Merge c3b50a9c93 into 3809375694

Support OpenAI o3 and o4-mini

README.md

@@ -22,7 +22,7 @@ English / [简体中文](./README_CN.md)
 [![MacOS][MacOS-image]][download-url]
 [![Linux][Linux-image]][download-url]
 
-[NextChatAI](https://nextchat.club?utm_source=readme) / [Web App Demo](https://app.nextchat.dev) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [Discord](https://discord.gg/YCkeafCafC) / [Enterprise Edition](#enterprise-edition) / [Twitter](https://twitter.com/NextChatDev)
+[NextChatAI](https://nextchat.club?utm_source=readme) / [iOS APP](https://apps.apple.com/us/app/nextchat-ai/id6743085599) / [Web App Demo](https://app.nextchat.dev) / [Desktop App](https://github.com/Yidadaa/ChatGPT-Next-Web/releases) / [Enterprise Edition](#enterprise-edition) 
 
 
 [saas-url]: https://nextchat.club?utm_source=readme
@@ -40,13 +40,14 @@ English / [简体中文](./README_CN.md)
 
 </div>
 
-## 🥳 Cheer for DeepSeek, China's AI star!
+## 🥳 Cheer for NextChat iOS Version Online!
- > Purpose-Built UI for DeepSeek Reasoner Model
+> [👉 Click Here to Install Now](https://apps.apple.com/us/app/nextchat-ai/id6743085599)
+
+> [❤️ Source Code Coming Soon](https://github.com/ChatGPTNextWeb/NextChat-iOS)
+
+![Github iOS Image](https://github.com/user-attachments/assets/e0aa334f-4c13-4dc9-8310-e3b09fa4b9f3)
+
  
-<img src="https://github.com/user-attachments/assets/f3952210-3af1-4dc0-9b81-40eaa4847d9a"/>
-
-
-
 ## 🫣 NextChat Support MCP  ! 
 > Before build, please set env ENABLE_MCP=true
 

app/client/platforms/openai.ts

@@ -198,7 +198,8 @@ export class ChatGPTApi implements LLMApi {
     const isDalle3 = _isDalle3(options.config.model);
     const isO1OrO3 =
       options.config.model.startsWith("o1") ||
-      options.config.model.startsWith("o3");
+      options.config.model.startsWith("o3") ||
+      options.config.model.startsWith("o4-mini");
     if (isDalle3) {
       const prompt = getMessageTextContent(
         options.messages.slice(-1)?.pop() as any,
@@ -243,7 +244,7 @@ export class ChatGPTApi implements LLMApi {
       }
 
       // add max_tokens to vision model
-      if (visionModel) {
+      if (visionModel && !isO1OrO3) {
         requestPayload["max_tokens"] = Math.max(modelConfig.max_tokens, 4000);
       }
     }

app/components/tts-config.tsx

@@ -1,19 +1,76 @@
 import { TTSConfig, TTSConfigValidator } from "../store";
+import React, { useState } from "react";
 
 import Locale from "../locales";
 import { ListItem, Select } from "./ui-lib";
 import {
+  ModelProvider,
   DEFAULT_TTS_ENGINE,
   DEFAULT_TTS_ENGINES,
   DEFAULT_TTS_MODELS,
   DEFAULT_TTS_VOICES,
 } from "../constant";
 import { InputRange } from "./input-range";
+import { IconButton } from "./button";
+import SpeakIcon from "../icons/speak.svg";
+import SpeakStopIcon from "../icons/speak-stop.svg";
+import { createTTSPlayer } from "../utils/audio";
+import { useAppConfig } from "../store";
+import { ClientApi } from "../client/api";
+import { showToast } from "../components/ui-lib";
 
+const ttsPlayer = createTTSPlayer();
 export function TTSConfigList(props: {
   ttsConfig: TTSConfig;
   updateConfig: (updater: (config: TTSConfig) => void) => void;
 }) {
+  const [speechLoading, setSpeechLoading] = useState(false);
+  const [speechStatus, setSpeechStatus] = useState(false);
+
+  const config = useAppConfig.getState();
+
+  function stopSpeech() {
+    ttsPlayer.stop();
+    setSpeechStatus(false);
+  }
+
+  async function playSpeech(text: string, ttsConfig: TTSConfig) {
+    try {
+      const api = new ClientApi(ModelProvider.GPT);
+      setSpeechLoading(true);
+      ttsPlayer.init();
+
+      const audioBuffer = await api.llm.speech({
+        model: ttsConfig.model,
+        input: text,
+        voice: ttsConfig.voice,
+        speed: ttsConfig.speed,
+      });
+
+      setSpeechStatus(true);
+      await ttsPlayer.play(audioBuffer, () => {
+        setSpeechStatus(false);
+      });
+    } catch (error) {
+      console.error("[OpenAI Speech]", error);
+      setSpeechStatus(false);
+      // Implement user-facing error notification here
+      if (typeof (error as Error).message === "string") {
+        showToast((error as Error).message);
+      }
+    } finally {
+      setSpeechLoading(false);
+    }
+  }
+
+  async function openaiSpeech(text: string) {
+    if (speechStatus) {
+      stopSpeech();
+    } else {
+      await playSpeech(text, config.ttsConfig);
+    }
+  }
+
   return (
     <>
       <ListItem
@@ -88,23 +145,41 @@ export function TTSConfigList(props: {
             title={Locale.Settings.TTS.Voice.Title}
             subTitle={Locale.Settings.TTS.Voice.SubTitle}
           >
-            <Select
+            <div style={{ display: "flex", gap: "10px" }}>
-              value={props.ttsConfig.voice}
+              <IconButton
-              onChange={(e) => {
+                aria={Locale.Chat.Actions.Speech}
-                props.updateConfig(
+                icon={speechStatus ? <SpeakStopIcon /> : <SpeakIcon />}
-                  (config) =>
+                text={
-                    (config.voice = TTSConfigValidator.voice(
+                  speechLoading
+                    ? "Loading..."
+                    : speechStatus
+                    ? Locale.Chat.Actions.Stop
+                    : Locale.Chat.Actions.Speech
+                }
+                onClick={() => {
+                  openaiSpeech(
+                    "NextChat,Unleash your imagination, experience the future of AI conversation.",
+                  );
+                }}
+              />
+
+              <Select
+                value={props.ttsConfig.voice}
+                onChange={(e) => {
+                  props.updateConfig((config) => {
+                    config.voice = TTSConfigValidator.voice(
                       e.currentTarget.value,
-                    )),
+                    );
-                );
+                  });
-              }}
+                }}
-            >
+              >
-              {DEFAULT_TTS_VOICES.map((v, i) => (
+                {DEFAULT_TTS_VOICES.map((v, i) => (
-                <option value={v} key={i}>
+                  <option value={v} key={i}>
-                  {v}
+                    {v}
-                </option>
+                  </option>
-              ))}
+                ))}
-            </Select>
+              </Select>
+            </div>
           </ListItem>
           <ListItem
             title={Locale.Settings.TTS.Speed.Title}

app/constant.ts

@@ -417,6 +417,14 @@ export const KnowledgeCutOffDate: Record<string, string> = {
   "gpt-4-turbo": "2023-12",
   "gpt-4-turbo-2024-04-09": "2023-12",
   "gpt-4-turbo-preview": "2023-12",
+  "gpt-4.1": "2024-06",
+  "gpt-4.1-2025-04-14": "2024-06",
+  "gpt-4.1-mini": "2024-06",
+  "gpt-4.1-mini-2025-04-14": "2024-06",
+  "gpt-4.1-nano": "2024-06",
+  "gpt-4.1-nano-2025-04-14": "2024-06",
+  "gpt-4.5-preview": "2023-10",
+  "gpt-4.5-preview-2025-02-27": "2023-10",
   "gpt-4o": "2023-10",
   "gpt-4o-2024-05-13": "2023-10",
   "gpt-4o-2024-08-06": "2023-10",
@@ -458,6 +466,7 @@ export const DEFAULT_TTS_VOICES = [
 export const VISION_MODEL_REGEXES = [
   /vision/,
   /gpt-4o/,
+  /gpt-4\.1/,
   /claude-3/,
   /gemini-1\.5/,
   /gemini-exp/,
@@ -469,6 +478,8 @@ export const VISION_MODEL_REGEXES = [
   /^dall-e-3$/, // Matches exactly "dall-e-3"
   /glm-4v/,
   /vl/i,
+  /o3/,
+  /o4-mini/,
 ];
 
 export const EXCLUDE_VISION_MODEL_REGEXES = [/claude-3-5-haiku-20241022/];
@@ -485,6 +496,14 @@ const openaiModels = [
   "gpt-4-32k-0613",
   "gpt-4-turbo",
   "gpt-4-turbo-preview",
+  "gpt-4.1",
+  "gpt-4.1-2025-04-14",
+  "gpt-4.1-mini",
+  "gpt-4.1-mini-2025-04-14",
+  "gpt-4.1-nano",
+  "gpt-4.1-nano-2025-04-14",
+  "gpt-4.5-preview",
+  "gpt-4.5-preview-2025-02-27",
   "gpt-4o",
   "gpt-4o-2024-05-13",
   "gpt-4o-2024-08-06",
@@ -499,6 +518,8 @@ const openaiModels = [
   "o1-mini",
   "o1-preview",
   "o3-mini",
+  "o3",
+  "o4-mini",
 ];
 
 const googleModels = [