@lobehub/chat 1.16.13 → 1.16.14

package/CHANGELOG.md

@@ -2,6 +2,31 @@
 
 # Changelog
 
+### [Version 1.16.14](https://github.com/lobehub/lobe-chat/compare/v1.16.13...v1.16.14)
+
+<sup>Released on **2024-09-13**</sup>
+
+#### 💄 Styles
+
+- **model**: Remove `OpenAI` deprecated model.
+
+<br/>
+
+<details>
+<summary><kbd>Improvements and Fixes</kbd></summary>
+
+#### Styles
+
+- **model**: Remove `OpenAI` deprecated model, closes [#3465](https://github.com/lobehub/lobe-chat/issues/3465) ([68a4fb2](https://github.com/lobehub/lobe-chat/commit/68a4fb2))
+
+</details>
+
+<div align="right">
+
+[![](https://img.shields.io/badge/-BACK_TO_TOP-151515?style=flat-square)](#readme-top)
+
+</div>
+
 ### [Version 1.16.13](https://github.com/lobehub/lobe-chat/compare/v1.16.12...v1.16.13)
 
 <sup>Released on **2024-09-13**</sup>

package/docs/usage/agents/model.mdx

@@ -17,7 +17,6 @@ tags:
 ## ChatGPT
 
 - **gpt-3.5-turbo**: Currently the fastest generating ChatGPT model, it is faster but may sacrifice some text quality, with a context length of 4k.
-- **gpt-3.5-turbo-16k**: Similar to gpt-4, the context limit is increased to 16k tokens, with a higher cost.
 - **gpt-4**: ChatGPT 4.0 has improved language understanding and generation capabilities compared to 3.5. It can better understand context and context, and generate more accurate and natural responses. This is thanks to improvements in the GPT-4 model, including better language modeling and deeper semantic understanding, but it may be slower than other models, with a context length of 8k.
 - **gpt-4-32k**: Similar to gpt-4, the context limit is increased to 32k tokens, with a higher cost.
 

package/docs/usage/agents/model.zh-CN.mdx

@@ -16,7 +16,6 @@ tags:
 ## ChatGPT
 
 - **gpt-3.5-turbo**：目前最生成速度最快的 chatgpt 模型更快，但可能会牺牲一些生成文本的质量，上下文长度为 4k。
-- **gpt-3.5-turbo-16k**：同 gpt-4，上下文限制增加到 16k token，同时费率更高。
 - **gpt-4**：ChatGPT 4.0 在语言理解和生成能力方面相对于 3.5 有所提升。它可以更好地理解上下文和语境，并生成更准确、自然的回答。这得益于 GPT-4 模型的改进，包括更好的语言建模和更深入的语义理解，但它的速度可能比其他模型慢，上下文长度为 8k。
 - **gpt-4-32k**：同 gpt-4，上下文限制增加到 32k token，同时费率更高。
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@lobehub/chat",
-  "version": "1.16.13",
+  "version": "1.16.14",
   "description": "Lobe Chat - an open-source, high-performance chatbot framework that supports speech synthesis, multimodal, and extensible Function Call plugin system. Supports one-click free deployment of your private ChatGPT/LLM web application.",
   "keywords": [
     "framework",

package/src/config/modelProviders/openai.ts

@@ -253,43 +253,6 @@ const OpenAI: ModelProviderCard = {
       },
       tokens: 4096,
     },
-    {
-      description:
-        'GPT 3.5 Turbo，适用于各种文本生成和理解任务，Currently points to gpt-3.5-turbo-0125', // Will be discontinued on September 13, 2024
-
-      displayName: 'GPT-3.5 Turbo 16K',
-      id: 'gpt-3.5-turbo-16k',
-      legacy: true,
-      pricing: {
-        input: 3,
-        output: 4,
-      },
-      tokens: 16_385,
-    },
-    {
-      description:
-        'GPT-3.5 Turbo 是 OpenAI 的一款基础模型，结合了高效性和经济性，广泛用于文本生成、理解和分析，专为指导性提示进行调整，去除了与聊天相关的优化。',
-      displayName: 'GPT-3.5 Turbo 0613',
-      // Will be discontinued on September 13, 2024
-      id: 'gpt-3.5-turbo-0613',
-      legacy: true,
-      pricing: {
-        input: 1.5,
-        output: 2,
-      },
-      tokens: 4096,
-    },
-    {
-      description:
-        'GPT-3.5 Turbo 是 OpenAI 的一款基础模型，结合了高效性和经济性，广泛用于文本生成、理解和分析，专为指导性提示进行调整，去除了与聊天相关的优化。', // Will be discontinued on September 13, 2024
-      id: 'gpt-3.5-turbo-16k-0613',
-      legacy: true,
-      pricing: {
-        input: 3,
-        output: 4,
-      },
-      tokens: 16_385,
-    },
   ],
   checkModel: 'gpt-4o-mini',
   description:

package/src/libs/agent-runtime/openai/__snapshots__/index.test.ts.snap

@@ -14,25 +14,10 @@ exports[`LobeOpenAI > models > should get models 1`] = `
     "tokens": 16385,
   },
   {
-    "description": "GPT 3.5 Turbo，适用于各种文本生成和理解任务，Currently points to gpt-3.5-turbo-0125",
-    "displayName": "GPT-3.5 Turbo 16K",
     "id": "gpt-3.5-turbo-16k",
-    "legacy": true,
-    "pricing": {
-      "input": 3,
-      "output": 4,
-    },
-    "tokens": 16385,
   },
   {
-    "description": "GPT-3.5 Turbo 是 OpenAI 的一款基础模型，结合了高效性和经济性，广泛用于文本生成、理解和分析，专为指导性提示进行调整，去除了与聊天相关的优化。",
     "id": "gpt-3.5-turbo-16k-0613",
-    "legacy": true,
-    "pricing": {
-      "input": 3,
-      "output": 4,
-    },
-    "tokens": 16385,
   },
   {
     "description": "最新的 GPT-4 Turbo 模型具备视觉功能。现在，视觉请求可以使用 JSON 模式和函数调用。 GPT-4 Turbo 是一个增强版本，为多模态任务提供成本效益高的支持。它在准确性和效率之间找到平衡，适合需要进行实时交互的应用程序场景。",
@@ -83,15 +68,7 @@ exports[`LobeOpenAI > models > should get models 1`] = `
     "id": "gpt-3.5-turbo-0301",
   },
   {
-    "description": "GPT-3.5 Turbo 是 OpenAI 的一款基础模型，结合了高效性和经济性，广泛用于文本生成、理解和分析，专为指导性提示进行调整，去除了与聊天相关的优化。",
-    "displayName": "GPT-3.5 Turbo 0613",
     "id": "gpt-3.5-turbo-0613",
-    "legacy": true,
-    "pricing": {
-      "input": 1.5,
-      "output": 2,
-    },
-    "tokens": 4096,
   },
   {
     "description": "GPT 3.5 Turbo，适用于各种文本生成和理解任务，Currently points to gpt-3.5-turbo-0125",

package/src/server/routers/edge/config/__snapshots__/index.test.ts.snap

@@ -61,18 +61,6 @@ exports[`configRouter > getGlobalConfig > Model Provider env > OPENAI_MODEL_LIST
     },
     "tokens": 16385,
   },
-  {
-    "description": "GPT 3.5 Turbo，适用于各种文本生成和理解任务，Currently points to gpt-3.5-turbo-0125",
-    "displayName": "GPT-3.5 Turbo 16K",
-    "enabled": true,
-    "id": "gpt-3.5-turbo-16k",
-    "legacy": true,
-    "pricing": {
-      "input": 3,
-      "output": 4,
-    },
-    "tokens": 16385,
-  },
   {
     "description": "GPT-4 提供了一个更大的上下文窗口，能够处理更长的文本输入，适用于需要广泛信息整合和数据分析的场景。",
     "displayName": "GPT-4",

package/src/server/routers/edge/config/index.test.ts

@@ -45,7 +45,7 @@ describe('configRouter', () => {
 
         it('should work correct with gpt-4', async () => {
           process.env.OPENAI_MODEL_LIST =
-            '-all,+gpt-3.5-turbo-1106,+gpt-3.5-turbo,+gpt-3.5-turbo-16k,+gpt-4,+gpt-4-32k,+gpt-4-1106-preview,+gpt-4-vision-preview';
+            '-all,+gpt-3.5-turbo-1106,+gpt-3.5-turbo,+gpt-4,+gpt-4-32k,+gpt-4-1106-preview,+gpt-4-vision-preview';
 
           const response = await router.getGlobalConfig();