docs: change SystemChatMessage and HumanChatMessage to SystemMessage, HumanMessage

.gitignore

@@ -20,3 +20,6 @@ yarn-debug.log*
 yarn-error.log*
 
 .vercel
+
+# IDE
+.idea

docs/ecosystem/helicone.md

@@ -25,7 +25,7 @@ const model = new OpenAI(
 
 );
 
-const res = await model.call("What is a helicone?");
+const res = await model.invoke("What is a helicone?");
 
 ```
 
@@ -59,7 +59,7 @@ const model = new OpenAI(
 
 );
 
-const res = await model.call("What is a helicone?");
+const res = await model.invoke("What is a helicone?");
 
 ```
 
@@ -95,7 +95,7 @@ const model = new OpenAI(
 
 );
 
-const res = await model.call("What is a helicone?");
+const res = await model.invoke("What is a helicone?");
 
 ```
 

docs/getting-started/guide-chat.mdx

@@ -26,7 +26,7 @@ import Example from "!!raw-loader!@examples/models/chat/chat_streaming_stdout.ts
 ```typescript
 import { ChatOpenAI } from "langchain/chat_models/openai";
 
-import { HumanChatMessage, SystemChatMessage } from "langchain/schema";
+import { HumanMessage, SystemMessage } from "langchain/schema";
 
 
 
@@ -41,13 +41,13 @@ const chat = new ChatOpenAI({ temperature: 0 });
 
 ### 聊天模型: 消息作为输入， 消息作为输出
 
-通过将一个或多个消息传递给聊天模型，可以获取聊天完成。响应也将是一条消息。LangChain当前支持的消息类型为`AIChatMessage`， `HumanChatMessage`， `SystemChatMessage` ，和通用`ChatMessage`-- ChatMessage采用任意角色参数，在这里，我们不会使用。大多数时候，您只需要处理`HumanChatMessage`， `AIChatMessage`和`SystemChatMessage`。
+通过将一个或多个消息传递给聊天模型，可以获取聊天完成。响应也将是一条消息。LangChain当前支持的消息类型为`AIMessage`， `HumanMessage`， `SystemMessage` ，和通用`ChatMessage`-- ChatMessage采用任意角色参数，在这里，我们不会使用。大多数时候，您只需要处理`HumanMessage`， `AIMessage`和`SystemMessage`。
 
 
 ```typescript
-const response = await chat.call([
+const response = await chat.invoke([
 
-  new HumanChatMessage(
+  new HumanMessage(
 
     "Translate this sentence from English to French. I love programming."
 
@@ -63,7 +63,7 @@ console.log(response);
 
 
 ```
-AIChatMessage { text: "J'aime programmer." }
+AIMessage { text: "J'aime programmer." }
 
 ```
 
@@ -75,15 +75,15 @@ OpenAI的在线聊天模型（目前包括`gpt-3.5-turbo`和`gpt-4`以及Azure O
 > **ⓘ** 注意，如果您使用Azure OpenAI，请确保更改部署名称以使用您选择的模型的部署。
 
 ```typescript
-const responseB = await chat.call([
+const responseB = await chat.invoke([
 
-  new SystemChatMessage(
+  new SystemMessage(
 
     "You are a helpful assistant that translates English to French."
 
   ),
 
-  new HumanChatMessage("Translate: I love programming."),
+  new HumanMessage("Translate: I love programming."),
 
 ]);
 
@@ -95,7 +95,7 @@ console.log(responseB);
 
 
 ```
-AIChatMessage { text: "J'aime programmer." }
+AIMessage { text: "J'aime programmer." }
 
 ```
 
@@ -109,13 +109,13 @@ const responseC = await chat.generate([
 
   [
 
-    new SystemChatMessage(
+    new SystemMessage(
 
       "You are a helpful assistant that translates English to French."
 
     ),
 
-    new HumanChatMessage(
+    new HumanMessage(
 
       "Translate this sentence from English to French. I love programming."
 
@@ -125,13 +125,13 @@ const responseC = await chat.generate([
 
   [
 
-    new SystemChatMessage(
+    new SystemMessage(
 
       "You are a helpful assistant that translates English to French."
 
     ),
 
-    new HumanChatMessage(
+    new HumanMessage(
 
       "Translate this sentence from English to French. I love artificial intelligence."
 
@@ -159,7 +159,7 @@ console.log(responseC);
 
         text: "J'aime programmer.",
 
-        message: AIChatMessage { text: "J'aime programmer." },
+        message: AIMessage { text: "J'aime programmer." },
 
       }
 
@@ -171,7 +171,7 @@ console.log(responseC);
 
         text: "J'aime l'intelligence artificielle.",
 
-        message: AIChatMessage { text: "J'aime l'intelligence artificielle." }
+        message: AIMessage { text: "J'aime l'intelligence artificielle." }
 
       }
 
@@ -257,7 +257,7 @@ console.log(responseA);
 
         text: "J'aime programmer.",
 
-        message: AIChatMessage { text: "J'aime programmer." }
+        message: AIMessage { text: "J'aime programmer." }
 
       }
 
@@ -293,7 +293,7 @@ const chain = new LLMChain({
 
 
 ```typescript
-const responseB = await chain.call({
+const responseB = await chain.invoke({
 
   input_language: "English",
 
@@ -509,7 +509,7 @@ const chain = new ConversationChain({
 该链将内部累加发送到模型和接收的输出消息。然后，在下一次调用时，它将把消息注入提示符中。所以你可以多次调用该链，并且它会记住先前的消息。(The chain will internally accumulate the messages sent to the model and the ones received as output. Then it will inject the messages into the prompt on the next call. So you can call the chain a few times and it remembers previous messages.)
 
 ```typescript
-const responseH = await chain.call({
+const responseH = await chain.invoke({
 
   input: "hi from London, how are you doing today",
 

docs/getting-started/guide-llm.mdx

@@ -143,7 +143,7 @@ import { OpenAI } from "langchain/llms/openai";
 初始化wrapper后，我们现在可以在一些输入上调用它！
 
 ```typescript
-const res = await model.call(
+const res = await model.invoke(
 
   "What would be a good company name a company that makes colorful socks?"
 
@@ -262,7 +262,7 @@ const chain = new LLMChain({ llm: model, prompt: prompt });
 
 ```typescript
 
-const res = await chain.call({ product: "colorful socks" });
+const res = await chain.invoke({ product: "colorful socks" });
 
 console.log(res);
 
@@ -369,7 +369,7 @@ console.log(`Executing with input "${input}"...`);
 
 
 
-const result = await executor.call({ input });
+const result = await executor.invoke({ input });
 
 
 
@@ -409,7 +409,7 @@ const memory = new BufferMemory();
 
 const chain = new ConversationChain({ llm: model, memory: memory });
 
-const res1 = await chain.call({ input: "Hi! I'm Jim." });
+const res1 = await chain.invoke({ input: "Hi! I'm Jim." });
 
 console.log(res1);
 
@@ -423,7 +423,7 @@ console.log(res1);
 
 
 ```typescript
-const res2 = await chain.call({ input: "What's my name?" });
+const res2 = await chain.invoke({ input: "What's my name?" });
 
 console.log(res2);
 

docs/modules/agents/toolkits/json.md

@@ -60,7 +60,7 @@ export const run = async () => {
 
 
 
-  const result = await executor.call({ input });
+  const result = await executor.invoke({ input });
 
 
 

docs/modules/agents/toolkits/openapi.md

@@ -66,7 +66,7 @@ export const run = async () => {
 
 
 
-  const result = await executor.call({ input });
+  const result = await executor.invoke({ input });
 
   console.log(`Got output ${result.output}`);
 

docs/modules/agents/tools/agents_with_vectorstores.md

@@ -123,7 +123,7 @@ console.log(`Executing with input "${input}"...`);
 
 
 
-const result = await executor.call({ input });
+const result = await executor.invoke({ input });
 
 
 

docs/modules/agents/tools/dynamic.mdx

@@ -80,7 +80,7 @@ export const run = async () => {
 
 
 
-  const result = await executor.call({ input });
+  const result = await executor.invoke({ input });
 
 
 

docs/modules/agents/tools/lambda_agent.md

@@ -68,7 +68,7 @@ const executor = await initializeAgentExecutorWithOptions(tools, model, {
 
 const input = `Find out the capital of Croatia. Once you have it, email the answer to testing123@gmail.com.`;
 
-const result = await executor.call({ input });
+const result = await executor.invoke({ input });
 
 console.log(result);
 

docs/modules/indexes/vector_stores/integrations/opensearch.md

@@ -162,7 +162,7 @@ const chain = VectorDBQAChain.fromLLM(model, vectorStore, {
 
 });
 
-const response = await chain.call({ query: "What is opensearch?" });
+const response = await chain.invoke({ query: "What is opensearch?" });
 
 
 

docs/modules/indexes/vector_stores/integrations/pinecone.md

@@ -182,7 +182,7 @@ const chain = VectorDBQAChain.fromLLM(model, vectorStore, {
 
 });
 
-const response = await chain.call({ query: "What is pinecone?" });
+const response = await chain.invoke({ query: "What is pinecone?" });
 
 console.log(response);
 

docs/modules/memory/examples/buffer_memory.md

@@ -17,7 +17,7 @@ const memory = new BufferMemory();
 
 const chain = new ConversationChain({ llm: model, memory: memory });
 
-const res1 = await chain.call({ input: "Hi! I'm Jim." });
+const res1 = await chain.invoke({ input: "Hi! I'm Jim." });
 
 console.log({ res1 });
 
@@ -31,7 +31,7 @@ console.log({ res1 });
 
 
 ```typescript
-const res2 = await chain.call({ input: "What's my name?" });
+const res2 = await chain.invoke({ input: "What's my name?" });
 
 console.log({ res2 });
 
@@ -50,15 +50,15 @@ console.log({ res2 });
 
 import { ChatMessageHistory } from "langchain/memory";
 
-import { HumanChatMessage, AIChatMessage } from "langchain/schema";
+import { HumanMessage, AIMessage } from "langchain/schema";
 
 
 
 const pastMessages = [
 
-  new HumanChatMessage("My name's Jonas"),
+  new HumanMessage("My name's Jonas"),
 
-  new AIChatMessage("Nice to meet you, Jonas!"),
+  new AIMessage("Nice to meet you, Jonas!"),
 
 ];
 

docs/modules/memory/examples/buffer_window_memory.md

@@ -19,7 +19,7 @@ const memory = new BufferWindowMemory({ k: 1 });
 
 const chain = new ConversationChain({ llm: model, memory: memory });
 
-const res1 = await chain.call({ input: "Hi! I'm Jim." });
+const res1 = await chain.invoke({ input: "Hi! I'm Jim." });
 
 console.log({ res1 });
 
@@ -33,7 +33,7 @@ console.log({ res1 });
 
 
 ```typescript
-const res2 = await chain.call({ input: "What's my name?" });
+const res2 = await chain.invoke({ input: "What's my name?" });
 
 console.log({ res2 });
 

docs/modules/memory/examples/motorhead_memory.md

@@ -74,7 +74,7 @@ const chain = new ConversationChain({
 
 
 
-const res1 = await chain.call({ input: "Hi! I'm Jim." });
+const res1 = await chain.invoke({ input: "Hi! I'm Jim." });
 
 console.log({ res1 });
 
@@ -90,7 +90,7 @@ console.log({ res1 });
 
 
 ```typescript
-const res2 = await chain.call({ input: "What's my name?" });
+const res2 = await chain.invoke({ input: "What's my name?" });
 
 console.log({ res2 });
 

docs/modules/models/chat/index.mdx

@@ -27,12 +27,12 @@ LangChain提供了一个标准接口来使用聊天模型。聊天模型是语
 
 目前LangChain支持四种不同类型的“聊天消息”:
 
-- `HumanChatMessage`: 模拟一个人类的视角发送的聊天消息。
-- `AIChatMessage`: 从AI系统的角度发送的聊天消息，用于与人类进行通信。
-- `SystemChatMessage`: 一种用于向AI系统提供有关对话信息的聊天消息。通常在对话开始时发送。
+- `HumanMessage`: 模拟一个人类的视角发送的聊天消息。
+- `AIMessage`: 从AI系统的角度发送的聊天消息，用于与人类进行通信。
+- `SystemMessage`: 一种用于向AI系统提供有关对话信息的聊天消息。通常在对话开始时发送。
 - `ChatMessage`: 一个通用的聊天消息，不仅有一个“文本”字段，还有一个任意的“角色”字段。
 
-要开始使用，只需使用“LLM”实现的“call”方法，传入一个字符串输入。在这个例子中，我们使用的是“ChatOpenAI”实现:
+要开始使用，只需使用“LLM”实现的“invoke”方法，传入一个字符串输入。在这个例子中，我们使用的是“ChatOpenAI”实现:
 
 <CodeBlock language="typescript">{Example}</CodeBlock>
 

docs/modules/models/chat/integrations.mdx

@@ -55,7 +55,7 @@ const respA = await chat.generate([
 
   [
 
-    new SystemChatMessage(
+    new SystemMessage(
 
       "You are a helpful assistant that translates English to French."
 
@@ -148,9 +148,9 @@ npm install google-auth-library
 
 ChatGoogleVertexAI 类的工作方式与其他基于聊天的 LLM 相同，具有一些例外情况:
 
-1. 第一个传入的 `SystemChatMessage` 被映射到 PaLM 模型期望的 "context" 参数。
-2. 不允许出现其他 `SystemChatMessage`。
-3. 在第一个 `SystemChatMessage` 之后，必须是一串奇数条消息，代表人类和模型之间的对话。
+1. 第一个传入的 `SystemMessage` 被映射到 PaLM 模型期望的 "context" 参数。
+2. 不允许出现其他 `SystemMessage`。
+3. 在第一个 `SystemMessage` 之后，必须是一串奇数条消息，代表人类和模型之间的对话。
 4. 发送的信息必须交错出现，先是人类信息，然后是 AI 回复，然后是人类信息，以此类推。