@langchain/classic 1.0.17 → 1.0.18

package/dist/experimental/babyagi/agent.js

@@ -97,16 +97,14 @@ var BabyAGI = class BabyAGI extends BaseChain {
 	* @returns Promise resolving to an array of tasks without taskID.
 	*/
 	async getNextTasks(result, task_description, objective, runManager) {
-		const taskNames = this.taskList.map((t) => t.taskName);
-		const incomplete_tasks = taskNames.join(", ");
+		const incomplete_tasks = this.taskList.map((t) => t.taskName).join(", ");
 		const { [this.creationChain.outputKeys[0]]: text } = await this.creationChain.call({
 			result,
 			task_description,
 			incomplete_tasks,
 			objective
 		}, runManager?.getChild());
-		const newTasks = text.split("\n");
-		return newTasks.filter((taskName) => taskName.trim()).map((taskName) => ({ taskName }));
+		return text.split("\n").filter((taskName) => taskName.trim()).map((taskName) => ({ taskName }));
 	}
 	/**
 	* Prioritizes the tasks based on the current task ID and the objective.
@@ -209,20 +207,18 @@ var BabyAGI = class BabyAGI extends BaseChain {
 	* @param rest Optional additional parameters.
 	* @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
-		});
+	static fromLLM({ llm, vectorstore, executionChain, verbose, callbacks, ...rest }) {
 		return new BabyAGI({
-			creationChain,
-			prioritizationChain,
+			creationChain: TaskCreationChain.fromLLM({
+				llm,
+				verbose,
+				callbacks
+			}),
+			prioritizationChain: TaskPrioritizationChain.fromLLM({
+				llm,
+				verbose,
+				callbacks
+			}),
 			executionChain: executionChain || TaskExecutionChain.fromLLM({
 				llm,
 				verbose,

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

@@ -1 +1 @@
-{"version":3,"file":"agent.js","names":["task: Task","result: string","task_description: string","objective: string","runManager?: CallbackManagerForChainRun","thisTaskID: number","query: string","task: string"],"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;CACR;CAED;CAEA;CAEA;CAEA;CAEA;CAEA;CAEA;CAEA,YAAY,EACV,eACA,qBACA,gBACA,aACA,gBAAgB,KAChB,SACA,WACc,EAAE;EAChB,MAAM,QAAW,SAAS,UAAU;EACpC,KAAK,WAAW,CAAE;EAClB,KAAK,gBAAgB;EACrB,KAAK,sBAAsB;EAC3B,KAAK,iBAAiB;EACtB,KAAK,gBAAgB;EACrB,KAAK,cAAc;EACnB,KAAK,gBAAgB;CACtB;CAED,aAAa;AACX,SAAO;CACR;CAED,IAAI,YAAY;AACd,SAAO,CAAC,aAAa,WAAY;CAClC;CAED,IAAI,aAAa;AACf,SAAO,CAAE;CACV;;;;;;CAOD,MAAM,QAAQA,MAAY;EACxB,KAAK,SAAS,KAAK,KAAK;CACzB;;;;;CAMD,gBAAgB;EACd,QAAQ,IAAI,uDAAuD;AACnE,OAAK,MAAM,KAAK,KAAK,UACnB,QAAQ,IAAI,GAAG,EAAE,OAAO,EAAE,EAAE,EAAE,UAAU,CAAC;CAE5C;;;;;;CAOD,cAAcA,MAAY;EACxB,QAAQ,IAAI,uDAAuD;EACnE,QAAQ,IAAI,GAAG,KAAK,OAAO,EAAE,EAAE,KAAK,UAAU,CAAC;CAChD;;;;;;CAOD,gBAAgBC,QAAgB;EAC9B,QAAQ,IAAI,yDAAyD;EACrE,QAAQ,IAAI,OAAO,MAAM,CAAC;CAC3B;;;;;;;;;;CAWD,MAAM,aACJA,QACAC,kBACAC,WACAC,YACqC;EACrC,MAAM,YAAY,KAAK,SAAS,IAAI,CAAC,MAAM,EAAE,SAAS;EACtD,MAAM,mBAAmB,UAAU,KAAK,KAAK;EAC7C,MAAM,EAAE,CAAC,KAAK,cAAc,WAAW,KAAK,MAAM,GAChD,MAAM,KAAK,cAAc,KACvB;GACE;GACA;GACA;GACA;EACD,GACD,YAAY,UAAU,CACvB;EACH,MAAM,WAAY,KAAgB,MAAM,KAAK;AAC7C,SAAO,SACJ,OAAO,CAAC,aAAa,SAAS,MAAM,CAAC,CACrC,IAAI,CAAC,cAAc,EAAE,SAAU,GAAE;CACrC;;;;;;;;CASD,MAAM,gBACJC,YACAF,WACAC,YACA;EACA,MAAM,YAAY,KAAK,SAAS,IAAI,CAAC,MAAM,EAAE,SAAS;EACtD,MAAM,aAAa,aAAa;EAChC,MAAM,EAAE,CAAC,KAAK,oBAAoB,WAAW,KAAK,MAAM,GACtD,MAAM,KAAK,oBAAoB,KAC7B;GACE,YAAY,UAAU,KAAK,KAAK;GAChC,cAAc,OAAO,WAAW;GAChC;EACD,GACD,YAAY,UAAU,CACvB;EACH,MAAM,WAAY,KAAgB,MAAM,CAAC,MAAM,KAAK;EACpD,MAAM,sBAAsB,CAAE;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;IACpC,oBAAoB,KAAK;KAAE;KAAQ;IAAU,EAAC;GAC/C;EACF;AACD,SAAO;CACR;;;;;;;CAQD,MAAM,YAAYE,OAAe,IAAI,GAAG;EACtC,MAAM,UAAU,MAAM,KAAK,YAAY,iBAAiB,OAAO,EAAE;AACjE,MAAI,CAAC,QACH,QAAO,CAAE;AAEX,SAAO,QAAQ,IAAI,CAAC,SAAS,OAAO,KAAK,SAAS,KAAK,CAAC;CACzD;;;;;;;;CASD,MAAM,YACJH,WACAI,MACAH,YACA;EACA,MAAM,UAAU,MAAM,KAAK,YAAY,UAAU;EACjD,MAAM,EAAE,CAAC,KAAK,eAAe,WAAW,KAAK,MAAM,GACjD,MAAM,KAAK,eAAe,KACxB;GACE;GACA,SAAS,QAAQ,KAAK,KAAK;GAC3B;EACD,GACD,YAAY,UAAU,CACvB;AACH,SAAO;CACR;CAED,MAAM,MACJ,EAAE,WAAW,YAAY,oBAAiC,EAC1DA,YACA;EACA,KAAK,WAAW,CAAE;EAClB,KAAK,gBAAgB;EACrB,MAAM,KAAK,QAAQ;GAAE,QAAQ;GAAK,UAAU;EAAW,EAAC;EAExD,IAAI,WAAW;AACf,SAAO,WAAW,KAAK,iBAAiB,KAAK,SAAS,SAAS,GAAG;GAChE,KAAK,eAAe;GAEpB,MAAM,OAAO,KAAK,SAAS,OAAO;GAClC,KAAK,cAAc,KAAK;GAExB,MAAM,SAAS,MAAM,KAAK,YACxB,WACA,KAAK,UACL,WACD;GACD,MAAM,aAAa,SAAS,KAAK,QAAQ,GAAG;GAC5C,KAAK,gBAAgB,OAAO;GAE5B,MAAM,KAAK,YAAY,aAAa,CAClC,IAAI,SAAS;IACX,aAAa;IACb,UAAU,EAAE,MAAM,KAAK,SAAU;GAClC,EACF,EAAC;GAEF,MAAM,WAAW,MAAM,KAAK,aAC1B,QACA,KAAK,UACL,WACA,WACD;AACD,QAAK,MAAM,WAAW,UAAU;IAC9B,KAAK,iBAAiB;IACtB,QAAQ,SAAS,KAAK,cAAc,SAAS;IAC7C,MAAM,KAAK,QAAQ,QAAgB;GACpC;GACD,KAAK,WAAW,MAAM,KAAK,gBACzB,YACA,WACA,WACD;GAED,YAAY;EACb;AACD,SAAO,CAAE;CACV;CAED,YAAiC;AAC/B,QAAM,IAAI,MAAM;CACjB;;;;;;;;;;;;CAaD,OAAO,QAAQ,EACb,KACA,aACA,gBACA,SACA,UACA,GAAG,MAIkC,EAAE;EACvC,MAAM,gBAAgB,kBAAkB,QAAQ;GAC9C;GACA;GACA;EACD,EAAC;EACF,MAAM,sBAAsB,wBAAwB,QAAQ;GAC1D;GACA;GACA;EACD,EAAC;AACF,SAAO,IAAI,QAAQ;GACjB;GACA;GACA,gBACE,kBACA,mBAAmB,QAAQ;IAAE;IAAK;IAAS;GAAW,EAAC;GACzD;GACA;GACA;GACA,GAAG;EACJ;CACF;AACF"}
+{"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,QAAW,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,SAAS,CACnB,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,KAAK,CAE1C,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,CAAC;GAQA,qBAP0B,wBAAwB,QAAQ;IAC1D;IACA;IACA;IACD,CAAC;GAIA,gBACE,kBACA,mBAAmB,QAAQ;IAAE;IAAK;IAAS;IAAW,CAAC;GACzD;GACA;GACA;GACA,GAAG;GACJ,CAAC"}

package/dist/experimental/babyagi/index.cjs

@@ -1,12 +1,12 @@
-const require_rolldown_runtime = require('../../_virtual/rolldown_runtime.cjs');
+Object.defineProperty(exports, Symbol.toStringTag, { value: 'Module' });
+const require_runtime = require('../../_virtual/_rolldown/runtime.cjs');
 const require_task_creation = require('./task_creation.cjs');
 const require_task_execution = require('./task_execution.cjs');
 const require_task_prioritization = require('./task_prioritization.cjs');
 const require_agent = require('./agent.cjs');
 
 //#region src/experimental/babyagi/index.ts
-var babyagi_exports = {};
-require_rolldown_runtime.__export(babyagi_exports, {
+var babyagi_exports = /* @__PURE__ */ require_runtime.__exportAll({
 	BabyAGI: () => require_agent.BabyAGI,
 	TaskCreationChain: () => require_task_creation.TaskCreationChain,
 	TaskExecutionChain: () => require_task_execution.TaskExecutionChain,

package/dist/experimental/babyagi/index.js

@@ -1,12 +1,11 @@
-import { __export } from "../../_virtual/rolldown_runtime.js";
+import { __exportAll } from "../../_virtual/_rolldown/runtime.js";
 import { TaskCreationChain } from "./task_creation.js";
 import { TaskExecutionChain } from "./task_execution.js";
 import { TaskPrioritizationChain } from "./task_prioritization.js";
 import { BabyAGI } from "./agent.js";
 
 //#region src/experimental/babyagi/index.ts
-var babyagi_exports = {};
-__export(babyagi_exports, {
+var babyagi_exports = /* @__PURE__ */ __exportAll({
 	BabyAGI: () => BabyAGI,
 	TaskCreationChain: () => TaskCreationChain,
 	TaskExecutionChain: () => TaskExecutionChain,

package/dist/experimental/babyagi/task_creation.cjs

@@ -1,6 +1,6 @@
-const require_rolldown_runtime = require('../../_virtual/rolldown_runtime.cjs');
+const require_runtime = require('../../_virtual/_rolldown/runtime.cjs');
 const require_llm_chain = require('../../chains/llm_chain.cjs');
-const __langchain_core_prompts = require_rolldown_runtime.__toESM(require("@langchain/core/prompts"));
+let _langchain_core_prompts = require("@langchain/core/prompts");
 
 //#region src/experimental/babyagi/task_creation.ts
 /** Chain to generate tasks. */
@@ -19,18 +19,16 @@ var TaskCreationChain = class TaskCreationChain extends require_llm_chain.LLMCha
 	* @returns A new instance of TaskCreationChain.
 	*/
 	static fromLLM(fields) {
-		const taskCreationTemplate = "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.";
-		const prompt = new __langchain_core_prompts.PromptTemplate({
-			template: taskCreationTemplate,
-			inputVariables: [
-				"result",
-				"task_description",
-				"incomplete_tasks",
-				"objective"
-			]
-		});
 		return new TaskCreationChain({
-			prompt,
+			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"
+				]
+			}),
 			...fields
 		});
 	}

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

@@ -1 +1 @@
-{"version":3,"file":"task_creation.cjs","names":["LLMChain","fields: Omit<LLMChainInput, \"prompt\">","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,2BAAS;CAC9C,OAAO,UAAU;AACf,SAAO;CACR;;;;;;;;;;;CAYD,OAAO,QAAQC,QAAiD;EAC9D,MAAM,uBACJ;EAQF,MAAM,SAAS,IAAIC,wCAAe;GAChC,UAAU;GACV,gBAAgB;IACd;IACA;IACA;IACA;GACD;EACF;AACD,SAAO,IAAI,kBAAkB;GAAE;GAAQ,GAAG;EAAQ;CACnD;AACF"}
+{"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,2BAAS;CAC9C,OAAO,UAAU;AACf,SAAO;;;;;;;;;;;;CAaT,OAAO,QAAQ,QAAiD;AAmB9D,SAAO,IAAI,kBAAkB;GAAE,QAThB,IAAIC,uCAAe;IAChC,UATA;IAUA,gBAAgB;KACd;KACA;KACA;KACA;KACD;IACF,CAAC;GACqC,GAAG;GAAQ,CAAC"}

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

@@ -1 +1 @@
-{"version":3,"file":"task_creation.d.cts","names":["LLMChain","LLMChainInput","TaskCreationChain","Omit"],"sources":["../../../src/experimental/babyagi/task_creation.d.ts"],"sourcesContent":["import { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n/** Chain to generate tasks. */\nexport declare class TaskCreationChain extends LLMChain {\n    static lc_name(): string;\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}\n//# sourceMappingURL=task_creation.d.ts.map"],"mappings":";;;;cAEqBE,iBAAAA,SAA0BF,QAAAA;EAA1BE,OAAAA,OAAAA,CAAAA,CAAAA,EAAAA,MAAiB;EAYND;;;;AAZuB;;;;;;yBAY5BE,KAAKF,2BAA2BD"}
+{"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"}

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

@@ -1 +1 @@
-{"version":3,"file":"task_creation.d.ts","names":["LLMChain","LLMChainInput","TaskCreationChain","Omit"],"sources":["../../../src/experimental/babyagi/task_creation.d.ts"],"sourcesContent":["import { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n/** Chain to generate tasks. */\nexport declare class TaskCreationChain extends LLMChain {\n    static lc_name(): string;\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}\n//# sourceMappingURL=task_creation.d.ts.map"],"mappings":";;;;cAEqBE,iBAAAA,SAA0BF,QAAAA;EAA1BE,OAAAA,OAAAA,CAAAA,CAAAA,EAAAA,MAAiB;EAYND;;;;AAZuB;;;;;;yBAY5BE,KAAKF,2BAA2BD"}
+{"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"}

package/dist/experimental/babyagi/task_creation.js

@@ -18,18 +18,16 @@ var TaskCreationChain = class TaskCreationChain extends LLMChain {
 	* @returns A new instance of TaskCreationChain.
 	*/
 	static fromLLM(fields) {
-		const taskCreationTemplate = "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.";
-		const prompt = new PromptTemplate({
-			template: taskCreationTemplate,
-			inputVariables: [
-				"result",
-				"task_description",
-				"incomplete_tasks",
-				"objective"
-			]
-		});
 		return new TaskCreationChain({
-			prompt,
+			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"
+				]
+			}),
 			...fields
 		});
 	}

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

@@ -1 +1 @@
-{"version":3,"file":"task_creation.js","names":["fields: Omit<LLMChainInput, \"prompt\">"],"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;CACR;;;;;;;;;;;CAYD,OAAO,QAAQA,QAAiD;EAC9D,MAAM,uBACJ;EAQF,MAAM,SAAS,IAAI,eAAe;GAChC,UAAU;GACV,gBAAgB;IACd;IACA;IACA;IACA;GACD;EACF;AACD,SAAO,IAAI,kBAAkB;GAAE;GAAQ,GAAG;EAAQ;CACnD;AACF"}
+{"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,QAThB,IAAI,eAAe;IAChC,UATA;IAUA,gBAAgB;KACd;KACA;KACA;KACA;KACD;IACF,CAAC;GACqC,GAAG;GAAQ,CAAC"}

package/dist/experimental/babyagi/task_execution.cjs

@@ -1,6 +1,6 @@
-const require_rolldown_runtime = require('../../_virtual/rolldown_runtime.cjs');
+const require_runtime = require('../../_virtual/_rolldown/runtime.cjs');
 const require_llm_chain = require('../../chains/llm_chain.cjs');
-const __langchain_core_prompts = require_rolldown_runtime.__toESM(require("@langchain/core/prompts"));
+let _langchain_core_prompts = require("@langchain/core/prompts");
 
 //#region src/experimental/babyagi/task_execution.ts
 /** Chain to execute tasks. */
@@ -18,17 +18,15 @@ var TaskExecutionChain = class TaskExecutionChain extends require_llm_chain.LLMC
 	* @returns An instance of LLMChain.
 	*/
 	static fromLLM(fields) {
-		const executionTemplate = "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:";
-		const prompt = new __langchain_core_prompts.PromptTemplate({
-			template: executionTemplate,
-			inputVariables: [
-				"objective",
-				"context",
-				"task"
-			]
-		});
 		return new TaskExecutionChain({
-			prompt,
+			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"
+				]
+			}),
 			...fields
 		});
 	}

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

@@ -1 +1 @@
-{"version":3,"file":"task_execution.cjs","names":["LLMChain","fields: Omit<LLMChainInput, \"prompt\">","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,2BAAS;CAC/C,OAAO,UAAU;AACf,SAAO;CACR;;;;;;;;;;CAWD,OAAO,QAAQC,QAAiD;EAC9D,MAAM,oBACJ;EAIF,MAAM,SAAS,IAAIC,wCAAe;GAChC,UAAU;GACV,gBAAgB;IAAC;IAAa;IAAW;GAAO;EACjD;AACD,SAAO,IAAI,mBAAmB;GAAE;GAAQ,GAAG;EAAQ;CACpD;AACF"}
+{"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,2BAAS;CAC/C,OAAO,UAAU;AACf,SAAO;;;;;;;;;;;CAYT,OAAO,QAAQ,QAAiD;AAU9D,SAAO,IAAI,mBAAmB;GAAE,QAJjB,IAAIC,uCAAe;IAChC,UALA;IAMA,gBAAgB;KAAC;KAAa;KAAW;KAAO;IACjD,CAAC;GACsC,GAAG;GAAQ,CAAC"}

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

@@ -1 +1 @@
-{"version":3,"file":"task_execution.d.cts","names":["LLMChain","LLMChainInput","TaskExecutionChain","Omit"],"sources":["../../../src/experimental/babyagi/task_execution.d.ts"],"sourcesContent":["import { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n/** Chain to execute tasks. */\nexport declare class TaskExecutionChain extends LLMChain {\n    static lc_name(): string;\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}\n//# sourceMappingURL=task_execution.d.ts.map"],"mappings":";;;;cAEqBE,kBAAAA,SAA2BF,QAAAA;EAA3BE,OAAAA,OAAAA,CAAAA,CAAAA,EAAAA,MAAkB;EAWPD;;;;AAXwB;;;;;yBAW7BE,KAAKF,2BAA2BD"}
+{"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"}

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

@@ -1 +1 @@
-{"version":3,"file":"task_execution.d.ts","names":["LLMChain","LLMChainInput","TaskExecutionChain","Omit"],"sources":["../../../src/experimental/babyagi/task_execution.d.ts"],"sourcesContent":["import { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n/** Chain to execute tasks. */\nexport declare class TaskExecutionChain extends LLMChain {\n    static lc_name(): string;\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}\n//# sourceMappingURL=task_execution.d.ts.map"],"mappings":";;;;cAEqBE,kBAAAA,SAA2BF,QAAAA;EAA3BE,OAAAA,OAAAA,CAAAA,CAAAA,EAAAA,MAAkB;EAWPD;;;;AAXwB;;;;;yBAW7BE,KAAKF,2BAA2BD"}
+{"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"}

package/dist/experimental/babyagi/task_execution.js

@@ -17,17 +17,15 @@ var TaskExecutionChain = class TaskExecutionChain extends LLMChain {
 	* @returns An instance of LLMChain.
 	*/
 	static fromLLM(fields) {
-		const executionTemplate = "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:";
-		const prompt = new PromptTemplate({
-			template: executionTemplate,
-			inputVariables: [
-				"objective",
-				"context",
-				"task"
-			]
-		});
 		return new TaskExecutionChain({
-			prompt,
+			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"
+				]
+			}),
 			...fields
 		});
 	}

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

@@ -1 +1 @@
-{"version":3,"file":"task_execution.js","names":["fields: Omit<LLMChainInput, \"prompt\">"],"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;CACR;;;;;;;;;;CAWD,OAAO,QAAQA,QAAiD;EAC9D,MAAM,oBACJ;EAIF,MAAM,SAAS,IAAI,eAAe;GAChC,UAAU;GACV,gBAAgB;IAAC;IAAa;IAAW;GAAO;EACjD;AACD,SAAO,IAAI,mBAAmB;GAAE;GAAQ,GAAG;EAAQ;CACpD;AACF"}
+{"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,QAJjB,IAAI,eAAe;IAChC,UALA;IAMA,gBAAgB;KAAC;KAAa;KAAW;KAAO;IACjD,CAAC;GACsC,GAAG;GAAQ,CAAC"}

package/dist/experimental/babyagi/task_prioritization.cjs

@@ -1,6 +1,6 @@
-const require_rolldown_runtime = require('../../_virtual/rolldown_runtime.cjs');
+const require_runtime = require('../../_virtual/_rolldown/runtime.cjs');
 const require_llm_chain = require('../../chains/llm_chain.cjs');
-const __langchain_core_prompts = require_rolldown_runtime.__toESM(require("@langchain/core/prompts"));
+let _langchain_core_prompts = require("@langchain/core/prompts");
 
 //#region src/experimental/babyagi/task_prioritization.ts
 /** Chain to prioritize tasks. */
@@ -17,17 +17,15 @@ var TaskPrioritizationChain = class TaskPrioritizationChain extends require_llm_
 	* @returns A new instance of TaskPrioritizationChain.
 	*/
 	static fromLLM(fields) {
-		const taskPrioritizationTemplate = "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}.";
-		const prompt = new __langchain_core_prompts.PromptTemplate({
-			template: taskPrioritizationTemplate,
-			inputVariables: [
-				"task_names",
-				"next_task_id",
-				"objective"
-			]
-		});
 		return new TaskPrioritizationChain({
-			prompt,
+			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"
+				]
+			}),
 			...fields
 		});
 	}

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

@@ -1 +1 @@
-{"version":3,"file":"task_prioritization.cjs","names":["LLMChain","fields: Omit<LLMChainInput, \"prompt\">","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,2BAAS;CACpD,OAAO,UAAU;AACf,SAAO;CACR;;;;;;;;;CAUD,OAAO,QAAQC,QAAiD;EAC9D,MAAM,6BACJ;EAOF,MAAM,SAAS,IAAIC,wCAAe;GAChC,UAAU;GACV,gBAAgB;IAAC;IAAc;IAAgB;GAAY;EAC5D;AACD,SAAO,IAAI,wBAAwB;GAAE;GAAQ,GAAG;EAAQ;CACzD;AACF"}
+{"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,2BAAS;CACpD,OAAO,UAAU;AACf,SAAO;;;;;;;;;;CAWT,OAAO,QAAQ,QAAiD;AAa9D,SAAO,IAAI,wBAAwB;GAAE,QAJtB,IAAIC,uCAAe;IAChC,UARA;IASA,gBAAgB;KAAC;KAAc;KAAgB;KAAY;IAC5D,CAAC;GAC2C,GAAG;GAAQ,CAAC"}

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

@@ -1 +1 @@
-{"version":3,"file":"task_prioritization.d.cts","names":["LLMChain","LLMChainInput","TaskPrioritizationChain","Omit"],"sources":["../../../src/experimental/babyagi/task_prioritization.d.ts"],"sourcesContent":["import { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n/** Chain to prioritize tasks. */\nexport declare class TaskPrioritizationChain extends LLMChain {\n    static lc_name(): string;\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}\n//# sourceMappingURL=task_prioritization.d.ts.map"],"mappings":";;;;cAEqBE,uBAAAA,SAAgCF,QAAAA;EAAhCE,OAAAA,OAAAA,CAAAA,CAAAA,EAAAA,MAAAA;EAUWD;;;;AAV6B;;;;yBAUlCE,KAAKF,2BAA2BD"}
+{"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"}

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

@@ -1 +1 @@
-{"version":3,"file":"task_prioritization.d.ts","names":["LLMChain","LLMChainInput","TaskPrioritizationChain","Omit"],"sources":["../../../src/experimental/babyagi/task_prioritization.d.ts"],"sourcesContent":["import { LLMChain, LLMChainInput } from \"../../chains/llm_chain.js\";\n/** Chain to prioritize tasks. */\nexport declare class TaskPrioritizationChain extends LLMChain {\n    static lc_name(): string;\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}\n//# sourceMappingURL=task_prioritization.d.ts.map"],"mappings":";;;;cAEqBE,uBAAAA,SAAgCF,QAAAA;EAAhCE,OAAAA,OAAAA,CAAAA,CAAAA,EAAAA,MAAAA;EAUWD;;;;AAV6B;;;;yBAUlCE,KAAKF,2BAA2BD"}
+{"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"}

package/dist/experimental/babyagi/task_prioritization.js

@@ -16,17 +16,15 @@ var TaskPrioritizationChain = class TaskPrioritizationChain extends LLMChain {
 	* @returns A new instance of TaskPrioritizationChain.
 	*/
 	static fromLLM(fields) {
-		const taskPrioritizationTemplate = "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}.";
-		const prompt = new PromptTemplate({
-			template: taskPrioritizationTemplate,
-			inputVariables: [
-				"task_names",
-				"next_task_id",
-				"objective"
-			]
-		});
 		return new TaskPrioritizationChain({
-			prompt,
+			prompt: new 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"
+				]
+			}),
 			...fields
 		});
 	}

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

@@ -1 +1 @@
-{"version":3,"file":"task_prioritization.js","names":["fields: Omit<LLMChainInput, \"prompt\">"],"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,gCAAgC,SAAS;CACpD,OAAO,UAAU;AACf,SAAO;CACR;;;;;;;;;CAUD,OAAO,QAAQA,QAAiD;EAC9D,MAAM,6BACJ;EAOF,MAAM,SAAS,IAAI,eAAe;GAChC,UAAU;GACV,gBAAgB;IAAC;IAAc;IAAgB;GAAY;EAC5D;AACD,SAAO,IAAI,wBAAwB;GAAE;GAAQ,GAAG;EAAQ;CACzD;AACF"}
+{"version":3,"file":"task_prioritization.js","names":[],"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,gCAAgC,SAAS;CACpD,OAAO,UAAU;AACf,SAAO;;;;;;;;;;CAWT,OAAO,QAAQ,QAAiD;AAa9D,SAAO,IAAI,wBAAwB;GAAE,QAJtB,IAAI,eAAe;IAChC,UARA;IASA,gBAAgB;KAAC;KAAc;KAAgB;KAAY;IAC5D,CAAC;GAC2C,GAAG;GAAQ,CAAC"}

package/dist/experimental/chains/violation_of_expectations/index.cjs

@@ -1,9 +1,9 @@
-const require_rolldown_runtime = require('../../../_virtual/rolldown_runtime.cjs');
+Object.defineProperty(exports, Symbol.toStringTag, { value: 'Module' });
+const require_runtime = require('../../../_virtual/_rolldown/runtime.cjs');
 const require_violation_of_expectations_chain = require('./violation_of_expectations_chain.cjs');
 
 //#region src/experimental/chains/violation_of_expectations/index.ts
-var violation_of_expectations_exports = {};
-require_rolldown_runtime.__export(violation_of_expectations_exports, { ViolationOfExpectationsChain: () => require_violation_of_expectations_chain.ViolationOfExpectationsChain });
+var violation_of_expectations_exports = /* @__PURE__ */ require_runtime.__exportAll({ ViolationOfExpectationsChain: () => require_violation_of_expectations_chain.ViolationOfExpectationsChain });
 
 //#endregion
 exports.ViolationOfExpectationsChain = require_violation_of_expectations_chain.ViolationOfExpectationsChain;

package/dist/experimental/chains/violation_of_expectations/index.js

@@ -1,9 +1,8 @@
-import { __export } from "../../../_virtual/rolldown_runtime.js";
+import { __exportAll } from "../../../_virtual/_rolldown/runtime.js";
 import { ViolationOfExpectationsChain } from "./violation_of_expectations_chain.js";
 
 //#region src/experimental/chains/violation_of_expectations/index.ts
-var violation_of_expectations_exports = {};
-__export(violation_of_expectations_exports, { ViolationOfExpectationsChain: () => ViolationOfExpectationsChain });
+var violation_of_expectations_exports = /* @__PURE__ */ __exportAll({ ViolationOfExpectationsChain: () => ViolationOfExpectationsChain });
 
 //#endregion
 export { ViolationOfExpectationsChain, violation_of_expectations_exports };

package/dist/experimental/chains/violation_of_expectations/types.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"types.cjs","names":[],"sources":["../../../../src/experimental/chains/violation_of_expectations/types.ts"],"sourcesContent":["import { BaseMessage, HumanMessage } from \"@langchain/core/messages\";\n\n/**\n * Contains the chunk of messages, along with the\n * users response, which is the next message after the chunk.\n */\nexport type MessageChunkResult = {\n  chunkedMessages: BaseMessage[];\n  /**\n   * User response can be undefined if the last message in\n   * the chat history was from the AI.\n   */\n  userResponse?: HumanMessage;\n};\n\nexport type PredictNextUserMessageResponse = {\n  userState: string;\n  predictedUserMessage: string;\n  insights: Array<string>;\n};\n\nexport type GetPredictionViolationsResponse = {\n  userResponse?: HumanMessage;\n  revisedPrediction: string;\n  explainedPredictionErrors: Array<string>;\n};\n\nexport const PREDICT_NEXT_USER_MESSAGE_FUNCTION = {\n  name: \"predictNextUserMessage\",\n  description: \"Predicts the next user message, along with insights.\",\n  parameters: {\n    type: \"object\",\n    properties: {\n      userState: {\n        type: \"string\",\n        description: \"Concise reasoning about the users internal mental state.\",\n      },\n      predictedUserMessage: {\n        type: \"string\",\n        description:\n          \"Your prediction on how they will respond to the AI's most recent message.\",\n      },\n      insights: {\n        type: \"array\",\n        items: {\n          type: \"string\",\n        },\n        description:\n          \"A concise list of any additional insights that would be useful to improve prediction.\",\n      },\n    },\n    required: [\"userState\", \"predictedUserMessage\", \"insights\"],\n  },\n};\n\nexport const PREDICTION_VIOLATIONS_FUNCTION = {\n  name: \"predictionViolations\",\n  description:\n    \"Generates violations, errors and differences between the predicted user response, and the actual response.\",\n  parameters: {\n    type: \"object\",\n    properties: {\n      violationExplanation: {\n        type: \"string\",\n        description: \"How was the predication violated?\",\n      },\n      explainedPredictionErrors: {\n        type: \"array\",\n        items: {\n          type: \"string\",\n        },\n        description: \"Explanations of how the prediction was violated and why\",\n      },\n    },\n    required: [\"violationExplanation\", \"explainedPredictionErrors\"],\n  },\n};\n"],"mappings":";;AA2BA,MAAa,qCAAqC;CAChD,MAAM;CACN,aAAa;CACb,YAAY;EACV,MAAM;EACN,YAAY;GACV,WAAW;IACT,MAAM;IACN,aAAa;GACd;GACD,sBAAsB;IACpB,MAAM;IACN,aACE;GACH;GACD,UAAU;IACR,MAAM;IACN,OAAO,EACL,MAAM,SACP;IACD,aACE;GACH;EACF;EACD,UAAU;GAAC;GAAa;GAAwB;EAAW;CAC5D;AACF;AAED,MAAa,iCAAiC;CAC5C,MAAM;CACN,aACE;CACF,YAAY;EACV,MAAM;EACN,YAAY;GACV,sBAAsB;IACpB,MAAM;IACN,aAAa;GACd;GACD,2BAA2B;IACzB,MAAM;IACN,OAAO,EACL,MAAM,SACP;IACD,aAAa;GACd;EACF;EACD,UAAU,CAAC,wBAAwB,2BAA4B;CAChE;AACF"}
+{"version":3,"file":"types.cjs","names":[],"sources":["../../../../src/experimental/chains/violation_of_expectations/types.ts"],"sourcesContent":["import { BaseMessage, HumanMessage } from \"@langchain/core/messages\";\n\n/**\n * Contains the chunk of messages, along with the\n * users response, which is the next message after the chunk.\n */\nexport type MessageChunkResult = {\n  chunkedMessages: BaseMessage[];\n  /**\n   * User response can be undefined if the last message in\n   * the chat history was from the AI.\n   */\n  userResponse?: HumanMessage;\n};\n\nexport type PredictNextUserMessageResponse = {\n  userState: string;\n  predictedUserMessage: string;\n  insights: Array<string>;\n};\n\nexport type GetPredictionViolationsResponse = {\n  userResponse?: HumanMessage;\n  revisedPrediction: string;\n  explainedPredictionErrors: Array<string>;\n};\n\nexport const PREDICT_NEXT_USER_MESSAGE_FUNCTION = {\n  name: \"predictNextUserMessage\",\n  description: \"Predicts the next user message, along with insights.\",\n  parameters: {\n    type: \"object\",\n    properties: {\n      userState: {\n        type: \"string\",\n        description: \"Concise reasoning about the users internal mental state.\",\n      },\n      predictedUserMessage: {\n        type: \"string\",\n        description:\n          \"Your prediction on how they will respond to the AI's most recent message.\",\n      },\n      insights: {\n        type: \"array\",\n        items: {\n          type: \"string\",\n        },\n        description:\n          \"A concise list of any additional insights that would be useful to improve prediction.\",\n      },\n    },\n    required: [\"userState\", \"predictedUserMessage\", \"insights\"],\n  },\n};\n\nexport const PREDICTION_VIOLATIONS_FUNCTION = {\n  name: \"predictionViolations\",\n  description:\n    \"Generates violations, errors and differences between the predicted user response, and the actual response.\",\n  parameters: {\n    type: \"object\",\n    properties: {\n      violationExplanation: {\n        type: \"string\",\n        description: \"How was the predication violated?\",\n      },\n      explainedPredictionErrors: {\n        type: \"array\",\n        items: {\n          type: \"string\",\n        },\n        description: \"Explanations of how the prediction was violated and why\",\n      },\n    },\n    required: [\"violationExplanation\", \"explainedPredictionErrors\"],\n  },\n};\n"],"mappings":";;AA2BA,MAAa,qCAAqC;CAChD,MAAM;CACN,aAAa;CACb,YAAY;EACV,MAAM;EACN,YAAY;GACV,WAAW;IACT,MAAM;IACN,aAAa;IACd;GACD,sBAAsB;IACpB,MAAM;IACN,aACE;IACH;GACD,UAAU;IACR,MAAM;IACN,OAAO,EACL,MAAM,UACP;IACD,aACE;IACH;GACF;EACD,UAAU;GAAC;GAAa;GAAwB;GAAW;EAC5D;CACF;AAED,MAAa,iCAAiC;CAC5C,MAAM;CACN,aACE;CACF,YAAY;EACV,MAAM;EACN,YAAY;GACV,sBAAsB;IACpB,MAAM;IACN,aAAa;IACd;GACD,2BAA2B;IACzB,MAAM;IACN,OAAO,EACL,MAAM,UACP;IACD,aAAa;IACd;GACF;EACD,UAAU,CAAC,wBAAwB,4BAA4B;EAChE;CACF"}

package/dist/experimental/chains/violation_of_expectations/types.d.cts

@@ -1,7 +1,6 @@
 import { BaseMessage, HumanMessage } from "@langchain/core/messages";
 
 //#region src/experimental/chains/violation_of_expectations/types.d.ts
-
 /**
  * Contains the chunk of messages, along with the
  * users response, which is the next message after the chunk.

package/dist/experimental/chains/violation_of_expectations/types.d.cts.map

@@ -1 +1 @@
-{"version":3,"file":"types.d.cts","names":["BaseMessage","HumanMessage","MessageChunkResult","PredictNextUserMessageResponse","Array","GetPredictionViolationsResponse","PREDICT_NEXT_USER_MESSAGE_FUNCTION","PREDICTION_VIOLATIONS_FUNCTION"],"sources":["../../../../src/experimental/chains/violation_of_expectations/types.d.ts"],"sourcesContent":["import { BaseMessage, HumanMessage } from \"@langchain/core/messages\";\n/**\n * Contains the chunk of messages, along with the\n * users response, which is the next message after the chunk.\n */\nexport type MessageChunkResult = {\n    chunkedMessages: BaseMessage[];\n    /**\n     * User response can be undefined if the last message in\n     * the chat history was from the AI.\n     */\n    userResponse?: HumanMessage;\n};\nexport type PredictNextUserMessageResponse = {\n    userState: string;\n    predictedUserMessage: string;\n    insights: Array<string>;\n};\nexport type GetPredictionViolationsResponse = {\n    userResponse?: HumanMessage;\n    revisedPrediction: string;\n    explainedPredictionErrors: Array<string>;\n};\nexport declare const PREDICT_NEXT_USER_MESSAGE_FUNCTION: {\n    name: string;\n    description: string;\n    parameters: {\n        type: string;\n        properties: {\n            userState: {\n                type: string;\n                description: string;\n            };\n            predictedUserMessage: {\n                type: string;\n                description: string;\n            };\n            insights: {\n                type: string;\n                items: {\n                    type: string;\n                };\n                description: string;\n            };\n        };\n        required: string[];\n    };\n};\nexport declare const PREDICTION_VIOLATIONS_FUNCTION: {\n    name: string;\n    description: string;\n    parameters: {\n        type: string;\n        properties: {\n            violationExplanation: {\n                type: string;\n                description: string;\n            };\n            explainedPredictionErrors: {\n                type: string;\n                items: {\n                    type: string;\n                };\n                description: string;\n            };\n        };\n        required: string[];\n    };\n};\n//# sourceMappingURL=types.d.ts.map"],"mappings":";;;;;;AAKA;;KAAYE,kBAAAA;mBACSF;;;;;iBAKFC"}
+{"version":3,"file":"types.d.cts","names":[],"sources":["../../../../src/experimental/chains/violation_of_expectations/types.ts"],"mappings":";;;;;AAMA;;KAAY,kBAAA;EACV,eAAA,EAAiB,WAAA;EAAjB;;;;EAKA,YAAA,GAAe,YAAA;AAAA"}

package/dist/experimental/chains/violation_of_expectations/types.d.ts

@@ -1,7 +1,6 @@
 import { BaseMessage, HumanMessage } from "@langchain/core/messages";
 
 //#region src/experimental/chains/violation_of_expectations/types.d.ts
-
 /**
  * Contains the chunk of messages, along with the
  * users response, which is the next message after the chunk.

package/dist/experimental/chains/violation_of_expectations/types.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"types.d.ts","names":["BaseMessage","HumanMessage","MessageChunkResult","PredictNextUserMessageResponse","Array","GetPredictionViolationsResponse","PREDICT_NEXT_USER_MESSAGE_FUNCTION","PREDICTION_VIOLATIONS_FUNCTION"],"sources":["../../../../src/experimental/chains/violation_of_expectations/types.d.ts"],"sourcesContent":["import { BaseMessage, HumanMessage } from \"@langchain/core/messages\";\n/**\n * Contains the chunk of messages, along with the\n * users response, which is the next message after the chunk.\n */\nexport type MessageChunkResult = {\n    chunkedMessages: BaseMessage[];\n    /**\n     * User response can be undefined if the last message in\n     * the chat history was from the AI.\n     */\n    userResponse?: HumanMessage;\n};\nexport type PredictNextUserMessageResponse = {\n    userState: string;\n    predictedUserMessage: string;\n    insights: Array<string>;\n};\nexport type GetPredictionViolationsResponse = {\n    userResponse?: HumanMessage;\n    revisedPrediction: string;\n    explainedPredictionErrors: Array<string>;\n};\nexport declare const PREDICT_NEXT_USER_MESSAGE_FUNCTION: {\n    name: string;\n    description: string;\n    parameters: {\n        type: string;\n        properties: {\n            userState: {\n                type: string;\n                description: string;\n            };\n            predictedUserMessage: {\n                type: string;\n                description: string;\n            };\n            insights: {\n                type: string;\n                items: {\n                    type: string;\n                };\n                description: string;\n            };\n        };\n        required: string[];\n    };\n};\nexport declare const PREDICTION_VIOLATIONS_FUNCTION: {\n    name: string;\n    description: string;\n    parameters: {\n        type: string;\n        properties: {\n            violationExplanation: {\n                type: string;\n                description: string;\n            };\n            explainedPredictionErrors: {\n                type: string;\n                items: {\n                    type: string;\n                };\n                description: string;\n            };\n        };\n        required: string[];\n    };\n};\n//# sourceMappingURL=types.d.ts.map"],"mappings":";;;;;;AAKA;;KAAYE,kBAAAA;mBACSF;;;;;iBAKFC"}
+{"version":3,"file":"types.d.ts","names":[],"sources":["../../../../src/experimental/chains/violation_of_expectations/types.ts"],"mappings":";;;;;AAMA;;KAAY,kBAAA;EACV,eAAA,EAAiB,WAAA;EAAjB;;;;EAKA,YAAA,GAAe,YAAA;AAAA"}

package/dist/experimental/chains/violation_of_expectations/types.js.map

@@ -1 +1 @@
-{"version":3,"file":"types.js","names":[],"sources":["../../../../src/experimental/chains/violation_of_expectations/types.ts"],"sourcesContent":["import { BaseMessage, HumanMessage } from \"@langchain/core/messages\";\n\n/**\n * Contains the chunk of messages, along with the\n * users response, which is the next message after the chunk.\n */\nexport type MessageChunkResult = {\n  chunkedMessages: BaseMessage[];\n  /**\n   * User response can be undefined if the last message in\n   * the chat history was from the AI.\n   */\n  userResponse?: HumanMessage;\n};\n\nexport type PredictNextUserMessageResponse = {\n  userState: string;\n  predictedUserMessage: string;\n  insights: Array<string>;\n};\n\nexport type GetPredictionViolationsResponse = {\n  userResponse?: HumanMessage;\n  revisedPrediction: string;\n  explainedPredictionErrors: Array<string>;\n};\n\nexport const PREDICT_NEXT_USER_MESSAGE_FUNCTION = {\n  name: \"predictNextUserMessage\",\n  description: \"Predicts the next user message, along with insights.\",\n  parameters: {\n    type: \"object\",\n    properties: {\n      userState: {\n        type: \"string\",\n        description: \"Concise reasoning about the users internal mental state.\",\n      },\n      predictedUserMessage: {\n        type: \"string\",\n        description:\n          \"Your prediction on how they will respond to the AI's most recent message.\",\n      },\n      insights: {\n        type: \"array\",\n        items: {\n          type: \"string\",\n        },\n        description:\n          \"A concise list of any additional insights that would be useful to improve prediction.\",\n      },\n    },\n    required: [\"userState\", \"predictedUserMessage\", \"insights\"],\n  },\n};\n\nexport const PREDICTION_VIOLATIONS_FUNCTION = {\n  name: \"predictionViolations\",\n  description:\n    \"Generates violations, errors and differences between the predicted user response, and the actual response.\",\n  parameters: {\n    type: \"object\",\n    properties: {\n      violationExplanation: {\n        type: \"string\",\n        description: \"How was the predication violated?\",\n      },\n      explainedPredictionErrors: {\n        type: \"array\",\n        items: {\n          type: \"string\",\n        },\n        description: \"Explanations of how the prediction was violated and why\",\n      },\n    },\n    required: [\"violationExplanation\", \"explainedPredictionErrors\"],\n  },\n};\n"],"mappings":";AA2BA,MAAa,qCAAqC;CAChD,MAAM;CACN,aAAa;CACb,YAAY;EACV,MAAM;EACN,YAAY;GACV,WAAW;IACT,MAAM;IACN,aAAa;GACd;GACD,sBAAsB;IACpB,MAAM;IACN,aACE;GACH;GACD,UAAU;IACR,MAAM;IACN,OAAO,EACL,MAAM,SACP;IACD,aACE;GACH;EACF;EACD,UAAU;GAAC;GAAa;GAAwB;EAAW;CAC5D;AACF;AAED,MAAa,iCAAiC;CAC5C,MAAM;CACN,aACE;CACF,YAAY;EACV,MAAM;EACN,YAAY;GACV,sBAAsB;IACpB,MAAM;IACN,aAAa;GACd;GACD,2BAA2B;IACzB,MAAM;IACN,OAAO,EACL,MAAM,SACP;IACD,aAAa;GACd;EACF;EACD,UAAU,CAAC,wBAAwB,2BAA4B;CAChE;AACF"}
+{"version":3,"file":"types.js","names":[],"sources":["../../../../src/experimental/chains/violation_of_expectations/types.ts"],"sourcesContent":["import { BaseMessage, HumanMessage } from \"@langchain/core/messages\";\n\n/**\n * Contains the chunk of messages, along with the\n * users response, which is the next message after the chunk.\n */\nexport type MessageChunkResult = {\n  chunkedMessages: BaseMessage[];\n  /**\n   * User response can be undefined if the last message in\n   * the chat history was from the AI.\n   */\n  userResponse?: HumanMessage;\n};\n\nexport type PredictNextUserMessageResponse = {\n  userState: string;\n  predictedUserMessage: string;\n  insights: Array<string>;\n};\n\nexport type GetPredictionViolationsResponse = {\n  userResponse?: HumanMessage;\n  revisedPrediction: string;\n  explainedPredictionErrors: Array<string>;\n};\n\nexport const PREDICT_NEXT_USER_MESSAGE_FUNCTION = {\n  name: \"predictNextUserMessage\",\n  description: \"Predicts the next user message, along with insights.\",\n  parameters: {\n    type: \"object\",\n    properties: {\n      userState: {\n        type: \"string\",\n        description: \"Concise reasoning about the users internal mental state.\",\n      },\n      predictedUserMessage: {\n        type: \"string\",\n        description:\n          \"Your prediction on how they will respond to the AI's most recent message.\",\n      },\n      insights: {\n        type: \"array\",\n        items: {\n          type: \"string\",\n        },\n        description:\n          \"A concise list of any additional insights that would be useful to improve prediction.\",\n      },\n    },\n    required: [\"userState\", \"predictedUserMessage\", \"insights\"],\n  },\n};\n\nexport const PREDICTION_VIOLATIONS_FUNCTION = {\n  name: \"predictionViolations\",\n  description:\n    \"Generates violations, errors and differences between the predicted user response, and the actual response.\",\n  parameters: {\n    type: \"object\",\n    properties: {\n      violationExplanation: {\n        type: \"string\",\n        description: \"How was the predication violated?\",\n      },\n      explainedPredictionErrors: {\n        type: \"array\",\n        items: {\n          type: \"string\",\n        },\n        description: \"Explanations of how the prediction was violated and why\",\n      },\n    },\n    required: [\"violationExplanation\", \"explainedPredictionErrors\"],\n  },\n};\n"],"mappings":";AA2BA,MAAa,qCAAqC;CAChD,MAAM;CACN,aAAa;CACb,YAAY;EACV,MAAM;EACN,YAAY;GACV,WAAW;IACT,MAAM;IACN,aAAa;IACd;GACD,sBAAsB;IACpB,MAAM;IACN,aACE;IACH;GACD,UAAU;IACR,MAAM;IACN,OAAO,EACL,MAAM,UACP;IACD,aACE;IACH;GACF;EACD,UAAU;GAAC;GAAa;GAAwB;GAAW;EAC5D;CACF;AAED,MAAa,iCAAiC;CAC5C,MAAM;CACN,aACE;CACF,YAAY;EACV,MAAM;EACN,YAAY;GACV,sBAAsB;IACpB,MAAM;IACN,aAAa;IACd;GACD,2BAA2B;IACzB,MAAM;IACN,OAAO,EACL,MAAM,UACP;IACD,aAAa;IACd;GACF;EACD,UAAU,CAAC,wBAAwB,4BAA4B;EAChE;CACF"}