@langchain/classic 1.0.39 → 1.0.41

package/dist/chains/question_answering/refine_prompts.cjs

@@ -1,13 +1,7 @@
-require("../../_virtual/_rolldown/runtime.cjs");
 let _langchain_core_prompts = require("@langchain/core/prompts");
 let _langchain_core_example_selectors = require("@langchain/core/example_selectors");
-const DEFAULT_REFINE_PROMPT = /* @__PURE__ */ new _langchain_core_prompts.PromptTemplate({
-	inputVariables: [
-		"question",
-		"existing_answer",
-		"context"
-	],
-	template: `The original question is as follows: {question}
+//#region src/chains/question_answering/refine_prompts.ts
+const DEFAULT_REFINE_PROMPT_TMPL = `The original question is as follows: {question}
 We have provided an existing answer: {existing_answer}
 We have the opportunity to refine the existing answer
 (only if needed) with some more context below.
@@ -15,12 +9,19 @@ We have the opportunity to refine the existing answer
 {context}
 ------------
 Given the new context, refine the original answer to better answer the question. 
-If the context isn't useful, return the original answer.`
+If the context isn't useful, return the original answer.`;
+const DEFAULT_REFINE_PROMPT = /*#__PURE__*/ new _langchain_core_prompts.PromptTemplate({
+	inputVariables: [
+		"question",
+		"existing_answer",
+		"context"
+	],
+	template: DEFAULT_REFINE_PROMPT_TMPL
 });
 const messages = [
-	/* @__PURE__ */ _langchain_core_prompts.HumanMessagePromptTemplate.fromTemplate("{question}"),
-	/* @__PURE__ */ _langchain_core_prompts.AIMessagePromptTemplate.fromTemplate("{existing_answer}"),
-	/* @__PURE__ */ _langchain_core_prompts.HumanMessagePromptTemplate.fromTemplate(`The original question is as follows: {question}
+	/*#__PURE__*/ _langchain_core_prompts.HumanMessagePromptTemplate.fromTemplate("{question}"),
+	/*#__PURE__*/ _langchain_core_prompts.AIMessagePromptTemplate.fromTemplate("{existing_answer}"),
+	/*#__PURE__*/ _langchain_core_prompts.HumanMessagePromptTemplate.fromTemplate(`The original question is as follows: {question}
 We have provided an existing answer: {existing_answer}
 We have the opportunity to refine the existing answer
 (only if needed) with some more context below.
@@ -30,24 +31,31 @@ We have the opportunity to refine the existing answer
 Given the new context, refine the original answer to better answer the question. 
 If the context isn't useful, return the original answer.`)
 ];
-const CHAT_REFINE_PROMPT = /* @__PURE__ */ _langchain_core_prompts.ChatPromptTemplate.fromMessages(messages);
-const REFINE_PROMPT_SELECTOR = /* @__PURE__ */ new _langchain_core_example_selectors.ConditionalPromptSelector(DEFAULT_REFINE_PROMPT, [[_langchain_core_example_selectors.isChatModel, CHAT_REFINE_PROMPT]]);
-const DEFAULT_TEXT_QA_PROMPT = /* @__PURE__ */ new _langchain_core_prompts.PromptTemplate({
-	inputVariables: ["context", "question"],
-	template: `Context information is below. 
+const CHAT_REFINE_PROMPT = /*#__PURE__*/ _langchain_core_prompts.ChatPromptTemplate.fromMessages(messages);
+const REFINE_PROMPT_SELECTOR = /*#__PURE__*/ new _langchain_core_example_selectors.ConditionalPromptSelector(DEFAULT_REFINE_PROMPT, [[_langchain_core_example_selectors.isChatModel, CHAT_REFINE_PROMPT]]);
+const DEFAULT_TEXT_QA_PROMPT_TMPL = `Context information is below. 
 ---------------------
 {context}
 ---------------------
-Given the context information and no prior knowledge, answer the question: {question}`
+Given the context information and no prior knowledge, answer the question: {question}`;
+const DEFAULT_TEXT_QA_PROMPT = /*#__PURE__*/ new _langchain_core_prompts.PromptTemplate({
+	inputVariables: ["context", "question"],
+	template: DEFAULT_TEXT_QA_PROMPT_TMPL
 });
-const chat_messages = [/* @__PURE__ */ _langchain_core_prompts.SystemMessagePromptTemplate.fromTemplate(`Context information is below. 
+const chat_messages = [/*#__PURE__*/ _langchain_core_prompts.SystemMessagePromptTemplate.fromTemplate(`Context information is below. 
 ---------------------
 {context}
 ---------------------
-Given the context information and no prior knowledge, answer any questions`), /* @__PURE__ */ _langchain_core_prompts.HumanMessagePromptTemplate.fromTemplate("{question}")];
-const CHAT_QUESTION_PROMPT = /* @__PURE__ */ _langchain_core_prompts.ChatPromptTemplate.fromMessages(chat_messages);
-const QUESTION_PROMPT_SELECTOR = /* @__PURE__ */ new _langchain_core_example_selectors.ConditionalPromptSelector(DEFAULT_TEXT_QA_PROMPT, [[_langchain_core_example_selectors.isChatModel, CHAT_QUESTION_PROMPT]]);
+Given the context information and no prior knowledge, answer any questions`), /*#__PURE__*/ _langchain_core_prompts.HumanMessagePromptTemplate.fromTemplate("{question}")];
+const CHAT_QUESTION_PROMPT = /*#__PURE__*/ _langchain_core_prompts.ChatPromptTemplate.fromMessages(chat_messages);
+const QUESTION_PROMPT_SELECTOR = /*#__PURE__*/ new _langchain_core_example_selectors.ConditionalPromptSelector(DEFAULT_TEXT_QA_PROMPT, [[_langchain_core_example_selectors.isChatModel, CHAT_QUESTION_PROMPT]]);
 //#endregion
+exports.CHAT_QUESTION_PROMPT = CHAT_QUESTION_PROMPT;
+exports.CHAT_REFINE_PROMPT = CHAT_REFINE_PROMPT;
+exports.DEFAULT_REFINE_PROMPT = DEFAULT_REFINE_PROMPT;
+exports.DEFAULT_REFINE_PROMPT_TMPL = DEFAULT_REFINE_PROMPT_TMPL;
+exports.DEFAULT_TEXT_QA_PROMPT = DEFAULT_TEXT_QA_PROMPT;
+exports.DEFAULT_TEXT_QA_PROMPT_TMPL = DEFAULT_TEXT_QA_PROMPT_TMPL;
 exports.QUESTION_PROMPT_SELECTOR = QUESTION_PROMPT_SELECTOR;
 exports.REFINE_PROMPT_SELECTOR = REFINE_PROMPT_SELECTOR;
 

package/dist/chains/question_answering/refine_prompts.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"refine_prompts.cjs","names":["PromptTemplate","ConditionalPromptSelector","isChatModel"],"sources":["../../../src/chains/question_answering/refine_prompts.ts"],"sourcesContent":["import {\n  PromptTemplate,\n  ChatPromptTemplate,\n  SystemMessagePromptTemplate,\n  HumanMessagePromptTemplate,\n  AIMessagePromptTemplate,\n} from \"@langchain/core/prompts\";\nimport {\n  ConditionalPromptSelector,\n  isChatModel,\n} from \"@langchain/core/example_selectors\";\n\nexport const DEFAULT_REFINE_PROMPT_TMPL = `The original question is as follows: {question}\nWe have provided an existing answer: {existing_answer}\nWe have the opportunity to refine the existing answer\n(only if needed) with some more context below.\n------------\n{context}\n------------\nGiven the new context, refine the original answer to better answer the question. \nIf the context isn't useful, return the original answer.`;\nexport const DEFAULT_REFINE_PROMPT = /*#__PURE__*/ new PromptTemplate({\n  inputVariables: [\"question\", \"existing_answer\", \"context\"],\n  template: DEFAULT_REFINE_PROMPT_TMPL,\n});\n\nconst refineTemplate = `The original question is as follows: {question}\nWe have provided an existing answer: {existing_answer}\nWe have the opportunity to refine the existing answer\n(only if needed) with some more context below.\n------------\n{context}\n------------\nGiven the new context, refine the original answer to better answer the question. \nIf the context isn't useful, return the original answer.`;\n\nconst messages = [\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(\"{question}\"),\n  /*#__PURE__*/ AIMessagePromptTemplate.fromTemplate(\"{existing_answer}\"),\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(refineTemplate),\n];\n\nexport const CHAT_REFINE_PROMPT =\n  /*#__PURE__*/ ChatPromptTemplate.fromMessages(messages);\n\nexport const REFINE_PROMPT_SELECTOR =\n  /*#__PURE__*/ new ConditionalPromptSelector(DEFAULT_REFINE_PROMPT, [\n    [isChatModel, CHAT_REFINE_PROMPT],\n  ]);\n\nexport const DEFAULT_TEXT_QA_PROMPT_TMPL = `Context information is below. \n---------------------\n{context}\n---------------------\nGiven the context information and no prior knowledge, answer the question: {question}`;\nexport const DEFAULT_TEXT_QA_PROMPT = /*#__PURE__*/ new PromptTemplate({\n  inputVariables: [\"context\", \"question\"],\n  template: DEFAULT_TEXT_QA_PROMPT_TMPL,\n});\n\nconst chat_qa_prompt_template = `Context information is below. \n---------------------\n{context}\n---------------------\nGiven the context information and no prior knowledge, answer any questions`;\nconst chat_messages = [\n  /*#__PURE__*/ SystemMessagePromptTemplate.fromTemplate(\n    chat_qa_prompt_template\n  ),\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(\"{question}\"),\n];\nexport const CHAT_QUESTION_PROMPT =\n  /*#__PURE__*/ ChatPromptTemplate.fromMessages(chat_messages);\nexport const QUESTION_PROMPT_SELECTOR =\n  /*#__PURE__*/ new ConditionalPromptSelector(DEFAULT_TEXT_QA_PROMPT, [\n    [isChatModel, CHAT_QUESTION_PROMPT],\n  ]);\n"],"mappings":";;;AAqBA,MAAa,wCAAsC,IAAIA,wBAAAA,eAAe;CACpE,gBAAgB;EAAC;EAAY;EAAmB;EAAU;CAC1D,UAAU;;;;;;;;;CACX,CAAC;AAYF,MAAM,WAAW;CACD,wCAAA,2BAA2B,aAAa,aAAa;CACrD,wCAAA,wBAAwB,aAAa,oBAAoB;CACzD,wCAAA,2BAA2B,aAAa;;;;;;;;0DAAe;CACtE;AAED,MAAa,qBACG,wCAAA,mBAAmB,aAAa,SAAS;AAEzD,MAAa,yCACG,IAAIC,kCAAAA,0BAA0B,uBAAuB,CACjE,CAACC,kCAAAA,aAAa,mBAAmB,CAClC,CAAC;AAOJ,MAAa,yCAAuC,IAAIF,wBAAAA,eAAe;CACrE,gBAAgB,CAAC,WAAW,WAAW;CACvC,UAAU;;;;;CACX,CAAC;AAOF,MAAM,gBAAgB,CACN,wCAAA,4BAA4B,aACxC;;;;4EACD,EACa,wCAAA,2BAA2B,aAAa,aAAa,CACpE;AACD,MAAa,uBACG,wCAAA,mBAAmB,aAAa,cAAc;AAC9D,MAAa,2CACG,IAAIC,kCAAAA,0BAA0B,wBAAwB,CAClE,CAACC,kCAAAA,aAAa,qBAAqB,CACpC,CAAC"}
+{"version":3,"file":"refine_prompts.cjs","names":["PromptTemplate","ConditionalPromptSelector","isChatModel"],"sources":["../../../src/chains/question_answering/refine_prompts.ts"],"sourcesContent":["import {\n  PromptTemplate,\n  ChatPromptTemplate,\n  SystemMessagePromptTemplate,\n  HumanMessagePromptTemplate,\n  AIMessagePromptTemplate,\n} from \"@langchain/core/prompts\";\nimport {\n  ConditionalPromptSelector,\n  isChatModel,\n} from \"@langchain/core/example_selectors\";\n\nexport const DEFAULT_REFINE_PROMPT_TMPL = `The original question is as follows: {question}\nWe have provided an existing answer: {existing_answer}\nWe have the opportunity to refine the existing answer\n(only if needed) with some more context below.\n------------\n{context}\n------------\nGiven the new context, refine the original answer to better answer the question. \nIf the context isn't useful, return the original answer.`;\nexport const DEFAULT_REFINE_PROMPT = /*#__PURE__*/ new PromptTemplate({\n  inputVariables: [\"question\", \"existing_answer\", \"context\"],\n  template: DEFAULT_REFINE_PROMPT_TMPL,\n});\n\nconst refineTemplate = `The original question is as follows: {question}\nWe have provided an existing answer: {existing_answer}\nWe have the opportunity to refine the existing answer\n(only if needed) with some more context below.\n------------\n{context}\n------------\nGiven the new context, refine the original answer to better answer the question. \nIf the context isn't useful, return the original answer.`;\n\nconst messages = [\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(\"{question}\"),\n  /*#__PURE__*/ AIMessagePromptTemplate.fromTemplate(\"{existing_answer}\"),\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(refineTemplate),\n];\n\nexport const CHAT_REFINE_PROMPT =\n  /*#__PURE__*/ ChatPromptTemplate.fromMessages(messages);\n\nexport const REFINE_PROMPT_SELECTOR =\n  /*#__PURE__*/ new ConditionalPromptSelector(DEFAULT_REFINE_PROMPT, [\n    [isChatModel, CHAT_REFINE_PROMPT],\n  ]);\n\nexport const DEFAULT_TEXT_QA_PROMPT_TMPL = `Context information is below. \n---------------------\n{context}\n---------------------\nGiven the context information and no prior knowledge, answer the question: {question}`;\nexport const DEFAULT_TEXT_QA_PROMPT = /*#__PURE__*/ new PromptTemplate({\n  inputVariables: [\"context\", \"question\"],\n  template: DEFAULT_TEXT_QA_PROMPT_TMPL,\n});\n\nconst chat_qa_prompt_template = `Context information is below. \n---------------------\n{context}\n---------------------\nGiven the context information and no prior knowledge, answer any questions`;\nconst chat_messages = [\n  /*#__PURE__*/ SystemMessagePromptTemplate.fromTemplate(\n    chat_qa_prompt_template\n  ),\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(\"{question}\"),\n];\nexport const CHAT_QUESTION_PROMPT =\n  /*#__PURE__*/ ChatPromptTemplate.fromMessages(chat_messages);\nexport const QUESTION_PROMPT_SELECTOR =\n  /*#__PURE__*/ new ConditionalPromptSelector(DEFAULT_TEXT_QA_PROMPT, [\n    [isChatModel, CHAT_QUESTION_PROMPT],\n  ]);\n"],"mappings":";;;AAYA,MAAa,6BAA6B;;;;;;;;;AAS1C,MAAa,sCAAsC,IAAIA,wBAAAA,eAAe;CACpE,gBAAgB;EAAC;EAAY;EAAmB;CAAS;CACzD,UAAU;AACZ,CAAC;AAYD,MAAM,WAAW;CACD,sCAAA,2BAA2B,aAAa,YAAY;CACpD,sCAAA,wBAAwB,aAAa,mBAAmB;CACxD,sCAAA,2BAA2B,aAAa;;;;;;;;yDAAc;AACtE;AAEA,MAAa,qBACG,sCAAA,mBAAmB,aAAa,QAAQ;AAExD,MAAa,uCACG,IAAIC,kCAAAA,0BAA0B,uBAAuB,CACjE,CAACC,kCAAAA,aAAa,kBAAkB,CAClC,CAAC;AAEH,MAAa,8BAA8B;;;;;AAK3C,MAAa,uCAAuC,IAAIF,wBAAAA,eAAe;CACrE,gBAAgB,CAAC,WAAW,UAAU;CACtC,UAAU;AACZ,CAAC;AAOD,MAAM,gBAAgB,CACN,sCAAA,4BAA4B,aACxC;;;;2EACF,GACc,sCAAA,2BAA2B,aAAa,YAAY,CACpE;AACA,MAAa,uBACG,sCAAA,mBAAmB,aAAa,aAAa;AAC7D,MAAa,yCACG,IAAIC,kCAAAA,0BAA0B,wBAAwB,CAClE,CAACC,kCAAAA,aAAa,oBAAoB,CACpC,CAAC"}

package/dist/chains/question_answering/refine_prompts.js

@@ -1,12 +1,7 @@
 import { AIMessagePromptTemplate, ChatPromptTemplate, HumanMessagePromptTemplate, PromptTemplate, SystemMessagePromptTemplate } from "@langchain/core/prompts";
 import { ConditionalPromptSelector, isChatModel } from "@langchain/core/example_selectors";
-const DEFAULT_REFINE_PROMPT = /* @__PURE__ */ new PromptTemplate({
-	inputVariables: [
-		"question",
-		"existing_answer",
-		"context"
-	],
-	template: `The original question is as follows: {question}
+//#region src/chains/question_answering/refine_prompts.ts
+const DEFAULT_REFINE_PROMPT_TMPL = `The original question is as follows: {question}
 We have provided an existing answer: {existing_answer}
 We have the opportunity to refine the existing answer
 (only if needed) with some more context below.
@@ -14,12 +9,19 @@ We have the opportunity to refine the existing answer
 {context}
 ------------
 Given the new context, refine the original answer to better answer the question. 
-If the context isn't useful, return the original answer.`
+If the context isn't useful, return the original answer.`;
+const DEFAULT_REFINE_PROMPT = /*#__PURE__*/ new PromptTemplate({
+	inputVariables: [
+		"question",
+		"existing_answer",
+		"context"
+	],
+	template: DEFAULT_REFINE_PROMPT_TMPL
 });
 const messages = [
-	/* @__PURE__ */ HumanMessagePromptTemplate.fromTemplate("{question}"),
-	/* @__PURE__ */ AIMessagePromptTemplate.fromTemplate("{existing_answer}"),
-	/* @__PURE__ */ HumanMessagePromptTemplate.fromTemplate(`The original question is as follows: {question}
+	/*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate("{question}"),
+	/*#__PURE__*/ AIMessagePromptTemplate.fromTemplate("{existing_answer}"),
+	/*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(`The original question is as follows: {question}
 We have provided an existing answer: {existing_answer}
 We have the opportunity to refine the existing answer
 (only if needed) with some more context below.
@@ -29,22 +31,25 @@ We have the opportunity to refine the existing answer
 Given the new context, refine the original answer to better answer the question. 
 If the context isn't useful, return the original answer.`)
 ];
-const REFINE_PROMPT_SELECTOR = /* @__PURE__ */ new ConditionalPromptSelector(DEFAULT_REFINE_PROMPT, [[isChatModel, /* @__PURE__ */ ChatPromptTemplate.fromMessages(messages)]]);
-const DEFAULT_TEXT_QA_PROMPT = /* @__PURE__ */ new PromptTemplate({
-	inputVariables: ["context", "question"],
-	template: `Context information is below. 
+const CHAT_REFINE_PROMPT = /*#__PURE__*/ ChatPromptTemplate.fromMessages(messages);
+const REFINE_PROMPT_SELECTOR = /*#__PURE__*/ new ConditionalPromptSelector(DEFAULT_REFINE_PROMPT, [[isChatModel, CHAT_REFINE_PROMPT]]);
+const DEFAULT_TEXT_QA_PROMPT_TMPL = `Context information is below. 
 ---------------------
 {context}
 ---------------------
-Given the context information and no prior knowledge, answer the question: {question}`
+Given the context information and no prior knowledge, answer the question: {question}`;
+const DEFAULT_TEXT_QA_PROMPT = /*#__PURE__*/ new PromptTemplate({
+	inputVariables: ["context", "question"],
+	template: DEFAULT_TEXT_QA_PROMPT_TMPL
 });
-const chat_messages = [/* @__PURE__ */ SystemMessagePromptTemplate.fromTemplate(`Context information is below. 
+const chat_messages = [/*#__PURE__*/ SystemMessagePromptTemplate.fromTemplate(`Context information is below. 
 ---------------------
 {context}
 ---------------------
-Given the context information and no prior knowledge, answer any questions`), /* @__PURE__ */ HumanMessagePromptTemplate.fromTemplate("{question}")];
-const QUESTION_PROMPT_SELECTOR = /* @__PURE__ */ new ConditionalPromptSelector(DEFAULT_TEXT_QA_PROMPT, [[isChatModel, /* @__PURE__ */ ChatPromptTemplate.fromMessages(chat_messages)]]);
+Given the context information and no prior knowledge, answer any questions`), /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate("{question}")];
+const CHAT_QUESTION_PROMPT = /*#__PURE__*/ ChatPromptTemplate.fromMessages(chat_messages);
+const QUESTION_PROMPT_SELECTOR = /*#__PURE__*/ new ConditionalPromptSelector(DEFAULT_TEXT_QA_PROMPT, [[isChatModel, CHAT_QUESTION_PROMPT]]);
 //#endregion
-export { QUESTION_PROMPT_SELECTOR, REFINE_PROMPT_SELECTOR };
+export { CHAT_QUESTION_PROMPT, CHAT_REFINE_PROMPT, DEFAULT_REFINE_PROMPT, DEFAULT_REFINE_PROMPT_TMPL, DEFAULT_TEXT_QA_PROMPT, DEFAULT_TEXT_QA_PROMPT_TMPL, QUESTION_PROMPT_SELECTOR, REFINE_PROMPT_SELECTOR };
 
 //# sourceMappingURL=refine_prompts.js.map

package/dist/chains/question_answering/refine_prompts.js.map

@@ -1 +1 @@
-{"version":3,"file":"refine_prompts.js","names":[],"sources":["../../../src/chains/question_answering/refine_prompts.ts"],"sourcesContent":["import {\n  PromptTemplate,\n  ChatPromptTemplate,\n  SystemMessagePromptTemplate,\n  HumanMessagePromptTemplate,\n  AIMessagePromptTemplate,\n} from \"@langchain/core/prompts\";\nimport {\n  ConditionalPromptSelector,\n  isChatModel,\n} from \"@langchain/core/example_selectors\";\n\nexport const DEFAULT_REFINE_PROMPT_TMPL = `The original question is as follows: {question}\nWe have provided an existing answer: {existing_answer}\nWe have the opportunity to refine the existing answer\n(only if needed) with some more context below.\n------------\n{context}\n------------\nGiven the new context, refine the original answer to better answer the question. \nIf the context isn't useful, return the original answer.`;\nexport const DEFAULT_REFINE_PROMPT = /*#__PURE__*/ new PromptTemplate({\n  inputVariables: [\"question\", \"existing_answer\", \"context\"],\n  template: DEFAULT_REFINE_PROMPT_TMPL,\n});\n\nconst refineTemplate = `The original question is as follows: {question}\nWe have provided an existing answer: {existing_answer}\nWe have the opportunity to refine the existing answer\n(only if needed) with some more context below.\n------------\n{context}\n------------\nGiven the new context, refine the original answer to better answer the question. \nIf the context isn't useful, return the original answer.`;\n\nconst messages = [\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(\"{question}\"),\n  /*#__PURE__*/ AIMessagePromptTemplate.fromTemplate(\"{existing_answer}\"),\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(refineTemplate),\n];\n\nexport const CHAT_REFINE_PROMPT =\n  /*#__PURE__*/ ChatPromptTemplate.fromMessages(messages);\n\nexport const REFINE_PROMPT_SELECTOR =\n  /*#__PURE__*/ new ConditionalPromptSelector(DEFAULT_REFINE_PROMPT, [\n    [isChatModel, CHAT_REFINE_PROMPT],\n  ]);\n\nexport const DEFAULT_TEXT_QA_PROMPT_TMPL = `Context information is below. \n---------------------\n{context}\n---------------------\nGiven the context information and no prior knowledge, answer the question: {question}`;\nexport const DEFAULT_TEXT_QA_PROMPT = /*#__PURE__*/ new PromptTemplate({\n  inputVariables: [\"context\", \"question\"],\n  template: DEFAULT_TEXT_QA_PROMPT_TMPL,\n});\n\nconst chat_qa_prompt_template = `Context information is below. \n---------------------\n{context}\n---------------------\nGiven the context information and no prior knowledge, answer any questions`;\nconst chat_messages = [\n  /*#__PURE__*/ SystemMessagePromptTemplate.fromTemplate(\n    chat_qa_prompt_template\n  ),\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(\"{question}\"),\n];\nexport const CHAT_QUESTION_PROMPT =\n  /*#__PURE__*/ ChatPromptTemplate.fromMessages(chat_messages);\nexport const QUESTION_PROMPT_SELECTOR =\n  /*#__PURE__*/ new ConditionalPromptSelector(DEFAULT_TEXT_QA_PROMPT, [\n    [isChatModel, CHAT_QUESTION_PROMPT],\n  ]);\n"],"mappings":";;AAqBA,MAAa,wCAAsC,IAAI,eAAe;CACpE,gBAAgB;EAAC;EAAY;EAAmB;EAAU;CAC1D,UAAU;;;;;;;;;CACX,CAAC;AAYF,MAAM,WAAW;CACD,2CAA2B,aAAa,aAAa;CACrD,wCAAwB,aAAa,oBAAoB;CACzD,2CAA2B,aAAa;;;;;;;;0DAAe;CACtE;AAKD,MAAa,yCACG,IAAI,0BAA0B,uBAAuB,CACjE,CAAC,aAAa,gBAJF,mBAAmB,aAAa,SAI9B,CAAmB,CAClC,CAAC;AAOJ,MAAa,yCAAuC,IAAI,eAAe;CACrE,gBAAgB,CAAC,WAAW,WAAW;CACvC,UAAU;;;;;CACX,CAAC;AAOF,MAAM,gBAAgB,CACN,4CAA4B,aACxC;;;;4EACD,EACa,2CAA2B,aAAa,aAAa,CACpE;AAGD,MAAa,2CACG,IAAI,0BAA0B,wBAAwB,CAClE,CAAC,aAAa,gBAHF,mBAAmB,aAAa,cAG9B,CAAqB,CACpC,CAAC"}
+{"version":3,"file":"refine_prompts.js","names":[],"sources":["../../../src/chains/question_answering/refine_prompts.ts"],"sourcesContent":["import {\n  PromptTemplate,\n  ChatPromptTemplate,\n  SystemMessagePromptTemplate,\n  HumanMessagePromptTemplate,\n  AIMessagePromptTemplate,\n} from \"@langchain/core/prompts\";\nimport {\n  ConditionalPromptSelector,\n  isChatModel,\n} from \"@langchain/core/example_selectors\";\n\nexport const DEFAULT_REFINE_PROMPT_TMPL = `The original question is as follows: {question}\nWe have provided an existing answer: {existing_answer}\nWe have the opportunity to refine the existing answer\n(only if needed) with some more context below.\n------------\n{context}\n------------\nGiven the new context, refine the original answer to better answer the question. \nIf the context isn't useful, return the original answer.`;\nexport const DEFAULT_REFINE_PROMPT = /*#__PURE__*/ new PromptTemplate({\n  inputVariables: [\"question\", \"existing_answer\", \"context\"],\n  template: DEFAULT_REFINE_PROMPT_TMPL,\n});\n\nconst refineTemplate = `The original question is as follows: {question}\nWe have provided an existing answer: {existing_answer}\nWe have the opportunity to refine the existing answer\n(only if needed) with some more context below.\n------------\n{context}\n------------\nGiven the new context, refine the original answer to better answer the question. \nIf the context isn't useful, return the original answer.`;\n\nconst messages = [\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(\"{question}\"),\n  /*#__PURE__*/ AIMessagePromptTemplate.fromTemplate(\"{existing_answer}\"),\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(refineTemplate),\n];\n\nexport const CHAT_REFINE_PROMPT =\n  /*#__PURE__*/ ChatPromptTemplate.fromMessages(messages);\n\nexport const REFINE_PROMPT_SELECTOR =\n  /*#__PURE__*/ new ConditionalPromptSelector(DEFAULT_REFINE_PROMPT, [\n    [isChatModel, CHAT_REFINE_PROMPT],\n  ]);\n\nexport const DEFAULT_TEXT_QA_PROMPT_TMPL = `Context information is below. \n---------------------\n{context}\n---------------------\nGiven the context information and no prior knowledge, answer the question: {question}`;\nexport const DEFAULT_TEXT_QA_PROMPT = /*#__PURE__*/ new PromptTemplate({\n  inputVariables: [\"context\", \"question\"],\n  template: DEFAULT_TEXT_QA_PROMPT_TMPL,\n});\n\nconst chat_qa_prompt_template = `Context information is below. \n---------------------\n{context}\n---------------------\nGiven the context information and no prior knowledge, answer any questions`;\nconst chat_messages = [\n  /*#__PURE__*/ SystemMessagePromptTemplate.fromTemplate(\n    chat_qa_prompt_template\n  ),\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(\"{question}\"),\n];\nexport const CHAT_QUESTION_PROMPT =\n  /*#__PURE__*/ ChatPromptTemplate.fromMessages(chat_messages);\nexport const QUESTION_PROMPT_SELECTOR =\n  /*#__PURE__*/ new ConditionalPromptSelector(DEFAULT_TEXT_QA_PROMPT, [\n    [isChatModel, CHAT_QUESTION_PROMPT],\n  ]);\n"],"mappings":";;;AAYA,MAAa,6BAA6B;;;;;;;;;AAS1C,MAAa,sCAAsC,IAAI,eAAe;CACpE,gBAAgB;EAAC;EAAY;EAAmB;CAAS;CACzD,UAAU;AACZ,CAAC;AAYD,MAAM,WAAW;CACD,yCAA2B,aAAa,YAAY;CACpD,sCAAwB,aAAa,mBAAmB;CACxD,yCAA2B,aAAa;;;;;;;;yDAAc;AACtE;AAEA,MAAa,qBACG,iCAAmB,aAAa,QAAQ;AAExD,MAAa,uCACG,IAAI,0BAA0B,uBAAuB,CACjE,CAAC,aAAa,kBAAkB,CAClC,CAAC;AAEH,MAAa,8BAA8B;;;;;AAK3C,MAAa,uCAAuC,IAAI,eAAe;CACrE,gBAAgB,CAAC,WAAW,UAAU;CACtC,UAAU;AACZ,CAAC;AAOD,MAAM,gBAAgB,CACN,0CAA4B,aACxC;;;;2EACF,GACc,yCAA2B,aAAa,YAAY,CACpE;AACA,MAAa,uBACG,iCAAmB,aAAa,aAAa;AAC7D,MAAa,yCACG,IAAI,0BAA0B,wBAAwB,CAClE,CAAC,aAAa,oBAAoB,CACpC,CAAC"}

package/dist/chains/question_answering/stuff_prompts.cjs

@@ -1,18 +1,18 @@
-require("../../_virtual/_rolldown/runtime.cjs");
 let _langchain_core_prompts = require("@langchain/core/prompts");
 let _langchain_core_example_selectors = require("@langchain/core/example_selectors");
 //#region src/chains/question_answering/stuff_prompts.ts
-const DEFAULT_QA_PROMPT = /* @__PURE__ */ new _langchain_core_prompts.PromptTemplate({
+const DEFAULT_QA_PROMPT = /*#__PURE__*/ new _langchain_core_prompts.PromptTemplate({
 	template: "Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.\n\n{context}\n\nQuestion: {question}\nHelpful Answer:",
 	inputVariables: ["context", "question"]
 });
-const messages = [/* @__PURE__ */ _langchain_core_prompts.SystemMessagePromptTemplate.fromTemplate(`Use the following pieces of context to answer the users question. 
+const messages = [/*#__PURE__*/ _langchain_core_prompts.SystemMessagePromptTemplate.fromTemplate(`Use the following pieces of context to answer the users question. 
 If you don't know the answer, just say that you don't know, don't try to make up an answer.
 ----------------
-{context}`), /* @__PURE__ */ _langchain_core_prompts.HumanMessagePromptTemplate.fromTemplate("{question}")];
-const CHAT_PROMPT = /* @__PURE__ */ _langchain_core_prompts.ChatPromptTemplate.fromMessages(messages);
-const QA_PROMPT_SELECTOR = /* @__PURE__ */ new _langchain_core_example_selectors.ConditionalPromptSelector(DEFAULT_QA_PROMPT, [[_langchain_core_example_selectors.isChatModel, CHAT_PROMPT]]);
+{context}`), /*#__PURE__*/ _langchain_core_prompts.HumanMessagePromptTemplate.fromTemplate("{question}")];
+const CHAT_PROMPT = /*#__PURE__*/ _langchain_core_prompts.ChatPromptTemplate.fromMessages(messages);
+const QA_PROMPT_SELECTOR = /*#__PURE__*/ new _langchain_core_example_selectors.ConditionalPromptSelector(DEFAULT_QA_PROMPT, [[_langchain_core_example_selectors.isChatModel, CHAT_PROMPT]]);
 //#endregion
+exports.DEFAULT_QA_PROMPT = DEFAULT_QA_PROMPT;
 exports.QA_PROMPT_SELECTOR = QA_PROMPT_SELECTOR;
 
 //# sourceMappingURL=stuff_prompts.cjs.map

package/dist/chains/question_answering/stuff_prompts.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"stuff_prompts.cjs","names":["PromptTemplate","ConditionalPromptSelector","isChatModel"],"sources":["../../../src/chains/question_answering/stuff_prompts.ts"],"sourcesContent":["import {\n  ChatPromptTemplate,\n  SystemMessagePromptTemplate,\n  HumanMessagePromptTemplate,\n  PromptTemplate,\n} from \"@langchain/core/prompts\";\nimport {\n  ConditionalPromptSelector,\n  isChatModel,\n} from \"@langchain/core/example_selectors\";\n\nexport const DEFAULT_QA_PROMPT = /*#__PURE__*/ new PromptTemplate({\n  template:\n    \"Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.\\n\\n{context}\\n\\nQuestion: {question}\\nHelpful Answer:\",\n  inputVariables: [\"context\", \"question\"],\n});\n\nconst system_template = `Use the following pieces of context to answer the users question. \nIf you don't know the answer, just say that you don't know, don't try to make up an answer.\n----------------\n{context}`;\nconst messages = [\n  /*#__PURE__*/ SystemMessagePromptTemplate.fromTemplate(system_template),\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(\"{question}\"),\n];\nconst CHAT_PROMPT = /*#__PURE__*/ ChatPromptTemplate.fromMessages(messages);\n\nexport const QA_PROMPT_SELECTOR = /*#__PURE__*/ new ConditionalPromptSelector(\n  DEFAULT_QA_PROMPT,\n  [[isChatModel, CHAT_PROMPT]]\n);\n"],"mappings":";;;;AAWA,MAAa,oCAAkC,IAAIA,wBAAAA,eAAe;CAChE,UACE;CACF,gBAAgB,CAAC,WAAW,WAAW;CACxC,CAAC;AAMF,MAAM,WAAW,CACD,wCAAA,4BAA4B,aAAa;;;WAAgB,EACzD,wCAAA,2BAA2B,aAAa,aAAa,CACpE;AACD,MAAM,cAA4B,wCAAA,mBAAmB,aAAa,SAAS;AAE3E,MAAa,qCAAmC,IAAIC,kCAAAA,0BAClD,mBACA,CAAC,CAACC,kCAAAA,aAAa,YAAY,CAAC,CAC7B"}
+{"version":3,"file":"stuff_prompts.cjs","names":["PromptTemplate","ConditionalPromptSelector","isChatModel"],"sources":["../../../src/chains/question_answering/stuff_prompts.ts"],"sourcesContent":["import {\n  ChatPromptTemplate,\n  SystemMessagePromptTemplate,\n  HumanMessagePromptTemplate,\n  PromptTemplate,\n} from \"@langchain/core/prompts\";\nimport {\n  ConditionalPromptSelector,\n  isChatModel,\n} from \"@langchain/core/example_selectors\";\n\nexport const DEFAULT_QA_PROMPT = /*#__PURE__*/ new PromptTemplate({\n  template:\n    \"Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.\\n\\n{context}\\n\\nQuestion: {question}\\nHelpful Answer:\",\n  inputVariables: [\"context\", \"question\"],\n});\n\nconst system_template = `Use the following pieces of context to answer the users question. \nIf you don't know the answer, just say that you don't know, don't try to make up an answer.\n----------------\n{context}`;\nconst messages = [\n  /*#__PURE__*/ SystemMessagePromptTemplate.fromTemplate(system_template),\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(\"{question}\"),\n];\nconst CHAT_PROMPT = /*#__PURE__*/ ChatPromptTemplate.fromMessages(messages);\n\nexport const QA_PROMPT_SELECTOR = /*#__PURE__*/ new ConditionalPromptSelector(\n  DEFAULT_QA_PROMPT,\n  [[isChatModel, CHAT_PROMPT]]\n);\n"],"mappings":";;;AAWA,MAAa,kCAAkC,IAAIA,wBAAAA,eAAe;CAChE,UACE;CACF,gBAAgB,CAAC,WAAW,UAAU;AACxC,CAAC;AAMD,MAAM,WAAW,CACD,sCAAA,4BAA4B,aAAa;;;UAAe,GACxD,sCAAA,2BAA2B,aAAa,YAAY,CACpE;AACA,MAAM,cAA4B,sCAAA,mBAAmB,aAAa,QAAQ;AAE1E,MAAa,mCAAmC,IAAIC,kCAAAA,0BAClD,mBACA,CAAC,CAACC,kCAAAA,aAAa,WAAW,CAAC,CAC7B"}

package/dist/chains/question_answering/stuff_prompts.js

@@ -1,16 +1,16 @@
 import { ChatPromptTemplate, HumanMessagePromptTemplate, PromptTemplate, SystemMessagePromptTemplate } from "@langchain/core/prompts";
 import { ConditionalPromptSelector, isChatModel } from "@langchain/core/example_selectors";
 //#region src/chains/question_answering/stuff_prompts.ts
-const DEFAULT_QA_PROMPT = /* @__PURE__ */ new PromptTemplate({
+const DEFAULT_QA_PROMPT = /*#__PURE__*/ new PromptTemplate({
 	template: "Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.\n\n{context}\n\nQuestion: {question}\nHelpful Answer:",
 	inputVariables: ["context", "question"]
 });
-const messages = [/* @__PURE__ */ SystemMessagePromptTemplate.fromTemplate(`Use the following pieces of context to answer the users question. 
+const messages = [/*#__PURE__*/ SystemMessagePromptTemplate.fromTemplate(`Use the following pieces of context to answer the users question. 
 If you don't know the answer, just say that you don't know, don't try to make up an answer.
 ----------------
-{context}`), /* @__PURE__ */ HumanMessagePromptTemplate.fromTemplate("{question}")];
-const QA_PROMPT_SELECTOR = /* @__PURE__ */ new ConditionalPromptSelector(DEFAULT_QA_PROMPT, [[isChatModel, /* @__PURE__ */ ChatPromptTemplate.fromMessages(messages)]]);
+{context}`), /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate("{question}")];
+const QA_PROMPT_SELECTOR = /*#__PURE__*/ new ConditionalPromptSelector(DEFAULT_QA_PROMPT, [[isChatModel, /* @__PURE__ */ ChatPromptTemplate.fromMessages(messages)]]);
 //#endregion
-export { QA_PROMPT_SELECTOR };
+export { DEFAULT_QA_PROMPT, QA_PROMPT_SELECTOR };
 
 //# sourceMappingURL=stuff_prompts.js.map

package/dist/chains/question_answering/stuff_prompts.js.map

@@ -1 +1 @@
-{"version":3,"file":"stuff_prompts.js","names":[],"sources":["../../../src/chains/question_answering/stuff_prompts.ts"],"sourcesContent":["import {\n  ChatPromptTemplate,\n  SystemMessagePromptTemplate,\n  HumanMessagePromptTemplate,\n  PromptTemplate,\n} from \"@langchain/core/prompts\";\nimport {\n  ConditionalPromptSelector,\n  isChatModel,\n} from \"@langchain/core/example_selectors\";\n\nexport const DEFAULT_QA_PROMPT = /*#__PURE__*/ new PromptTemplate({\n  template:\n    \"Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.\\n\\n{context}\\n\\nQuestion: {question}\\nHelpful Answer:\",\n  inputVariables: [\"context\", \"question\"],\n});\n\nconst system_template = `Use the following pieces of context to answer the users question. \nIf you don't know the answer, just say that you don't know, don't try to make up an answer.\n----------------\n{context}`;\nconst messages = [\n  /*#__PURE__*/ SystemMessagePromptTemplate.fromTemplate(system_template),\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(\"{question}\"),\n];\nconst CHAT_PROMPT = /*#__PURE__*/ ChatPromptTemplate.fromMessages(messages);\n\nexport const QA_PROMPT_SELECTOR = /*#__PURE__*/ new ConditionalPromptSelector(\n  DEFAULT_QA_PROMPT,\n  [[isChatModel, CHAT_PROMPT]]\n);\n"],"mappings":";;;AAWA,MAAa,oCAAkC,IAAI,eAAe;CAChE,UACE;CACF,gBAAgB,CAAC,WAAW,WAAW;CACxC,CAAC;AAMF,MAAM,WAAW,CACD,4CAA4B,aAAa;;;WAAgB,EACzD,2CAA2B,aAAa,aAAa,CACpE;AAGD,MAAa,qCAAmC,IAAI,0BAClD,mBACA,CAAC,CAAC,aAAa,gBAJiB,mBAAmB,aAAa,SAIjD,CAAY,CAAC,CAC7B"}
+{"version":3,"file":"stuff_prompts.js","names":[],"sources":["../../../src/chains/question_answering/stuff_prompts.ts"],"sourcesContent":["import {\n  ChatPromptTemplate,\n  SystemMessagePromptTemplate,\n  HumanMessagePromptTemplate,\n  PromptTemplate,\n} from \"@langchain/core/prompts\";\nimport {\n  ConditionalPromptSelector,\n  isChatModel,\n} from \"@langchain/core/example_selectors\";\n\nexport const DEFAULT_QA_PROMPT = /*#__PURE__*/ new PromptTemplate({\n  template:\n    \"Use the following pieces of context to answer the question at the end. If you don't know the answer, just say that you don't know, don't try to make up an answer.\\n\\n{context}\\n\\nQuestion: {question}\\nHelpful Answer:\",\n  inputVariables: [\"context\", \"question\"],\n});\n\nconst system_template = `Use the following pieces of context to answer the users question. \nIf you don't know the answer, just say that you don't know, don't try to make up an answer.\n----------------\n{context}`;\nconst messages = [\n  /*#__PURE__*/ SystemMessagePromptTemplate.fromTemplate(system_template),\n  /*#__PURE__*/ HumanMessagePromptTemplate.fromTemplate(\"{question}\"),\n];\nconst CHAT_PROMPT = /*#__PURE__*/ ChatPromptTemplate.fromMessages(messages);\n\nexport const QA_PROMPT_SELECTOR = /*#__PURE__*/ new ConditionalPromptSelector(\n  DEFAULT_QA_PROMPT,\n  [[isChatModel, CHAT_PROMPT]]\n);\n"],"mappings":";;;AAWA,MAAa,kCAAkC,IAAI,eAAe;CAChE,UACE;CACF,gBAAgB,CAAC,WAAW,UAAU;AACxC,CAAC;AAMD,MAAM,WAAW,CACD,0CAA4B,aAAa;;;UAAe,GACxD,yCAA2B,aAAa,YAAY,CACpE;AAGA,MAAa,mCAAmC,IAAI,0BAClD,mBACA,CAAC,CAAC,aAAa,gBAJiB,mBAAmB,aAAa,QAIjD,CAAW,CAAC,CAC7B"}

package/dist/chains/retrieval.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"retrieval.cjs","names":["RunnableSequence","RunnablePassthrough"],"sources":["../../src/chains/retrieval.ts"],"sourcesContent":["import type { BaseRetrieverInterface } from \"@langchain/core/retrievers\";\nimport {\n  type Runnable,\n  RunnableSequence,\n  type RunnableInterface,\n  RunnablePassthrough,\n} from \"@langchain/core/runnables\";\nimport type { BaseMessage } from \"@langchain/core/messages\";\nimport type { DocumentInterface, Document } from \"@langchain/core/documents\";\n\n/**\n * Parameters for the createRetrievalChain method.\n */\nexport type CreateRetrievalChainParams<RunOutput> = {\n  /**\n   * Retriever-like object that returns list of documents. Should\n   * either be a subclass of BaseRetriever or a Runnable that returns\n   * a list of documents. If a subclass of BaseRetriever, then it\n   * is expected that an `input` key be passed in - this is what\n   * is will be used to pass into the retriever. If this is NOT a\n   * subclass of BaseRetriever, then all the inputs will be passed\n   * into this runnable, meaning that runnable should take a object\n   * as input.\n   */\n  retriever:\n    | BaseRetrieverInterface\n    // oxlint-disable-next-line @typescript-eslint/no-explicit-any\n    | RunnableInterface<Record<string, any>, DocumentInterface[]>;\n  /**\n   * Runnable that takes inputs and produces a string output.\n   * The inputs to this will be any original inputs to this chain, a new\n   * context key with the retrieved documents, and chat_history (if not present\n   * in the inputs) with a value of `[]` (to easily enable conversational\n   * retrieval).\n   */\n  // oxlint-disable-next-line @typescript-eslint/no-explicit-any\n  combineDocsChain: RunnableInterface<Record<string, any>, RunOutput>;\n};\n\nfunction isBaseRetriever(x: unknown): x is BaseRetrieverInterface {\n  return !!x && typeof (x as BaseRetrieverInterface).invoke === \"function\";\n}\n\n/**\n * Create a retrieval chain that retrieves documents and then passes them on.\n * @param {CreateRetrievalChainParams} params A params object\n *     containing a retriever and a combineDocsChain.\n * @returns An LCEL Runnable which returns a an object\n *     containing at least `context` and `answer` keys.\n * @example\n * ```typescript\n * // pnpm add langchain @langchain/openai\n *\n * import { ChatOpenAI } from \"@langchain/openai\";\n * import { pull } from \"langchain/hub\";\n * import { createRetrievalChain } from \"@langchain/classic/chains/retrieval\";\n * import { createStuffDocumentsChain } from \"@langchain/classic/chains/combine_documents\";\n *\n * const retrievalQAChatPrompt = await pull(\"langchain-ai/retrieval-qa-chat\");\n * const llm = new ChatOpenAI({ model: \"gpt-4o-mini\" });\n * const retriever = ...\n * const combineDocsChain = await createStuffDocumentsChain(...);\n * const retrievalChain = await createRetrievalChain({\n *   retriever,\n *   combineDocsChain,\n * });\n * const response = await chain.invoke({ input: \"...\" });\n * ```\n */\nexport async function createRetrievalChain<RunOutput>({\n  retriever,\n  combineDocsChain,\n}: CreateRetrievalChainParams<RunOutput>): Promise<\n  Runnable<\n    { input: string; chat_history?: BaseMessage[] | string } & {\n      [key: string]: unknown;\n    },\n    { context: Document[]; answer: RunOutput } & { [key: string]: unknown }\n  >\n> {\n  let retrieveDocumentsChain: Runnable<{ input: string }, DocumentInterface[]>;\n  if (isBaseRetriever(retriever)) {\n    retrieveDocumentsChain = RunnableSequence.from([\n      (input) => input.input,\n      retriever,\n    ]);\n  } else {\n    // TODO: Fix typing by adding withConfig to core RunnableInterface\n    retrieveDocumentsChain = retriever as Runnable;\n  }\n  const retrievalChain = RunnableSequence.from<{\n    input: string;\n    chat_history?: BaseMessage[] | string;\n  }>([\n    RunnablePassthrough.assign({\n      context: retrieveDocumentsChain.withConfig({\n        runName: \"retrieve_documents\",\n      }),\n      chat_history: (input) => input.chat_history ?? [],\n    }),\n    RunnablePassthrough.assign({\n      answer: combineDocsChain,\n    }),\n  ]).withConfig({ runName: \"retrieval_chain\" });\n  return retrievalChain;\n}\n"],"mappings":";;;;;AAuCA,SAAS,gBAAgB,GAAyC;AAChE,QAAO,CAAC,CAAC,KAAK,OAAQ,EAA6B,WAAW;;;;;;;;;;;;;;;;;;;;;;;;;;;;AA6BhE,eAAsB,qBAAgC,EACpD,WACA,oBAQA;CACA,IAAI;AACJ,KAAI,gBAAgB,UAAU,CAC5B,0BAAyBA,0BAAAA,iBAAiB,KAAK,EAC5C,UAAU,MAAM,OACjB,UACD,CAAC;KAGF,0BAAyB;AAgB3B,QAduBA,0BAAAA,iBAAiB,KAGrC,CACDC,0BAAAA,oBAAoB,OAAO;EACzB,SAAS,uBAAuB,WAAW,EACzC,SAAS,sBACV,CAAC;EACF,eAAe,UAAU,MAAM,gBAAgB,EAAE;EAClD,CAAC,EACFA,0BAAAA,oBAAoB,OAAO,EACzB,QAAQ,kBACT,CAAC,CACH,CAAC,CAAC,WAAW,EAAE,SAAS,mBAAmB,CACvB"}
+{"version":3,"file":"retrieval.cjs","names":["RunnableSequence","RunnablePassthrough"],"sources":["../../src/chains/retrieval.ts"],"sourcesContent":["import type { BaseRetrieverInterface } from \"@langchain/core/retrievers\";\nimport {\n  type Runnable,\n  RunnableSequence,\n  type RunnableInterface,\n  RunnablePassthrough,\n} from \"@langchain/core/runnables\";\nimport type { BaseMessage } from \"@langchain/core/messages\";\nimport type { DocumentInterface, Document } from \"@langchain/core/documents\";\n\n/**\n * Parameters for the createRetrievalChain method.\n */\nexport type CreateRetrievalChainParams<RunOutput> = {\n  /**\n   * Retriever-like object that returns list of documents. Should\n   * either be a subclass of BaseRetriever or a Runnable that returns\n   * a list of documents. If a subclass of BaseRetriever, then it\n   * is expected that an `input` key be passed in - this is what\n   * is will be used to pass into the retriever. If this is NOT a\n   * subclass of BaseRetriever, then all the inputs will be passed\n   * into this runnable, meaning that runnable should take a object\n   * as input.\n   */\n  retriever:\n    | BaseRetrieverInterface\n    // oxlint-disable-next-line @typescript-eslint/no-explicit-any\n    | RunnableInterface<Record<string, any>, DocumentInterface[]>;\n  /**\n   * Runnable that takes inputs and produces a string output.\n   * The inputs to this will be any original inputs to this chain, a new\n   * context key with the retrieved documents, and chat_history (if not present\n   * in the inputs) with a value of `[]` (to easily enable conversational\n   * retrieval).\n   */\n  // oxlint-disable-next-line @typescript-eslint/no-explicit-any\n  combineDocsChain: RunnableInterface<Record<string, any>, RunOutput>;\n};\n\nfunction isBaseRetriever(x: unknown): x is BaseRetrieverInterface {\n  return !!x && typeof (x as BaseRetrieverInterface).invoke === \"function\";\n}\n\n/**\n * Create a retrieval chain that retrieves documents and then passes them on.\n * @param {CreateRetrievalChainParams} params A params object\n *     containing a retriever and a combineDocsChain.\n * @returns An LCEL Runnable which returns a an object\n *     containing at least `context` and `answer` keys.\n * @example\n * ```typescript\n * // pnpm add langchain @langchain/openai\n *\n * import { ChatOpenAI } from \"@langchain/openai\";\n * import { pull } from \"langchain/hub\";\n * import { createRetrievalChain } from \"@langchain/classic/chains/retrieval\";\n * import { createStuffDocumentsChain } from \"@langchain/classic/chains/combine_documents\";\n *\n * const retrievalQAChatPrompt = await pull(\"langchain-ai/retrieval-qa-chat\");\n * const llm = new ChatOpenAI({ model: \"gpt-4o-mini\" });\n * const retriever = ...\n * const combineDocsChain = await createStuffDocumentsChain(...);\n * const retrievalChain = await createRetrievalChain({\n *   retriever,\n *   combineDocsChain,\n * });\n * const response = await chain.invoke({ input: \"...\" });\n * ```\n */\nexport async function createRetrievalChain<RunOutput>({\n  retriever,\n  combineDocsChain,\n}: CreateRetrievalChainParams<RunOutput>): Promise<\n  Runnable<\n    { input: string; chat_history?: BaseMessage[] | string } & {\n      [key: string]: unknown;\n    },\n    { context: Document[]; answer: RunOutput } & { [key: string]: unknown }\n  >\n> {\n  let retrieveDocumentsChain: Runnable<{ input: string }, DocumentInterface[]>;\n  if (isBaseRetriever(retriever)) {\n    retrieveDocumentsChain = RunnableSequence.from([\n      (input) => input.input,\n      retriever,\n    ]);\n  } else {\n    // TODO: Fix typing by adding withConfig to core RunnableInterface\n    retrieveDocumentsChain = retriever as Runnable;\n  }\n  const retrievalChain = RunnableSequence.from<{\n    input: string;\n    chat_history?: BaseMessage[] | string;\n  }>([\n    RunnablePassthrough.assign({\n      context: retrieveDocumentsChain.withConfig({\n        runName: \"retrieve_documents\",\n      }),\n      chat_history: (input) => input.chat_history ?? [],\n    }),\n    RunnablePassthrough.assign({\n      answer: combineDocsChain,\n    }),\n  ]).withConfig({ runName: \"retrieval_chain\" });\n  return retrievalChain;\n}\n"],"mappings":";;;;;AAuCA,SAAS,gBAAgB,GAAyC;CAChE,OAAO,CAAC,CAAC,KAAK,OAAQ,EAA6B,WAAW;AAChE;;;;;;;;;;;;;;;;;;;;;;;;;;;AA4BA,eAAsB,qBAAgC,EACpD,WACA,oBAQA;CACA,IAAI;CACJ,IAAI,gBAAgB,SAAS,GAC3B,yBAAyBA,0BAAAA,iBAAiB,KAAK,EAC5C,UAAU,MAAM,OACjB,SACF,CAAC;MAGD,yBAAyB;CAgB3B,OAduBA,0BAAAA,iBAAiB,KAGrC,CACDC,0BAAAA,oBAAoB,OAAO;EACzB,SAAS,uBAAuB,WAAW,EACzC,SAAS,qBACX,CAAC;EACD,eAAe,UAAU,MAAM,gBAAgB,CAAC;CAClD,CAAC,GACDA,0BAAAA,oBAAoB,OAAO,EACzB,QAAQ,iBACV,CAAC,CACH,CAAC,CAAC,CAAC,WAAW,EAAE,SAAS,kBAAkB,CACvB;AACtB"}

package/dist/chains/retrieval.d.cts

@@ -2,7 +2,6 @@ import { BaseMessage } from "@langchain/core/messages";
 import { Runnable, RunnableInterface } from "@langchain/core/runnables";
 import { BaseRetrieverInterface } from "@langchain/core/retrievers";
 import { Document, DocumentInterface } from "@langchain/core/documents";
-
 //#region src/chains/retrieval.d.ts
 /**
  * Parameters for the createRetrievalChain method.
@@ -54,10 +53,7 @@ type CreateRetrievalChainParams<RunOutput> = {
  * const response = await chain.invoke({ input: "..." });
  * ```
  */
-declare function createRetrievalChain<RunOutput>({
-  retriever,
-  combineDocsChain
-}: CreateRetrievalChainParams<RunOutput>): Promise<Runnable<{
+declare function createRetrievalChain<RunOutput>({ retriever, combineDocsChain }: CreateRetrievalChainParams<RunOutput>): Promise<Runnable<{
   input: string;
   chat_history?: BaseMessage[] | string;
 } & {

package/dist/chains/retrieval.d.cts.map

@@ -1 +1 @@
-{"version":3,"file":"retrieval.d.cts","names":[],"sources":["../../src/chains/retrieval.ts"],"mappings":";;;;;;;;AAaA;KAAY,0BAAA;EAA0B;;;;;;;;;;EAWpC,SAAA,EACI,sBAAA,GAEA,iBAAA,CAAkB,MAAA,eAAqB,iBAAA;EAH3C;;;;;;;EAYA,gBAAA,EAAkB,iBAAA,CAAkB,MAAA,eAAqB,SAAA;AAAA;;;AAiC3D;;;;;;;;;;;;;;;;;;;;;;;;iBAAsB,oBAAA,WAAA,CAAA;EACpB,SAAA;EACA;AAAA,GACC,0BAAA,CAA2B,SAAA,IAAa,OAAA,CACzC,QAAA;EACI,KAAA;EAAe,YAAA,GAAe,WAAA;AAAA;EAAA,CAC7B,GAAA;AAAA;EAED,OAAA,EAAS,QAAA;EAAY,MAAA,EAAQ,SAAA;AAAA;EAAA,CAAiB,GAAA;AAAA"}
+{"version":3,"file":"retrieval.d.cts","names":[],"sources":["../../src/chains/retrieval.ts"],"mappings":";;;;;;;;KAaY,2BAA2B;;;;;;;;;;;EAWrC,WACI,yBAEA,kBAAkB,qBAAqB;;;;;;;;EAS3C,kBAAkB,kBAAkB,qBAAqB;;;;;;;;;;;;;;;;;;;;;;;;;;;;iBAiCrC,qBAAqB,aACzC,WACA,oBACC,2BAA2B,aAAa,QACzC;EACI;EAAe,eAAe;;GAC7B;;EAED,SAAS;EAAY,QAAQ;;GAAiB"}

package/dist/chains/retrieval.d.ts

@@ -2,7 +2,6 @@ import { BaseMessage } from "@langchain/core/messages";
 import { Runnable, RunnableInterface } from "@langchain/core/runnables";
 import { Document, DocumentInterface } from "@langchain/core/documents";
 import { BaseRetrieverInterface } from "@langchain/core/retrievers";
-
 //#region src/chains/retrieval.d.ts
 /**
  * Parameters for the createRetrievalChain method.
@@ -54,10 +53,7 @@ type CreateRetrievalChainParams<RunOutput> = {
  * const response = await chain.invoke({ input: "..." });
  * ```
  */
-declare function createRetrievalChain<RunOutput>({
-  retriever,
-  combineDocsChain
-}: CreateRetrievalChainParams<RunOutput>): Promise<Runnable<{
+declare function createRetrievalChain<RunOutput>({ retriever, combineDocsChain }: CreateRetrievalChainParams<RunOutput>): Promise<Runnable<{
   input: string;
   chat_history?: BaseMessage[] | string;
 } & {

package/dist/chains/retrieval.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"retrieval.d.ts","names":[],"sources":["../../src/chains/retrieval.ts"],"mappings":";;;;;;;;AAaA;KAAY,0BAAA;EAA0B;;;;;;;;;;EAWpC,SAAA,EACI,sBAAA,GAEA,iBAAA,CAAkB,MAAA,eAAqB,iBAAA;EAH3C;;;;;;;EAYA,gBAAA,EAAkB,iBAAA,CAAkB,MAAA,eAAqB,SAAA;AAAA;;;AAiC3D;;;;;;;;;;;;;;;;;;;;;;;;iBAAsB,oBAAA,WAAA,CAAA;EACpB,SAAA;EACA;AAAA,GACC,0BAAA,CAA2B,SAAA,IAAa,OAAA,CACzC,QAAA;EACI,KAAA;EAAe,YAAA,GAAe,WAAA;AAAA;EAAA,CAC7B,GAAA;AAAA;EAED,OAAA,EAAS,QAAA;EAAY,MAAA,EAAQ,SAAA;AAAA;EAAA,CAAiB,GAAA;AAAA"}
+{"version":3,"file":"retrieval.d.ts","names":[],"sources":["../../src/chains/retrieval.ts"],"mappings":";;;;;;;;KAaY,2BAA2B;;;;;;;;;;;EAWrC,WACI,yBAEA,kBAAkB,qBAAqB;;;;;;;;EAS3C,kBAAkB,kBAAkB,qBAAqB;;;;;;;;;;;;;;;;;;;;;;;;;;;;iBAiCrC,qBAAqB,aACzC,WACA,oBACC,2BAA2B,aAAa,QACzC;EACI;EAAe,eAAe;;GAC7B;;EAED,SAAS;EAAY,QAAQ;;GAAiB"}

package/dist/chains/retrieval.js.map

@@ -1 +1 @@
-{"version":3,"file":"retrieval.js","names":[],"sources":["../../src/chains/retrieval.ts"],"sourcesContent":["import type { BaseRetrieverInterface } from \"@langchain/core/retrievers\";\nimport {\n  type Runnable,\n  RunnableSequence,\n  type RunnableInterface,\n  RunnablePassthrough,\n} from \"@langchain/core/runnables\";\nimport type { BaseMessage } from \"@langchain/core/messages\";\nimport type { DocumentInterface, Document } from \"@langchain/core/documents\";\n\n/**\n * Parameters for the createRetrievalChain method.\n */\nexport type CreateRetrievalChainParams<RunOutput> = {\n  /**\n   * Retriever-like object that returns list of documents. Should\n   * either be a subclass of BaseRetriever or a Runnable that returns\n   * a list of documents. If a subclass of BaseRetriever, then it\n   * is expected that an `input` key be passed in - this is what\n   * is will be used to pass into the retriever. If this is NOT a\n   * subclass of BaseRetriever, then all the inputs will be passed\n   * into this runnable, meaning that runnable should take a object\n   * as input.\n   */\n  retriever:\n    | BaseRetrieverInterface\n    // oxlint-disable-next-line @typescript-eslint/no-explicit-any\n    | RunnableInterface<Record<string, any>, DocumentInterface[]>;\n  /**\n   * Runnable that takes inputs and produces a string output.\n   * The inputs to this will be any original inputs to this chain, a new\n   * context key with the retrieved documents, and chat_history (if not present\n   * in the inputs) with a value of `[]` (to easily enable conversational\n   * retrieval).\n   */\n  // oxlint-disable-next-line @typescript-eslint/no-explicit-any\n  combineDocsChain: RunnableInterface<Record<string, any>, RunOutput>;\n};\n\nfunction isBaseRetriever(x: unknown): x is BaseRetrieverInterface {\n  return !!x && typeof (x as BaseRetrieverInterface).invoke === \"function\";\n}\n\n/**\n * Create a retrieval chain that retrieves documents and then passes them on.\n * @param {CreateRetrievalChainParams} params A params object\n *     containing a retriever and a combineDocsChain.\n * @returns An LCEL Runnable which returns a an object\n *     containing at least `context` and `answer` keys.\n * @example\n * ```typescript\n * // pnpm add langchain @langchain/openai\n *\n * import { ChatOpenAI } from \"@langchain/openai\";\n * import { pull } from \"langchain/hub\";\n * import { createRetrievalChain } from \"@langchain/classic/chains/retrieval\";\n * import { createStuffDocumentsChain } from \"@langchain/classic/chains/combine_documents\";\n *\n * const retrievalQAChatPrompt = await pull(\"langchain-ai/retrieval-qa-chat\");\n * const llm = new ChatOpenAI({ model: \"gpt-4o-mini\" });\n * const retriever = ...\n * const combineDocsChain = await createStuffDocumentsChain(...);\n * const retrievalChain = await createRetrievalChain({\n *   retriever,\n *   combineDocsChain,\n * });\n * const response = await chain.invoke({ input: \"...\" });\n * ```\n */\nexport async function createRetrievalChain<RunOutput>({\n  retriever,\n  combineDocsChain,\n}: CreateRetrievalChainParams<RunOutput>): Promise<\n  Runnable<\n    { input: string; chat_history?: BaseMessage[] | string } & {\n      [key: string]: unknown;\n    },\n    { context: Document[]; answer: RunOutput } & { [key: string]: unknown }\n  >\n> {\n  let retrieveDocumentsChain: Runnable<{ input: string }, DocumentInterface[]>;\n  if (isBaseRetriever(retriever)) {\n    retrieveDocumentsChain = RunnableSequence.from([\n      (input) => input.input,\n      retriever,\n    ]);\n  } else {\n    // TODO: Fix typing by adding withConfig to core RunnableInterface\n    retrieveDocumentsChain = retriever as Runnable;\n  }\n  const retrievalChain = RunnableSequence.from<{\n    input: string;\n    chat_history?: BaseMessage[] | string;\n  }>([\n    RunnablePassthrough.assign({\n      context: retrieveDocumentsChain.withConfig({\n        runName: \"retrieve_documents\",\n      }),\n      chat_history: (input) => input.chat_history ?? [],\n    }),\n    RunnablePassthrough.assign({\n      answer: combineDocsChain,\n    }),\n  ]).withConfig({ runName: \"retrieval_chain\" });\n  return retrievalChain;\n}\n"],"mappings":";;;;AAuCA,SAAS,gBAAgB,GAAyC;AAChE,QAAO,CAAC,CAAC,KAAK,OAAQ,EAA6B,WAAW;;;;;;;;;;;;;;;;;;;;;;;;;;;;AA6BhE,eAAsB,qBAAgC,EACpD,WACA,oBAQA;CACA,IAAI;AACJ,KAAI,gBAAgB,UAAU,CAC5B,0BAAyB,iBAAiB,KAAK,EAC5C,UAAU,MAAM,OACjB,UACD,CAAC;KAGF,0BAAyB;AAgB3B,QAduB,iBAAiB,KAGrC,CACD,oBAAoB,OAAO;EACzB,SAAS,uBAAuB,WAAW,EACzC,SAAS,sBACV,CAAC;EACF,eAAe,UAAU,MAAM,gBAAgB,EAAE;EAClD,CAAC,EACF,oBAAoB,OAAO,EACzB,QAAQ,kBACT,CAAC,CACH,CAAC,CAAC,WAAW,EAAE,SAAS,mBAAmB,CACvB"}
+{"version":3,"file":"retrieval.js","names":[],"sources":["../../src/chains/retrieval.ts"],"sourcesContent":["import type { BaseRetrieverInterface } from \"@langchain/core/retrievers\";\nimport {\n  type Runnable,\n  RunnableSequence,\n  type RunnableInterface,\n  RunnablePassthrough,\n} from \"@langchain/core/runnables\";\nimport type { BaseMessage } from \"@langchain/core/messages\";\nimport type { DocumentInterface, Document } from \"@langchain/core/documents\";\n\n/**\n * Parameters for the createRetrievalChain method.\n */\nexport type CreateRetrievalChainParams<RunOutput> = {\n  /**\n   * Retriever-like object that returns list of documents. Should\n   * either be a subclass of BaseRetriever or a Runnable that returns\n   * a list of documents. If a subclass of BaseRetriever, then it\n   * is expected that an `input` key be passed in - this is what\n   * is will be used to pass into the retriever. If this is NOT a\n   * subclass of BaseRetriever, then all the inputs will be passed\n   * into this runnable, meaning that runnable should take a object\n   * as input.\n   */\n  retriever:\n    | BaseRetrieverInterface\n    // oxlint-disable-next-line @typescript-eslint/no-explicit-any\n    | RunnableInterface<Record<string, any>, DocumentInterface[]>;\n  /**\n   * Runnable that takes inputs and produces a string output.\n   * The inputs to this will be any original inputs to this chain, a new\n   * context key with the retrieved documents, and chat_history (if not present\n   * in the inputs) with a value of `[]` (to easily enable conversational\n   * retrieval).\n   */\n  // oxlint-disable-next-line @typescript-eslint/no-explicit-any\n  combineDocsChain: RunnableInterface<Record<string, any>, RunOutput>;\n};\n\nfunction isBaseRetriever(x: unknown): x is BaseRetrieverInterface {\n  return !!x && typeof (x as BaseRetrieverInterface).invoke === \"function\";\n}\n\n/**\n * Create a retrieval chain that retrieves documents and then passes them on.\n * @param {CreateRetrievalChainParams} params A params object\n *     containing a retriever and a combineDocsChain.\n * @returns An LCEL Runnable which returns a an object\n *     containing at least `context` and `answer` keys.\n * @example\n * ```typescript\n * // pnpm add langchain @langchain/openai\n *\n * import { ChatOpenAI } from \"@langchain/openai\";\n * import { pull } from \"langchain/hub\";\n * import { createRetrievalChain } from \"@langchain/classic/chains/retrieval\";\n * import { createStuffDocumentsChain } from \"@langchain/classic/chains/combine_documents\";\n *\n * const retrievalQAChatPrompt = await pull(\"langchain-ai/retrieval-qa-chat\");\n * const llm = new ChatOpenAI({ model: \"gpt-4o-mini\" });\n * const retriever = ...\n * const combineDocsChain = await createStuffDocumentsChain(...);\n * const retrievalChain = await createRetrievalChain({\n *   retriever,\n *   combineDocsChain,\n * });\n * const response = await chain.invoke({ input: \"...\" });\n * ```\n */\nexport async function createRetrievalChain<RunOutput>({\n  retriever,\n  combineDocsChain,\n}: CreateRetrievalChainParams<RunOutput>): Promise<\n  Runnable<\n    { input: string; chat_history?: BaseMessage[] | string } & {\n      [key: string]: unknown;\n    },\n    { context: Document[]; answer: RunOutput } & { [key: string]: unknown }\n  >\n> {\n  let retrieveDocumentsChain: Runnable<{ input: string }, DocumentInterface[]>;\n  if (isBaseRetriever(retriever)) {\n    retrieveDocumentsChain = RunnableSequence.from([\n      (input) => input.input,\n      retriever,\n    ]);\n  } else {\n    // TODO: Fix typing by adding withConfig to core RunnableInterface\n    retrieveDocumentsChain = retriever as Runnable;\n  }\n  const retrievalChain = RunnableSequence.from<{\n    input: string;\n    chat_history?: BaseMessage[] | string;\n  }>([\n    RunnablePassthrough.assign({\n      context: retrieveDocumentsChain.withConfig({\n        runName: \"retrieve_documents\",\n      }),\n      chat_history: (input) => input.chat_history ?? [],\n    }),\n    RunnablePassthrough.assign({\n      answer: combineDocsChain,\n    }),\n  ]).withConfig({ runName: \"retrieval_chain\" });\n  return retrievalChain;\n}\n"],"mappings":";;;;AAuCA,SAAS,gBAAgB,GAAyC;CAChE,OAAO,CAAC,CAAC,KAAK,OAAQ,EAA6B,WAAW;AAChE;;;;;;;;;;;;;;;;;;;;;;;;;;;AA4BA,eAAsB,qBAAgC,EACpD,WACA,oBAQA;CACA,IAAI;CACJ,IAAI,gBAAgB,SAAS,GAC3B,yBAAyB,iBAAiB,KAAK,EAC5C,UAAU,MAAM,OACjB,SACF,CAAC;MAGD,yBAAyB;CAgB3B,OAduB,iBAAiB,KAGrC,CACD,oBAAoB,OAAO;EACzB,SAAS,uBAAuB,WAAW,EACzC,SAAS,qBACX,CAAC;EACD,eAAe,UAAU,MAAM,gBAAgB,CAAC;CAClD,CAAC,GACD,oBAAoB,OAAO,EACzB,QAAQ,iBACV,CAAC,CACH,CAAC,CAAC,CAAC,WAAW,EAAE,SAAS,kBAAkB,CACvB;AACtB"}

package/dist/chains/retrieval_qa.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"retrieval_qa.cjs","names":["BaseChain","loadQAStuffChain"],"sources":["../../src/chains/retrieval_qa.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport type { BaseRetrieverInterface } from \"@langchain/core/retrievers\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { BaseChain, ChainInputs } from \"./base.js\";\nimport { SerializedVectorDBQAChain } from \"./serde.js\";\nimport {\n  StuffQAChainParams,\n  loadQAStuffChain,\n} from \"./question_answering/load.js\";\n\n// oxlint-disable-next-line @typescript-eslint/no-explicit-any\nexport type LoadValues = Record<string, any>;\n\n/**\n * Interface for the input parameters of the RetrievalQAChain class.\n */\nexport interface RetrievalQAChainInput extends Omit<ChainInputs, \"memory\"> {\n  retriever: BaseRetrieverInterface;\n  combineDocumentsChain: BaseChain;\n  inputKey?: string;\n  returnSourceDocuments?: boolean;\n}\n\n/**\n * Class representing a chain for performing question-answering tasks with\n * a retrieval component.\n * @example\n * ```typescript\n * import { createStuffDocumentsChain } from \"@langchain/classic/chains/combine_documents\";\n * import { ChatPromptTemplate } from \"@langchain/core/prompts\";\n * import { createRetrievalChain } from \"@langchain/classic/chains/retrieval\";\n * import { MemoryVectorStore } from \"@langchain/classic/vectorstores/memory\";\n *\n * const documents = [...your documents here];\n * const embeddings = ...your embeddings model;\n * const llm = ...your LLM model;\n *\n * const vectorstore = await MemoryVectorStore.fromDocuments(\n *   documents,\n *   embeddings\n * );\n * const prompt = ChatPromptTemplate.fromTemplate(`Answer the user's question: {input} based on the following context {context}`);\n *\n * const combineDocsChain = await createStuffDocumentsChain({\n *   llm,\n *   prompt,\n * });\n * const retriever = vectorstore.asRetriever();\n *\n * const retrievalChain = await createRetrievalChain({\n *   combineDocsChain,\n *   retriever,\n * });\n * ```\n */\nexport class RetrievalQAChain\n  extends BaseChain\n  implements RetrievalQAChainInput\n{\n  static lc_name() {\n    return \"RetrievalQAChain\";\n  }\n\n  inputKey = \"query\";\n\n  get inputKeys() {\n    return [this.inputKey];\n  }\n\n  get outputKeys() {\n    return this.combineDocumentsChain.outputKeys.concat(\n      this.returnSourceDocuments ? [\"sourceDocuments\"] : []\n    );\n  }\n\n  retriever: BaseRetrieverInterface;\n\n  combineDocumentsChain: BaseChain;\n\n  returnSourceDocuments = false;\n\n  constructor(fields: RetrievalQAChainInput) {\n    super(fields);\n    this.retriever = fields.retriever;\n    this.combineDocumentsChain = fields.combineDocumentsChain;\n    this.inputKey = fields.inputKey ?? this.inputKey;\n    this.returnSourceDocuments =\n      fields.returnSourceDocuments ?? this.returnSourceDocuments;\n  }\n\n  /** @ignore */\n  async _call(\n    values: ChainValues,\n    runManager?: CallbackManagerForChainRun\n  ): Promise<ChainValues> {\n    if (!(this.inputKey in values)) {\n      throw new Error(`Question key \"${this.inputKey}\" not found.`);\n    }\n    const question: string = values[this.inputKey];\n    const docs = await this.retriever.invoke(\n      question,\n      runManager?.getChild(\"retriever\")\n    );\n    const inputs = { question, input_documents: docs, ...values };\n    const result = await this.combineDocumentsChain.call(\n      inputs,\n      runManager?.getChild(\"combine_documents\")\n    );\n    if (this.returnSourceDocuments) {\n      return {\n        ...result,\n        sourceDocuments: docs,\n      };\n    }\n    return result;\n  }\n\n  _chainType() {\n    return \"retrieval_qa\" as const;\n  }\n\n  static async deserialize(\n    _data: SerializedVectorDBQAChain,\n    _values: LoadValues\n  ): Promise<RetrievalQAChain> {\n    throw new Error(\"Not implemented\");\n  }\n\n  serialize(): SerializedVectorDBQAChain {\n    throw new Error(\"Not implemented\");\n  }\n\n  /**\n   * Creates a new instance of RetrievalQAChain using a BaseLanguageModel\n   * and a BaseRetriever.\n   * @param llm The BaseLanguageModel used to generate a new question.\n   * @param retriever The BaseRetriever used to retrieve relevant documents.\n   * @param options Optional parameters for the RetrievalQAChain.\n   * @returns A new instance of RetrievalQAChain.\n   */\n  static fromLLM(\n    llm: BaseLanguageModelInterface,\n    retriever: BaseRetrieverInterface,\n    options?: Partial<\n      Omit<\n        RetrievalQAChainInput,\n        \"retriever\" | \"combineDocumentsChain\" | \"index\"\n      >\n    > &\n      StuffQAChainParams\n  ): RetrievalQAChain {\n    const qaChain = loadQAStuffChain(llm, {\n      prompt: options?.prompt,\n    });\n    return new this({\n      ...options,\n      retriever,\n      combineDocumentsChain: qaChain,\n    });\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAwDA,IAAa,mBAAb,cACUA,aAAAA,UAEV;CACE,OAAO,UAAU;AACf,SAAO;;CAGT,WAAW;CAEX,IAAI,YAAY;AACd,SAAO,CAAC,KAAK,SAAS;;CAGxB,IAAI,aAAa;AACf,SAAO,KAAK,sBAAsB,WAAW,OAC3C,KAAK,wBAAwB,CAAC,kBAAkB,GAAG,EAAE,CACtD;;CAGH;CAEA;CAEA,wBAAwB;CAExB,YAAY,QAA+B;AACzC,QAAM,OAAO;AACb,OAAK,YAAY,OAAO;AACxB,OAAK,wBAAwB,OAAO;AACpC,OAAK,WAAW,OAAO,YAAY,KAAK;AACxC,OAAK,wBACH,OAAO,yBAAyB,KAAK;;;CAIzC,MAAM,MACJ,QACA,YACsB;AACtB,MAAI,EAAE,KAAK,YAAY,QACrB,OAAM,IAAI,MAAM,iBAAiB,KAAK,SAAS,cAAc;EAE/D,MAAM,WAAmB,OAAO,KAAK;EACrC,MAAM,OAAO,MAAM,KAAK,UAAU,OAChC,UACA,YAAY,SAAS,YAAY,CAClC;EACD,MAAM,SAAS;GAAE;GAAU,iBAAiB;GAAM,GAAG;GAAQ;EAC7D,MAAM,SAAS,MAAM,KAAK,sBAAsB,KAC9C,QACA,YAAY,SAAS,oBAAoB,CAC1C;AACD,MAAI,KAAK,sBACP,QAAO;GACL,GAAG;GACH,iBAAiB;GAClB;AAEH,SAAO;;CAGT,aAAa;AACX,SAAO;;CAGT,aAAa,YACX,OACA,SAC2B;AAC3B,QAAM,IAAI,MAAM,kBAAkB;;CAGpC,YAAuC;AACrC,QAAM,IAAI,MAAM,kBAAkB;;;;;;;;;;CAWpC,OAAO,QACL,KACA,WACA,SAOkB;EAClB,MAAM,UAAUC,aAAAA,iBAAiB,KAAK,EACpC,QAAQ,SAAS,QAClB,CAAC;AACF,SAAO,IAAI,KAAK;GACd,GAAG;GACH;GACA,uBAAuB;GACxB,CAAC"}
+{"version":3,"file":"retrieval_qa.cjs","names":["BaseChain","loadQAStuffChain"],"sources":["../../src/chains/retrieval_qa.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport type { BaseRetrieverInterface } from \"@langchain/core/retrievers\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { BaseChain, ChainInputs } from \"./base.js\";\nimport { SerializedVectorDBQAChain } from \"./serde.js\";\nimport {\n  StuffQAChainParams,\n  loadQAStuffChain,\n} from \"./question_answering/load.js\";\n\n// oxlint-disable-next-line @typescript-eslint/no-explicit-any\nexport type LoadValues = Record<string, any>;\n\n/**\n * Interface for the input parameters of the RetrievalQAChain class.\n */\nexport interface RetrievalQAChainInput extends Omit<ChainInputs, \"memory\"> {\n  retriever: BaseRetrieverInterface;\n  combineDocumentsChain: BaseChain;\n  inputKey?: string;\n  returnSourceDocuments?: boolean;\n}\n\n/**\n * Class representing a chain for performing question-answering tasks with\n * a retrieval component.\n * @example\n * ```typescript\n * import { createStuffDocumentsChain } from \"@langchain/classic/chains/combine_documents\";\n * import { ChatPromptTemplate } from \"@langchain/core/prompts\";\n * import { createRetrievalChain } from \"@langchain/classic/chains/retrieval\";\n * import { MemoryVectorStore } from \"@langchain/classic/vectorstores/memory\";\n *\n * const documents = [...your documents here];\n * const embeddings = ...your embeddings model;\n * const llm = ...your LLM model;\n *\n * const vectorstore = await MemoryVectorStore.fromDocuments(\n *   documents,\n *   embeddings\n * );\n * const prompt = ChatPromptTemplate.fromTemplate(`Answer the user's question: {input} based on the following context {context}`);\n *\n * const combineDocsChain = await createStuffDocumentsChain({\n *   llm,\n *   prompt,\n * });\n * const retriever = vectorstore.asRetriever();\n *\n * const retrievalChain = await createRetrievalChain({\n *   combineDocsChain,\n *   retriever,\n * });\n * ```\n */\nexport class RetrievalQAChain\n  extends BaseChain\n  implements RetrievalQAChainInput\n{\n  static lc_name() {\n    return \"RetrievalQAChain\";\n  }\n\n  inputKey = \"query\";\n\n  get inputKeys() {\n    return [this.inputKey];\n  }\n\n  get outputKeys() {\n    return this.combineDocumentsChain.outputKeys.concat(\n      this.returnSourceDocuments ? [\"sourceDocuments\"] : []\n    );\n  }\n\n  retriever: BaseRetrieverInterface;\n\n  combineDocumentsChain: BaseChain;\n\n  returnSourceDocuments = false;\n\n  constructor(fields: RetrievalQAChainInput) {\n    super(fields);\n    this.retriever = fields.retriever;\n    this.combineDocumentsChain = fields.combineDocumentsChain;\n    this.inputKey = fields.inputKey ?? this.inputKey;\n    this.returnSourceDocuments =\n      fields.returnSourceDocuments ?? this.returnSourceDocuments;\n  }\n\n  /** @ignore */\n  async _call(\n    values: ChainValues,\n    runManager?: CallbackManagerForChainRun\n  ): Promise<ChainValues> {\n    if (!(this.inputKey in values)) {\n      throw new Error(`Question key \"${this.inputKey}\" not found.`);\n    }\n    const question: string = values[this.inputKey];\n    const docs = await this.retriever.invoke(\n      question,\n      runManager?.getChild(\"retriever\")\n    );\n    const inputs = { question, input_documents: docs, ...values };\n    const result = await this.combineDocumentsChain.call(\n      inputs,\n      runManager?.getChild(\"combine_documents\")\n    );\n    if (this.returnSourceDocuments) {\n      return {\n        ...result,\n        sourceDocuments: docs,\n      };\n    }\n    return result;\n  }\n\n  _chainType() {\n    return \"retrieval_qa\" as const;\n  }\n\n  static async deserialize(\n    _data: SerializedVectorDBQAChain,\n    _values: LoadValues\n  ): Promise<RetrievalQAChain> {\n    throw new Error(\"Not implemented\");\n  }\n\n  serialize(): SerializedVectorDBQAChain {\n    throw new Error(\"Not implemented\");\n  }\n\n  /**\n   * Creates a new instance of RetrievalQAChain using a BaseLanguageModel\n   * and a BaseRetriever.\n   * @param llm The BaseLanguageModel used to generate a new question.\n   * @param retriever The BaseRetriever used to retrieve relevant documents.\n   * @param options Optional parameters for the RetrievalQAChain.\n   * @returns A new instance of RetrievalQAChain.\n   */\n  static fromLLM(\n    llm: BaseLanguageModelInterface,\n    retriever: BaseRetrieverInterface,\n    options?: Partial<\n      Omit<\n        RetrievalQAChainInput,\n        \"retriever\" | \"combineDocumentsChain\" | \"index\"\n      >\n    > &\n      StuffQAChainParams\n  ): RetrievalQAChain {\n    const qaChain = loadQAStuffChain(llm, {\n      prompt: options?.prompt,\n    });\n    return new this({\n      ...options,\n      retriever,\n      combineDocumentsChain: qaChain,\n    });\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAwDA,IAAa,mBAAb,cACUA,aAAAA,UAEV;CACE,OAAO,UAAU;EACf,OAAO;CACT;CAEA,WAAW;CAEX,IAAI,YAAY;EACd,OAAO,CAAC,KAAK,QAAQ;CACvB;CAEA,IAAI,aAAa;EACf,OAAO,KAAK,sBAAsB,WAAW,OAC3C,KAAK,wBAAwB,CAAC,iBAAiB,IAAI,CAAC,CACtD;CACF;CAEA;CAEA;CAEA,wBAAwB;CAExB,YAAY,QAA+B;EACzC,MAAM,MAAM;EACZ,KAAK,YAAY,OAAO;EACxB,KAAK,wBAAwB,OAAO;EACpC,KAAK,WAAW,OAAO,YAAY,KAAK;EACxC,KAAK,wBACH,OAAO,yBAAyB,KAAK;CACzC;;CAGA,MAAM,MACJ,QACA,YACsB;EACtB,IAAI,EAAE,KAAK,YAAY,SACrB,MAAM,IAAI,MAAM,iBAAiB,KAAK,SAAS,aAAa;EAE9D,MAAM,WAAmB,OAAO,KAAK;EACrC,MAAM,OAAO,MAAM,KAAK,UAAU,OAChC,UACA,YAAY,SAAS,WAAW,CAClC;EACA,MAAM,SAAS;GAAE;GAAU,iBAAiB;GAAM,GAAG;EAAO;EAC5D,MAAM,SAAS,MAAM,KAAK,sBAAsB,KAC9C,QACA,YAAY,SAAS,mBAAmB,CAC1C;EACA,IAAI,KAAK,uBACP,OAAO;GACL,GAAG;GACH,iBAAiB;EACnB;EAEF,OAAO;CACT;CAEA,aAAa;EACX,OAAO;CACT;CAEA,aAAa,YACX,OACA,SAC2B;EAC3B,MAAM,IAAI,MAAM,iBAAiB;CACnC;CAEA,YAAuC;EACrC,MAAM,IAAI,MAAM,iBAAiB;CACnC;;;;;;;;;CAUA,OAAO,QACL,KACA,WACA,SAOkB;EAClB,MAAM,UAAUC,aAAAA,iBAAiB,KAAK,EACpC,QAAQ,SAAS,OACnB,CAAC;EACD,OAAO,IAAI,KAAK;GACd,GAAG;GACH;GACA,uBAAuB;EACzB,CAAC;CACH;AACF"}

package/dist/chains/retrieval_qa.d.cts

@@ -5,7 +5,6 @@ import { ChainValues } from "@langchain/core/utils/types";
 import { BaseLanguageModelInterface } from "@langchain/core/language_models/base";
 import { CallbackManagerForChainRun } from "@langchain/core/callbacks/manager";
 import { BaseRetrieverInterface } from "@langchain/core/retrievers";
-
 //#region src/chains/retrieval_qa.d.ts
 type LoadValues = Record<string, any>;
 /**
@@ -74,5 +73,5 @@ declare class RetrievalQAChain extends BaseChain implements RetrievalQAChainInpu
   static fromLLM(llm: BaseLanguageModelInterface, retriever: BaseRetrieverInterface, options?: Partial<Omit<RetrievalQAChainInput, "retriever" | "combineDocumentsChain" | "index">> & StuffQAChainParams): RetrievalQAChain;
 }
 //#endregion
-export { RetrievalQAChain, RetrievalQAChainInput };
+export { LoadValues, RetrievalQAChain, RetrievalQAChainInput };
 //# sourceMappingURL=retrieval_qa.d.cts.map

package/dist/chains/retrieval_qa.d.cts.map

@@ -1 +1 @@
-{"version":3,"file":"retrieval_qa.d.cts","names":[],"sources":["../../src/chains/retrieval_qa.ts"],"mappings":";;;;;;;;;KAYY,UAAA,GAAa,MAAA;;AAAzB;;UAKiB,qBAAA,SAA8B,IAAA,CAAK,WAAA;EAClD,SAAA,EAAW,sBAAA;EACX,qBAAA,EAAuB,SAAA;EACvB,QAAA;EACA,qBAAA;AAAA;;;;;;;;;;;;;;;;;AAmCF;;;;;;;;;;;;;;;;cAAa,gBAAA,SACH,SAAA,YACG,qBAAA;EAAA,OAEJ,OAAA,CAAA;EAIP,QAAA;EAAA,IAEI,SAAA,CAAA;EAAA,IAIA,UAAA,CAAA;EAMJ,SAAA,EAAW,sBAAA;EAEX,qBAAA,EAAuB,SAAA;EAEvB,qBAAA;EAEA,WAAA,CAAY,MAAA,EAAQ,qBAAA;EAxBY;EAkC1B,KAAA,CACJ,MAAA,EAAQ,WAAA,EACR,UAAA,GAAa,0BAAA,GACZ,OAAA,CAAQ,WAAA;EAuBX,UAAA,CAAA;EAAA,OAIa,WAAA,CACX,KAAA,EAAO,yBAAA,EACP,OAAA,EAAS,UAAA,GACR,OAAA,CAAQ,gBAAA;EAIX,SAAA,CAAA,GAAa,yBAAA;EA/DT;;;;;;;;EAAA,OA2EG,OAAA,CACL,GAAA,EAAK,0BAAA,EACL,SAAA,EAAW,sBAAA,EACX,OAAA,GAAU,OAAA,CACR,IAAA,CACE,qBAAA,sDAIF,kBAAA,GACD,gBAAA;AAAA"}
+{"version":3,"file":"retrieval_qa.d.cts","names":[],"sources":["../../src/chains/retrieval_qa.ts"],"mappings":";;;;;;;;KAYY,aAAa;;;;UAKR,8BAA8B,KAAK;EAClD,WAAW;EACX,uBAAuB;EACvB;EACA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;cAmCW,yBACH,qBACG;SAEJ;EAIP;MAEI;MAIA;EAMJ,WAAW;EAEX,uBAAuB;EAEvB;EAEA,YAAY,QAAQ;;EAUd,MACJ,QAAQ,aACR,aAAa,6BACZ,QAAQ;EAuBX;SAIa,YACX,OAAO,2BACP,SAAS,aACR,QAAQ;EAIX,aAAa;;;;;;;;;SAYN,QACL,KAAK,4BACL,WAAW,wBACX,UAAU,QACR,KACE,2EAIF,qBACD"}

package/dist/chains/retrieval_qa.d.ts

@@ -5,7 +5,6 @@ import { BaseLanguageModelInterface } from "@langchain/core/language_models/base
 import { CallbackManagerForChainRun } from "@langchain/core/callbacks/manager";
 import { ChainValues } from "@langchain/core/utils/types";
 import { BaseRetrieverInterface } from "@langchain/core/retrievers";
-
 //#region src/chains/retrieval_qa.d.ts
 type LoadValues = Record<string, any>;
 /**
@@ -74,5 +73,5 @@ declare class RetrievalQAChain extends BaseChain implements RetrievalQAChainInpu
   static fromLLM(llm: BaseLanguageModelInterface, retriever: BaseRetrieverInterface, options?: Partial<Omit<RetrievalQAChainInput, "retriever" | "combineDocumentsChain" | "index">> & StuffQAChainParams): RetrievalQAChain;
 }
 //#endregion
-export { RetrievalQAChain, RetrievalQAChainInput };
+export { LoadValues, RetrievalQAChain, RetrievalQAChainInput };
 //# sourceMappingURL=retrieval_qa.d.ts.map

package/dist/chains/retrieval_qa.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"retrieval_qa.d.ts","names":[],"sources":["../../src/chains/retrieval_qa.ts"],"mappings":";;;;;;;;;KAYY,UAAA,GAAa,MAAA;;AAAzB;;UAKiB,qBAAA,SAA8B,IAAA,CAAK,WAAA;EAClD,SAAA,EAAW,sBAAA;EACX,qBAAA,EAAuB,SAAA;EACvB,QAAA;EACA,qBAAA;AAAA;;;;;;;;;;;;;;;;;AAmCF;;;;;;;;;;;;;;;;cAAa,gBAAA,SACH,SAAA,YACG,qBAAA;EAAA,OAEJ,OAAA,CAAA;EAIP,QAAA;EAAA,IAEI,SAAA,CAAA;EAAA,IAIA,UAAA,CAAA;EAMJ,SAAA,EAAW,sBAAA;EAEX,qBAAA,EAAuB,SAAA;EAEvB,qBAAA;EAEA,WAAA,CAAY,MAAA,EAAQ,qBAAA;EAxBY;EAkC1B,KAAA,CACJ,MAAA,EAAQ,WAAA,EACR,UAAA,GAAa,0BAAA,GACZ,OAAA,CAAQ,WAAA;EAuBX,UAAA,CAAA;EAAA,OAIa,WAAA,CACX,KAAA,EAAO,yBAAA,EACP,OAAA,EAAS,UAAA,GACR,OAAA,CAAQ,gBAAA;EAIX,SAAA,CAAA,GAAa,yBAAA;EA/DT;;;;;;;;EAAA,OA2EG,OAAA,CACL,GAAA,EAAK,0BAAA,EACL,SAAA,EAAW,sBAAA,EACX,OAAA,GAAU,OAAA,CACR,IAAA,CACE,qBAAA,sDAIF,kBAAA,GACD,gBAAA;AAAA"}
+{"version":3,"file":"retrieval_qa.d.ts","names":[],"sources":["../../src/chains/retrieval_qa.ts"],"mappings":";;;;;;;;KAYY,aAAa;;;;UAKR,8BAA8B,KAAK;EAClD,WAAW;EACX,uBAAuB;EACvB;EACA;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;cAmCW,yBACH,qBACG;SAEJ;EAIP;MAEI;MAIA;EAMJ,WAAW;EAEX,uBAAuB;EAEvB;EAEA,YAAY,QAAQ;;EAUd,MACJ,QAAQ,aACR,aAAa,6BACZ,QAAQ;EAuBX;SAIa,YACX,OAAO,2BACP,SAAS,aACR,QAAQ;EAIX,aAAa;;;;;;;;;SAYN,QACL,KAAK,4BACL,WAAW,wBACX,UAAU,QACR,KACE,2EAIF,qBACD"}

package/dist/chains/retrieval_qa.js.map

@@ -1 +1 @@
-{"version":3,"file":"retrieval_qa.js","names":[],"sources":["../../src/chains/retrieval_qa.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport type { BaseRetrieverInterface } from \"@langchain/core/retrievers\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { BaseChain, ChainInputs } from \"./base.js\";\nimport { SerializedVectorDBQAChain } from \"./serde.js\";\nimport {\n  StuffQAChainParams,\n  loadQAStuffChain,\n} from \"./question_answering/load.js\";\n\n// oxlint-disable-next-line @typescript-eslint/no-explicit-any\nexport type LoadValues = Record<string, any>;\n\n/**\n * Interface for the input parameters of the RetrievalQAChain class.\n */\nexport interface RetrievalQAChainInput extends Omit<ChainInputs, \"memory\"> {\n  retriever: BaseRetrieverInterface;\n  combineDocumentsChain: BaseChain;\n  inputKey?: string;\n  returnSourceDocuments?: boolean;\n}\n\n/**\n * Class representing a chain for performing question-answering tasks with\n * a retrieval component.\n * @example\n * ```typescript\n * import { createStuffDocumentsChain } from \"@langchain/classic/chains/combine_documents\";\n * import { ChatPromptTemplate } from \"@langchain/core/prompts\";\n * import { createRetrievalChain } from \"@langchain/classic/chains/retrieval\";\n * import { MemoryVectorStore } from \"@langchain/classic/vectorstores/memory\";\n *\n * const documents = [...your documents here];\n * const embeddings = ...your embeddings model;\n * const llm = ...your LLM model;\n *\n * const vectorstore = await MemoryVectorStore.fromDocuments(\n *   documents,\n *   embeddings\n * );\n * const prompt = ChatPromptTemplate.fromTemplate(`Answer the user's question: {input} based on the following context {context}`);\n *\n * const combineDocsChain = await createStuffDocumentsChain({\n *   llm,\n *   prompt,\n * });\n * const retriever = vectorstore.asRetriever();\n *\n * const retrievalChain = await createRetrievalChain({\n *   combineDocsChain,\n *   retriever,\n * });\n * ```\n */\nexport class RetrievalQAChain\n  extends BaseChain\n  implements RetrievalQAChainInput\n{\n  static lc_name() {\n    return \"RetrievalQAChain\";\n  }\n\n  inputKey = \"query\";\n\n  get inputKeys() {\n    return [this.inputKey];\n  }\n\n  get outputKeys() {\n    return this.combineDocumentsChain.outputKeys.concat(\n      this.returnSourceDocuments ? [\"sourceDocuments\"] : []\n    );\n  }\n\n  retriever: BaseRetrieverInterface;\n\n  combineDocumentsChain: BaseChain;\n\n  returnSourceDocuments = false;\n\n  constructor(fields: RetrievalQAChainInput) {\n    super(fields);\n    this.retriever = fields.retriever;\n    this.combineDocumentsChain = fields.combineDocumentsChain;\n    this.inputKey = fields.inputKey ?? this.inputKey;\n    this.returnSourceDocuments =\n      fields.returnSourceDocuments ?? this.returnSourceDocuments;\n  }\n\n  /** @ignore */\n  async _call(\n    values: ChainValues,\n    runManager?: CallbackManagerForChainRun\n  ): Promise<ChainValues> {\n    if (!(this.inputKey in values)) {\n      throw new Error(`Question key \"${this.inputKey}\" not found.`);\n    }\n    const question: string = values[this.inputKey];\n    const docs = await this.retriever.invoke(\n      question,\n      runManager?.getChild(\"retriever\")\n    );\n    const inputs = { question, input_documents: docs, ...values };\n    const result = await this.combineDocumentsChain.call(\n      inputs,\n      runManager?.getChild(\"combine_documents\")\n    );\n    if (this.returnSourceDocuments) {\n      return {\n        ...result,\n        sourceDocuments: docs,\n      };\n    }\n    return result;\n  }\n\n  _chainType() {\n    return \"retrieval_qa\" as const;\n  }\n\n  static async deserialize(\n    _data: SerializedVectorDBQAChain,\n    _values: LoadValues\n  ): Promise<RetrievalQAChain> {\n    throw new Error(\"Not implemented\");\n  }\n\n  serialize(): SerializedVectorDBQAChain {\n    throw new Error(\"Not implemented\");\n  }\n\n  /**\n   * Creates a new instance of RetrievalQAChain using a BaseLanguageModel\n   * and a BaseRetriever.\n   * @param llm The BaseLanguageModel used to generate a new question.\n   * @param retriever The BaseRetriever used to retrieve relevant documents.\n   * @param options Optional parameters for the RetrievalQAChain.\n   * @returns A new instance of RetrievalQAChain.\n   */\n  static fromLLM(\n    llm: BaseLanguageModelInterface,\n    retriever: BaseRetrieverInterface,\n    options?: Partial<\n      Omit<\n        RetrievalQAChainInput,\n        \"retriever\" | \"combineDocumentsChain\" | \"index\"\n      >\n    > &\n      StuffQAChainParams\n  ): RetrievalQAChain {\n    const qaChain = loadQAStuffChain(llm, {\n      prompt: options?.prompt,\n    });\n    return new this({\n      ...options,\n      retriever,\n      combineDocumentsChain: qaChain,\n    });\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAwDA,IAAa,mBAAb,cACU,UAEV;CACE,OAAO,UAAU;AACf,SAAO;;CAGT,WAAW;CAEX,IAAI,YAAY;AACd,SAAO,CAAC,KAAK,SAAS;;CAGxB,IAAI,aAAa;AACf,SAAO,KAAK,sBAAsB,WAAW,OAC3C,KAAK,wBAAwB,CAAC,kBAAkB,GAAG,EAAE,CACtD;;CAGH;CAEA;CAEA,wBAAwB;CAExB,YAAY,QAA+B;AACzC,QAAM,OAAO;AACb,OAAK,YAAY,OAAO;AACxB,OAAK,wBAAwB,OAAO;AACpC,OAAK,WAAW,OAAO,YAAY,KAAK;AACxC,OAAK,wBACH,OAAO,yBAAyB,KAAK;;;CAIzC,MAAM,MACJ,QACA,YACsB;AACtB,MAAI,EAAE,KAAK,YAAY,QACrB,OAAM,IAAI,MAAM,iBAAiB,KAAK,SAAS,cAAc;EAE/D,MAAM,WAAmB,OAAO,KAAK;EACrC,MAAM,OAAO,MAAM,KAAK,UAAU,OAChC,UACA,YAAY,SAAS,YAAY,CAClC;EACD,MAAM,SAAS;GAAE;GAAU,iBAAiB;GAAM,GAAG;GAAQ;EAC7D,MAAM,SAAS,MAAM,KAAK,sBAAsB,KAC9C,QACA,YAAY,SAAS,oBAAoB,CAC1C;AACD,MAAI,KAAK,sBACP,QAAO;GACL,GAAG;GACH,iBAAiB;GAClB;AAEH,SAAO;;CAGT,aAAa;AACX,SAAO;;CAGT,aAAa,YACX,OACA,SAC2B;AAC3B,QAAM,IAAI,MAAM,kBAAkB;;CAGpC,YAAuC;AACrC,QAAM,IAAI,MAAM,kBAAkB;;;;;;;;;;CAWpC,OAAO,QACL,KACA,WACA,SAOkB;EAClB,MAAM,UAAU,iBAAiB,KAAK,EACpC,QAAQ,SAAS,QAClB,CAAC;AACF,SAAO,IAAI,KAAK;GACd,GAAG;GACH;GACA,uBAAuB;GACxB,CAAC"}
+{"version":3,"file":"retrieval_qa.js","names":[],"sources":["../../src/chains/retrieval_qa.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport type { BaseRetrieverInterface } from \"@langchain/core/retrievers\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { BaseChain, ChainInputs } from \"./base.js\";\nimport { SerializedVectorDBQAChain } from \"./serde.js\";\nimport {\n  StuffQAChainParams,\n  loadQAStuffChain,\n} from \"./question_answering/load.js\";\n\n// oxlint-disable-next-line @typescript-eslint/no-explicit-any\nexport type LoadValues = Record<string, any>;\n\n/**\n * Interface for the input parameters of the RetrievalQAChain class.\n */\nexport interface RetrievalQAChainInput extends Omit<ChainInputs, \"memory\"> {\n  retriever: BaseRetrieverInterface;\n  combineDocumentsChain: BaseChain;\n  inputKey?: string;\n  returnSourceDocuments?: boolean;\n}\n\n/**\n * Class representing a chain for performing question-answering tasks with\n * a retrieval component.\n * @example\n * ```typescript\n * import { createStuffDocumentsChain } from \"@langchain/classic/chains/combine_documents\";\n * import { ChatPromptTemplate } from \"@langchain/core/prompts\";\n * import { createRetrievalChain } from \"@langchain/classic/chains/retrieval\";\n * import { MemoryVectorStore } from \"@langchain/classic/vectorstores/memory\";\n *\n * const documents = [...your documents here];\n * const embeddings = ...your embeddings model;\n * const llm = ...your LLM model;\n *\n * const vectorstore = await MemoryVectorStore.fromDocuments(\n *   documents,\n *   embeddings\n * );\n * const prompt = ChatPromptTemplate.fromTemplate(`Answer the user's question: {input} based on the following context {context}`);\n *\n * const combineDocsChain = await createStuffDocumentsChain({\n *   llm,\n *   prompt,\n * });\n * const retriever = vectorstore.asRetriever();\n *\n * const retrievalChain = await createRetrievalChain({\n *   combineDocsChain,\n *   retriever,\n * });\n * ```\n */\nexport class RetrievalQAChain\n  extends BaseChain\n  implements RetrievalQAChainInput\n{\n  static lc_name() {\n    return \"RetrievalQAChain\";\n  }\n\n  inputKey = \"query\";\n\n  get inputKeys() {\n    return [this.inputKey];\n  }\n\n  get outputKeys() {\n    return this.combineDocumentsChain.outputKeys.concat(\n      this.returnSourceDocuments ? [\"sourceDocuments\"] : []\n    );\n  }\n\n  retriever: BaseRetrieverInterface;\n\n  combineDocumentsChain: BaseChain;\n\n  returnSourceDocuments = false;\n\n  constructor(fields: RetrievalQAChainInput) {\n    super(fields);\n    this.retriever = fields.retriever;\n    this.combineDocumentsChain = fields.combineDocumentsChain;\n    this.inputKey = fields.inputKey ?? this.inputKey;\n    this.returnSourceDocuments =\n      fields.returnSourceDocuments ?? this.returnSourceDocuments;\n  }\n\n  /** @ignore */\n  async _call(\n    values: ChainValues,\n    runManager?: CallbackManagerForChainRun\n  ): Promise<ChainValues> {\n    if (!(this.inputKey in values)) {\n      throw new Error(`Question key \"${this.inputKey}\" not found.`);\n    }\n    const question: string = values[this.inputKey];\n    const docs = await this.retriever.invoke(\n      question,\n      runManager?.getChild(\"retriever\")\n    );\n    const inputs = { question, input_documents: docs, ...values };\n    const result = await this.combineDocumentsChain.call(\n      inputs,\n      runManager?.getChild(\"combine_documents\")\n    );\n    if (this.returnSourceDocuments) {\n      return {\n        ...result,\n        sourceDocuments: docs,\n      };\n    }\n    return result;\n  }\n\n  _chainType() {\n    return \"retrieval_qa\" as const;\n  }\n\n  static async deserialize(\n    _data: SerializedVectorDBQAChain,\n    _values: LoadValues\n  ): Promise<RetrievalQAChain> {\n    throw new Error(\"Not implemented\");\n  }\n\n  serialize(): SerializedVectorDBQAChain {\n    throw new Error(\"Not implemented\");\n  }\n\n  /**\n   * Creates a new instance of RetrievalQAChain using a BaseLanguageModel\n   * and a BaseRetriever.\n   * @param llm The BaseLanguageModel used to generate a new question.\n   * @param retriever The BaseRetriever used to retrieve relevant documents.\n   * @param options Optional parameters for the RetrievalQAChain.\n   * @returns A new instance of RetrievalQAChain.\n   */\n  static fromLLM(\n    llm: BaseLanguageModelInterface,\n    retriever: BaseRetrieverInterface,\n    options?: Partial<\n      Omit<\n        RetrievalQAChainInput,\n        \"retriever\" | \"combineDocumentsChain\" | \"index\"\n      >\n    > &\n      StuffQAChainParams\n  ): RetrievalQAChain {\n    const qaChain = loadQAStuffChain(llm, {\n      prompt: options?.prompt,\n    });\n    return new this({\n      ...options,\n      retriever,\n      combineDocumentsChain: qaChain,\n    });\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAwDA,IAAa,mBAAb,cACU,UAEV;CACE,OAAO,UAAU;EACf,OAAO;CACT;CAEA,WAAW;CAEX,IAAI,YAAY;EACd,OAAO,CAAC,KAAK,QAAQ;CACvB;CAEA,IAAI,aAAa;EACf,OAAO,KAAK,sBAAsB,WAAW,OAC3C,KAAK,wBAAwB,CAAC,iBAAiB,IAAI,CAAC,CACtD;CACF;CAEA;CAEA;CAEA,wBAAwB;CAExB,YAAY,QAA+B;EACzC,MAAM,MAAM;EACZ,KAAK,YAAY,OAAO;EACxB,KAAK,wBAAwB,OAAO;EACpC,KAAK,WAAW,OAAO,YAAY,KAAK;EACxC,KAAK,wBACH,OAAO,yBAAyB,KAAK;CACzC;;CAGA,MAAM,MACJ,QACA,YACsB;EACtB,IAAI,EAAE,KAAK,YAAY,SACrB,MAAM,IAAI,MAAM,iBAAiB,KAAK,SAAS,aAAa;EAE9D,MAAM,WAAmB,OAAO,KAAK;EACrC,MAAM,OAAO,MAAM,KAAK,UAAU,OAChC,UACA,YAAY,SAAS,WAAW,CAClC;EACA,MAAM,SAAS;GAAE;GAAU,iBAAiB;GAAM,GAAG;EAAO;EAC5D,MAAM,SAAS,MAAM,KAAK,sBAAsB,KAC9C,QACA,YAAY,SAAS,mBAAmB,CAC1C;EACA,IAAI,KAAK,uBACP,OAAO;GACL,GAAG;GACH,iBAAiB;EACnB;EAEF,OAAO;CACT;CAEA,aAAa;EACX,OAAO;CACT;CAEA,aAAa,YACX,OACA,SAC2B;EAC3B,MAAM,IAAI,MAAM,iBAAiB;CACnC;CAEA,YAAuC;EACrC,MAAM,IAAI,MAAM,iBAAiB;CACnC;;;;;;;;;CAUA,OAAO,QACL,KACA,WACA,SAOkB;EAClB,MAAM,UAAU,iBAAiB,KAAK,EACpC,QAAQ,SAAS,OACnB,CAAC;EACD,OAAO,IAAI,KAAK;GACd,GAAG;GACH;GACA,uBAAuB;EACzB,CAAC;CACH;AACF"}

package/dist/chains/router/llm_router.cjs.map

@@ -1 +1 @@
-{"version":3,"file":"llm_router.cjs","names":["RouterChain","LLMChain"],"sources":["../../../src/chains/router/llm_router.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { LLMChain } from \"../../chains/llm_chain.js\";\nimport { RouterChain } from \"./multi_route.js\";\nimport { ChainInputs } from \"../../chains/base.js\";\n\n/**\n * A type that represents the output schema of a router chain. It defines\n * the structure of the output data returned by the router chain.\n */\nexport type RouterOutputSchema = {\n  destination: string;\n  next_inputs: { [key: string]: string };\n};\n\n/**\n * An interface that extends the default ChainInputs interface and adds an\n * additional \"llmChain\" property.\n */\nexport interface LLMRouterChainInput extends ChainInputs {\n  llmChain: LLMChain<RouterOutputSchema>;\n}\n\n/**\n * A class that represents an LLM router chain in the LangChain framework.\n * It extends the RouterChain class and implements the LLMRouterChainInput\n * interface. It provides additional functionality specific to LLMs and\n * routing based on LLM predictions.\n */\nexport class LLMRouterChain extends RouterChain implements LLMRouterChainInput {\n  llmChain: LLMChain<RouterOutputSchema>;\n\n  constructor(fields: LLMRouterChainInput) {\n    super(fields);\n    this.llmChain = fields.llmChain;\n  }\n\n  get inputKeys(): string[] {\n    return this.llmChain.inputKeys;\n  }\n\n  async _call(\n    values: ChainValues,\n    runManager?: CallbackManagerForChainRun | undefined\n  ): Promise<RouterOutputSchema> {\n    return this.llmChain.predict(values, runManager?.getChild());\n  }\n\n  _chainType(): string {\n    return \"llm_router_chain\";\n  }\n\n  /**\n   * A static method that creates an instance of LLMRouterChain from a\n   * BaseLanguageModel and a BasePromptTemplate. It takes in an optional\n   * options object and returns an instance of LLMRouterChain with the\n   * specified LLMChain.\n   * @param llm A BaseLanguageModel instance.\n   * @param prompt A BasePromptTemplate instance.\n   * @param options Optional LLMRouterChainInput object, excluding \"llmChain\".\n   * @returns An instance of LLMRouterChain.\n   */\n  static fromLLM(\n    llm: BaseLanguageModelInterface,\n    prompt: BasePromptTemplate,\n    options?: Omit<LLMRouterChainInput, \"llmChain\">\n  ) {\n    const llmChain = new LLMChain<RouterOutputSchema>({ llm, prompt });\n    return new LLMRouterChain({ ...options, llmChain });\n  }\n}\n"],"mappings":";;;;;;;;;AA+BA,IAAa,iBAAb,MAAa,uBAAuBA,oBAAAA,YAA2C;CAC7E;CAEA,YAAY,QAA6B;AACvC,QAAM,OAAO;AACb,OAAK,WAAW,OAAO;;CAGzB,IAAI,YAAsB;AACxB,SAAO,KAAK,SAAS;;CAGvB,MAAM,MACJ,QACA,YAC6B;AAC7B,SAAO,KAAK,SAAS,QAAQ,QAAQ,YAAY,UAAU,CAAC;;CAG9D,aAAqB;AACnB,SAAO;;;;;;;;;;;;CAaT,OAAO,QACL,KACA,QACA,SACA;EACA,MAAM,WAAW,IAAIC,kBAAAA,SAA6B;GAAE;GAAK;GAAQ,CAAC;AAClE,SAAO,IAAI,eAAe;GAAE,GAAG;GAAS;GAAU,CAAC"}
+{"version":3,"file":"llm_router.cjs","names":["RouterChain","LLMChain"],"sources":["../../../src/chains/router/llm_router.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { LLMChain } from \"../../chains/llm_chain.js\";\nimport { RouterChain } from \"./multi_route.js\";\nimport { ChainInputs } from \"../../chains/base.js\";\n\n/**\n * A type that represents the output schema of a router chain. It defines\n * the structure of the output data returned by the router chain.\n */\nexport type RouterOutputSchema = {\n  destination: string;\n  next_inputs: { [key: string]: string };\n};\n\n/**\n * An interface that extends the default ChainInputs interface and adds an\n * additional \"llmChain\" property.\n */\nexport interface LLMRouterChainInput extends ChainInputs {\n  llmChain: LLMChain<RouterOutputSchema>;\n}\n\n/**\n * A class that represents an LLM router chain in the LangChain framework.\n * It extends the RouterChain class and implements the LLMRouterChainInput\n * interface. It provides additional functionality specific to LLMs and\n * routing based on LLM predictions.\n */\nexport class LLMRouterChain extends RouterChain implements LLMRouterChainInput {\n  llmChain: LLMChain<RouterOutputSchema>;\n\n  constructor(fields: LLMRouterChainInput) {\n    super(fields);\n    this.llmChain = fields.llmChain;\n  }\n\n  get inputKeys(): string[] {\n    return this.llmChain.inputKeys;\n  }\n\n  async _call(\n    values: ChainValues,\n    runManager?: CallbackManagerForChainRun | undefined\n  ): Promise<RouterOutputSchema> {\n    return this.llmChain.predict(values, runManager?.getChild());\n  }\n\n  _chainType(): string {\n    return \"llm_router_chain\";\n  }\n\n  /**\n   * A static method that creates an instance of LLMRouterChain from a\n   * BaseLanguageModel and a BasePromptTemplate. It takes in an optional\n   * options object and returns an instance of LLMRouterChain with the\n   * specified LLMChain.\n   * @param llm A BaseLanguageModel instance.\n   * @param prompt A BasePromptTemplate instance.\n   * @param options Optional LLMRouterChainInput object, excluding \"llmChain\".\n   * @returns An instance of LLMRouterChain.\n   */\n  static fromLLM(\n    llm: BaseLanguageModelInterface,\n    prompt: BasePromptTemplate,\n    options?: Omit<LLMRouterChainInput, \"llmChain\">\n  ) {\n    const llmChain = new LLMChain<RouterOutputSchema>({ llm, prompt });\n    return new LLMRouterChain({ ...options, llmChain });\n  }\n}\n"],"mappings":";;;;;;;;;AA+BA,IAAa,iBAAb,MAAa,uBAAuBA,oBAAAA,YAA2C;CAC7E;CAEA,YAAY,QAA6B;EACvC,MAAM,MAAM;EACZ,KAAK,WAAW,OAAO;CACzB;CAEA,IAAI,YAAsB;EACxB,OAAO,KAAK,SAAS;CACvB;CAEA,MAAM,MACJ,QACA,YAC6B;EAC7B,OAAO,KAAK,SAAS,QAAQ,QAAQ,YAAY,SAAS,CAAC;CAC7D;CAEA,aAAqB;EACnB,OAAO;CACT;;;;;;;;;;;CAYA,OAAO,QACL,KACA,QACA,SACA;EACA,MAAM,WAAW,IAAIC,kBAAAA,SAA6B;GAAE;GAAK;EAAO,CAAC;EACjE,OAAO,IAAI,eAAe;GAAE,GAAG;GAAS;EAAS,CAAC;CACpD;AACF"}

package/dist/chains/router/llm_router.d.cts

@@ -5,7 +5,6 @@ import { ChainValues } from "@langchain/core/utils/types";
 import { BasePromptTemplate } from "@langchain/core/prompts";
 import { BaseLanguageModelInterface } from "@langchain/core/language_models/base";
 import { CallbackManagerForChainRun } from "@langchain/core/callbacks/manager";
-
 //#region src/chains/router/llm_router.d.ts
 /**
  * A type that represents the output schema of a router chain. It defines

package/dist/chains/router/llm_router.d.cts.map

@@ -1 +1 @@
-{"version":3,"file":"llm_router.d.cts","names":[],"sources":["../../../src/chains/router/llm_router.ts"],"mappings":";;;;;;;;;;;AAYA;;KAAY,kBAAA;EACV,WAAA;EACA,WAAA;IAAA,CAAgB,GAAA;EAAA;AAAA;;AAOlB;;;UAAiB,mBAAA,SAA4B,WAAA;EAC3C,QAAA,EAAU,QAAA,CAAS,kBAAA;AAAA;;;;;;;cASR,cAAA,SAAuB,WAAA,YAAuB,mBAAA;EACzD,QAAA,EAAU,QAAA,CAAS,kBAAA;EAEnB,WAAA,CAAY,MAAA,EAAQ,mBAAA;EAAA,IAKhB,SAAA,CAAA;EAIE,KAAA,CACJ,MAAA,EAAQ,WAAA,EACR,UAAA,GAAa,0BAAA,eACZ,OAAA,CAAQ,kBAAA;EAIX,UAAA,CAAA;EAlBU;;;;;;;;;;EAAA,OAgCH,OAAA,CACL,GAAA,EAAK,0BAAA,EACL,MAAA,EAAQ,kBAAA,EACR,OAAA,GAAU,IAAA,CAAK,mBAAA,gBAAgC,cAAA;AAAA"}
+{"version":3,"file":"llm_router.d.cts","names":[],"sources":["../../../src/chains/router/llm_router.ts"],"mappings":";;;;;;;;;;;;KAYY;EACV;EACA;KAAgB;;;;;;;UAOD,4BAA4B;EAC3C,UAAU,SAAS;;;;;;;;cASR,uBAAuB,uBAAuB;EACzD,UAAU,SAAS;EAEnB,YAAY,QAAQ;MAKhB;EAIE,MACJ,QAAQ,aACR,aAAa,yCACZ,QAAQ;EAIX;;;;;;;;;;;SAcO,QACL,KAAK,4BACL,QAAQ,oBACR,UAAU,KAAK,mCAAgC"}

package/dist/chains/router/llm_router.d.ts

@@ -5,7 +5,6 @@ import { BasePromptTemplate } from "@langchain/core/prompts";
 import { BaseLanguageModelInterface } from "@langchain/core/language_models/base";
 import { CallbackManagerForChainRun } from "@langchain/core/callbacks/manager";
 import { ChainValues } from "@langchain/core/utils/types";
-
 //#region src/chains/router/llm_router.d.ts
 /**
  * A type that represents the output schema of a router chain. It defines

package/dist/chains/router/llm_router.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"llm_router.d.ts","names":[],"sources":["../../../src/chains/router/llm_router.ts"],"mappings":";;;;;;;;;;;AAYA;;KAAY,kBAAA;EACV,WAAA;EACA,WAAA;IAAA,CAAgB,GAAA;EAAA;AAAA;;AAOlB;;;UAAiB,mBAAA,SAA4B,WAAA;EAC3C,QAAA,EAAU,QAAA,CAAS,kBAAA;AAAA;;;;;;;cASR,cAAA,SAAuB,WAAA,YAAuB,mBAAA;EACzD,QAAA,EAAU,QAAA,CAAS,kBAAA;EAEnB,WAAA,CAAY,MAAA,EAAQ,mBAAA;EAAA,IAKhB,SAAA,CAAA;EAIE,KAAA,CACJ,MAAA,EAAQ,WAAA,EACR,UAAA,GAAa,0BAAA,eACZ,OAAA,CAAQ,kBAAA;EAIX,UAAA,CAAA;EAlBU;;;;;;;;;;EAAA,OAgCH,OAAA,CACL,GAAA,EAAK,0BAAA,EACL,MAAA,EAAQ,kBAAA,EACR,OAAA,GAAU,IAAA,CAAK,mBAAA,gBAAgC,cAAA;AAAA"}
+{"version":3,"file":"llm_router.d.ts","names":[],"sources":["../../../src/chains/router/llm_router.ts"],"mappings":";;;;;;;;;;;;KAYY;EACV;EACA;KAAgB;;;;;;;UAOD,4BAA4B;EAC3C,UAAU,SAAS;;;;;;;;cASR,uBAAuB,uBAAuB;EACzD,UAAU,SAAS;EAEnB,YAAY,QAAQ;MAKhB;EAIE,MACJ,QAAQ,aACR,aAAa,yCACZ,QAAQ;EAIX;;;;;;;;;;;SAcO,QACL,KAAK,4BACL,QAAQ,oBACR,UAAU,KAAK,mCAAgC"}

package/dist/chains/router/llm_router.js.map

@@ -1 +1 @@
-{"version":3,"file":"llm_router.js","names":[],"sources":["../../../src/chains/router/llm_router.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { LLMChain } from \"../../chains/llm_chain.js\";\nimport { RouterChain } from \"./multi_route.js\";\nimport { ChainInputs } from \"../../chains/base.js\";\n\n/**\n * A type that represents the output schema of a router chain. It defines\n * the structure of the output data returned by the router chain.\n */\nexport type RouterOutputSchema = {\n  destination: string;\n  next_inputs: { [key: string]: string };\n};\n\n/**\n * An interface that extends the default ChainInputs interface and adds an\n * additional \"llmChain\" property.\n */\nexport interface LLMRouterChainInput extends ChainInputs {\n  llmChain: LLMChain<RouterOutputSchema>;\n}\n\n/**\n * A class that represents an LLM router chain in the LangChain framework.\n * It extends the RouterChain class and implements the LLMRouterChainInput\n * interface. It provides additional functionality specific to LLMs and\n * routing based on LLM predictions.\n */\nexport class LLMRouterChain extends RouterChain implements LLMRouterChainInput {\n  llmChain: LLMChain<RouterOutputSchema>;\n\n  constructor(fields: LLMRouterChainInput) {\n    super(fields);\n    this.llmChain = fields.llmChain;\n  }\n\n  get inputKeys(): string[] {\n    return this.llmChain.inputKeys;\n  }\n\n  async _call(\n    values: ChainValues,\n    runManager?: CallbackManagerForChainRun | undefined\n  ): Promise<RouterOutputSchema> {\n    return this.llmChain.predict(values, runManager?.getChild());\n  }\n\n  _chainType(): string {\n    return \"llm_router_chain\";\n  }\n\n  /**\n   * A static method that creates an instance of LLMRouterChain from a\n   * BaseLanguageModel and a BasePromptTemplate. It takes in an optional\n   * options object and returns an instance of LLMRouterChain with the\n   * specified LLMChain.\n   * @param llm A BaseLanguageModel instance.\n   * @param prompt A BasePromptTemplate instance.\n   * @param options Optional LLMRouterChainInput object, excluding \"llmChain\".\n   * @returns An instance of LLMRouterChain.\n   */\n  static fromLLM(\n    llm: BaseLanguageModelInterface,\n    prompt: BasePromptTemplate,\n    options?: Omit<LLMRouterChainInput, \"llmChain\">\n  ) {\n    const llmChain = new LLMChain<RouterOutputSchema>({ llm, prompt });\n    return new LLMRouterChain({ ...options, llmChain });\n  }\n}\n"],"mappings":";;;;;;;;;AA+BA,IAAa,iBAAb,MAAa,uBAAuB,YAA2C;CAC7E;CAEA,YAAY,QAA6B;AACvC,QAAM,OAAO;AACb,OAAK,WAAW,OAAO;;CAGzB,IAAI,YAAsB;AACxB,SAAO,KAAK,SAAS;;CAGvB,MAAM,MACJ,QACA,YAC6B;AAC7B,SAAO,KAAK,SAAS,QAAQ,QAAQ,YAAY,UAAU,CAAC;;CAG9D,aAAqB;AACnB,SAAO;;;;;;;;;;;;CAaT,OAAO,QACL,KACA,QACA,SACA;EACA,MAAM,WAAW,IAAI,SAA6B;GAAE;GAAK;GAAQ,CAAC;AAClE,SAAO,IAAI,eAAe;GAAE,GAAG;GAAS;GAAU,CAAC"}
+{"version":3,"file":"llm_router.js","names":[],"sources":["../../../src/chains/router/llm_router.ts"],"sourcesContent":["import type { BaseLanguageModelInterface } from \"@langchain/core/language_models/base\";\nimport { ChainValues } from \"@langchain/core/utils/types\";\nimport { BasePromptTemplate } from \"@langchain/core/prompts\";\nimport { CallbackManagerForChainRun } from \"@langchain/core/callbacks/manager\";\nimport { LLMChain } from \"../../chains/llm_chain.js\";\nimport { RouterChain } from \"./multi_route.js\";\nimport { ChainInputs } from \"../../chains/base.js\";\n\n/**\n * A type that represents the output schema of a router chain. It defines\n * the structure of the output data returned by the router chain.\n */\nexport type RouterOutputSchema = {\n  destination: string;\n  next_inputs: { [key: string]: string };\n};\n\n/**\n * An interface that extends the default ChainInputs interface and adds an\n * additional \"llmChain\" property.\n */\nexport interface LLMRouterChainInput extends ChainInputs {\n  llmChain: LLMChain<RouterOutputSchema>;\n}\n\n/**\n * A class that represents an LLM router chain in the LangChain framework.\n * It extends the RouterChain class and implements the LLMRouterChainInput\n * interface. It provides additional functionality specific to LLMs and\n * routing based on LLM predictions.\n */\nexport class LLMRouterChain extends RouterChain implements LLMRouterChainInput {\n  llmChain: LLMChain<RouterOutputSchema>;\n\n  constructor(fields: LLMRouterChainInput) {\n    super(fields);\n    this.llmChain = fields.llmChain;\n  }\n\n  get inputKeys(): string[] {\n    return this.llmChain.inputKeys;\n  }\n\n  async _call(\n    values: ChainValues,\n    runManager?: CallbackManagerForChainRun | undefined\n  ): Promise<RouterOutputSchema> {\n    return this.llmChain.predict(values, runManager?.getChild());\n  }\n\n  _chainType(): string {\n    return \"llm_router_chain\";\n  }\n\n  /**\n   * A static method that creates an instance of LLMRouterChain from a\n   * BaseLanguageModel and a BasePromptTemplate. It takes in an optional\n   * options object and returns an instance of LLMRouterChain with the\n   * specified LLMChain.\n   * @param llm A BaseLanguageModel instance.\n   * @param prompt A BasePromptTemplate instance.\n   * @param options Optional LLMRouterChainInput object, excluding \"llmChain\".\n   * @returns An instance of LLMRouterChain.\n   */\n  static fromLLM(\n    llm: BaseLanguageModelInterface,\n    prompt: BasePromptTemplate,\n    options?: Omit<LLMRouterChainInput, \"llmChain\">\n  ) {\n    const llmChain = new LLMChain<RouterOutputSchema>({ llm, prompt });\n    return new LLMRouterChain({ ...options, llmChain });\n  }\n}\n"],"mappings":";;;;;;;;;AA+BA,IAAa,iBAAb,MAAa,uBAAuB,YAA2C;CAC7E;CAEA,YAAY,QAA6B;EACvC,MAAM,MAAM;EACZ,KAAK,WAAW,OAAO;CACzB;CAEA,IAAI,YAAsB;EACxB,OAAO,KAAK,SAAS;CACvB;CAEA,MAAM,MACJ,QACA,YAC6B;EAC7B,OAAO,KAAK,SAAS,QAAQ,QAAQ,YAAY,SAAS,CAAC;CAC7D;CAEA,aAAqB;EACnB,OAAO;CACT;;;;;;;;;;;CAYA,OAAO,QACL,KACA,QACA,SACA;EACA,MAAM,WAAW,IAAI,SAA6B;GAAE;GAAK;EAAO,CAAC;EACjE,OAAO,IAAI,eAAe;GAAE,GAAG;GAAS;EAAS,CAAC;CACpD;AACF"}