メインコンテンツまでスキップ

LangChainについて

公式ドキュメントを読む

分类1分类2进展
LCELInterface
Streaming
How toRoute between multiple runnables✅
Cancelling requests✅
Use RunnableMaps✅
Add message history (memory)
Cookbook✅Prompt + LLM
✅Multiple chains
✅Retrieval augmented generation (RAG)
✅Querying a SQL DB
Adding memory
✅Using tools
Agents
Model I/OQuickstart
Concepts
PromptsQuick Start
Example selectors
Few Shot Prompt Templates
Partial prompt templates
Composition
LLMsQuick Start
Streaming
Caching
Custom chat models
Tracking token usage
Cancelling requests
Dealing with API Errors
Dealing with rate limits
OpenAI Function calling
Subscribing to events
Adding a timeout
Chat Models
Output Parsers
Retrieval首页/概念
Document loaders
Text Splitters
Retrievers
Text embedding models
Vector stores
Indexing
Experimental
Chains
Agents
More
Guides
User casesSQL
Chatbots
Q&A with RAG
Tool use
Interacting with APIs
Tabular Question Answering
Summarization
Agent Simulations
Autonomous Agents
Code Understanding
Extraction

LangChain生態系

利点:Java Scriptのサポート、LllamaInde xよりもはるかに優れています(llamdaはtsをサポートしていますが、ドキュメントとAPIはPythonバージョンよりもかなり悪いです)。

生態系:

Diagram outlining the hierarchical organization of the LangChain framework, displaying the interconnected parts across multiple layers.

コンセプトは

LLMとChatモデル

モデル:LLMとチャットモデルの2種類があります。

import { OpenAI, ChatOpenAI } from "@langchain/openai";

const llm = new OpenAI({
modelName: "gpt-3.5-turbo-instruct",
});

const chatModel = new ChatOpenAI({
modelName: "gpt-3.5-turbo",
});

AnthropicのモデルはXMLに最適ですが、Open AIのモデルはJSONに最適です。

Typescriptのバージョン

npm下载地址

インストールする。

npm install langchain @langchain/core @langchain/community @langchain/openai langsmith

LangChain所有第三方的库:链接

クイックスタート

import { ChatOpenAI } from "@langchain/openai";

async function main() {
const chatModel = new ChatOpenAI({});
let str = await chatModel.invoke("what is LangSmith?");
console.log(str);
}

main();

構成

OpenAI可配置的内容:见官网

モデル名/温度/API Key/URL

文档

import { OpenAI } from "@langchain/openai";

const model = new OpenAI({
modelName: "gpt-3.5-turbo",
temperature: 0.9,
openAIApiKey: "YOUR-API-KEY",
configuration: {
baseURL: "https://your_custom_url.com",
},
});

JSONスキーマ

const jsonModeModel = new ChatOpenAI({
modelName: "gpt-4-1106-preview",
maxTokens: 128,
}).bind({
response_format: {
type: "json_object",
},
});

定义

関数呼び出し/ツール

1つ目はツールです

官方文档

最新のツールを使用する

const llm = new ChatOpenAI();

const llmWithTools = llm.bind({
tools: [tool],
tool_choice: tool,
});

const prompt = ChatPromptTemplate.fromMessages([
["system", "You are the funniest comedian, tell the user a joke about their topic."],
["human", "Topic: {topic}"]
])

const chain = prompt.pipe(llmWithTools);
const result = await chain.invoke({ topic: "Large Language Models" });

Parserの指定

文档

import { JsonOutputToolsParser } from "langchain/output_parsers";

const outputParser = new JsonOutputToolsParser();

第二に、関数呼び出し

官方文档

2つの方法があります

** 呼び出し時に関数を渡す **

const result = await model.invoke([new HumanMessage("What a beautiful day!")], {
functions: [extractionFunctionSchema],
function_call: { name: "extractor" },
});

** 関数をモデルにバインド **

同じモデルを繰り返し使用できます。

const model = new ChatOpenAI({ modelName: "gpt-4" }).bind({
functions: [extractionFunctionSchema],
function_call: { name: "extractor" },
});

APIを定義する

2つの方法

const extractionFunctionSchema = {
name: "extractor",
description: "Extracts fields from the input.",
parameters: {
type: "object",
properties: {
tone: {
type: "string",
enum: ["positive", "negative"],
description: "The overall tone of the input",
},
word_count: {
type: "number",
description: "The number of words in the input",
},
chat_response: {
type: "string",
description: "A response to the human's input",
},
},
required: ["tone", "word_count", "chat_response"],
},
};

** Zodを使用 **

import { ChatOpenAI } from "@langchain/openai";
import { z } from "zod";
import { zodToJsonSchema } from "zod-to-json-schema";
import { HumanMessage } from "@langchain/core/messages";

const extractionFunctionSchema = {
name: "extractor",
description: "Extracts fields from the input.",
parameters: zodToJsonSchema(
z.object({
tone: z
.enum(["positive", "negative"])
.describe("The overall tone of the input"),
entity: z.string().describe("The entity mentioned in the input"),
word_count: z.number().describe("The number of words in the input"),
chat_response: z.string().describe("A response to the human's input"),
final_punctuation: z
.optional(z.string())
.describe("The final punctuation mark in the input, if any."),
})
),
};

モデルI/O

Loader

CSV-TS

Retriever(重要)

官方

2つのカテゴリーに分ける

Retriever说明
Knowledge Bases for Amazon Bedrock
Chaindesk Retriever
ChatGPT Plugin Retriever
Dria Retriever
Exa Search
HyDE Retriever
Amazon Kendra Retriever
Metal Retriever
Supabase Hybrid Search
Tavily Search API
Time-Weighted Retriever
Vector Store
Vespa Retriever
Zep Retriever

類似性:ScoreThreshold

文档

ScoreThresholdはパーセンテージです。

  • 1.0は完全一致です。
  • 95はほぼ同じです。
import { MemoryVectorStore } from "langchain/vectorstores/memory";
import { OpenAIEmbeddings } from "@langchain/openai";
import { ScoreThresholdRetriever } from "langchain/retrievers/score_threshold";

async function main() {
const vectorStore = await MemoryVectorStore.fromTexts(
[
"Buildings are made out of brick",
"Buildings are made out of wood",
"Buildings are made out of stone",
"Buildings are made out of atoms",
"Buildings are made out of building materials",
"Cars are made out of metal",
"Cars are made out of plastic",
],
[{ id: 1 }, { id: 2 }, { id: 3 }, { id: 4 }, { id: 5 }],
new OpenAIEmbeddings()
);

const retriever = ScoreThresholdRetriever.fromVectorStore(vectorStore, {
minSimilarityScore: 0.95, // Finds results with at least this similarity score
maxK: 100, // The maximum K value to use. Use it based to your chunk size to make sure you don't run out of tokens
kIncrement: 2, // How much to increase K by each time. It'll fetch N results, then N + kIncrement, then N + kIncrement * 2, etc.
});

const result = await retriever.getRelevantDocuments(
"building is made out of atom"
);

console.log(result);
};

main();

// [
// Document {
// pageContent: 'Buildings are made out of atoms',
// metadata: { id: 4 }
// }
// ]

** Self-Query(構造化データのクエリに最適)**

文档

スーパベース

Quick Start

混合检索

Supabase官方文档

パルサー

解析器说明
常见String output parser
格式化Structured output parser方便自定义
OpenAI Tools常用
标准格式JSON Output Functions Parser常用
HTTP Response Output Parser
XML output parser
列表List parser常用
Custom list parser常用
其它Datetime parser有用
Auto-fixing parser

多くのチェーン。

Serial Serial

2つの方法

  • . p
  • RunnableSequence.from []

.pipeの使用

const prompt = ChatPromptTemplate.fromMessages([
["human", "Tell me a short joke about {topic}"],
]);
const model = new ChatOpenAI({});
const outputParser = new StringOutputParser();

const chain = prompt.pipe(model).pipe(outputParser);
const response = await chain.invoke({
topic: "ice cream",
});

RunnableSequence.fromの使い方

const model = new ChatOpenAI({});
const promptTemplate = PromptTemplate.fromTemplate(
"Tell me a joke about {topic}"
);

const chain = RunnableSequence.from([
promptTemplate,
model
]);
const result = await chain.invoke({ topic: "bears" });

バッチとパラレル。

セルラー自身のサポート

const chain = promptTemplate.pipe(model);
await chain.batch([{ topic: "bears" }, { topic: "cats" }])

RunnableMapの使用

const model = new ChatAnthropic({});
const jokeChain = PromptTemplate.fromTemplate(
"Tell me a joke about {topic}"
).pipe(model);

const poemChain = PromptTemplate.fromTemplate(
"write a 2-line poem about {topic}"
).pipe(model);

const mapChain = RunnableMap.from({
joke: jokeChain,
poem: poemChain,
});

const result = await mapChain.invoke({ topic: "bear" });

ブランチブランチ

官方文档

2つの方法

  • RunnableBranch
  • カスタムファクトリー機能

中止、再試行、Fallback

N/Aは

例:シリアル

import { PromptTemplate } from "@langchain/core/prompts";
import { RunnableSequence } from "@langchain/core/runnables";
import { StringOutputParser } from "@langchain/core/output_parsers";
import { ChatOpenAI } from "@langchain/openai";

async function main() {
const prompt1 = PromptTemplate.fromTemplate(
`What is the city {person} is from? Only respond with the name of the city.`
);
const prompt2 = PromptTemplate.fromTemplate(
`What country is the city {city} in? Respond in {language}.`
);

const model = new ChatOpenAI({});

const chain1 = prompt1.pipe(model).pipe(new StringOutputParser());

const combinedChain = RunnableSequence.from([
{
city: chain1,
language: (input) => input.language,
},
prompt2,
model,
new StringOutputParser(),
]);

const result = await combinedChain.invoke({
person: "Obama",
language: "German",
});

console.log(result);
}

main();

结果见这里

image-20240301094802136

image-20240301095114942

RAGさん

官方文档

≪ロード| Loader | Eas ≫

文档

分类项目
本地资源Folders with multiple files
ChatGPT files
CSV files
Docx files
EPUB files
JSON files
JSONLines files
Notion markdown export
Open AI Whisper Audio
PDF files
PPTX files
Subtitles
Text files
Unstructured
Web资源Cheerio
Puppeteer
Playwright
Apify Dataset
AssemblyAI Audio Transcript
Azure Blob Storage Container
Azure Blob Storage File
College Confidential
Confluence
Couchbase
Figma
GitBook
GitHub
Hacker News
IMSDB
Notion API
PDF files
Recursive URL Loader
S3 File
SearchApi Loader
SerpAPI Loader
Sitemap Loader
Sonix Audio
Blockchain Data
YouTube transcripts

更通用的ELT工具:unstructured

分割する

官网

Pythonのバージョン

安装LangChain全家桶

pip install langchain langchain-community langchain-core "langserve[all]" langchain-cli langsmith langchain-openai

最新版本号:0.2.6(截止到2024年7月3日)

历史版本

Hub Hubについて

LangSmithにはGitHubに似たハブがあります。

例如RLM

import { UnstructuredDirectoryLoader } from "langchain/document_loaders/fs/unstructured";

import { RecursiveCharacterTextSplitter } from "langchain/text_splitter";
import { MemoryVectorStore } from "langchain/vectorstores/memory"
import { OpenAIEmbeddings, ChatOpenAI } from "@langchain/openai";
import { pull } from "langchain/hub";
import { ChatPromptTemplate } from "@langchain/core/prompts";
import { StringOutputParser } from "@langchain/core/output_parsers";
import { createStuffDocumentsChain } from "langchain/chains/combine_documents";

async function main() {
const options = {
apiUrl: "http://localhost:8000/general/v0/general",
};

const loader = new UnstructuredDirectoryLoader(
"sample-docs",
options
);
const docs = await loader.load();
// console.log(docs);

const vectorStore = await MemoryVectorStore.fromDocuments(docs, new OpenAIEmbeddings());

const retriever = vectorStore.asRetriever();
const prompt = await pull<ChatPromptTemplate>("rlm/rag-prompt");
const llm = new ChatOpenAI({ modelName: "gpt-3.5-turbo", temperature: 0 });

const ragChain = await createStuffDocumentsChain({
llm,
prompt,
outputParser: new StringOutputParser(),
})
const retrievedDocs = await retriever.getRelevantDocuments("what is task decomposition")

const r = await ragChain.invoke({
question: "列出名字和联系方式",
context: retrievedDocs,
})
console.log(r);
}

main();