@langchain/classic 1.0.39 → 1.0.41

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

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

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

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

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

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

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

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

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

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

package/dist/experimental/babyagi/task_creation.js

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

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

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

package/dist/experimental/babyagi/task_execution.cjs

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

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

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

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

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

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

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

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

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

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

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

package/dist/experimental/babyagi/task_execution.js

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

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

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

package/dist/experimental/babyagi/task_prioritization.cjs

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

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

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

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

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

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

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

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

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

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

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

package/dist/experimental/babyagi/task_prioritization.js

@@ -15,15 +15,16 @@ var TaskPrioritizationChain = class TaskPrioritizationChain extends LLMChain {
 	* @returns A new instance of TaskPrioritizationChain.
 	*/
 	static fromLLM(fields) {
+		const 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"
+			]
+		});
 		return new TaskPrioritizationChain({
-			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"
-				]
-			}),
+			prompt,
 			...fields
 		});
 	}

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

@@ -1 +1 @@
-{"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,QAAA,IAJlB,eAAe;IAChC,UAAU;IACV,gBAAgB;KAAC;KAAc;KAAgB;KAAY;IAC5D,CAC0C;GAAE,GAAG;GAAQ,CAAC"}
+{"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;EACf,OAAO;CACT;;;;;;;;;CAUA,OAAO,QAAQ,QAAiD;EAS9D,MAAM,SAAS,IAAI,eAAe;GAChC,UAAU;GACV,gBAAgB;IAAC;IAAc;IAAgB;GAAW;EAC5D,CAAC;EACD,OAAO,IAAI,wBAAwB;GAAE;GAAQ,GAAG;EAAO,CAAC;CAC1D;AACF"}

package/dist/experimental/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;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"}
+{"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;GACf;GACA,sBAAsB;IACpB,MAAM;IACN,aACE;GACJ;GACA,UAAU;IACR,MAAM;IACN,OAAO,EACL,MAAM,SACR;IACA,aACE;GACJ;EACF;EACA,UAAU;GAAC;GAAa;GAAwB;EAAU;CAC5D;AACF;AAEA,MAAa,iCAAiC;CAC5C,MAAM;CACN,aACE;CACF,YAAY;EACV,MAAM;EACN,YAAY;GACV,sBAAsB;IACpB,MAAM;IACN,aAAa;GACf;GACA,2BAA2B;IACzB,MAAM;IACN,OAAO,EACL,MAAM,SACR;IACA,aAAa;GACf;EACF;EACA,UAAU,CAAC,wBAAwB,2BAA2B;CAChE;AACF"}

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

@@ -1,5 +1,4 @@
 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

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

@@ -1 +1 @@
-{"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"}
+{"version":3,"file":"types.d.cts","names":[],"sources":["../../../../src/experimental/chains/violation_of_expectations/types.ts"],"mappings":";;;;;;KAMY;EACV,iBAAiB;;;;;EAKjB,eAAe"}

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

@@ -1,5 +1,4 @@
 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

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

@@ -1 +1 @@
-{"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"}
+{"version":3,"file":"types.d.ts","names":[],"sources":["../../../../src/experimental/chains/violation_of_expectations/types.ts"],"mappings":";;;;;;KAMY;EACV,iBAAiB;;;;;EAKjB,eAAe"}

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;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"}
+{"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;GACf;GACA,sBAAsB;IACpB,MAAM;IACN,aACE;GACJ;GACA,UAAU;IACR,MAAM;IACN,OAAO,EACL,MAAM,SACR;IACA,aACE;GACJ;EACF;EACA,UAAU;GAAC;GAAa;GAAwB;EAAU;CAC5D;AACF;AAEA,MAAa,iCAAiC;CAC5C,MAAM;CACN,aACE;CACF,YAAY;EACV,MAAM;EACN,YAAY;GACV,sBAAsB;IACpB,MAAM;IACN,aAAa;GACf;GACA,2BAA2B;IACzB,MAAM;IACN,OAAO,EACL,MAAM,SACR;IACA,aAAa;GACf;EACF;EACA,UAAU,CAAC,wBAAwB,2BAA2B;CAChE;AACF"}

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

@@ -1,4 +1,3 @@
-require("../../../_virtual/_rolldown/runtime.cjs");
 const require_base = require("../../../chains/base.cjs");
 const require_openai_functions = require("../../../output_parsers/openai_functions.cjs");
 const require_types = require("./types.cjs");

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

@@ -1 +1 @@
-{"version":3,"file":"violation_of_expectations_chain.cjs","names":["BaseChain","JsonOutputFunctionsParser","StringOutputParser","HumanMessage","PREDICT_NEXT_USER_MESSAGE_FUNCTION","PREDICT_NEXT_USER_MESSAGE_PROMPT","PREDICTION_VIOLATIONS_FUNCTION","PREDICTION_VIOLATIONS_PROMPT","GENERATE_REVISED_PREDICTION_PROMPT","GENERATE_FACTS_PROMPT"],"sources":["../../../../src/experimental/chains/violation_of_expectations/violation_of_expectations_chain.ts"],"sourcesContent":["import type { BaseRetrieverInterface } from \"@langchain/core/retrievers\";\nimport { ChatOpenAI } from \"@langchain/openai\";\nimport {\n  BaseMessage,\n  HumanMessage,\n  isBaseMessage,\n} from \"@langchain/core/messages\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { StringOutputParser } from \"@langchain/core/output_parsers\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { JsonOutputFunctionsParser } from \"../../../output_parsers/openai_functions.js\";\nimport { BaseChain, ChainInputs } from \"../../../chains/base.js\";\nimport {\n  GetPredictionViolationsResponse,\n  MessageChunkResult,\n  PREDICTION_VIOLATIONS_FUNCTION,\n  PREDICT_NEXT_USER_MESSAGE_FUNCTION,\n  PredictNextUserMessageResponse,\n} from \"./types.js\";\nimport {\n  GENERATE_FACTS_PROMPT,\n  GENERATE_REVISED_PREDICTION_PROMPT,\n  PREDICTION_VIOLATIONS_PROMPT,\n  PREDICT_NEXT_USER_MESSAGE_PROMPT,\n} from \"./violation_of_expectations_prompt.js\";\n\n/**\n * Interface for the input parameters of the ViolationOfExpectationsChain class.\n */\nexport interface ViolationOfExpectationsChainInput extends ChainInputs {\n  /**\n   * The retriever to use for retrieving stored\n   * thoughts and insights.\n   */\n  retriever: BaseRetrieverInterface;\n  /**\n   * The LLM to use\n   */\n  llm: ChatOpenAI;\n}\n\n/**\n * Chain that generates key insights/facts of a user based on a\n * a chat conversation with an AI.\n */\nexport class ViolationOfExpectationsChain\n  extends BaseChain\n  implements ViolationOfExpectationsChainInput\n{\n  static lc_name() {\n    return \"ViolationOfExpectationsChain\";\n  }\n\n  _chainType(): string {\n    return \"violation_of_expectation_chain\";\n  }\n\n  chatHistoryKey = \"chat_history\";\n\n  thoughtsKey = \"thoughts\";\n\n  get inputKeys() {\n    return [this.chatHistoryKey];\n  }\n\n  get outputKeys() {\n    return [this.thoughtsKey];\n  }\n\n  retriever: BaseRetrieverInterface;\n\n  llm: ChatOpenAI;\n\n  jsonOutputParser: JsonOutputFunctionsParser;\n\n  stringOutputParser: StringOutputParser;\n\n  constructor(fields: ViolationOfExpectationsChainInput) {\n    super(fields);\n    this.retriever = fields.retriever;\n    this.llm = fields.llm;\n    this.jsonOutputParser = new JsonOutputFunctionsParser();\n    this.stringOutputParser = new StringOutputParser();\n  }\n\n  getChatHistoryString(chatHistory: BaseMessage[]): string {\n    return chatHistory\n      .map((chatMessage) => {\n        if (chatMessage._getType() === \"human\") {\n          return `Human: ${chatMessage.content}`;\n        } else if (chatMessage._getType() === \"ai\") {\n          return `AI: ${chatMessage.content}`;\n        } else {\n          return `${chatMessage.content}`;\n        }\n      })\n      .join(\"\\n\");\n  }\n\n  removeDuplicateStrings(strings: Array<string>): Array<string> {\n    return [...new Set(strings)];\n  }\n\n  /**\n   * This method breaks down the chat history into chunks of messages.\n   * Each chunk consists of a sequence of messages ending with an AI message and the subsequent user response, if any.\n   *\n   * @param {BaseMessage[]} chatHistory - The chat history to be chunked.\n   *\n   * @returns {MessageChunkResult[]} An array of message chunks. Each chunk includes a sequence of messages and the subsequent user response.\n   *\n   * @description\n   * The method iterates over the chat history and pushes each message into a temporary array.\n   * When it encounters an AI message, it checks for a subsequent user message.\n   * If a user message is found, it is considered as the user response to the AI message.\n   * If no user message is found after the AI message, the user response is undefined.\n   * The method then pushes the chunk (sequence of messages and user response) into the result array.\n   * This process continues until all messages in the chat history have been processed.\n   */\n  chunkMessagesByAIResponse(chatHistory: BaseMessage[]): MessageChunkResult[] {\n    const newArray: MessageChunkResult[] = [];\n    const tempArray: BaseMessage[] = [];\n\n    chatHistory.forEach((item, index) => {\n      tempArray.push(item);\n      if (item._getType() === \"ai\") {\n        let userResponse: BaseMessage | undefined = chatHistory[index + 1];\n        if (!userResponse || userResponse._getType() !== \"human\") {\n          userResponse = undefined;\n        }\n\n        newArray.push({\n          chunkedMessages: tempArray,\n          userResponse: userResponse\n            ? new HumanMessage(userResponse)\n            : undefined,\n        });\n      }\n    });\n\n    return newArray;\n  }\n\n  /**\n   * This method processes a chat history to generate insights about the user.\n   *\n   * @param {ChainValues} values - The input values for the chain. It should contain a key for chat history.\n   * @param {CallbackManagerForChainRun} [runManager] - Optional callback manager for the chain run.\n   *\n   * @returns {Promise<ChainValues>} A promise that resolves to a list of insights about the user.\n   *\n   * @throws {Error} If the chat history key is not found in the input values or if the chat history is not an array of BaseMessages.\n   *\n   * @description\n   * The method performs the following steps:\n   * 1. Checks if the chat history key is present in the input values and if the chat history is an array of BaseMessages.\n   * 2. Breaks the chat history into chunks of messages.\n   * 3. For each chunk, it generates an initial prediction for the user's next message.\n   * 4. For each prediction, it generates insights and prediction violations, and regenerates the prediction based on the violations.\n   * 5. For each set of messages, it generates a fact/insight about the user.\n   * The method returns a list of these insights.\n   */\n  async _call(\n    values: ChainValues,\n    runManager?: CallbackManagerForChainRun\n  ): Promise<ChainValues> {\n    if (!(this.chatHistoryKey in values)) {\n      throw new Error(`Chat history key ${this.chatHistoryKey} not found`);\n    }\n\n    const chatHistory: unknown[] = values[this.chatHistoryKey];\n\n    const isEveryMessageBaseMessage = chatHistory.every((message) =>\n      isBaseMessage(message)\n    );\n    if (!isEveryMessageBaseMessage) {\n      throw new Error(\"Chat history must be an array of BaseMessages\");\n    }\n\n    const messageChunks = this.chunkMessagesByAIResponse(\n      chatHistory as BaseMessage[]\n    );\n\n    // Generate the initial prediction for every user message.\n    const userPredictions = await Promise.all(\n      messageChunks.map(async (chatHistoryChunk) => ({\n        userPredictions: await this.predictNextUserMessage(\n          chatHistoryChunk.chunkedMessages\n        ),\n        userResponse: chatHistoryChunk.userResponse,\n        runManager,\n      }))\n    );\n\n    // Generate insights, and prediction violations for every user message.\n    // This call also regenerates the prediction based on the violations.\n    const predictionViolations = await Promise.all(\n      userPredictions.map((prediction) =>\n        this.getPredictionViolations({\n          userPredictions: prediction.userPredictions,\n          userResponse: prediction.userResponse,\n          runManager,\n        })\n      )\n    );\n\n    // Generate a fact/insight about the user for every set of messages.\n    const insights = await Promise.all(\n      predictionViolations.map((violation) =>\n        this.generateFacts({\n          userResponse: violation.userResponse,\n          predictions: {\n            revisedPrediction: violation.revisedPrediction,\n            explainedPredictionErrors: violation.explainedPredictionErrors,\n          },\n        })\n      )\n    );\n\n    return {\n      insights,\n    };\n  }\n\n  /**\n   * This method predicts the next user message based on the chat history.\n   *\n   * @param {BaseMessage[]} chatHistory - The chat history based on which the next user message is predicted.\n   * @param {CallbackManagerForChainRun} [runManager] - Optional callback manager for the chain run.\n   *\n   * @returns {Promise<PredictNextUserMessageResponse>} A promise that resolves to the predicted next user message, the user state, and any insights.\n   *\n   * @throws {Error} If the response from the language model does not contain the expected keys: 'userState', 'predictedUserMessage', and 'insights'.\n   */\n  private async predictNextUserMessage(\n    chatHistory: BaseMessage[],\n    runManager?: CallbackManagerForChainRun\n  ): Promise<PredictNextUserMessageResponse> {\n    const messageString = this.getChatHistoryString(chatHistory);\n\n    const llmWithFunctions = this.llm\n      .bindTools([PREDICT_NEXT_USER_MESSAGE_FUNCTION])\n      .withConfig({\n        function_call: { name: PREDICT_NEXT_USER_MESSAGE_FUNCTION.name },\n      });\n\n    const chain = PREDICT_NEXT_USER_MESSAGE_PROMPT.pipe(llmWithFunctions).pipe(\n      this.jsonOutputParser\n    );\n\n    const res = await chain.invoke(\n      {\n        chat_history: messageString,\n      },\n      runManager?.getChild(\"prediction\")\n    );\n\n    if (\n      !(\n        \"userState\" in res &&\n        \"predictedUserMessage\" in res &&\n        \"insights\" in res\n      )\n    ) {\n      throw new Error(`Invalid response from LLM: ${JSON.stringify(res)}`);\n    }\n\n    const predictionResponse = res as PredictNextUserMessageResponse;\n\n    // Query the retriever for relevant insights. Use the generates insights as a query.\n    const retrievedDocs = await this.retrieveRelevantInsights(\n      predictionResponse.insights\n    );\n    const relevantDocs = this.removeDuplicateStrings([\n      ...predictionResponse.insights,\n      ...retrievedDocs,\n    ]);\n\n    return {\n      ...predictionResponse,\n      insights: relevantDocs,\n    };\n  }\n\n  /**\n   * Retrieves relevant insights based on the provided insights.\n   *\n   * @param {Array<string>} insights - An array of insights to be used for retrieving relevant documents.\n   *\n   * @returns {Promise<Array<string>>} A promise that resolves to an array of relevant insights content.\n   */\n  private async retrieveRelevantInsights(\n    insights: Array<string>\n  ): Promise<Array<string>> {\n    // Only extract the first relevant doc from the retriever. We don't need more than one.\n    const relevantInsightsDocuments = await Promise.all(\n      insights.map(async (insight) => {\n        const relevantInsight = await this.retriever.invoke(insight);\n        return relevantInsight[0];\n      })\n    );\n\n    const relevantInsightsContent = relevantInsightsDocuments.map(\n      (document) => document.pageContent\n    );\n\n    return relevantInsightsContent;\n  }\n\n  /**\n   * This method generates prediction violations based on the predicted and actual user responses.\n   * It also generates a revised prediction based on the identified violations.\n   *\n   * @param {Object} params - The parameters for the method.\n   * @param {PredictNextUserMessageResponse} params.userPredictions - The predicted user message, user state, and insights.\n   * @param {BaseMessage} [params.userResponse] - The actual user response.\n   * @param {CallbackManagerForChainRun} [params.runManager] - Optional callback manager for the chain run.\n   *\n   * @returns {Promise<{ userResponse: BaseMessage | undefined; revisedPrediction: string; explainedPredictionErrors: Array<string>; }>} A promise that resolves to an object containing the actual user response, the revised prediction, and the explained prediction errors.\n   *\n   * @throws {Error} If the response from the language model does not contain the expected keys: 'violationExplanation', 'explainedPredictionErrors', and 'accuratePrediction'.\n   */\n  private async getPredictionViolations({\n    userPredictions,\n    userResponse,\n    runManager,\n  }: {\n    userPredictions: PredictNextUserMessageResponse;\n    userResponse?: BaseMessage;\n    runManager?: CallbackManagerForChainRun;\n  }): Promise<GetPredictionViolationsResponse> {\n    const llmWithFunctions = this.llm\n      .bindTools([PREDICTION_VIOLATIONS_FUNCTION])\n      .withConfig({\n        function_call: { name: PREDICTION_VIOLATIONS_FUNCTION.name },\n      });\n\n    const chain = PREDICTION_VIOLATIONS_PROMPT.pipe(llmWithFunctions).pipe(\n      this.jsonOutputParser\n    );\n\n    if (typeof userResponse?.content !== \"string\") {\n      throw new Error(\"This chain does not support non-string model output.\");\n    }\n    const res = (await chain.invoke(\n      {\n        predicted_output: userPredictions.predictedUserMessage,\n        actual_output: userResponse?.content ?? \"\",\n        user_insights: userPredictions.insights.join(\"\\n\"),\n      },\n      runManager?.getChild(\"prediction_violations\")\n    )) as Awaited<{\n      violationExplanation: string;\n      explainedPredictionErrors: Array<string>;\n      accuratePrediction: boolean;\n    }>;\n\n    // Generate a revised prediction based on violations.\n    const revisedPrediction = await this.generateRevisedPrediction({\n      originalPrediction: userPredictions.predictedUserMessage,\n      explainedPredictionErrors: res.explainedPredictionErrors,\n      userInsights: userPredictions.insights,\n      runManager,\n    });\n\n    return {\n      userResponse,\n      revisedPrediction,\n      explainedPredictionErrors: res.explainedPredictionErrors,\n    };\n  }\n\n  /**\n   * This method generates a revised prediction based on the original prediction, explained prediction errors, and user insights.\n   *\n   * @param {Object} params - The parameters for the method.\n   * @param {string} params.originalPrediction - The original prediction made by the model.\n   * @param {Array<string>} params.explainedPredictionErrors - An array of explained prediction errors.\n   * @param {Array<string>} params.userInsights - An array of insights about the user.\n   * @param {CallbackManagerForChainRun} [params.runManager] - Optional callback manager for the chain run.\n   *\n   * @returns {Promise<string>} A promise that resolves to a revised prediction.\n   */\n  private async generateRevisedPrediction({\n    originalPrediction,\n    explainedPredictionErrors,\n    userInsights,\n    runManager,\n  }: {\n    originalPrediction: string;\n    explainedPredictionErrors: Array<string>;\n    userInsights: Array<string>;\n    runManager?: CallbackManagerForChainRun;\n  }): Promise<string> {\n    const revisedPredictionChain = GENERATE_REVISED_PREDICTION_PROMPT.pipe(\n      this.llm\n    ).pipe(this.stringOutputParser);\n\n    const revisedPredictionRes = await revisedPredictionChain.invoke(\n      {\n        prediction: originalPrediction,\n        explained_prediction_errors: explainedPredictionErrors.join(\"\\n\"),\n        user_insights: userInsights.join(\"\\n\"),\n      },\n      runManager?.getChild(\"prediction_revision\")\n    );\n\n    return revisedPredictionRes;\n  }\n\n  /**\n   * This method generates facts or insights about the user based on the revised prediction, explained prediction errors, and the user's response.\n   *\n   * @param {Object} params - The parameters for the method.\n   * @param {BaseMessage} [params.userResponse] - The actual user response.\n   * @param {Object} params.predictions - The revised prediction and explained prediction errors.\n   * @param {string} params.predictions.revisedPrediction - The revised prediction made by the model.\n   * @param {Array<string>} params.predictions.explainedPredictionErrors - An array of explained prediction errors.\n   * @param {CallbackManagerForChainRun} [params.runManager] - Optional callback manager for the chain run.\n   *\n   * @returns {Promise<string>} A promise that resolves to a string containing the generated facts or insights about the user.\n   */\n  private async generateFacts({\n    userResponse,\n    predictions,\n    runManager,\n  }: {\n    userResponse?: BaseMessage;\n    /**\n     * Optional if the prediction was accurate.\n     */\n    predictions: {\n      revisedPrediction: string;\n      explainedPredictionErrors: Array<string>;\n    };\n    runManager?: CallbackManagerForChainRun;\n  }): Promise<string> {\n    const chain = GENERATE_FACTS_PROMPT.pipe(this.llm).pipe(\n      this.stringOutputParser\n    );\n\n    if (typeof userResponse?.content !== \"string\") {\n      throw new Error(\"This chain does not support non-string model output.\");\n    }\n    const res = await chain.invoke(\n      {\n        prediction_violations: predictions.explainedPredictionErrors.join(\"\\n\"),\n        prediction: predictions.revisedPrediction,\n        user_message: userResponse?.content ?? \"\",\n      },\n      runManager?.getChild(\"generate_facts\")\n    );\n\n    return res;\n  }\n\n  /**\n   * Static method that creates a ViolationOfExpectationsChain instance from a\n   * ChatOpenAI and retriever. It also accepts optional options\n   * to customize the chain.\n   *\n   * @param llm The ChatOpenAI instance.\n   * @param retriever The retriever used for similarity search.\n   * @param options Optional options to customize the chain.\n   *\n   * @returns A new instance of ViolationOfExpectationsChain.\n   */\n  static fromLLM(\n    llm: ChatOpenAI,\n    retriever: BaseRetrieverInterface,\n    options?: Partial<\n      Omit<ViolationOfExpectationsChainInput, \"llm\" | \"retriever\">\n    >\n  ): ViolationOfExpectationsChain {\n    return new this({\n      retriever,\n      llm,\n      ...options,\n    });\n  }\n}\n"],"mappings":";;;;;;;;;;;;AA6CA,IAAa,+BAAb,cACUA,aAAAA,UAEV;CACE,OAAO,UAAU;AACf,SAAO;;CAGT,aAAqB;AACnB,SAAO;;CAGT,iBAAiB;CAEjB,cAAc;CAEd,IAAI,YAAY;AACd,SAAO,CAAC,KAAK,eAAe;;CAG9B,IAAI,aAAa;AACf,SAAO,CAAC,KAAK,YAAY;;CAG3B;CAEA;CAEA;CAEA;CAEA,YAAY,QAA2C;AACrD,QAAM,OAAO;AACb,OAAK,YAAY,OAAO;AACxB,OAAK,MAAM,OAAO;AAClB,OAAK,mBAAmB,IAAIC,yBAAAA,2BAA2B;AACvD,OAAK,qBAAqB,IAAIC,+BAAAA,oBAAoB;;CAGpD,qBAAqB,aAAoC;AACvD,SAAO,YACJ,KAAK,gBAAgB;AACpB,OAAI,YAAY,UAAU,KAAK,QAC7B,QAAO,UAAU,YAAY;YACpB,YAAY,UAAU,KAAK,KACpC,QAAO,OAAO,YAAY;OAE1B,QAAO,GAAG,YAAY;IAExB,CACD,KAAK,KAAK;;CAGf,uBAAuB,SAAuC;AAC5D,SAAO,CAAC,GAAG,IAAI,IAAI,QAAQ,CAAC;;;;;;;;;;;;;;;;;;CAmB9B,0BAA0B,aAAkD;EAC1E,MAAM,WAAiC,EAAE;EACzC,MAAM,YAA2B,EAAE;AAEnC,cAAY,SAAS,MAAM,UAAU;AACnC,aAAU,KAAK,KAAK;AACpB,OAAI,KAAK,UAAU,KAAK,MAAM;IAC5B,IAAI,eAAwC,YAAY,QAAQ;AAChE,QAAI,CAAC,gBAAgB,aAAa,UAAU,KAAK,QAC/C,gBAAe,KAAA;AAGjB,aAAS,KAAK;KACZ,iBAAiB;KACjB,cAAc,eACV,IAAIC,yBAAAA,aAAa,aAAa,GAC9B,KAAA;KACL,CAAC;;IAEJ;AAEF,SAAO;;;;;;;;;;;;;;;;;;;;;CAsBT,MAAM,MACJ,QACA,YACsB;AACtB,MAAI,EAAE,KAAK,kBAAkB,QAC3B,OAAM,IAAI,MAAM,oBAAoB,KAAK,eAAe,YAAY;EAGtE,MAAM,cAAyB,OAAO,KAAK;AAK3C,MAAI,CAH8B,YAAY,OAAO,aAAA,GAAA,yBAAA,eACrC,QAAQ,CAEM,CAC5B,OAAM,IAAI,MAAM,gDAAgD;EAGlE,MAAM,gBAAgB,KAAK,0BACzB,YACD;EAGD,MAAM,kBAAkB,MAAM,QAAQ,IACpC,cAAc,IAAI,OAAO,sBAAsB;GAC7C,iBAAiB,MAAM,KAAK,uBAC1B,iBAAiB,gBAClB;GACD,cAAc,iBAAiB;GAC/B;GACD,EAAE,CACJ;EAID,MAAM,uBAAuB,MAAM,QAAQ,IACzC,gBAAgB,KAAK,eACnB,KAAK,wBAAwB;GAC3B,iBAAiB,WAAW;GAC5B,cAAc,WAAW;GACzB;GACD,CAAC,CACH,CACF;AAeD,SAAO,EACL,UAAA,MAbqB,QAAQ,IAC7B,qBAAqB,KAAK,cACxB,KAAK,cAAc;GACjB,cAAc,UAAU;GACxB,aAAa;IACX,mBAAmB,UAAU;IAC7B,2BAA2B,UAAU;IACtC;GACF,CAAC,CACH,CACF,EAIA;;;;;;;;;;;;CAaH,MAAc,uBACZ,aACA,YACyC;EACzC,MAAM,gBAAgB,KAAK,qBAAqB,YAAY;EAE5D,MAAM,mBAAmB,KAAK,IAC3B,UAAU,CAACC,cAAAA,mCAAmC,CAAC,CAC/C,WAAW,EACV,eAAe,EAAE,MAAMA,cAAAA,mCAAmC,MAAM,EACjE,CAAC;EAMJ,MAAM,MAAM,MAJEC,yCAAAA,iCAAiC,KAAK,iBAAiB,CAAC,KACpE,KAAK,iBAGgB,CAAC,OACtB,EACE,cAAc,eACf,EACD,YAAY,SAAS,aAAa,CACnC;AAED,MACE,EACE,eAAe,OACf,0BAA0B,OAC1B,cAAc,KAGhB,OAAM,IAAI,MAAM,8BAA8B,KAAK,UAAU,IAAI,GAAG;EAGtE,MAAM,qBAAqB;EAG3B,MAAM,gBAAgB,MAAM,KAAK,yBAC/B,mBAAmB,SACpB;EACD,MAAM,eAAe,KAAK,uBAAuB,CAC/C,GAAG,mBAAmB,UACtB,GAAG,cACJ,CAAC;AAEF,SAAO;GACL,GAAG;GACH,UAAU;GACX;;;;;;;;;CAUH,MAAc,yBACZ,UACwB;AAaxB,UAJgC,MAPQ,QAAQ,IAC9C,SAAS,IAAI,OAAO,YAAY;AAE9B,WAAO,MADuB,KAAK,UAAU,OAAO,QAAQ,EACrC;IACvB,CACH,EAEyD,KACvD,aAAa,SAAS,YAGK;;;;;;;;;;;;;;;CAgBhC,MAAc,wBAAwB,EACpC,iBACA,cACA,cAK2C;EAC3C,MAAM,mBAAmB,KAAK,IAC3B,UAAU,CAACC,cAAAA,+BAA+B,CAAC,CAC3C,WAAW,EACV,eAAe,EAAE,MAAMA,cAAAA,+BAA+B,MAAM,EAC7D,CAAC;EAEJ,MAAM,QAAQC,yCAAAA,6BAA6B,KAAK,iBAAiB,CAAC,KAChE,KAAK,iBACN;AAED,MAAI,OAAO,cAAc,YAAY,SACnC,OAAM,IAAI,MAAM,uDAAuD;EAEzE,MAAM,MAAO,MAAM,MAAM,OACvB;GACE,kBAAkB,gBAAgB;GAClC,eAAe,cAAc,WAAW;GACxC,eAAe,gBAAgB,SAAS,KAAK,KAAK;GACnD,EACD,YAAY,SAAS,wBAAwB,CAC9C;AAcD,SAAO;GACL;GACA,mBAAA,MAT8B,KAAK,0BAA0B;IAC7D,oBAAoB,gBAAgB;IACpC,2BAA2B,IAAI;IAC/B,cAAc,gBAAgB;IAC9B;IACD,CAAC;GAKA,2BAA2B,IAAI;GAChC;;;;;;;;;;;;;CAcH,MAAc,0BAA0B,EACtC,oBACA,2BACA,cACA,cAMkB;AAclB,SAAO,MAbwBC,yCAAAA,mCAAmC,KAChE,KAAK,IACN,CAAC,KAAK,KAAK,mBAE6C,CAAC,OACxD;GACE,YAAY;GACZ,6BAA6B,0BAA0B,KAAK,KAAK;GACjE,eAAe,aAAa,KAAK,KAAK;GACvC,EACD,YAAY,SAAS,sBAAsB,CAC5C;;;;;;;;;;;;;;CAiBH,MAAc,cAAc,EAC1B,cACA,aACA,cAWkB;EAClB,MAAM,QAAQC,yCAAAA,sBAAsB,KAAK,KAAK,IAAI,CAAC,KACjD,KAAK,mBACN;AAED,MAAI,OAAO,cAAc,YAAY,SACnC,OAAM,IAAI,MAAM,uDAAuD;AAWzE,SAAO,MATW,MAAM,OACtB;GACE,uBAAuB,YAAY,0BAA0B,KAAK,KAAK;GACvE,YAAY,YAAY;GACxB,cAAc,cAAc,WAAW;GACxC,EACD,YAAY,SAAS,iBAAiB,CACvC;;;;;;;;;;;;;CAgBH,OAAO,QACL,KACA,WACA,SAG8B;AAC9B,SAAO,IAAI,KAAK;GACd;GACA;GACA,GAAG;GACJ,CAAC"}
+{"version":3,"file":"violation_of_expectations_chain.cjs","names":["BaseChain","JsonOutputFunctionsParser","StringOutputParser","HumanMessage","PREDICT_NEXT_USER_MESSAGE_FUNCTION","PREDICT_NEXT_USER_MESSAGE_PROMPT","PREDICTION_VIOLATIONS_FUNCTION","PREDICTION_VIOLATIONS_PROMPT","GENERATE_REVISED_PREDICTION_PROMPT","GENERATE_FACTS_PROMPT"],"sources":["../../../../src/experimental/chains/violation_of_expectations/violation_of_expectations_chain.ts"],"sourcesContent":["import type { BaseRetrieverInterface } from \"@langchain/core/retrievers\";\nimport { ChatOpenAI } from \"@langchain/openai\";\nimport {\n  BaseMessage,\n  HumanMessage,\n  isBaseMessage,\n} from \"@langchain/core/messages\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { StringOutputParser } from \"@langchain/core/output_parsers\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { JsonOutputFunctionsParser } from \"../../../output_parsers/openai_functions.js\";\nimport { BaseChain, ChainInputs } from \"../../../chains/base.js\";\nimport {\n  GetPredictionViolationsResponse,\n  MessageChunkResult,\n  PREDICTION_VIOLATIONS_FUNCTION,\n  PREDICT_NEXT_USER_MESSAGE_FUNCTION,\n  PredictNextUserMessageResponse,\n} from \"./types.js\";\nimport {\n  GENERATE_FACTS_PROMPT,\n  GENERATE_REVISED_PREDICTION_PROMPT,\n  PREDICTION_VIOLATIONS_PROMPT,\n  PREDICT_NEXT_USER_MESSAGE_PROMPT,\n} from \"./violation_of_expectations_prompt.js\";\n\n/**\n * Interface for the input parameters of the ViolationOfExpectationsChain class.\n */\nexport interface ViolationOfExpectationsChainInput extends ChainInputs {\n  /**\n   * The retriever to use for retrieving stored\n   * thoughts and insights.\n   */\n  retriever: BaseRetrieverInterface;\n  /**\n   * The LLM to use\n   */\n  llm: ChatOpenAI;\n}\n\n/**\n * Chain that generates key insights/facts of a user based on a\n * a chat conversation with an AI.\n */\nexport class ViolationOfExpectationsChain\n  extends BaseChain\n  implements ViolationOfExpectationsChainInput\n{\n  static lc_name() {\n    return \"ViolationOfExpectationsChain\";\n  }\n\n  _chainType(): string {\n    return \"violation_of_expectation_chain\";\n  }\n\n  chatHistoryKey = \"chat_history\";\n\n  thoughtsKey = \"thoughts\";\n\n  get inputKeys() {\n    return [this.chatHistoryKey];\n  }\n\n  get outputKeys() {\n    return [this.thoughtsKey];\n  }\n\n  retriever: BaseRetrieverInterface;\n\n  llm: ChatOpenAI;\n\n  jsonOutputParser: JsonOutputFunctionsParser;\n\n  stringOutputParser: StringOutputParser;\n\n  constructor(fields: ViolationOfExpectationsChainInput) {\n    super(fields);\n    this.retriever = fields.retriever;\n    this.llm = fields.llm;\n    this.jsonOutputParser = new JsonOutputFunctionsParser();\n    this.stringOutputParser = new StringOutputParser();\n  }\n\n  getChatHistoryString(chatHistory: BaseMessage[]): string {\n    return chatHistory\n      .map((chatMessage) => {\n        if (chatMessage._getType() === \"human\") {\n          return `Human: ${chatMessage.content}`;\n        } else if (chatMessage._getType() === \"ai\") {\n          return `AI: ${chatMessage.content}`;\n        } else {\n          return `${chatMessage.content}`;\n        }\n      })\n      .join(\"\\n\");\n  }\n\n  removeDuplicateStrings(strings: Array<string>): Array<string> {\n    return [...new Set(strings)];\n  }\n\n  /**\n   * This method breaks down the chat history into chunks of messages.\n   * Each chunk consists of a sequence of messages ending with an AI message and the subsequent user response, if any.\n   *\n   * @param {BaseMessage[]} chatHistory - The chat history to be chunked.\n   *\n   * @returns {MessageChunkResult[]} An array of message chunks. Each chunk includes a sequence of messages and the subsequent user response.\n   *\n   * @description\n   * The method iterates over the chat history and pushes each message into a temporary array.\n   * When it encounters an AI message, it checks for a subsequent user message.\n   * If a user message is found, it is considered as the user response to the AI message.\n   * If no user message is found after the AI message, the user response is undefined.\n   * The method then pushes the chunk (sequence of messages and user response) into the result array.\n   * This process continues until all messages in the chat history have been processed.\n   */\n  chunkMessagesByAIResponse(chatHistory: BaseMessage[]): MessageChunkResult[] {\n    const newArray: MessageChunkResult[] = [];\n    const tempArray: BaseMessage[] = [];\n\n    chatHistory.forEach((item, index) => {\n      tempArray.push(item);\n      if (item._getType() === \"ai\") {\n        let userResponse: BaseMessage | undefined = chatHistory[index + 1];\n        if (!userResponse || userResponse._getType() !== \"human\") {\n          userResponse = undefined;\n        }\n\n        newArray.push({\n          chunkedMessages: tempArray,\n          userResponse: userResponse\n            ? new HumanMessage(userResponse)\n            : undefined,\n        });\n      }\n    });\n\n    return newArray;\n  }\n\n  /**\n   * This method processes a chat history to generate insights about the user.\n   *\n   * @param {ChainValues} values - The input values for the chain. It should contain a key for chat history.\n   * @param {CallbackManagerForChainRun} [runManager] - Optional callback manager for the chain run.\n   *\n   * @returns {Promise<ChainValues>} A promise that resolves to a list of insights about the user.\n   *\n   * @throws {Error} If the chat history key is not found in the input values or if the chat history is not an array of BaseMessages.\n   *\n   * @description\n   * The method performs the following steps:\n   * 1. Checks if the chat history key is present in the input values and if the chat history is an array of BaseMessages.\n   * 2. Breaks the chat history into chunks of messages.\n   * 3. For each chunk, it generates an initial prediction for the user's next message.\n   * 4. For each prediction, it generates insights and prediction violations, and regenerates the prediction based on the violations.\n   * 5. For each set of messages, it generates a fact/insight about the user.\n   * The method returns a list of these insights.\n   */\n  async _call(\n    values: ChainValues,\n    runManager?: CallbackManagerForChainRun\n  ): Promise<ChainValues> {\n    if (!(this.chatHistoryKey in values)) {\n      throw new Error(`Chat history key ${this.chatHistoryKey} not found`);\n    }\n\n    const chatHistory: unknown[] = values[this.chatHistoryKey];\n\n    const isEveryMessageBaseMessage = chatHistory.every((message) =>\n      isBaseMessage(message)\n    );\n    if (!isEveryMessageBaseMessage) {\n      throw new Error(\"Chat history must be an array of BaseMessages\");\n    }\n\n    const messageChunks = this.chunkMessagesByAIResponse(\n      chatHistory as BaseMessage[]\n    );\n\n    // Generate the initial prediction for every user message.\n    const userPredictions = await Promise.all(\n      messageChunks.map(async (chatHistoryChunk) => ({\n        userPredictions: await this.predictNextUserMessage(\n          chatHistoryChunk.chunkedMessages\n        ),\n        userResponse: chatHistoryChunk.userResponse,\n        runManager,\n      }))\n    );\n\n    // Generate insights, and prediction violations for every user message.\n    // This call also regenerates the prediction based on the violations.\n    const predictionViolations = await Promise.all(\n      userPredictions.map((prediction) =>\n        this.getPredictionViolations({\n          userPredictions: prediction.userPredictions,\n          userResponse: prediction.userResponse,\n          runManager,\n        })\n      )\n    );\n\n    // Generate a fact/insight about the user for every set of messages.\n    const insights = await Promise.all(\n      predictionViolations.map((violation) =>\n        this.generateFacts({\n          userResponse: violation.userResponse,\n          predictions: {\n            revisedPrediction: violation.revisedPrediction,\n            explainedPredictionErrors: violation.explainedPredictionErrors,\n          },\n        })\n      )\n    );\n\n    return {\n      insights,\n    };\n  }\n\n  /**\n   * This method predicts the next user message based on the chat history.\n   *\n   * @param {BaseMessage[]} chatHistory - The chat history based on which the next user message is predicted.\n   * @param {CallbackManagerForChainRun} [runManager] - Optional callback manager for the chain run.\n   *\n   * @returns {Promise<PredictNextUserMessageResponse>} A promise that resolves to the predicted next user message, the user state, and any insights.\n   *\n   * @throws {Error} If the response from the language model does not contain the expected keys: 'userState', 'predictedUserMessage', and 'insights'.\n   */\n  private async predictNextUserMessage(\n    chatHistory: BaseMessage[],\n    runManager?: CallbackManagerForChainRun\n  ): Promise<PredictNextUserMessageResponse> {\n    const messageString = this.getChatHistoryString(chatHistory);\n\n    const llmWithFunctions = this.llm\n      .bindTools([PREDICT_NEXT_USER_MESSAGE_FUNCTION])\n      .withConfig({\n        function_call: { name: PREDICT_NEXT_USER_MESSAGE_FUNCTION.name },\n      });\n\n    const chain = PREDICT_NEXT_USER_MESSAGE_PROMPT.pipe(llmWithFunctions).pipe(\n      this.jsonOutputParser\n    );\n\n    const res = await chain.invoke(\n      {\n        chat_history: messageString,\n      },\n      runManager?.getChild(\"prediction\")\n    );\n\n    if (\n      !(\n        \"userState\" in res &&\n        \"predictedUserMessage\" in res &&\n        \"insights\" in res\n      )\n    ) {\n      throw new Error(`Invalid response from LLM: ${JSON.stringify(res)}`);\n    }\n\n    const predictionResponse = res as PredictNextUserMessageResponse;\n\n    // Query the retriever for relevant insights. Use the generates insights as a query.\n    const retrievedDocs = await this.retrieveRelevantInsights(\n      predictionResponse.insights\n    );\n    const relevantDocs = this.removeDuplicateStrings([\n      ...predictionResponse.insights,\n      ...retrievedDocs,\n    ]);\n\n    return {\n      ...predictionResponse,\n      insights: relevantDocs,\n    };\n  }\n\n  /**\n   * Retrieves relevant insights based on the provided insights.\n   *\n   * @param {Array<string>} insights - An array of insights to be used for retrieving relevant documents.\n   *\n   * @returns {Promise<Array<string>>} A promise that resolves to an array of relevant insights content.\n   */\n  private async retrieveRelevantInsights(\n    insights: Array<string>\n  ): Promise<Array<string>> {\n    // Only extract the first relevant doc from the retriever. We don't need more than one.\n    const relevantInsightsDocuments = await Promise.all(\n      insights.map(async (insight) => {\n        const relevantInsight = await this.retriever.invoke(insight);\n        return relevantInsight[0];\n      })\n    );\n\n    const relevantInsightsContent = relevantInsightsDocuments.map(\n      (document) => document.pageContent\n    );\n\n    return relevantInsightsContent;\n  }\n\n  /**\n   * This method generates prediction violations based on the predicted and actual user responses.\n   * It also generates a revised prediction based on the identified violations.\n   *\n   * @param {Object} params - The parameters for the method.\n   * @param {PredictNextUserMessageResponse} params.userPredictions - The predicted user message, user state, and insights.\n   * @param {BaseMessage} [params.userResponse] - The actual user response.\n   * @param {CallbackManagerForChainRun} [params.runManager] - Optional callback manager for the chain run.\n   *\n   * @returns {Promise<{ userResponse: BaseMessage | undefined; revisedPrediction: string; explainedPredictionErrors: Array<string>; }>} A promise that resolves to an object containing the actual user response, the revised prediction, and the explained prediction errors.\n   *\n   * @throws {Error} If the response from the language model does not contain the expected keys: 'violationExplanation', 'explainedPredictionErrors', and 'accuratePrediction'.\n   */\n  private async getPredictionViolations({\n    userPredictions,\n    userResponse,\n    runManager,\n  }: {\n    userPredictions: PredictNextUserMessageResponse;\n    userResponse?: BaseMessage;\n    runManager?: CallbackManagerForChainRun;\n  }): Promise<GetPredictionViolationsResponse> {\n    const llmWithFunctions = this.llm\n      .bindTools([PREDICTION_VIOLATIONS_FUNCTION])\n      .withConfig({\n        function_call: { name: PREDICTION_VIOLATIONS_FUNCTION.name },\n      });\n\n    const chain = PREDICTION_VIOLATIONS_PROMPT.pipe(llmWithFunctions).pipe(\n      this.jsonOutputParser\n    );\n\n    if (typeof userResponse?.content !== \"string\") {\n      throw new Error(\"This chain does not support non-string model output.\");\n    }\n    const res = (await chain.invoke(\n      {\n        predicted_output: userPredictions.predictedUserMessage,\n        actual_output: userResponse?.content ?? \"\",\n        user_insights: userPredictions.insights.join(\"\\n\"),\n      },\n      runManager?.getChild(\"prediction_violations\")\n    )) as Awaited<{\n      violationExplanation: string;\n      explainedPredictionErrors: Array<string>;\n      accuratePrediction: boolean;\n    }>;\n\n    // Generate a revised prediction based on violations.\n    const revisedPrediction = await this.generateRevisedPrediction({\n      originalPrediction: userPredictions.predictedUserMessage,\n      explainedPredictionErrors: res.explainedPredictionErrors,\n      userInsights: userPredictions.insights,\n      runManager,\n    });\n\n    return {\n      userResponse,\n      revisedPrediction,\n      explainedPredictionErrors: res.explainedPredictionErrors,\n    };\n  }\n\n  /**\n   * This method generates a revised prediction based on the original prediction, explained prediction errors, and user insights.\n   *\n   * @param {Object} params - The parameters for the method.\n   * @param {string} params.originalPrediction - The original prediction made by the model.\n   * @param {Array<string>} params.explainedPredictionErrors - An array of explained prediction errors.\n   * @param {Array<string>} params.userInsights - An array of insights about the user.\n   * @param {CallbackManagerForChainRun} [params.runManager] - Optional callback manager for the chain run.\n   *\n   * @returns {Promise<string>} A promise that resolves to a revised prediction.\n   */\n  private async generateRevisedPrediction({\n    originalPrediction,\n    explainedPredictionErrors,\n    userInsights,\n    runManager,\n  }: {\n    originalPrediction: string;\n    explainedPredictionErrors: Array<string>;\n    userInsights: Array<string>;\n    runManager?: CallbackManagerForChainRun;\n  }): Promise<string> {\n    const revisedPredictionChain = GENERATE_REVISED_PREDICTION_PROMPT.pipe(\n      this.llm\n    ).pipe(this.stringOutputParser);\n\n    const revisedPredictionRes = await revisedPredictionChain.invoke(\n      {\n        prediction: originalPrediction,\n        explained_prediction_errors: explainedPredictionErrors.join(\"\\n\"),\n        user_insights: userInsights.join(\"\\n\"),\n      },\n      runManager?.getChild(\"prediction_revision\")\n    );\n\n    return revisedPredictionRes;\n  }\n\n  /**\n   * This method generates facts or insights about the user based on the revised prediction, explained prediction errors, and the user's response.\n   *\n   * @param {Object} params - The parameters for the method.\n   * @param {BaseMessage} [params.userResponse] - The actual user response.\n   * @param {Object} params.predictions - The revised prediction and explained prediction errors.\n   * @param {string} params.predictions.revisedPrediction - The revised prediction made by the model.\n   * @param {Array<string>} params.predictions.explainedPredictionErrors - An array of explained prediction errors.\n   * @param {CallbackManagerForChainRun} [params.runManager] - Optional callback manager for the chain run.\n   *\n   * @returns {Promise<string>} A promise that resolves to a string containing the generated facts or insights about the user.\n   */\n  private async generateFacts({\n    userResponse,\n    predictions,\n    runManager,\n  }: {\n    userResponse?: BaseMessage;\n    /**\n     * Optional if the prediction was accurate.\n     */\n    predictions: {\n      revisedPrediction: string;\n      explainedPredictionErrors: Array<string>;\n    };\n    runManager?: CallbackManagerForChainRun;\n  }): Promise<string> {\n    const chain = GENERATE_FACTS_PROMPT.pipe(this.llm).pipe(\n      this.stringOutputParser\n    );\n\n    if (typeof userResponse?.content !== \"string\") {\n      throw new Error(\"This chain does not support non-string model output.\");\n    }\n    const res = await chain.invoke(\n      {\n        prediction_violations: predictions.explainedPredictionErrors.join(\"\\n\"),\n        prediction: predictions.revisedPrediction,\n        user_message: userResponse?.content ?? \"\",\n      },\n      runManager?.getChild(\"generate_facts\")\n    );\n\n    return res;\n  }\n\n  /**\n   * Static method that creates a ViolationOfExpectationsChain instance from a\n   * ChatOpenAI and retriever. It also accepts optional options\n   * to customize the chain.\n   *\n   * @param llm The ChatOpenAI instance.\n   * @param retriever The retriever used for similarity search.\n   * @param options Optional options to customize the chain.\n   *\n   * @returns A new instance of ViolationOfExpectationsChain.\n   */\n  static fromLLM(\n    llm: ChatOpenAI,\n    retriever: BaseRetrieverInterface,\n    options?: Partial<\n      Omit<ViolationOfExpectationsChainInput, \"llm\" | \"retriever\">\n    >\n  ): ViolationOfExpectationsChain {\n    return new this({\n      retriever,\n      llm,\n      ...options,\n    });\n  }\n}\n"],"mappings":";;;;;;;;;;;AA6CA,IAAa,+BAAb,cACUA,aAAAA,UAEV;CACE,OAAO,UAAU;EACf,OAAO;CACT;CAEA,aAAqB;EACnB,OAAO;CACT;CAEA,iBAAiB;CAEjB,cAAc;CAEd,IAAI,YAAY;EACd,OAAO,CAAC,KAAK,cAAc;CAC7B;CAEA,IAAI,aAAa;EACf,OAAO,CAAC,KAAK,WAAW;CAC1B;CAEA;CAEA;CAEA;CAEA;CAEA,YAAY,QAA2C;EACrD,MAAM,MAAM;EACZ,KAAK,YAAY,OAAO;EACxB,KAAK,MAAM,OAAO;EAClB,KAAK,mBAAmB,IAAIC,yBAAAA,0BAA0B;EACtD,KAAK,qBAAqB,IAAIC,+BAAAA,mBAAmB;CACnD;CAEA,qBAAqB,aAAoC;EACvD,OAAO,YACJ,KAAK,gBAAgB;GACpB,IAAI,YAAY,SAAS,MAAM,SAC7B,OAAO,UAAU,YAAY;QACxB,IAAI,YAAY,SAAS,MAAM,MACpC,OAAO,OAAO,YAAY;QAE1B,OAAO,GAAG,YAAY;EAE1B,CAAC,CAAC,CACD,KAAK,IAAI;CACd;CAEA,uBAAuB,SAAuC;EAC5D,OAAO,CAAC,GAAG,IAAI,IAAI,OAAO,CAAC;CAC7B;;;;;;;;;;;;;;;;;CAkBA,0BAA0B,aAAkD;EAC1E,MAAM,WAAiC,CAAC;EACxC,MAAM,YAA2B,CAAC;EAElC,YAAY,SAAS,MAAM,UAAU;GACnC,UAAU,KAAK,IAAI;GACnB,IAAI,KAAK,SAAS,MAAM,MAAM;IAC5B,IAAI,eAAwC,YAAY,QAAQ;IAChE,IAAI,CAAC,gBAAgB,aAAa,SAAS,MAAM,SAC/C,eAAe,KAAA;IAGjB,SAAS,KAAK;KACZ,iBAAiB;KACjB,cAAc,eACV,IAAIC,yBAAAA,aAAa,YAAY,IAC7B,KAAA;IACN,CAAC;GACH;EACF,CAAC;EAED,OAAO;CACT;;;;;;;;;;;;;;;;;;;;CAqBA,MAAM,MACJ,QACA,YACsB;EACtB,IAAI,EAAE,KAAK,kBAAkB,SAC3B,MAAM,IAAI,MAAM,oBAAoB,KAAK,eAAe,WAAW;EAGrE,MAAM,cAAyB,OAAO,KAAK;EAK3C,IAAI,CAH8B,YAAY,OAAO,aAAA,GAAA,yBAAA,cAAA,CACrC,OAAO,CAEM,GAC3B,MAAM,IAAI,MAAM,+CAA+C;EAGjE,MAAM,gBAAgB,KAAK,0BACzB,WACF;EAGA,MAAM,kBAAkB,MAAM,QAAQ,IACpC,cAAc,IAAI,OAAO,sBAAsB;GAC7C,iBAAiB,MAAM,KAAK,uBAC1B,iBAAiB,eACnB;GACA,cAAc,iBAAiB;GAC/B;EACF,EAAE,CACJ;EAIA,MAAM,uBAAuB,MAAM,QAAQ,IACzC,gBAAgB,KAAK,eACnB,KAAK,wBAAwB;GAC3B,iBAAiB,WAAW;GAC5B,cAAc,WAAW;GACzB;EACF,CAAC,CACH,CACF;EAeA,OAAO,EACL,UAAA,MAbqB,QAAQ,IAC7B,qBAAqB,KAAK,cACxB,KAAK,cAAc;GACjB,cAAc,UAAU;GACxB,aAAa;IACX,mBAAmB,UAAU;IAC7B,2BAA2B,UAAU;GACvC;EACF,CAAC,CACH,CACF,EAIA;CACF;;;;;;;;;;;CAYA,MAAc,uBACZ,aACA,YACyC;EACzC,MAAM,gBAAgB,KAAK,qBAAqB,WAAW;EAE3D,MAAM,mBAAmB,KAAK,IAC3B,UAAU,CAACC,cAAAA,kCAAkC,CAAC,CAAC,CAC/C,WAAW,EACV,eAAe,EAAE,MAAMA,cAAAA,mCAAmC,KAAK,EACjE,CAAC;EAMH,MAAM,MAAM,MAJEC,yCAAAA,iCAAiC,KAAK,gBAAgB,CAAC,CAAC,KACpE,KAAK,gBAGe,CAAC,CAAC,OACtB,EACE,cAAc,cAChB,GACA,YAAY,SAAS,YAAY,CACnC;EAEA,IACE,EACE,eAAe,OACf,0BAA0B,OAC1B,cAAc,MAGhB,MAAM,IAAI,MAAM,8BAA8B,KAAK,UAAU,GAAG,GAAG;EAGrE,MAAM,qBAAqB;EAG3B,MAAM,gBAAgB,MAAM,KAAK,yBAC/B,mBAAmB,QACrB;EACA,MAAM,eAAe,KAAK,uBAAuB,CAC/C,GAAG,mBAAmB,UACtB,GAAG,aACL,CAAC;EAED,OAAO;GACL,GAAG;GACH,UAAU;EACZ;CACF;;;;;;;;CASA,MAAc,yBACZ,UACwB;EAaxB,QAJgC,MAPQ,QAAQ,IAC9C,SAAS,IAAI,OAAO,YAAY;GAE9B,QAAO,MADuB,KAAK,UAAU,OAAO,OAAO,EAAA,CACpC;EACzB,CAAC,CACH,EAAA,CAE0D,KACvD,aAAa,SAAS,WAGI;CAC/B;;;;;;;;;;;;;;CAeA,MAAc,wBAAwB,EACpC,iBACA,cACA,cAK2C;EAC3C,MAAM,mBAAmB,KAAK,IAC3B,UAAU,CAACC,cAAAA,8BAA8B,CAAC,CAAC,CAC3C,WAAW,EACV,eAAe,EAAE,MAAMA,cAAAA,+BAA+B,KAAK,EAC7D,CAAC;EAEH,MAAM,QAAQC,yCAAAA,6BAA6B,KAAK,gBAAgB,CAAC,CAAC,KAChE,KAAK,gBACP;EAEA,IAAI,OAAO,cAAc,YAAY,UACnC,MAAM,IAAI,MAAM,sDAAsD;EAExE,MAAM,MAAO,MAAM,MAAM,OACvB;GACE,kBAAkB,gBAAgB;GAClC,eAAe,cAAc,WAAW;GACxC,eAAe,gBAAgB,SAAS,KAAK,IAAI;EACnD,GACA,YAAY,SAAS,uBAAuB,CAC9C;EAcA,OAAO;GACL;GACA,mBAAA,MAT8B,KAAK,0BAA0B;IAC7D,oBAAoB,gBAAgB;IACpC,2BAA2B,IAAI;IAC/B,cAAc,gBAAgB;IAC9B;GACF,CAAC;GAKC,2BAA2B,IAAI;EACjC;CACF;;;;;;;;;;;;CAaA,MAAc,0BAA0B,EACtC,oBACA,2BACA,cACA,cAMkB;EAclB,OAAO,MAbwBC,yCAAAA,mCAAmC,KAChE,KAAK,GACP,CAAC,CAAC,KAAK,KAAK,kBAE4C,CAAC,CAAC,OACxD;GACE,YAAY;GACZ,6BAA6B,0BAA0B,KAAK,IAAI;GAChE,eAAe,aAAa,KAAK,IAAI;EACvC,GACA,YAAY,SAAS,qBAAqB,CAC5C;CAGF;;;;;;;;;;;;;CAcA,MAAc,cAAc,EAC1B,cACA,aACA,cAWkB;EAClB,MAAM,QAAQC,yCAAAA,sBAAsB,KAAK,KAAK,GAAG,CAAC,CAAC,KACjD,KAAK,kBACP;EAEA,IAAI,OAAO,cAAc,YAAY,UACnC,MAAM,IAAI,MAAM,sDAAsD;EAWxE,OAAO,MATW,MAAM,OACtB;GACE,uBAAuB,YAAY,0BAA0B,KAAK,IAAI;GACtE,YAAY,YAAY;GACxB,cAAc,cAAc,WAAW;EACzC,GACA,YAAY,SAAS,gBAAgB,CACvC;CAGF;;;;;;;;;;;;CAaA,OAAO,QACL,KACA,WACA,SAG8B;EAC9B,OAAO,IAAI,KAAK;GACd;GACA;GACA,GAAG;EACL,CAAC;CACH;AACF"}

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

@@ -7,7 +7,6 @@ import { ChainValues } from "@langchain/core/utils/types";
 import { CallbackManagerForChainRun } from "@langchain/core/callbacks/manager";
 import { BaseRetrieverInterface } from "@langchain/core/retrievers";
 import { ChatOpenAI } from "@langchain/openai";
-
 //#region src/experimental/chains/violation_of_expectations/violation_of_expectations_chain.d.ts
 /**
  * Interface for the input parameters of the ViolationOfExpectationsChain class.
@@ -78,10 +77,63 @@ declare class ViolationOfExpectationsChain extends BaseChain implements Violatio
    * The method returns a list of these insights.
    */
   _call(values: ChainValues, runManager?: CallbackManagerForChainRun): Promise<ChainValues>;
+  /**
+   * This method predicts the next user message based on the chat history.
+   *
+   * @param {BaseMessage[]} chatHistory - The chat history based on which the next user message is predicted.
+   * @param {CallbackManagerForChainRun} [runManager] - Optional callback manager for the chain run.
+   *
+   * @returns {Promise<PredictNextUserMessageResponse>} A promise that resolves to the predicted next user message, the user state, and any insights.
+   *
+   * @throws {Error} If the response from the language model does not contain the expected keys: 'userState', 'predictedUserMessage', and 'insights'.
+   */
   private predictNextUserMessage;
+  /**
+   * Retrieves relevant insights based on the provided insights.
+   *
+   * @param {Array<string>} insights - An array of insights to be used for retrieving relevant documents.
+   *
+   * @returns {Promise<Array<string>>} A promise that resolves to an array of relevant insights content.
+   */
   private retrieveRelevantInsights;
+  /**
+   * This method generates prediction violations based on the predicted and actual user responses.
+   * It also generates a revised prediction based on the identified violations.
+   *
+   * @param {Object} params - The parameters for the method.
+   * @param {PredictNextUserMessageResponse} params.userPredictions - The predicted user message, user state, and insights.
+   * @param {BaseMessage} [params.userResponse] - The actual user response.
+   * @param {CallbackManagerForChainRun} [params.runManager] - Optional callback manager for the chain run.
+   *
+   * @returns {Promise<{ userResponse: BaseMessage | undefined; revisedPrediction: string; explainedPredictionErrors: Array<string>; }>} A promise that resolves to an object containing the actual user response, the revised prediction, and the explained prediction errors.
+   *
+   * @throws {Error} If the response from the language model does not contain the expected keys: 'violationExplanation', 'explainedPredictionErrors', and 'accuratePrediction'.
+   */
   private getPredictionViolations;
+  /**
+   * This method generates a revised prediction based on the original prediction, explained prediction errors, and user insights.
+   *
+   * @param {Object} params - The parameters for the method.
+   * @param {string} params.originalPrediction - The original prediction made by the model.
+   * @param {Array<string>} params.explainedPredictionErrors - An array of explained prediction errors.
+   * @param {Array<string>} params.userInsights - An array of insights about the user.
+   * @param {CallbackManagerForChainRun} [params.runManager] - Optional callback manager for the chain run.
+   *
+   * @returns {Promise<string>} A promise that resolves to a revised prediction.
+   */
   private generateRevisedPrediction;
+  /**
+   * This method generates facts or insights about the user based on the revised prediction, explained prediction errors, and the user's response.
+   *
+   * @param {Object} params - The parameters for the method.
+   * @param {BaseMessage} [params.userResponse] - The actual user response.
+   * @param {Object} params.predictions - The revised prediction and explained prediction errors.
+   * @param {string} params.predictions.revisedPrediction - The revised prediction made by the model.
+   * @param {Array<string>} params.predictions.explainedPredictionErrors - An array of explained prediction errors.
+   * @param {CallbackManagerForChainRun} [params.runManager] - Optional callback manager for the chain run.
+   *
+   * @returns {Promise<string>} A promise that resolves to a string containing the generated facts or insights about the user.
+   */
   private generateFacts;
   /**
    * Static method that creates a ViolationOfExpectationsChain instance from a

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

@@ -1 +1 @@
-{"version":3,"file":"violation_of_expectations_chain.d.cts","names":[],"sources":["../../../../src/experimental/chains/violation_of_expectations/violation_of_expectations_chain.ts"],"mappings":";;;;;;;;;;;;;AA6BA;UAAiB,iCAAA,SAA0C,WAAA;;;;;EAKzD,SAAA,EAAW,sBAAA;EALyD;;;EASpE,GAAA,EAAK,UAAA;AAAA;;;;AAOP;cAAa,4BAAA,SACH,SAAA,YACG,iCAAA;EAAA,OAEJ,OAAA,CAAA;EAIP,UAAA,CAAA;EAIA,cAAA;EAEA,WAAA;EAAA,IAEI,SAAA,CAAA;EAAA,IAIA,UAAA,CAAA;EAIJ,SAAA,EAAW,sBAAA;EAEX,GAAA,EAAK,UAAA;EAEL,gBAAA,EAAkB,yBAAA;EAElB,kBAAA,EAAoB,kBAAA;EAEpB,WAAA,CAAY,MAAA,EAAQ,iCAAA;EAQpB,oBAAA,CAAqB,WAAA,EAAa,WAAA;EAclC,sBAAA,CAAuB,OAAA,EAAS,KAAA,WAAgB,KAAA;EAkErC;;;;;;;;;;;;;;;;EA9CX,yBAAA,CAA0B,WAAA,EAAa,WAAA,KAAgB,kBAAA;EA5DvD;;;;;;;;;;;;;;;;;;;EAuGM,KAAA,CACJ,MAAA,EAAQ,WAAA,EACR,UAAA,GAAa,0BAAA,GACZ,OAAA,CAAQ,WAAA;EAAA,QAqEG,sBAAA;EAAA,QAyDA,wBAAA;EAAA,QA+BA,uBAAA;EAAA,QA6DA,yBAAA;EAAA,QAuCA,aAAA;EApQR;;;;;;;;;;;EAAA,OAiTC,OAAA,CACL,GAAA,EAAK,UAAA,EACL,SAAA,EAAW,sBAAA,EACX,OAAA,GAAU,OAAA,CACR,IAAA,CAAK,iCAAA,0BAEN,4BAAA;AAAA"}
+{"version":3,"file":"violation_of_expectations_chain.d.cts","names":[],"sources":["../../../../src/experimental/chains/violation_of_expectations/violation_of_expectations_chain.ts"],"mappings":";;;;;;;;;;;;;UA6BiB,0CAA0C;;;;;EAKzD,WAAW;;;;EAIX,KAAK;;;;;;cAOM,qCACH,qBACG;SAEJ;EAIP;EAIA;EAEA;MAEI;MAIA;EAIJ,WAAW;EAEX,KAAK;EAEL,kBAAkB;EAElB,oBAAoB;EAEpB,YAAY,QAAQ;EAQpB,qBAAqB,aAAa;EAclC,uBAAuB,SAAS,gBAAgB;;;;;;;;;;;;;;;;;EAoBhD,0BAA0B,aAAa,gBAAgB;;;;;;;;;;;;;;;;;;;;EA2CjD,MACJ,QAAQ,aACR,aAAa,6BACZ,QAAQ;;;;;;;;;;;UAqEG;;;;;;;;UAyDA;;;;;;;;;;;;;;UA+BA;;;;;;;;;;;;UA6DA;;;;;;;;;;;;;UAuCA;;;;;;;;;;;;SA6CP,QACL,KAAK,YACL,WAAW,wBACX,UAAU,QACR,KAAK,2DAEN"}