;EAAA,OAcvB,OAAA,CAAQ,MAAA,EAAQ,IAAA,CAAK,aAAA,cAA2B,QAAA;AAAA"}
+{"version":3,"file":"task_execution.d.ts","names":[],"sources":["../../../src/experimental/babyagi/task_execution.ts"],"mappings":";;;cAIa,2BAA2B;SAC/B;;;;;;;;;;SAaA,QAAQ,QAAQ,KAAK,2BAA2B"}

package/dist/experimental/babyagi/task_execution.js

@@ -16,15 +16,16 @@ var TaskExecutionChain = class TaskExecutionChain extends LLMChain {
 	* @returns An instance of LLMChain.
 	*/
 	static fromLLM(fields) {
+		const prompt = new PromptTemplate({
+			template: "You are an AI who performs one task based on the following objective: {objective}.Take into account these previously completed tasks: {context}. Your task: {task}. Response:",
+			inputVariables: [
+				"objective",
+				"context",
+				"task"
+			]
+		});
 		return new TaskExecutionChain({
-			prompt: new PromptTemplate({
-				template: "You are an AI who performs one task based on the following objective: {objective}.Take into account these previously completed tasks: {context}. Your task: {task}. Response:",
-				inputVariables: [
-					"objective",
-					"context",
-					"task"
-				]
-			}),
+			prompt,
 			...fields
 		});
 	}

package/dist/experimental/babyagi/task_execution.js.map

@@ -1 +1 @@
-{"version":3,"file":"task_execution.js","names":[],"sources":["../../../src/experimental/babyagi/task_execution.ts"],"sourcesContent":["import { PromptTemplate } from \"@langchain/core/prompts\";\nimport { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n\n/** Chain to execute tasks. */\nexport class TaskExecutionChain extends LLMChain {\n  static lc_name() {\n    return \"TaskExecutionChain\";\n  }\n\n  /**\n   * A static factory method that creates an instance of TaskExecutionChain.\n   * It constructs a prompt template for task execution, which is then used\n   * to create a new instance of TaskExecutionChain. The prompt template\n   * instructs an AI to perform a task based on a given objective, taking\n   * into account previously completed tasks.\n   * @param fields An object of type LLMChainInput, excluding the \"prompt\" field.\n   * @returns An instance of LLMChain.\n   */\n  static fromLLM(fields: Omit<LLMChainInput, \"prompt\">): LLMChain {\n    const executionTemplate =\n      `You are an AI who performs one task based on the following objective: ` +\n      `{objective}.` +\n      `Take into account these previously completed tasks: {context}.` +\n      ` Your task: {task}. Response:`;\n    const prompt = new PromptTemplate({\n      template: executionTemplate,\n      inputVariables: [\"objective\", \"context\", \"task\"],\n    });\n    return new TaskExecutionChain({ prompt, ...fields });\n  }\n}\n"],"mappings":";;;;AAIA,IAAa,qBAAb,MAAa,2BAA2B,SAAS;CAC/C,OAAO,UAAU;AACf,SAAO;;;;;;;;;;;CAYT,OAAO,QAAQ,QAAiD;AAU9D,SAAO,IAAI,mBAAmB;GAAE,QAAA,IAJb,eAAe;IAChC,UAAU;IACV,gBAAgB;KAAC;KAAa;KAAW;KAAO;IACjD,CACqC;GAAE,GAAG;GAAQ,CAAC"}
+{"version":3,"file":"task_execution.js","names":[],"sources":["../../../src/experimental/babyagi/task_execution.ts"],"sourcesContent":["import { PromptTemplate } from \"@langchain/core/prompts\";\nimport { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n\n/** Chain to execute tasks. */\nexport class TaskExecutionChain extends LLMChain {\n  static lc_name() {\n    return \"TaskExecutionChain\";\n  }\n\n  /**\n   * A static factory method that creates an instance of TaskExecutionChain.\n   * It constructs a prompt template for task execution, which is then used\n   * to create a new instance of TaskExecutionChain. The prompt template\n   * instructs an AI to perform a task based on a given objective, taking\n   * into account previously completed tasks.\n   * @param fields An object of type LLMChainInput, excluding the \"prompt\" field.\n   * @returns An instance of LLMChain.\n   */\n  static fromLLM(fields: Omit<LLMChainInput, \"prompt\">): LLMChain {\n    const executionTemplate =\n      `You are an AI who performs one task based on the following objective: ` +\n      `{objective}.` +\n      `Take into account these previously completed tasks: {context}.` +\n      ` Your task: {task}. Response:`;\n    const prompt = new PromptTemplate({\n      template: executionTemplate,\n      inputVariables: [\"objective\", \"context\", \"task\"],\n    });\n    return new TaskExecutionChain({ prompt, ...fields });\n  }\n}\n"],"mappings":";;;;AAIA,IAAa,qBAAb,MAAa,2BAA2B,SAAS;CAC/C,OAAO,UAAU;EACf,OAAO;CACT;;;;;;;;;;CAWA,OAAO,QAAQ,QAAiD;EAM9D,MAAM,SAAS,IAAI,eAAe;GAChC,UAAU;GACV,gBAAgB;IAAC;IAAa;IAAW;GAAM;EACjD,CAAC;EACD,OAAO,IAAI,mBAAmB;GAAE;GAAQ,GAAG;EAAO,CAAC;CACrD;AACF"}

package/dist/experimental/babyagi/task_prioritization.cjs

@@ -1,4 +1,3 @@
-require("../../_virtual/_rolldown/runtime.cjs");
 const require_llm_chain = require("../../chains/llm_chain.cjs");
 let _langchain_core_prompts = require("@langchain/core/prompts");
 //#region src/experimental/babyagi/task_prioritization.ts
@@ -16,15 +15,16 @@ var TaskPrioritizationChain = class TaskPrioritizationChain extends require_llm_
 	* @returns A new instance of TaskPrioritizationChain.
 	*/
 	static fromLLM(fields) {
+		const prompt = new _langchain_core_prompts.PromptTemplate({
+			template: "You are a task prioritization AI tasked with cleaning the formatting of and reprioritizing the following tasks: {task_names}. Consider the ultimate objective of your team: {objective}. Do not remove any tasks. Return the result as a numbered list, like: #. First task #. Second task Start the task list with number {next_task_id}.",
+			inputVariables: [
+				"task_names",
+				"next_task_id",
+				"objective"
+			]
+		});
 		return new TaskPrioritizationChain({
-			prompt: new _langchain_core_prompts.PromptTemplate({
-				template: "You are a task prioritization AI tasked with cleaning the formatting of and reprioritizing the following tasks: {task_names}. Consider the ultimate objective of your team: {objective}. Do not remove any tasks. Return the result as a numbered list, like: #. First task #. Second task Start the task list with number {next_task_id}.",
-				inputVariables: [
-					"task_names",
-					"next_task_id",
-					"objective"
-				]
-			}),
+			prompt,
 			...fields
 		});
 	}

package/dist/experimental/babyagi/task_prioritization.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"task_prioritization.cjs","names":["LLMChain","PromptTemplate"],"sources":["../../../src/experimental/babyagi/task_prioritization.ts"],"sourcesContent":["import { PromptTemplate } from \"@langchain/core/prompts\";\nimport { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n\n/** Chain to prioritize tasks. */\nexport class TaskPrioritizationChain extends LLMChain {\n  static lc_name() {\n    return \"TaskPrioritizationChain\";\n  }\n\n  /**\n   * Static method to create a new TaskPrioritizationChain from a\n   * BaseLanguageModel. It generates a prompt using the PromptTemplate class\n   * and the task prioritization template, and returns a new instance of\n   * TaskPrioritizationChain.\n   * @param fields Object with fields used to initialize the chain, excluding the prompt.\n   * @returns A new instance of TaskPrioritizationChain.\n   */\n  static fromLLM(fields: Omit<LLMChainInput, \"prompt\">): LLMChain {\n    const taskPrioritizationTemplate =\n      `You are a task prioritization AI tasked with cleaning the formatting of ` +\n      `and reprioritizing the following tasks: {task_names}.` +\n      ` Consider the ultimate objective of your team: {objective}.` +\n      ` Do not remove any tasks. Return the result as a numbered list, like:` +\n      ` #. First task` +\n      ` #. Second task` +\n      ` Start the task list with number {next_task_id}.`;\n    const prompt = new PromptTemplate({\n      template: taskPrioritizationTemplate,\n      inputVariables: [\"task_names\", \"next_task_id\", \"objective\"],\n    });\n    return new TaskPrioritizationChain({ prompt, ...fields });\n  }\n}\n"],"mappings":";;;;;AAIA,IAAa,0BAAb,MAAa,gCAAgCA,kBAAAA,SAAS;CACpD,OAAO,UAAU;AACf,SAAO;;;;;;;;;;CAWT,OAAO,QAAQ,QAAiD;AAa9D,SAAO,IAAI,wBAAwB;GAAE,QAAA,IAJlBC,wBAAAA,eAAe;IAChC,UAAU;IACV,gBAAgB;KAAC;KAAc;KAAgB;KAAY;IAC5D,CAC0C;GAAE,GAAG;GAAQ,CAAC"}
+{"version":3,"file":"task_prioritization.cjs","names":["LLMChain","PromptTemplate"],"sources":["../../../src/experimental/babyagi/task_prioritization.ts"],"sourcesContent":["import { PromptTemplate } from \"@langchain/core/prompts\";\nimport { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n\n/** Chain to prioritize tasks. */\nexport class TaskPrioritizationChain extends LLMChain {\n  static lc_name() {\n    return \"TaskPrioritizationChain\";\n  }\n\n  /**\n   * Static method to create a new TaskPrioritizationChain from a\n   * BaseLanguageModel. It generates a prompt using the PromptTemplate class\n   * and the task prioritization template, and returns a new instance of\n   * TaskPrioritizationChain.\n   * @param fields Object with fields used to initialize the chain, excluding the prompt.\n   * @returns A new instance of TaskPrioritizationChain.\n   */\n  static fromLLM(fields: Omit<LLMChainInput, \"prompt\">): LLMChain {\n    const taskPrioritizationTemplate =\n      `You are a task prioritization AI tasked with cleaning the formatting of ` +\n      `and reprioritizing the following tasks: {task_names}.` +\n      ` Consider the ultimate objective of your team: {objective}.` +\n      ` Do not remove any tasks. Return the result as a numbered list, like:` +\n      ` #. First task` +\n      ` #. Second task` +\n      ` Start the task list with number {next_task_id}.`;\n    const prompt = new PromptTemplate({\n      template: taskPrioritizationTemplate,\n      inputVariables: [\"task_names\", \"next_task_id\", \"objective\"],\n    });\n    return new TaskPrioritizationChain({ prompt, ...fields });\n  }\n}\n"],"mappings":";;;;AAIA,IAAa,0BAAb,MAAa,gCAAgCA,kBAAAA,SAAS;CACpD,OAAO,UAAU;EACf,OAAO;CACT;;;;;;;;;CAUA,OAAO,QAAQ,QAAiD;EAS9D,MAAM,SAAS,IAAIC,wBAAAA,eAAe;GAChC,UAAU;GACV,gBAAgB;IAAC;IAAc;IAAgB;GAAW;EAC5D,CAAC;EACD,OAAO,IAAI,wBAAwB;GAAE;GAAQ,GAAG;EAAO,CAAC;CAC1D;AACF"}

package/dist/experimental/babyagi/task_prioritization.d.cts

@@ -1,5 +1,4 @@
 import { LLMChain, LLMChainInput } from "../../chains/llm_chain.cjs";
-
 //#region src/experimental/babyagi/task_prioritization.d.ts
 /** Chain to prioritize tasks. */
 declare class TaskPrioritizationChain extends LLMChain {

package/dist/experimental/babyagi/task_prioritization.d.cts.map

@@ -1 +1 @@
-{"version":3,"file":"task_prioritization.d.cts","names":[],"sources":["../../../src/experimental/babyagi/task_prioritization.ts"],"mappings":";;;;cAIa,uBAAA,SAAgC,QAAA;EAAA,OACpC,OAAA,CAAA;EAD4B;;;;;;;;EAAA,OAa5B,OAAA,CAAQ,MAAA,EAAQ,IAAA,CAAK,aAAA,cAA2B,QAAA;AAAA"}
+{"version":3,"file":"task_prioritization.d.cts","names":[],"sources":["../../../src/experimental/babyagi/task_prioritization.ts"],"mappings":";;;cAIa,gCAAgC;SACpC;;;;;;;;;SAYA,QAAQ,QAAQ,KAAK,2BAA2B"}

package/dist/experimental/babyagi/task_prioritization.d.ts

@@ -1,5 +1,4 @@
 import { LLMChain, LLMChainInput } from "../../chains/llm_chain.js";
-
 //#region src/experimental/babyagi/task_prioritization.d.ts
 /** Chain to prioritize tasks. */
 declare class TaskPrioritizationChain extends LLMChain {

package/dist/experimental/babyagi/task_prioritization.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"task_prioritization.d.ts","names":[],"sources":["../../../src/experimental/babyagi/task_prioritization.ts"],"mappings":";;;;cAIa,uBAAA,SAAgC,QAAA;EAAA,OACpC,OAAA,CAAA;EAD4B;;;;;;;;EAAA,OAa5B,OAAA,CAAQ,MAAA,EAAQ,IAAA,CAAK,aAAA,cAA2B,QAAA;AAAA"}
+{"version":3,"file":"task_prioritization.d.ts","names":[],"sources":["../../../src/experimental/babyagi/task_prioritization.ts"],"mappings":";;;cAIa,gCAAgC;SACpC;;;;;;;;;SAYA,QAAQ,QAAQ,KAAK,2BAA2B"}