langchain 0.1.36 → 0.2.0-rc.1

package/dist/chains/conversational_retrieval_chain.js

@@ -10,37 +10,79 @@ Chat History:
 Follow Up Input: {question}
 Standalone question:`;
 /**
+ * @deprecated This class will be removed in 0.3.0. See below for an example implementation using
+ * `createRetrievalChain`.
+ *
  * Class for conducting conversational question-answering tasks with a
  * retrieval component. Extends the BaseChain class and implements the
  * ConversationalRetrievalQAChainInput interface.
  * @example
  * ```typescript
- * const model = new ChatAnthropic({});
- *
- * const text = fs.readFileSync("state_of_the_union.txt", "utf8");
- *
- * const textSplitter = new RecursiveCharacterTextSplitter({ chunkSize: 1000 });
- * const docs = await textSplitter.createDocuments([text]);
+ * import { ChatAnthropic } from "@langchain/anthropic";
+ * import {
+ *   ChatPromptTemplate,
+ *   MessagesPlaceholder,
+ * } from "@langchain/core/prompts";
+ * import { BaseMessage } from "@langchain/core/messages";
+ * import { createStuffDocumentsChain } from "langchain/chains/combine_documents";
+ * import { createHistoryAwareRetriever } from "langchain/chains/history_aware_retriever";
+ * import { createRetrievalChain } from "langchain/chains/retrieval";
  *
- * const vectorStore = await HNSWLib.fromDocuments(docs, new OpenAIEmbeddings());
+ * const retriever = ...your retriever;
+ * const llm = new ChatAnthropic();
  *
- * const chain = ConversationalRetrievalQAChain.fromLLM(
- *   model,
- *   vectorStore.asRetriever(),
- * );
+ * // Contextualize question
+ * const contextualizeQSystemPrompt = `
+ * Given a chat history and the latest user question
+ * which might reference context in the chat history,
+ * formulate a standalone question which can be understood
+ * without the chat history. Do NOT answer the question, just
+ * reformulate it if needed and otherwise return it as is.`;
+ * const contextualizeQPrompt = ChatPromptTemplate.fromMessages([
+ *   ["system", contextualizeQSystemPrompt],
+ *   new MessagesPlaceholder("chat_history"),
+ *   ["human", "{input}"],
+ * ]);
+ * const historyAwareRetriever = await createHistoryAwareRetriever({
+ *   llm,
+ *   retriever,
+ *   rephrasePrompt: contextualizeQPrompt,
+ * });
  *
- * const question = "What did the president say about Justice Breyer?";
+ * // Answer question
+ * const qaSystemPrompt = `
+ * You are an assistant for question-answering tasks. Use
+ * the following pieces of retrieved context to answer the
+ * question. If you don't know the answer, just say that you
+ * don't know. Use three sentences maximum and keep the answer
+ * concise.
+ * \n\n
+ * {context}`;
+ * const qaPrompt = ChatPromptTemplate.fromMessages([
+ *   ["system", qaSystemPrompt],
+ *   new MessagesPlaceholder("chat_history"),
+ *   ["human", "{input}"],
+ * ]);
  *
- * const res = await chain.call({ question, chat_history: "" });
- * console.log(res);
+ * // Below we use createStuffDocuments_chain to feed all retrieved context
+ * // into the LLM. Note that we can also use StuffDocumentsChain and other
+ * // instances of BaseCombineDocumentsChain.
+ * const questionAnswerChain = await createStuffDocumentsChain({
+ *   llm,
+ *   prompt: qaPrompt,
+ * });
  *
- * const chatHistory = `${question}\n${res.text}`;
- * const followUpRes = await chain.call({
- *   question: "Was that nice?",
- *   chat_history: chatHistory,
+ * const ragChain = await createRetrievalChain({
+ *   retriever: historyAwareRetriever,
+ *   combineDocsChain: questionAnswerChain,
  * });
- * console.log(followUpRes);
  *
+ * // Usage:
+ * const chat_history: BaseMessage[] = [];
+ * const response = await ragChain.invoke({
+ *   chat_history,
+ *   input: "...",
+ * });
  * ```
  */
 export class ConversationalRetrievalQAChain extends BaseChain {

package/dist/chains/graph_qa/cypher.cjs

@@ -1,9 +1,14 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.GraphCypherQAChain = exports.INTERMEDIATE_STEPS_KEY = void 0;
-const llm_chain_js_1 = require("../../chains/llm_chain.cjs");
+const llm_chain_js_1 = require("../llm_chain.cjs");
 const base_js_1 = require("../base.cjs");
 const prompts_js_1 = require("./prompts.cjs");
+const entrypoint_deprecation_js_1 = require("../../util/entrypoint_deprecation.cjs");
+/* #__PURE__ */ (0, entrypoint_deprecation_js_1.logVersion020MigrationWarning)({
+    oldEntrypointName: "chains/graph_qa/cypher",
+    newPackageName: "@langchain/community",
+});
 exports.INTERMEDIATE_STEPS_KEY = "intermediateSteps";
 /**
  * @example
@@ -12,12 +17,13 @@ exports.INTERMEDIATE_STEPS_KEY = "intermediateSteps";
  *   llm: new ChatOpenAI({ temperature: 0 }),
  *   graph: new Neo4jGraph(),
  * });
- * const res = await chain.run("Who played in Pulp Fiction?");
+ * const res = await chain.invoke("Who played in Pulp Fiction?");
  * ```
  */
 class GraphCypherQAChain extends base_js_1.BaseChain {
     constructor(props) {
         super(props);
+        // eslint-disable-next-line @typescript-eslint/no-explicit-any
         Object.defineProperty(this, "graph", {
             enumerable: true,
             configurable: true,

package/dist/chains/graph_qa/cypher.d.ts

@@ -2,12 +2,11 @@ import type { BaseLanguageModelInterface } from "@langchain/core/language_models
 import { ChainValues } from "@langchain/core/utils/types";
 import { BasePromptTemplate } from "@langchain/core/prompts";
 import { CallbackManagerForChainRun } from "@langchain/core/callbacks/manager";
-import { Neo4jGraph } from "@langchain/community/graphs/neo4j_graph";
-import { LLMChain } from "../../chains/llm_chain.js";
+import { LLMChain } from "../llm_chain.js";
 import { BaseChain, ChainInputs } from "../base.js";
 export declare const INTERMEDIATE_STEPS_KEY = "intermediateSteps";
 export interface GraphCypherQAChainInput extends ChainInputs {
-    graph: Neo4jGraph;
+    graph: any;
     cypherGenerationChain: LLMChain;
     qaChain: LLMChain;
     inputKey?: string;
@@ -17,7 +16,7 @@ export interface GraphCypherQAChainInput extends ChainInputs {
     returnDirect?: boolean;
 }
 export interface FromLLMInput {
-    graph: Neo4jGraph;
+    graph: any;
     llm?: BaseLanguageModelInterface;
     cypherLLM?: BaseLanguageModelInterface;
     qaLLM?: BaseLanguageModelInterface;
@@ -33,7 +32,7 @@ export interface FromLLMInput {
  *   llm: new ChatOpenAI({ temperature: 0 }),
  *   graph: new Neo4jGraph(),
  * });
- * const res = await chain.run("Who played in Pulp Fiction?");
+ * const res = await chain.invoke("Who played in Pulp Fiction?");
  * ```
  */
 export declare class GraphCypherQAChain extends BaseChain {

package/dist/chains/graph_qa/cypher.js

@@ -1,6 +1,11 @@
-import { LLMChain } from "../../chains/llm_chain.js";
+import { LLMChain } from "../llm_chain.js";
 import { BaseChain } from "../base.js";
 import { CYPHER_GENERATION_PROMPT, CYPHER_QA_PROMPT } from "./prompts.js";
+import { logVersion020MigrationWarning } from "../../util/entrypoint_deprecation.js";
+/* #__PURE__ */ logVersion020MigrationWarning({
+    oldEntrypointName: "chains/graph_qa/cypher",
+    newPackageName: "@langchain/community",
+});
 export const INTERMEDIATE_STEPS_KEY = "intermediateSteps";
 /**
  * @example
@@ -9,12 +14,13 @@ export const INTERMEDIATE_STEPS_KEY = "intermediateSteps";
  *   llm: new ChatOpenAI({ temperature: 0 }),
  *   graph: new Neo4jGraph(),
  * });
- * const res = await chain.run("Who played in Pulp Fiction?");
+ * const res = await chain.invoke("Who played in Pulp Fiction?");
  * ```
  */
 export class GraphCypherQAChain extends BaseChain {
     constructor(props) {
         super(props);
+        // eslint-disable-next-line @typescript-eslint/no-explicit-any
         Object.defineProperty(this, "graph", {
             enumerable: true,
             configurable: true,

package/dist/chains/llm_chain.cjs

@@ -29,16 +29,21 @@ function _getLanguageModel(llmLike) {
     }
 }
 /**
+ * @deprecated This class will be removed in 0.3.0. Use the LangChain Expression Language (LCEL) instead.
+ * See the example below for how to use LCEL with the LLMChain class:
+ *
  * Chain to run queries against LLMs.
  *
  * @example
  * ```ts
- * import { LLMChain } from "langchain/chains";
- * import { OpenAI } from "langchain/llms/openai";
- * import { PromptTemplate } from "langchain/prompts";
+ * import { ChatPromptTemplate } from "@langchain/core/prompts";
+ * import { ChatOpenAI } from "@langchain/openai";
+ *
+ * const prompt = ChatPromptTemplate.fromTemplate("Tell me a {adjective} joke");
+ * const llm = new ChatOpenAI();
+ * const chain = prompt.pipe(llm);
  *
- * const prompt = PromptTemplate.fromTemplate("Tell me a {adjective} joke");
- * const llm = new LLMChain({ llm: new OpenAI(), prompt });
+ * const response = await chain.invoke({ adjective: "funny" });
  * ```
  */
 class LLMChain extends base_js_1.BaseChain {

package/dist/chains/llm_chain.d.ts

@@ -29,16 +29,21 @@ export interface LLMChainInput<T extends string | object = string, Model extends
     outputKey?: string;
 }
 /**
+ * @deprecated This class will be removed in 0.3.0. Use the LangChain Expression Language (LCEL) instead.
+ * See the example below for how to use LCEL with the LLMChain class:
+ *
  * Chain to run queries against LLMs.
  *
  * @example
  * ```ts
- * import { LLMChain } from "langchain/chains";
- * import { OpenAI } from "langchain/llms/openai";
- * import { PromptTemplate } from "langchain/prompts";
+ * import { ChatPromptTemplate } from "@langchain/core/prompts";
+ * import { ChatOpenAI } from "@langchain/openai";
+ *
+ * const prompt = ChatPromptTemplate.fromTemplate("Tell me a {adjective} joke");
+ * const llm = new ChatOpenAI();
+ * const chain = prompt.pipe(llm);
  *
- * const prompt = PromptTemplate.fromTemplate("Tell me a {adjective} joke");
- * const llm = new LLMChain({ llm: new OpenAI(), prompt });
+ * const response = await chain.invoke({ adjective: "funny" });
  * ```
  */
 export declare class LLMChain<T extends string | object = string, Model extends LLMType = LLMType> extends BaseChain implements LLMChainInput<T> {

package/dist/chains/llm_chain.js

@@ -26,16 +26,21 @@ function _getLanguageModel(llmLike) {
     }
 }
 /**
+ * @deprecated This class will be removed in 0.3.0. Use the LangChain Expression Language (LCEL) instead.
+ * See the example below for how to use LCEL with the LLMChain class:
+ *
  * Chain to run queries against LLMs.
  *
  * @example
  * ```ts
- * import { LLMChain } from "langchain/chains";
- * import { OpenAI } from "langchain/llms/openai";
- * import { PromptTemplate } from "langchain/prompts";
+ * import { ChatPromptTemplate } from "@langchain/core/prompts";
+ * import { ChatOpenAI } from "@langchain/openai";
+ *
+ * const prompt = ChatPromptTemplate.fromTemplate("Tell me a {adjective} joke");
+ * const llm = new ChatOpenAI();
+ * const chain = prompt.pipe(llm);
  *
- * const prompt = PromptTemplate.fromTemplate("Tell me a {adjective} joke");
- * const llm = new LLMChain({ llm: new OpenAI(), prompt });
+ * const response = await chain.invoke({ adjective: "funny" });
  * ```
  */
 export class LLMChain extends BaseChain {

package/dist/chains/query_constructor/index.cjs

@@ -1,6 +1,6 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
-exports.loadQueryConstructorRunnable = exports.formatAttributeInfo = exports.StructuredQueryOutputParser = exports.EXAMPLE_PROMPT = exports.DEFAULT_SUFFIX = exports.DEFAULT_SCHEMA = exports.DEFAULT_PREFIX = exports.DEFAULT_EXAMPLES = exports.QueryTransformer = void 0;
+exports.loadQueryConstructorRunnable = exports.formatAttributeInfo = exports.StructuredQueryOutputParser = exports.EXAMPLE_PROMPT = exports.DEFAULT_SUFFIX = exports.DEFAULT_SCHEMA = exports.DEFAULT_PREFIX = exports.DEFAULT_EXAMPLES = exports.QueryTransformer = exports.AttributeInfo = void 0;
 const zod_1 = require("zod");
 const prompts_1 = require("@langchain/core/prompts");
 const parser_js_1 = require("./parser.cjs");
@@ -13,6 +13,34 @@ Object.defineProperty(exports, "DEFAULT_SCHEMA", { enumerable: true, get: functi
 Object.defineProperty(exports, "DEFAULT_SUFFIX", { enumerable: true, get: function () { return prompt_js_1.DEFAULT_SUFFIX; } });
 Object.defineProperty(exports, "EXAMPLE_PROMPT", { enumerable: true, get: function () { return prompt_js_1.EXAMPLE_PROMPT; } });
 const structured_js_1 = require("../../output_parsers/structured.cjs");
+/**
+ * A simple data structure that holds information about an attribute. It
+ * is typically used to provide metadata about attributes in other classes
+ * or data structures within the LangChain framework.
+ */
+class AttributeInfo {
+    constructor(name, type, description) {
+        Object.defineProperty(this, "name", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: name
+        });
+        Object.defineProperty(this, "type", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: type
+        });
+        Object.defineProperty(this, "description", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: description
+        });
+    }
+}
+exports.AttributeInfo = AttributeInfo;
 const queryInputSchema = /* #__PURE__ */ zod_1.z.object({
     query: /* #__PURE__ */ zod_1.z
         .string()

package/dist/chains/query_constructor/index.d.ts

@@ -5,7 +5,17 @@ import { QueryTransformer, TraverseType } from "./parser.js";
 import { Comparator, Operator, StructuredQuery } from "./ir.js";
 import { DEFAULT_EXAMPLES, DEFAULT_PREFIX, DEFAULT_SCHEMA, DEFAULT_SUFFIX, EXAMPLE_PROMPT } from "./prompt.js";
 import { AsymmetricStructuredOutputParser } from "../../output_parsers/structured.js";
-import { AttributeInfo } from "../../schema/query_constructor.js";
+/**
+ * A simple data structure that holds information about an attribute. It
+ * is typically used to provide metadata about attributes in other classes
+ * or data structures within the LangChain framework.
+ */
+export declare class AttributeInfo {
+    name: string;
+    type: string;
+    description: string;
+    constructor(name: string, type: string, description: string);
+}
 export { QueryTransformer, type TraverseType };
 export { DEFAULT_EXAMPLES, DEFAULT_PREFIX, DEFAULT_SCHEMA, DEFAULT_SUFFIX, EXAMPLE_PROMPT, };
 declare const queryInputSchema: z.ZodObject<{

package/dist/chains/query_constructor/index.js

@@ -4,6 +4,33 @@ import { QueryTransformer } from "./parser.js";
 import { Comparators, Operators, StructuredQuery, } from "./ir.js";
 import { DEFAULT_EXAMPLES, DEFAULT_PREFIX, DEFAULT_SCHEMA, DEFAULT_SUFFIX, EXAMPLE_PROMPT, } from "./prompt.js";
 import { AsymmetricStructuredOutputParser } from "../../output_parsers/structured.js";
+/**
+ * A simple data structure that holds information about an attribute. It
+ * is typically used to provide metadata about attributes in other classes
+ * or data structures within the LangChain framework.
+ */
+export class AttributeInfo {
+    constructor(name, type, description) {
+        Object.defineProperty(this, "name", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: name
+        });
+        Object.defineProperty(this, "type", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: type
+        });
+        Object.defineProperty(this, "description", {
+            enumerable: true,
+            configurable: true,
+            writable: true,
+            value: description
+        });
+    }
+}
 export { QueryTransformer };
 export { DEFAULT_EXAMPLES, DEFAULT_PREFIX, DEFAULT_SCHEMA, DEFAULT_SUFFIX, EXAMPLE_PROMPT, };
 const queryInputSchema = /* #__PURE__ */ z.object({

package/dist/chains/query_constructor/prompt.cjs

@@ -1,7 +1,7 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.DEFAULT_SUFFIX = exports.DEFAULT_PREFIX = exports.DEFAULT_SCHEMA = exports.EXAMPLE_PROMPT = exports.EXAMPLE_PROMPT_TEMPLATE = exports.DEFAULT_EXAMPLES = exports.NO_FILTER_ANSWER = exports.FULL_ANSWER = exports.SONG_DATA_SOURCE = void 0;
-const index_js_1 = require("../../prompts/index.cjs");
+const prompts_1 = require("@langchain/core/prompts");
 exports.SONG_DATA_SOURCE = `\
 \`\`\`json
 {
@@ -65,7 +65,7 @@ User Query:
 Structured Request:
 {structured_request}
 `;
-exports.EXAMPLE_PROMPT = new index_js_1.PromptTemplate({
+exports.EXAMPLE_PROMPT = new prompts_1.PromptTemplate({
     inputVariables: ["i", "data_source", "user_query", "structured_request"],
     template: exports.EXAMPLE_PROMPT_TEMPLATE,
 });

package/dist/chains/query_constructor/prompt.d.ts

@@ -1,4 +1,4 @@
-import { PromptTemplate } from "../../prompts/index.js";
+import { PromptTemplate } from "@langchain/core/prompts";
 export declare const SONG_DATA_SOURCE: string;
 export declare const FULL_ANSWER = "```json\n{{\n    \"query\": \"teenager love\",\n    \"filter\": \"and(or(eq(\\\"artist\\\", \\\"Taylor Swift\\\"), eq(\\\"artist\\\", \\\"Katy Perry\\\")), lt(\\\"length\\\", 180), eq(\\\"genre\\\", \\\"pop\\\"))\"\n}}";
 export declare const NO_FILTER_ANSWER = "```json\n{{\n    \"query\": \"\",\n    \"filter\": \"NO_FILTER\"\n}}\n```";

package/dist/chains/query_constructor/prompt.js

@@ -1,4 +1,4 @@
-import { PromptTemplate } from "../../prompts/index.js";
+import { PromptTemplate } from "@langchain/core/prompts";
 export const SONG_DATA_SOURCE = `\
 \`\`\`json
 {

package/dist/chains/retrieval_qa.cjs

@@ -4,28 +4,37 @@ exports.RetrievalQAChain = void 0;
 const base_js_1 = require("./base.cjs");
 const load_js_1 = require("./question_answering/load.cjs");
 /**
+ * @deprecated This class will be removed in 0.3.0. See below for an example implementation using
+ * `createRetrievalChain`:
  * Class representing a chain for performing question-answering tasks with
  * a retrieval component.
  * @example
  * ```typescript
- * // Initialize the OpenAI model and the remote retriever with the specified configuration
- * const model = new ChatOpenAI({});
- * const retriever = new RemoteLangChainRetriever({
- *   url: "http://example.com/api",
- *   auth: { bearer: "foo" },
- *   inputKey: "message",
- *   responseKey: "response",
- * });
+ * import { createStuffDocumentsChain } from "langchain/chains/combine_documents";
+ * import { ChatPromptTemplate } from "@langchain/core/prompts";
+ * import { createRetrievalChain } from "langchain/chains/retrieval";
+ * import { MemoryVectorStore } from "langchain/vectorstores/memory";
+ *
+ * const documents = [...your documents here];
+ * const embeddings = ...your embeddings model;
+ * const llm = ...your LLM model;
  *
- * // Create a RetrievalQAChain using the model and retriever
- * const chain = RetrievalQAChain.fromLLM(model, retriever);
+ * const vectorstore = await MemoryVectorStore.fromDocuments(
+ *   documents,
+ *   embeddings
+ * );
+ * const prompt = ChatPromptTemplate.fromTemplate(`Answer the user's question: {input}`);
  *
- * // Execute the chain with a query and log the result
- * const res = await chain.call({
- *   query: "What did the president say about Justice Breyer?",
+ * const combineDocsChain = await createStuffDocumentsChain({
+ *   llm,
+ *   prompt,
  * });
- * console.log({ res });
+ * const retriever = vectorstore.asRetriever();
  *
+ * const retrievalChain = await createRetrievalChain({
+ *   combineDocsChain,
+ *   retriever,
+ * });
  * ```
  */
 class RetrievalQAChain extends base_js_1.BaseChain {

package/dist/chains/retrieval_qa.d.ts

@@ -16,28 +16,37 @@ export interface RetrievalQAChainInput extends Omit<ChainInputs, "memory"> {
     returnSourceDocuments?: boolean;
 }
 /**
+ * @deprecated This class will be removed in 0.3.0. See below for an example implementation using
+ * `createRetrievalChain`:
  * Class representing a chain for performing question-answering tasks with
  * a retrieval component.
  * @example
  * ```typescript
- * // Initialize the OpenAI model and the remote retriever with the specified configuration
- * const model = new ChatOpenAI({});
- * const retriever = new RemoteLangChainRetriever({
- *   url: "http://example.com/api",
- *   auth: { bearer: "foo" },
- *   inputKey: "message",
- *   responseKey: "response",
- * });
+ * import { createStuffDocumentsChain } from "langchain/chains/combine_documents";
+ * import { ChatPromptTemplate } from "@langchain/core/prompts";
+ * import { createRetrievalChain } from "langchain/chains/retrieval";
+ * import { MemoryVectorStore } from "langchain/vectorstores/memory";
+ *
+ * const documents = [...your documents here];
+ * const embeddings = ...your embeddings model;
+ * const llm = ...your LLM model;
  *
- * // Create a RetrievalQAChain using the model and retriever
- * const chain = RetrievalQAChain.fromLLM(model, retriever);
+ * const vectorstore = await MemoryVectorStore.fromDocuments(
+ *   documents,
+ *   embeddings
+ * );
+ * const prompt = ChatPromptTemplate.fromTemplate(`Answer the user's question: {input}`);
  *
- * // Execute the chain with a query and log the result
- * const res = await chain.call({
- *   query: "What did the president say about Justice Breyer?",
+ * const combineDocsChain = await createStuffDocumentsChain({
+ *   llm,
+ *   prompt,
  * });
- * console.log({ res });
+ * const retriever = vectorstore.asRetriever();
  *
+ * const retrievalChain = await createRetrievalChain({
+ *   combineDocsChain,
+ *   retriever,
+ * });
  * ```
  */
 export declare class RetrievalQAChain extends BaseChain implements RetrievalQAChainInput {

package/dist/chains/retrieval_qa.js

@@ -1,28 +1,37 @@
 import { BaseChain } from "./base.js";
 import { loadQAStuffChain, } from "./question_answering/load.js";
 /**
+ * @deprecated This class will be removed in 0.3.0. See below for an example implementation using
+ * `createRetrievalChain`:
  * Class representing a chain for performing question-answering tasks with
  * a retrieval component.
  * @example
  * ```typescript
- * // Initialize the OpenAI model and the remote retriever with the specified configuration
- * const model = new ChatOpenAI({});
- * const retriever = new RemoteLangChainRetriever({
- *   url: "http://example.com/api",
- *   auth: { bearer: "foo" },
- *   inputKey: "message",
- *   responseKey: "response",
- * });
+ * import { createStuffDocumentsChain } from "langchain/chains/combine_documents";
+ * import { ChatPromptTemplate } from "@langchain/core/prompts";
+ * import { createRetrievalChain } from "langchain/chains/retrieval";
+ * import { MemoryVectorStore } from "langchain/vectorstores/memory";
+ *
+ * const documents = [...your documents here];
+ * const embeddings = ...your embeddings model;
+ * const llm = ...your LLM model;
  *
- * // Create a RetrievalQAChain using the model and retriever
- * const chain = RetrievalQAChain.fromLLM(model, retriever);
+ * const vectorstore = await MemoryVectorStore.fromDocuments(
+ *   documents,
+ *   embeddings
+ * );
+ * const prompt = ChatPromptTemplate.fromTemplate(`Answer the user's question: {input}`);
  *
- * // Execute the chain with a query and log the result
- * const res = await chain.call({
- *   query: "What did the president say about Justice Breyer?",
+ * const combineDocsChain = await createStuffDocumentsChain({
+ *   llm,
+ *   prompt,
  * });
- * console.log({ res });
+ * const retriever = vectorstore.asRetriever();
  *
+ * const retrievalChain = await createRetrievalChain({
+ *   combineDocsChain,
+ *   retriever,
+ * });
  * ```
  */
 export class RetrievalQAChain extends BaseChain {

package/dist/chains/sql_db/sql_db_chain.d.ts

@@ -51,9 +51,9 @@ export declare class SqlDatabaseChain extends BaseChain {
     database: SqlDatabase;
     prompt: PromptTemplate<{
         input: any;
-        top_k: any;
         dialect: any;
         table_info: any;
+        top_k: any;
     }, any>;
     topK: number;
     inputKey: string;

package/dist/chains/sql_db/sql_db_prompt.d.ts

@@ -1,45 +1,45 @@
 import { BasePromptTemplate, PromptTemplate } from "@langchain/core/prompts";
 export declare const DEFAULT_SQL_DATABASE_PROMPT: PromptTemplate<{
     input: any;
-    top_k: any;
     dialect: any;
     table_info: any;
+    top_k: any;
 }, any>;
 export declare const SQL_POSTGRES_PROMPT: PromptTemplate<{
     input: any;
-    top_k: any;
     dialect: any;
     table_info: any;
+    top_k: any;
 }, any>;
 export declare const SQL_SQLITE_PROMPT: PromptTemplate<{
     input: any;
-    top_k: any;
     dialect: any;
     table_info: any;
+    top_k: any;
 }, any>;
 export declare const SQL_MYSQL_PROMPT: PromptTemplate<{
     input: any;
-    top_k: any;
     dialect: any;
     table_info: any;
+    top_k: any;
 }, any>;
 export declare const SQL_MSSQL_PROMPT: PromptTemplate<{
     input: any;
-    top_k: any;
     dialect: any;
     table_info: any;
+    top_k: any;
 }, any>;
 export declare const SQL_SAP_HANA_PROMPT: PromptTemplate<{
     input: any;
-    top_k: any;
     dialect: any;
     table_info: any;
+    top_k: any;
 }, any>;
 export declare const SQL_ORACLE_PROMPT: PromptTemplate<{
     input: any;
-    top_k: any;
     dialect: any;
     table_info: any;
+    top_k: any;
 }, any>;
 export type SqlDialect = "oracle" | "postgres" | "sqlite" | "mysql" | "mssql" | "sap hana";
 export declare const SQL_PROMPTS_MAP: Record<SqlDialect, BasePromptTemplate>;