javascript chat update.

examples/server/README.md

@@ -167,7 +167,7 @@ node .
 ### Interactive mode
 
 Check the sample in [chat.mjs](chat.mjs).
-Run with node:
+Run with NodeJS version 16 or later:
 
 ```sh
 node chat.mjs

examples/server/chat.mjs

@@ -1,61 +1,87 @@
-import * as readline from 'node:readline/promises';
+import * as readline from 'node:readline'
-import { stdin as input, stdout as output } from 'node:process';
+import { stdin, stdout } from 'node:process'
 
 const chat = [
-  { human: "Hello, Assistant.",
+    {
-    assistant: "Hello. How may I help you today?" },
+        human: "Hello, Assistant.",
-  { human: "Please tell me the largest city in Europe.",
+        assistant: "Hello. How may I help you today?"
-    assistant: "Sure. The largest city in Europe is Moscow, the capital of Russia." },
+    },
+    {
+        human: "Please tell me the largest city in Europe.",
+        assistant: "Sure. The largest city in Europe is Moscow, the capital of Russia."
+    },
 ]
 
+const instruction = `A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.`
+
 function format_prompt(question) {
-  return "A chat between a curious human and an artificial intelligence assistant. "
+    return `${instruction}\n${
-    + "The assistant gives helpful, detailed, and polite answers to the human's questions.\n"
+        chat.map(m =>`### Human: ${m.human}\n### Assistant: ${m.assistant}`).join("\n")
-    + chat.map(m => `### Human: ${m.human}\n### Assistant: ${m.assistant}`).join("\n")
+    }\n### Human: ${question}\n### Assistant:`
-    + `\n### Human: ${question}\n### Assistant:`
 }
 
-async function ChatCompletion(question) {
+async function tokenize(content) {
-  const result = await fetch("http://127.0.0.1:8080/completion", {
+    const result = await fetch("http://127.0.0.1:8080/tokenize", {
-    method: 'POST',
+        method: 'POST',
-    body: JSON.stringify({
+        body: JSON.stringify({ content })
-      prompt: format_prompt(question),
-      temperature: 0.2,
-      top_k: 40,
-      top_p: 0.9,
-      n_keep: 29,
-      n_predict: 256,
-      stop: ["\n### Human:"], // stop completion after generating this
-      stream: true,
     })
-  })
 
-  if (!result.ok) {
+    if (!result.ok) {
-    return;
+        return []
-  }
-
-  let answer = ''
-
-  for await (var chunk of result.body) {
-    const t = Buffer.from(chunk).toString('utf8')
-    if (t.startsWith('data: ')) {
-      const message = JSON.parse(t.substring(6))
-      answer += message.content
-      process.stdout.write(message.content)
-      if (message.stop) break;
     }
-  }
 
-  process.stdout.write('\n')
+    return await result.json().tokens
-  chat.push({ human: question, assistant: answer })
 }
 
-const rl = readline.createInterface({ input, output });
+const n_keep = await tokenize(instruction).length
+
+async function chat_completion(question) {
+    const result = await fetch("http://127.0.0.1:8080/completion", {
+        method: 'POST',
+        body: JSON.stringify({
+            prompt: format_prompt(question),
+            temperature: 0.2,
+            top_k: 40,
+            top_p: 0.9,
+            n_keep: n_keep,
+            n_predict: 256,
+            stop: ["\n### Human:"], // stop completion after generating this
+            stream: true,
+        })
+    })
+
+    if (!result.ok) {
+        return
+    }
+
+    let answer = ''
+
+    for await (var chunk of result.body) {
+        const t = Buffer.from(chunk).toString('utf8')
+        if (t.startsWith('data: ')) {
+            const message = JSON.parse(t.substring(6))
+            answer += message.content
+            process.stdout.write(message.content)
+            if (message.stop) {
+                if (message.truncated) {
+                    chat.shift()
+                }
+                break
+            }
+        }
+    }
+
+    process.stdout.write('\n')
+    chat.push({ human: question, assistant: answer.trimStart() })
+}
+
+const rl = readline.createInterface({ input: stdin, output: stdout });
+
+const readlineQuestion = (rl, query, options) => new Promise((resolve, reject) => {
+    rl.question(query, options, resolve)
+});
 
 while(true) {
-
+    const question = await readlineQuestion(rl, '> ')
-  const question = await rl.question('> ')
+    await chat_completion(question)
-  await ChatCompletion(question);
-
 }
-