langchain 0.2.10 → 0.2.11

package/dist/chains/tests/conversation_chain.int.test.js

@@ -1,9 +0,0 @@
-import { test } from "@jest/globals";
-import { OpenAI } from "@langchain/openai";
-import { ConversationChain } from "../conversation.js";
-test("Test ConversationChain", async () => {
-    const model = new OpenAI({ modelName: "gpt-3.5-turbo-instruct" });
-    const chain = new ConversationChain({ llm: model });
-    const res = await chain.call({ input: "my favorite color" });
-    console.log({ res });
-});

package/dist/chains/tests/conversational_retrieval_chain.int.test.d.ts

@@ -1 +0,0 @@
-export {};

package/dist/chains/tests/conversational_retrieval_chain.int.test.js

@@ -1,243 +0,0 @@
-import { expect, test } from "@jest/globals";
-import { OpenAI, OpenAIEmbeddings, ChatOpenAI } from "@langchain/openai";
-import { PromptTemplate } from "@langchain/core/prompts";
-import { ConversationalRetrievalQAChain } from "../conversational_retrieval_chain.js";
-import { MemoryVectorStore } from "../../vectorstores/memory.js";
-import { BufferMemory } from "../../memory/buffer_memory.js";
-test("Test ConversationalRetrievalQAChain from LLM", async () => {
-    const model = new OpenAI({ modelName: "gpt-3.5-turbo-instruct" });
-    const vectorStore = await MemoryVectorStore.fromTexts(["Hello world", "Bye bye", "hello nice world", "bye", "hi"], [{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }], new OpenAIEmbeddings());
-    const chain = ConversationalRetrievalQAChain.fromLLM(model, vectorStore.asRetriever());
-    const res = await chain.call({ question: "foo", chat_history: "bar" });
-    console.log({ res });
-});
-test("Test ConversationalRetrievalQAChain from LLM with flag option to return source", async () => {
-    const model = new OpenAI({ modelName: "gpt-3.5-turbo-instruct" });
-    const vectorStore = await MemoryVectorStore.fromTexts(["Hello world", "Bye bye", "hello nice world", "bye", "hi"], [{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }], new OpenAIEmbeddings());
-    const chain = ConversationalRetrievalQAChain.fromLLM(model, vectorStore.asRetriever(), {
-        returnSourceDocuments: true,
-    });
-    const res = await chain.call({ question: "foo", chat_history: "bar" });
-    expect(res).toEqual(expect.objectContaining({
-        text: expect.any(String),
-        sourceDocuments: expect.arrayContaining([
-            expect.objectContaining({
-                metadata: expect.objectContaining({
-                    id: expect.any(Number),
-                }),
-                pageContent: expect.any(String),
-            }),
-        ]),
-    }));
-});
-test("Test ConversationalRetrievalQAChain from LLM with flag option to return source and memory set", async () => {
-    const model = new OpenAI({ modelName: "gpt-3.5-turbo-instruct" });
-    const vectorStore = await MemoryVectorStore.fromTexts(["Hello world", "Bye bye", "hello nice world", "bye", "hi"], [{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }], new OpenAIEmbeddings());
-    const chain = ConversationalRetrievalQAChain.fromLLM(model, vectorStore.asRetriever(), {
-        returnSourceDocuments: true,
-        memory: new BufferMemory({
-            memoryKey: "chat_history",
-            inputKey: "question",
-            outputKey: "text",
-        }),
-    });
-    const res = await chain.call({ question: "foo", chat_history: "bar" });
-    expect(res).toEqual(expect.objectContaining({
-        text: expect.any(String),
-        sourceDocuments: expect.arrayContaining([
-            expect.objectContaining({
-                metadata: expect.objectContaining({
-                    id: expect.any(Number),
-                }),
-                pageContent: expect.any(String),
-            }),
-        ]),
-    }));
-});
-test("Test ConversationalRetrievalQAChain from LLM with override default prompts", async () => {
-    const model = new OpenAI({
-        modelName: "gpt-3.5-turbo-instruct",
-        temperature: 0,
-    });
-    const vectorStore = await MemoryVectorStore.fromTexts(["Hello world", "Bye bye", "hello nice world", "bye", "hi"], [{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }], new OpenAIEmbeddings());
-    const qa_template = `Use the following pieces of context to answer the question at the end. If you don't know the answer, just say "Sorry I dont know, I am learning from Aliens", don't try to make up an answer.
-  {context}
-
-  Question: {question}
-  Helpful Answer:`;
-    const chain = ConversationalRetrievalQAChain.fromLLM(model, vectorStore.asRetriever(), {
-        qaTemplate: qa_template,
-    });
-    const res = await chain.call({
-        question: "What is better programming Language Python or Javascript ",
-        chat_history: "bar",
-    });
-    expect(res.text).toContain("I am learning from Aliens");
-    console.log({ res });
-});
-test("Test ConversationalRetrievalQAChain from LLM with a chat model", async () => {
-    const model = new ChatOpenAI({
-        modelName: "gpt-3.5-turbo",
-        temperature: 0,
-    });
-    const vectorStore = await MemoryVectorStore.fromTexts(["Hello world", "Bye bye", "hello nice world", "bye", "hi"], [{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }], new OpenAIEmbeddings());
-    const qa_template = `Use the following pieces of context to answer the question at the end. If you don't know the answer, just say "Sorry I dont know, I am learning from Aliens", don't try to make up an answer.
-  {context}
-
-  Question: {question}
-  Helpful Answer:`;
-    const chain = ConversationalRetrievalQAChain.fromLLM(model, vectorStore.asRetriever(), {
-        qaChainOptions: {
-            type: "stuff",
-            prompt: PromptTemplate.fromTemplate(qa_template),
-        },
-    });
-    const res = await chain.call({
-        question: "What is better programming Language Python or Javascript ",
-        chat_history: "bar",
-    });
-    expect(res.text).toContain("I am learning from Aliens");
-    console.log({ res });
-});
-test("Test ConversationalRetrievalQAChain from LLM with a map reduce chain", async () => {
-    const model = new ChatOpenAI({
-        modelName: "gpt-3.5-turbo",
-        temperature: 0,
-    });
-    const vectorStore = await MemoryVectorStore.fromTexts(["Hello world", "Bye bye", "hello nice world", "bye", "hi"], [{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }], new OpenAIEmbeddings());
-    const chain = ConversationalRetrievalQAChain.fromLLM(model, vectorStore.asRetriever(), {
-        qaChainOptions: {
-            type: "map_reduce",
-        },
-    });
-    const res = await chain.call({
-        question: "What is better programming Language Python or Javascript ",
-        chat_history: "bar",
-    });
-    console.log({ res });
-});
-test("Test ConversationalRetrievalQAChain from LLM without memory", async () => {
-    const model = new OpenAI({
-        temperature: 0,
-    });
-    const vectorStore = await MemoryVectorStore.fromTexts([
-        "Mitochondria are the powerhouse of the cell",
-        "Foo is red",
-        "Bar is red",
-        "Buildings are made out of brick",
-        "Mitochondria are made of lipids",
-    ], [{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }], new OpenAIEmbeddings());
-    const chain = ConversationalRetrievalQAChain.fromLLM(model, vectorStore.asRetriever());
-    const question = "What is the powerhouse of the cell?";
-    const res = await chain.call({
-        question,
-        chat_history: "",
-    });
-    console.log({ res });
-    const res2 = await chain.call({
-        question: "What are they made out of?",
-        chat_history: question + res.text,
-    });
-    console.log({ res2 });
-});
-test("Test ConversationalRetrievalQAChain from LLM with a chat model without memory", async () => {
-    const model = new ChatOpenAI({
-        modelName: "gpt-3.5-turbo",
-        temperature: 0,
-    });
-    const vectorStore = await MemoryVectorStore.fromTexts([
-        "Mitochondria are the powerhouse of the cell",
-        "Foo is red",
-        "Bar is red",
-        "Buildings are made out of brick",
-        "Mitochondria are made of lipids",
-    ], [{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }], new OpenAIEmbeddings());
-    const chain = ConversationalRetrievalQAChain.fromLLM(model, vectorStore.asRetriever());
-    const question = "What is the powerhouse of the cell?";
-    const res = await chain.call({
-        question,
-        chat_history: "",
-    });
-    console.log({ res });
-    const res2 = await chain.call({
-        question: "What are they made out of?",
-        chat_history: question + res.text,
-    });
-    console.log({ res2 });
-});
-test("Test ConversationalRetrievalQAChain from LLM with memory", async () => {
-    const model = new OpenAI({
-        temperature: 0,
-    });
-    const vectorStore = await MemoryVectorStore.fromTexts([
-        "Mitochondria are the powerhouse of the cell",
-        "Foo is red",
-        "Bar is red",
-        "Buildings are made out of brick",
-        "Mitochondria are made of lipids",
-    ], [{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }], new OpenAIEmbeddings());
-    const chain = ConversationalRetrievalQAChain.fromLLM(model, vectorStore.asRetriever(), {
-        memory: new BufferMemory({
-            memoryKey: "chat_history",
-        }),
-    });
-    const res = await chain.call({
-        question: "What is the powerhouse of the cell?",
-    });
-    console.log({ res });
-    const res2 = await chain.call({
-        question: "What are they made out of?",
-    });
-    console.log({ res2 });
-});
-test("Test ConversationalRetrievalQAChain from LLM with a chat model and memory", async () => {
-    const model = new ChatOpenAI({
-        modelName: "gpt-3.5-turbo",
-        temperature: 0,
-    });
-    const vectorStore = await MemoryVectorStore.fromTexts([
-        "Mitochondria are the powerhouse of the cell",
-        "Foo is red",
-        "Bar is red",
-        "Buildings are made out of brick",
-        "Mitochondria are made of lipids",
-    ], [{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }], new OpenAIEmbeddings());
-    const chain = ConversationalRetrievalQAChain.fromLLM(model, vectorStore.asRetriever(), {
-        memory: new BufferMemory({
-            memoryKey: "chat_history",
-            returnMessages: true,
-        }),
-    });
-    const res = await chain.call({
-        question: "What is the powerhouse of the cell?",
-    });
-    console.log({ res });
-    const res2 = await chain.call({
-        question: "What are they made out of?",
-    });
-    console.log({ res2 });
-});
-test("Test ConversationalRetrievalQAChain from LLM with deprecated history syntax", async () => {
-    const model = new OpenAI({
-        temperature: 0,
-    });
-    const vectorStore = await MemoryVectorStore.fromTexts([
-        "Mitochondria are the powerhouse of the cell",
-        "Foo is red",
-        "Bar is red",
-        "Buildings are made out of brick",
-        "Mitochondria are made of lipids",
-    ], [{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }], new OpenAIEmbeddings());
-    const chain = ConversationalRetrievalQAChain.fromLLM(model, vectorStore.asRetriever());
-    const question = "What is the powerhouse of the cell?";
-    const res = await chain.call({
-        question,
-        chat_history: [],
-    });
-    console.log({ res });
-    const res2 = await chain.call({
-        question: "What are they made out of?",
-        chat_history: [[question, res.text]],
-    });
-    console.log({ res2 });
-});

package/dist/chains/tests/example_data/open_meteo_docs.d.ts

@@ -1 +0,0 @@
-export declare const OPEN_METEO_DOCS = "BASE URL: https://api.open-meteo.com/\n\nAPI Documentation\nThe API endpoint /v1/forecast accepts a geographical coordinate, a list of weather variables and responds with a JSON hourly weather forecast for 7 days. Time always starts at 0:00 today and contains 168 hours. All URL parameters are listed below:\n\nParameter\tFormat\tRequired\tDefault\tDescription\nlatitude, longitude\tFloating point\tYes\t\tGeographical WGS84 coordinate of the location\nhourly\tString array\tNo\t\tA list of weather variables which should be returned. Values can be comma separated, or multiple &hourly= parameter in the URL can be used.\ndaily\tString array\tNo\t\tA list of daily weather variable aggregations which should be returned. Values can be comma separated, or multiple &daily= parameter in the URL can be used. If daily weather variables are specified, parameter timezone is required.\ncurrent_weather\tBool\tNo\tfalse\tInclude current weather conditions in the JSON output.\ntemperature_unit\tString\tNo\tcelsius\tIf fahrenheit is set, all temperature values are converted to Fahrenheit.\nwindspeed_unit\tString\tNo\tkmh\tOther wind speed speed units: ms, mph and kn\nprecipitation_unit\tString\tNo\tmm\tOther precipitation amount units: inch\ntimeformat\tString\tNo\tiso8601\tIf format unixtime is selected, all time values are returned in UNIX epoch time in seconds. Please note that all timestamp are in GMT+0! For daily values with unix timestamps, please apply utc_offset_seconds again to get the correct date.\ntimezone\tString\tNo\tGMT\tIf timezone is set, all timestamps are returned as local-time and data is returned starting at 00:00 local-time. Any time zone name from the time zone database is supported. If auto is set as a time zone, the coordinates will be automatically resolved to the local time zone.\npast_days\tInteger (0-2)\tNo\t0\tIf past_days is set, yesterday or the day before yesterday data are also returned.\nstart_date\nend_date\tString (yyyy-mm-dd)\tNo\t\tThe time interval to get weather data. A day must be specified as an ISO8601 date (e.g. 2022-06-30).\nmodels\tString array\tNo\tauto\tManually select one or more weather models. Per default, the best suitable weather models will be combined.\n\nVariable\tValid time\tUnit\tDescription\ntemperature_2m\tInstant\t\u00B0C (\u00B0F)\tAir temperature at 2 meters above ground\nsnowfall\tPreceding hour sum\tcm (inch)\tSnowfall amount of the preceding hour in centimeters. For the water equivalent in millimeter, divide by 7. E.g. 7 cm snow = 10 mm precipitation water equivalent\nrain\tPreceding hour sum\tmm (inch)\tRain from large scale weather systems of the preceding hour in millimeter\nshowers\tPreceding hour sum\tmm (inch)\tShowers from convective precipitation in millimeters from the preceding hour\nweathercode\tInstant\tWMO code\tWeather condition as a numeric code. Follow WMO weather interpretation codes. See table below for details.\nsnow_depth\tInstant\tmeters\tSnow depth on the ground\nfreezinglevel_height\tInstant\tmeters\tAltitude above sea level of the 0\u00B0C level\nvisibility\tInstant\tmeters\tViewing distance in meters. Influenced by low clouds, humidity and aerosols. Maximum visibility is approximately 24 km.";

package/dist/chains/tests/example_data/open_meteo_docs.js

@@ -1,29 +0,0 @@
-export const OPEN_METEO_DOCS = `BASE URL: https://api.open-meteo.com/
-
-API Documentation
-The API endpoint /v1/forecast accepts a geographical coordinate, a list of weather variables and responds with a JSON hourly weather forecast for 7 days. Time always starts at 0:00 today and contains 168 hours. All URL parameters are listed below:
-
-Parameter	Format	Required	Default	Description
-latitude, longitude	Floating point	Yes		Geographical WGS84 coordinate of the location
-hourly	String array	No		A list of weather variables which should be returned. Values can be comma separated, or multiple &hourly= parameter in the URL can be used.
-daily	String array	No		A list of daily weather variable aggregations which should be returned. Values can be comma separated, or multiple &daily= parameter in the URL can be used. If daily weather variables are specified, parameter timezone is required.
-current_weather	Bool	No	false	Include current weather conditions in the JSON output.
-temperature_unit	String	No	celsius	If fahrenheit is set, all temperature values are converted to Fahrenheit.
-windspeed_unit	String	No	kmh	Other wind speed speed units: ms, mph and kn
-precipitation_unit	String	No	mm	Other precipitation amount units: inch
-timeformat	String	No	iso8601	If format unixtime is selected, all time values are returned in UNIX epoch time in seconds. Please note that all timestamp are in GMT+0! For daily values with unix timestamps, please apply utc_offset_seconds again to get the correct date.
-timezone	String	No	GMT	If timezone is set, all timestamps are returned as local-time and data is returned starting at 00:00 local-time. Any time zone name from the time zone database is supported. If auto is set as a time zone, the coordinates will be automatically resolved to the local time zone.
-past_days	Integer (0-2)	No	0	If past_days is set, yesterday or the day before yesterday data are also returned.
-start_date
-end_date	String (yyyy-mm-dd)	No		The time interval to get weather data. A day must be specified as an ISO8601 date (e.g. 2022-06-30).
-models	String array	No	auto	Manually select one or more weather models. Per default, the best suitable weather models will be combined.
-
-Variable	Valid time	Unit	Description
-temperature_2m	Instant	°C (°F)	Air temperature at 2 meters above ground
-snowfall	Preceding hour sum	cm (inch)	Snowfall amount of the preceding hour in centimeters. For the water equivalent in millimeter, divide by 7. E.g. 7 cm snow = 10 mm precipitation water equivalent
-rain	Preceding hour sum	mm (inch)	Rain from large scale weather systems of the preceding hour in millimeter
-showers	Preceding hour sum	mm (inch)	Showers from convective precipitation in millimeters from the preceding hour
-weathercode	Instant	WMO code	Weather condition as a numeric code. Follow WMO weather interpretation codes. See table below for details.
-snow_depth	Instant	meters	Snow depth on the ground
-freezinglevel_height	Instant	meters	Altitude above sea level of the 0°C level
-visibility	Instant	meters	Viewing distance in meters. Influenced by low clouds, humidity and aerosols. Maximum visibility is approximately 24 km.`;

package/dist/chains/tests/history_aware_retriever.int.test.d.ts

@@ -1 +0,0 @@
-export {};

package/dist/chains/tests/history_aware_retriever.int.test.js

@@ -1,41 +0,0 @@
-import { test } from "@jest/globals";
-import { ChatPromptTemplate } from "@langchain/core/prompts";
-import { ChatOpenAI, OpenAIEmbeddings } from "@langchain/openai";
-import { MemoryVectorStore } from "../../vectorstores/memory.js";
-import { createHistoryAwareRetriever } from "../history_aware_retriever.js";
-const QUESTION_GEN_TEMPLATE = `Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.
-
-Chat History:
-{chat_history}
-Follow Up Input: {input}
-Standalone question:`;
-test("History aware retriever with a followup", async () => {
-    const questionGenPrompt = ChatPromptTemplate.fromTemplate(QUESTION_GEN_TEMPLATE);
-    const vectorstore = await MemoryVectorStore.fromTexts([
-        "Mitochondria is the powerhouse of the cell",
-        "Foo is red",
-        "Bar is red",
-        "Buildings are made out of brick",
-        "Mitochondria are made of lipids",
-    ], [{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }], new OpenAIEmbeddings());
-    const retriever = vectorstore.asRetriever(2);
-    const llm = new ChatOpenAI({});
-    const chain = await createHistoryAwareRetriever({
-        llm,
-        retriever,
-        rephrasePrompt: questionGenPrompt,
-    });
-    const outputDocs = await chain.invoke({
-        input: "What is the powerhouse of the cell?",
-        chat_history: "",
-    });
-    expect(outputDocs[0].pageContent).toBe("Mitochondria is the powerhouse of the cell");
-    const outputDocs2 = await chain.invoke({
-        input: "What are they made of?",
-        chat_history: [
-            "Human: What is the powerhouse of the cell?",
-            "Assistant: Mitochondria is the powerhouse of the cell",
-        ].join("\n"),
-    });
-    expect(outputDocs2[0].pageContent).toBe("Mitochondria are made of lipids");
-});

package/dist/chains/tests/history_aware_retriever.test.d.ts

@@ -1 +0,0 @@
-export {};

package/dist/chains/tests/history_aware_retriever.test.js

@@ -1,27 +0,0 @@
-import { test } from "@jest/globals";
-import { ChatPromptTemplate } from "@langchain/core/prompts";
-import { FakeRetriever } from "@langchain/core/utils/testing";
-import { Document } from "@langchain/core/documents";
-import { FakeListLLM } from "../../util/testing/llms/fake.js";
-import { createHistoryAwareRetriever } from "../history_aware_retriever.js";
-test("createHistoryAwareRetriever", async () => {
-    const answer = "I know the answer!";
-    const questionGenPrompt = ChatPromptTemplate.fromTemplate(`hi! {input} {chat_history}`);
-    const fakeRetrievedDocs = [
-        new Document({ pageContent: "some fake content" }),
-    ];
-    const retriever = new FakeRetriever({
-        output: fakeRetrievedDocs,
-    });
-    const llm = new FakeListLLM({ responses: [answer] });
-    const input = "What is the answer?";
-    const chain = await createHistoryAwareRetriever({
-        llm,
-        retriever,
-        rephrasePrompt: questionGenPrompt,
-    });
-    const output = await chain.invoke({ input, chat_history: [] });
-    expect(output).toEqual(fakeRetrievedDocs);
-    const output2 = await chain.invoke({ input, chat_history: "foo" });
-    expect(output2).toEqual(fakeRetrievedDocs);
-});

package/dist/chains/tests/llm_chain.int.test.d.ts

@@ -1 +0,0 @@
-export {};

package/dist/chains/tests/llm_chain.int.test.js

@@ -1,119 +0,0 @@
-import { test } from "@jest/globals";
-import { OpenAI, ChatOpenAI } from "@langchain/openai";
-import { ChatPromptTemplate, HumanMessagePromptTemplate, PromptTemplate, } from "@langchain/core/prompts";
-import { LLMChain } from "../llm_chain.js";
-import { BufferMemory } from "../../memory/buffer_memory.js";
-test("Test OpenAI", async () => {
-    const model = new OpenAI({ modelName: "gpt-3.5-turbo-instruct" });
-    const prompt = new PromptTemplate({
-        template: "Print {foo}",
-        inputVariables: ["foo"],
-    });
-    const chain = new LLMChain({ prompt, llm: model });
-    const res = await chain.call({ foo: "my favorite color" });
-    console.log({ res });
-});
-test("Test OpenAI with timeout", async () => {
-    const model = new OpenAI({ modelName: "gpt-3.5-turbo-instruct" });
-    const prompt = new PromptTemplate({
-        template: "Print {foo}",
-        inputVariables: ["foo"],
-    });
-    const chain = new LLMChain({ prompt, llm: model });
-    await expect(() => chain.call({
-        foo: "my favorite color",
-        timeout: 10,
-    })).rejects.toThrow();
-});
-test("Test run method", async () => {
-    const model = new OpenAI({ modelName: "gpt-3.5-turbo-instruct" });
-    const prompt = new PromptTemplate({
-        template: "Print {foo}",
-        inputVariables: ["foo"],
-    });
-    const chain = new LLMChain({ prompt, llm: model });
-    const res = await chain.run("my favorite color");
-    console.log({ res });
-});
-test("Test run method", async () => {
-    const model = new OpenAI({ modelName: "gpt-3.5-turbo-instruct" });
-    const prompt = new PromptTemplate({
-        template: "{history} Print {foo}",
-        inputVariables: ["foo", "history"],
-    });
-    const chain = new LLMChain({
-        prompt,
-        llm: model,
-        memory: new BufferMemory(),
-    });
-    const res = await chain.run("my favorite color");
-    console.log({ res });
-});
-test("Test memory + cancellation", async () => {
-    const model = new OpenAI({ modelName: "gpt-3.5-turbo-instruct" });
-    const prompt = new PromptTemplate({
-        template: "{history} Print {foo}",
-        inputVariables: ["foo", "history"],
-    });
-    const chain = new LLMChain({
-        prompt,
-        llm: model,
-        memory: new BufferMemory(),
-    });
-    await expect(() => chain.call({
-        foo: "my favorite color",
-        signal: AbortSignal.timeout(20),
-    })).rejects.toThrow();
-});
-test("Test memory + timeout", async () => {
-    const model = new OpenAI({ modelName: "gpt-3.5-turbo-instruct" });
-    const prompt = new PromptTemplate({
-        template: "{history} Print {foo}",
-        inputVariables: ["foo", "history"],
-    });
-    const chain = new LLMChain({
-        prompt,
-        llm: model,
-        memory: new BufferMemory(),
-    });
-    await expect(() => chain.call({
-        foo: "my favorite color",
-        timeout: 20,
-    })).rejects.toThrow();
-});
-test("Test apply", async () => {
-    const model = new OpenAI({ modelName: "gpt-3.5-turbo-instruct" });
-    const prompt = new PromptTemplate({
-        template: "Print {foo}",
-        inputVariables: ["foo"],
-    });
-    const chain = new LLMChain({ prompt, llm: model });
-    const res = await chain.apply([{ foo: "my favorite color" }]);
-    console.log({ res });
-});
-test("Test LLMChain with ChatOpenAI", async () => {
-    const model = new ChatOpenAI({ temperature: 0.9 });
-    const template = "What is a good name for a company that makes {product}?";
-    const prompt = new PromptTemplate({ template, inputVariables: ["product"] });
-    const humanMessagePrompt = new HumanMessagePromptTemplate(prompt);
-    const chatPromptTemplate = ChatPromptTemplate.fromMessages([
-        humanMessagePrompt,
-    ]);
-    const chatChain = new LLMChain({ llm: model, prompt: chatPromptTemplate });
-    const res = await chatChain.call({ product: "colorful socks" });
-    console.log({ res });
-});
-test("Test passing a runnable to an LLMChain", async () => {
-    const model = new ChatOpenAI({ modelName: "gpt-3.5-turbo-1106" });
-    const runnableModel = model.bind({
-        response_format: {
-            type: "json_object",
-        },
-    });
-    const prompt = PromptTemplate.fromTemplate("You are a bee --I mean a spelling bee. Respond with a JSON key of 'spelling':\nQuestion:{input}");
-    const chain = new LLMChain({ llm: runnableModel, prompt });
-    const response = await chain.invoke({ input: "How do you spell today?" });
-    expect(JSON.parse(response.text)).toMatchObject({
-        spelling: expect.any(String),
-    });
-});

package/dist/chains/tests/openai_moderation.int.test.d.ts

@@ -1 +0,0 @@
-export {};

package/dist/chains/tests/openai_moderation.int.test.js

@@ -1,30 +0,0 @@
-import { test } from "@jest/globals";
-import { OpenAIModerationChain } from "../openai_moderation.js";
-test("OpenAI Moderation Test", async () => {
-    const badString = "I hate myself and want to do harm to myself";
-    const goodString = "The cat (Felis catus) is a domestic species of small carnivorous mammal.";
-    const moderation = new OpenAIModerationChain();
-    const { output: badResult } = await moderation.call({
-        input: badString,
-    });
-    const { output: goodResult } = await moderation.call({
-        input: goodString,
-    });
-    expect(badResult).toEqual("Text was found that violates OpenAI's content policy.");
-    expect(goodResult).toEqual("The cat (Felis catus) is a domestic species of small carnivorous mammal.");
-});
-test("OpenAI Moderation Test in non-english language", async () => {
-    const badString = "Vi devus mortigi vin nun! Kaj donu al ĉiuj aliaj pecon da oksigeno kaj ozono, kovru ĝin, por ke ni povu spiri ene de ĉi tiu blua veziko. Ĉar por kio vi estas ĉi tie? Venu por adori min? Mortigu vin mem. Mi volas diri, cent procento. Mil procentoj."; // Written in Esperanto. It's LTG's most famous quote and it's extremely crass, and as such it should not pass, but it does. However, we can check category_scores to see that, indeed, it detected some sort self-harm language in the text, albeit it's non-conclusive.
-    const goodString = "La kato ( Felis catus ) estas hejma specio de malgranda karnovora mamulo.";
-    const moderation = new OpenAIModerationChain();
-    const { output: badResult, results } = await moderation.call({
-        input: badString,
-    });
-    const { output: goodResult } = await moderation.call({
-        input: goodString,
-    });
-    expect(badResult).toEqual("Vi devus mortigi vin nun! Kaj donu al ĉiuj aliaj pecon da oksigeno kaj ozono, kovru ĝin, por ke ni povu spiri ene de ĉi tiu blua veziko. Ĉar por kio vi estas ĉi tie? Venu por adori min? Mortigu vin mem. Mi volas diri, cent procento. Mil procentoj.");
-    expect(goodResult).toEqual("La kato ( Felis catus ) estas hejma specio de malgranda karnovora mamulo.");
-    console.log(results[0].category_scores);
-    expect(results[0].category_scores["self-harm"]).toBeGreaterThan(0.01); // We can have a more granular control over moderation this way. It's not conclusive, but it's better than nothing if the language is not english.
-});

package/dist/chains/tests/retrieval_chain.int.test.d.ts

@@ -1 +0,0 @@
-export {};

package/dist/chains/tests/retrieval_chain.int.test.js

@@ -1,69 +0,0 @@
-import { test } from "@jest/globals";
-import { ChatPromptTemplate } from "@langchain/core/prompts";
-import { ChatOpenAI, OpenAIEmbeddings } from "@langchain/openai";
-import { StringOutputParser } from "@langchain/core/output_parsers";
-import { RunnablePassthrough, RunnableSequence, } from "@langchain/core/runnables";
-import { MemoryVectorStore } from "../../vectorstores/memory.js";
-import { createHistoryAwareRetriever } from "../history_aware_retriever.js";
-import { createRetrievalChain } from "../retrieval.js";
-const QUESTION_GEN_TEMPLATE = `Given the following conversation and a follow up question, rephrase the follow up question to be a standalone question.
-
-Chat History:
-{chat_history}
-Follow Up Input: {input}
-Standalone question:`;
-const COMBINE_DOCS_PROMPT = `Based on the following context:
-
-{context}
-
-And chat history:
-{chat_history}
-
-Answer the following question:
-{input}`;
-test("Retrieval chain with a history aware retriever and a followup", async () => {
-    const questionGenPrompt = ChatPromptTemplate.fromTemplate(QUESTION_GEN_TEMPLATE);
-    const vectorstore = await MemoryVectorStore.fromTexts([
-        "Mitochondria is the powerhouse of the cell",
-        "Foo is red",
-        "Bar is red",
-        "Buildings are made out of brick",
-        "Mitochondria are made of lipids",
-    ], [{ id: 2 }, { id: 1 }, { id: 3 }, { id: 4 }, { id: 5 }], new OpenAIEmbeddings());
-    const retriever = vectorstore.asRetriever(2);
-    const llm = new ChatOpenAI({});
-    const historyAwareRetriever = await createHistoryAwareRetriever({
-        llm,
-        retriever,
-        rephrasePrompt: questionGenPrompt,
-    });
-    const combineDocsPrompt = ChatPromptTemplate.fromTemplate(COMBINE_DOCS_PROMPT);
-    const combineDocsChain = RunnableSequence.from([
-        RunnablePassthrough.assign({
-            context: (input) => input.context.map((doc) => doc.pageContent).join("\n\n"),
-        }),
-        combineDocsPrompt,
-        llm,
-        new StringOutputParser(),
-    ]);
-    const chain = await createRetrievalChain({
-        retriever: historyAwareRetriever,
-        combineDocsChain,
-    });
-    const results = await chain.invoke({
-        input: "What is the powerhouse of the cell?",
-        chat_history: "",
-    });
-    console.log(results);
-    expect(results.answer.toLowerCase()).toContain("mitochondria");
-    const results2 = await chain.invoke({
-        input: "What are they made of?",
-        extraparam: "unused",
-        chat_history: [
-            "Human: What is the powerhouse of the cell?",
-            "Assistant: Mitochondria is the powerhouse of the cell",
-        ].join("\n"),
-    });
-    console.log(results2);
-    expect(results2.answer.toLowerCase()).toContain("lipids");
-});

package/dist/chains/tests/retrieval_chain.test.d.ts

@@ -1 +0,0 @@
-export {};

package/dist/chains/tests/retrieval_chain.test.js

@@ -1,36 +0,0 @@
-import { test } from "@jest/globals";
-import { ChatPromptTemplate } from "@langchain/core/prompts";
-import { FakeRetriever } from "@langchain/core/utils/testing";
-import { Document } from "@langchain/core/documents";
-import { createRetrievalChain } from "../retrieval.js";
-import { FakeListLLM } from "../../util/testing/llms/fake.js";
-test("createRetrievalChain", async () => {
-    const answer = "I know the answer!";
-    const combineDocsPrompt = ChatPromptTemplate.fromTemplate(`hi! {input} {chat_history}`);
-    const fakeRetrievedDocs = [
-        new Document({ pageContent: "some fake content" }),
-    ];
-    const llm = new FakeListLLM({ responses: [answer] });
-    const input = "What is the answer?";
-    const retriever = new FakeRetriever({
-        output: fakeRetrievedDocs,
-    });
-    const chain = await createRetrievalChain({
-        retriever,
-        combineDocsChain: combineDocsPrompt.pipe(llm),
-    });
-    const output = await chain.invoke({ input });
-    expect(output).toEqual({
-        answer,
-        chat_history: [],
-        context: fakeRetrievedDocs,
-        input,
-    });
-    const output2 = await chain.invoke({ input, chat_history: "foo" });
-    expect(output2).toEqual({
-        answer,
-        chat_history: "foo",
-        context: fakeRetrievedDocs,
-        input,
-    });
-});

package/dist/chains/tests/sequential_chain.int.test.d.ts

@@ -1 +0,0 @@
-export {};