@lobehub/chat 1.44.2 → 1.45.0

package/docs/usage/tools-calling/groq.zh-CN.mdx

@@ -17,11 +17,11 @@ tags:
 
 Groq 平台的模型 Tools Calling 能力一览：
 
-| 模型         | 支持 Tools Calling | 流式 （Stream） | 并发（Parallel） | 简单指令得分 | 复杂指令 |
-| ------------ | ------------------ | --------------- | ---------------- | ------------ | -------- |
-| LLAMA3 70B   | ✅                 | ❌              | ✅               | 🌟🌟         | 🌟🌟     |
-| LLAMA3 8B    | ✅                 | ❌              | ✅               | 🌟🌟         | 🌟       |
-| Mixtral-8x7B | ✅                 | ❌              | ✅               | ⛔           | 🌟🌟     |
+| 模型           | 支持 Tools Calling | 流式 （Stream） | 并发（Parallel） | 简单指令得分 | 复杂指令 |
+| ------------ | ---------------- | ----------- | ------------ | ------ | ---- |
+| LLAMA3 70B   | ✅                | ❌           | ✅            | 🌟🌟   | 🌟🌟 |
+| LLAMA3 8B    | ✅                | ❌           | ✅            | 🌟🌟   | 🌟   |
+| Mixtral-8x7B | ✅                | ❌           | ✅            | ⛔      | 🌟🌟 |
 
 ## LLAMA3 70B
 
@@ -33,21 +33,17 @@ Groq 平台的模型 Tools Calling 能力一览：
 
 从上述视频中可以看到 LLAMA3 70B 支持并发 Tools Calling，可以同时调用多次天气查询。
 
-<Image
-  alt="LLAMA3 70B 简单指令的 Tools Calling"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/f9cd0d4d-0e44-4bff-98cc-560f11259a60"
-/>
+<Image alt="LLAMA3 70B 简单指令的 Tools Calling" src="https://github.com/lobehub/lobe-chat/assets/28616219/f9cd0d4d-0e44-4bff-98cc-560f11259a60" />
 
 <details>
   <summary>Tools Calling 原始输出：</summary>
 
-```yml
-[no stream response] 2024-7-8 15:50:40.166
+  ```yml
+  [no stream response] 2024-7-8 15:50:40.166
 
-{"id":"chatcmpl-ec4b6c0b-1078-4f50-a39c-e58b3b1f9c31","object":"chat.completion","created":1720425030,"model":"llama3-70b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_v89g","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"杭州\"}"}},{"id":"call_jxwk","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"北京}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":969,"prompt_time":0.224209489,"completion_tokens":68,"completion_time":0.194285714,"total_tokens":1037,"total_time":0.418495203},"system_fingerprint":"fp_87cbfbbc4d","x_groq":{"id":"req_01j28n57x9e78a6bfbn9sdn139"}}
-
-```
+  {"id":"chatcmpl-ec4b6c0b-1078-4f50-a39c-e58b3b1f9c31","object":"chat.completion","created":1720425030,"model":"llama3-70b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_v89g","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"杭州\"}"}},{"id":"call_jxwk","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"北京}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":969,"prompt_time":0.224209489,"completion_tokens":68,"completion_time":0.194285714,"total_tokens":1037,"total_time":0.418495203},"system_fingerprint":"fp_87cbfbbc4d","x_groq":{"id":"req_01j28n57x9e78a6bfbn9sdn139"}}
 
+  ```
 </details>
 
 ### 复杂调用指令：文生图
@@ -56,22 +52,18 @@ Groq 平台的模型 Tools Calling 能力一览：
 
 <Video src="https://github.com/lobehub/lobe-chat/assets/28616219/b790f5d8-e797-4325-a974-436505b16fba" />
 
-<Image
-  alt="LLAMA3 70B 复杂指令的 Tools Calling"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/082170fa-6d09-4602-8e23-eb678024305f"
-/>
+<Image alt="LLAMA3 70B 复杂指令的 Tools Calling" src="https://github.com/lobehub/lobe-chat/assets/28616219/082170fa-6d09-4602-8e23-eb678024305f" />
 
 <details>
-<summary>Tools Calling 原始输出：</summary>
-
-```yml
-[no stream response] 2024-7-8 18:0:34.811
+  <summary>Tools Calling 原始输出：</summary>
 
-{"id":"chatcmpl-e3b59ca9-1172-4ae2-96c7-3d6997a1f8a8","object":"chat.completion","created":1720432834,"model":"llama3-70b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_azm9","type":"function","function":{"name":"lobe-image-designer____text2image____builtin","arguments":"{\"prompts\":[\"A small, fluffy, and playful golden retriever puppy with a white patch on its forehead, sitting on a green grass field with a bright blue sky in the background, photo.\",\"A cute, little, brown and white Dalmatian puppy with a red collar, running around in a park with a sunny day, illustration.\",\"A tiny, grey and white Poodle puppy with a pink ribbon, sitting on a white couch with a few toys surrounding it, watercolor painting.\",\"A sweet, small, black and white Chihuahua puppy with a pink bow, lying on a soft, white blanket with a few stuffed animals nearby, oil painting.\"],\"quality\":\"standard\",\"seeds\":[],\"size\":\"1024x1024\",\"style\":\"vivid\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":2305,"prompt_time":3.027052298,"completion_tokens":246,"completion_time":0.702857143,"total_tokens":2551,"total_time":3.729909441},"system_fingerprint":"fp_7ab5f7e105","x_groq":{"id":"req_01j28wk2q0efvs22qatw7rd0ds"}}
+  ```yml
+  [no stream response] 2024-7-8 18:0:34.811
 
-POST /api/chat/groq 200 in 17462ms
-```
+  {"id":"chatcmpl-e3b59ca9-1172-4ae2-96c7-3d6997a1f8a8","object":"chat.completion","created":1720432834,"model":"llama3-70b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_azm9","type":"function","function":{"name":"lobe-image-designer____text2image____builtin","arguments":"{\"prompts\":[\"A small, fluffy, and playful golden retriever puppy with a white patch on its forehead, sitting on a green grass field with a bright blue sky in the background, photo.\",\"A cute, little, brown and white Dalmatian puppy with a red collar, running around in a park with a sunny day, illustration.\",\"A tiny, grey and white Poodle puppy with a pink ribbon, sitting on a white couch with a few toys surrounding it, watercolor painting.\",\"A sweet, small, black and white Chihuahua puppy with a pink bow, lying on a soft, white blanket with a few stuffed animals nearby, oil painting.\"],\"quality\":\"standard\",\"seeds\":[],\"size\":\"1024x1024\",\"style\":\"vivid\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":2305,"prompt_time":3.027052298,"completion_tokens":246,"completion_time":0.702857143,"total_tokens":2551,"total_time":3.729909441},"system_fingerprint":"fp_7ab5f7e105","x_groq":{"id":"req_01j28wk2q0efvs22qatw7rd0ds"}}
 
+  POST /api/chat/groq 200 in 17462ms
+  ```
 </details>
 
 ## LLAMA3-8B
@@ -84,22 +76,18 @@ POST /api/chat/groq 200 in 17462ms
 
 从上述视频中可以看到 LLAMA3-8B 对于天气插件可以正常调用，并获得正确的总结结果。但是它并没有完全 follow 我们的描述指令，没有回答「好的」。
 
-<Image
-  alt="LLAMA3-8B 简单指令的 Tools Calling"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/9d553f4e-0818-4f6c-be9d-70da289dd723"
-/>
+<Image alt="LLAMA3-8B 简单指令的 Tools Calling" src="https://github.com/lobehub/lobe-chat/assets/28616219/9d553f4e-0818-4f6c-be9d-70da289dd723" />
 
 <details>
   <summary>Tools Calling 原始输出：</summary>
 
-```yml
-[no stream response] 2024-7-9 11:33:16.920
+  ```yml
+  [no stream response] 2024-7-9 11:33:16.920
 
-{"id":"chatcmpl-f3672d59-e91d-4253-af1b-bfc4e0912085","object":"chat.completion","created":1720495996,"model":"llama3-8b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_rjtk","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"杭州市\"}"}},{"id":"call_7pqh","type":"functi,"function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"北京市\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":969,"ppt_time":0.145428625,"completion_tokens":128,"completion_time":0.101364747,"total_tokens":1097,"total_time":0.246793372},"system_fingerprint":"fp_33d61fdfc3","x_groq":{"id":"req_01j2artze1exz82nettf2h9066"}}
-
-POST /api/chat/groq 200 in 1649ms
-```
+  {"id":"chatcmpl-f3672d59-e91d-4253-af1b-bfc4e0912085","object":"chat.completion","created":1720495996,"model":"llama3-8b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_rjtk","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"杭州市\"}"}},{"id":"call_7pqh","type":"functi,"function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"北京市\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":969,"ppt_time":0.145428625,"completion_tokens":128,"completion_time":0.101364747,"total_tokens":1097,"total_time":0.246793372},"system_fingerprint":"fp_33d61fdfc3","x_groq":{"id":"req_01j2artze1exz82nettf2h9066"}}
 
+  POST /api/chat/groq 200 in 1649ms
+  ```
 </details>
 
 ### 复杂调用指令：文生图
@@ -110,22 +98,18 @@ POST /api/chat/groq 200 in 1649ms
 
 LLAMA3 8B 在 DallE 的输出场景下，只会输出 1 张图片，而不是像 LLAMA3 70B 一样输出 4 张，意味着在复杂 Tools 指令层面，能力和 GPT 3.5 Turbo 接近，不如 GPT 4。
 
-<Image
-  alt="LLAMA3 8B 复杂指令的 Tools Calling"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/b0180793-5934-4296-a569-60fbc70e8262"
-/>
+<Image alt="LLAMA3 8B 复杂指令的 Tools Calling" src="https://github.com/lobehub/lobe-chat/assets/28616219/b0180793-5934-4296-a569-60fbc70e8262" />
 
 <details>
-<summary>Tools Calling 原始输出：</summary>
-
-```yml
-[no stream response] 2024-7-9 11:58:27.40
+  <summary>Tools Calling 原始输出：</summary>
 
-{"id":"chatcmpl-3c38f4d2-3424-416c-9fb0-0969d2683959","object":"chat.completion","created":1720497506,"model":"llama3-8b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_k6xj","type":"function","function":{"name":"lobe-image-designer____text2image____builtin","arguments":"{\"prompts\":[\"Create a watercolor painting of a small white dog with a pink nose, wearing a red collar and sitting on a green grass. The dog's ears should be floppy and its fur should be curly.\"],\"quality\":\"standard\",\"seeds\":[],\"size\":\"1024x1024\",\"style\":\"natural\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":2282,"prompt_time":0.342335558,"completion_tokens":148,"completion_time":0.118023813,"total_tokens":2430,"total_time":0.460359371},"system_fingerprint":"fp_179b0f92c9","x_groq":{"id":"req_01j2at921tec8aymdq48czcw1y"}}
+  ```yml
+  [no stream response] 2024-7-9 11:58:27.40
 
-POST /api/chat/groq 200 in 2517ms
-```
+  {"id":"chatcmpl-3c38f4d2-3424-416c-9fb0-0969d2683959","object":"chat.completion","created":1720497506,"model":"llama3-8b-8192","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_k6xj","type":"function","function":{"name":"lobe-image-designer____text2image____builtin","arguments":"{\"prompts\":[\"Create a watercolor painting of a small white dog with a pink nose, wearing a red collar and sitting on a green grass. The dog's ears should be floppy and its fur should be curly.\"],\"quality\":\"standard\",\"seeds\":[],\"size\":\"1024x1024\",\"style\":\"natural\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":2282,"prompt_time":0.342335558,"completion_tokens":148,"completion_time":0.118023813,"total_tokens":2430,"total_time":0.460359371},"system_fingerprint":"fp_179b0f92c9","x_groq":{"id":"req_01j2at921tec8aymdq48czcw1y"}}
 
+  POST /api/chat/groq 200 in 2517ms
+  ```
 </details>
 
 ## Mixtral-8x7B
@@ -138,23 +122,19 @@ POST /api/chat/groq 200 in 2517ms
 
 从上述视频中可以看到 Mixtral-8x7B 对于天气插件的查询输出的参数有问题，导致无法正常调用插件。
 
-<Image
-  alt="Mixtral-8x7B 简单指令的 Tools Calling"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/1b7bf28e-fa31-4838-ae92-9100a4bbb71c"
-/>
+<Image alt="Mixtral-8x7B 简单指令的 Tools Calling" src="https://github.com/lobehub/lobe-chat/assets/28616219/1b7bf28e-fa31-4838-ae92-9100a4bbb71c" />
 
 <details>
   <summary>Tools Calling 原始输出：</summary>
 
-```yml
-
-[no stream response] 2024-7-8 22:18:19.682
+  ```yml
 
-{"id":"chatcmpl-9f89d669-5642-48be-b5cd-7a29756800c0","object":"chat.completion","created":1720448299,"model":"mixtral-8x7b-32768","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_719t","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"Hangzhou,Beijing\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":1262,"prompt_time":0.116684046,"completion_tokens":102,"completion_time":0.163113006,"total_tokens":1364,"total_time":0.279797052},"system_fingerprint":"fp_c5f20b5bb1","x_groq":{"id":"req_01j29bbc8xen2s3thp9qen5bys"}}
+  [no stream response] 2024-7-8 22:18:19.682
 
-POST /api/chat/groq 200 in 4860ms
-```
+  {"id":"chatcmpl-9f89d669-5642-48be-b5cd-7a29756800c0","object":"chat.completion","created":1720448299,"model":"mixtral-8x7b-32768","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_719t","type":"function","function":{"name":"realtime-weather____fetchCurrentWeather","arguments":"{\"city\":\"Hangzhou,Beijing\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":1262,"prompt_time":0.116684046,"completion_tokens":102,"completion_time":0.163113006,"total_tokens":1364,"total_time":0.279797052},"system_fingerprint":"fp_c5f20b5bb1","x_groq":{"id":"req_01j29bbc8xen2s3thp9qen5bys"}}
 
+  POST /api/chat/groq 200 in 4860ms
+  ```
 </details>
 
 ### 复杂调用指令：文生图
@@ -165,25 +145,19 @@ POST /api/chat/groq 200 in 4860ms
 
 非常意外地，Mixtral 8x7B 在文生图的 Tools Calling 的场景下，居然可以正常出图，而且出图的能力基本和 LLAMA3 70B 持平。
 
-<Image
-  alt="Mixtral-8x7B 复杂指令的 Tools Calling"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/6e7bc3fa-3bc7-4c23-8f88-f38bb889c594"
-/>
-<Image
-  alt="Mixtral-8x7B 复杂指令的 Tools Calling"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/815b2792-adaf-4315-9014-f20531a3978b"
-/>
+<Image alt="Mixtral-8x7B 复杂指令的 Tools Calling" src="https://github.com/lobehub/lobe-chat/assets/28616219/6e7bc3fa-3bc7-4c23-8f88-f38bb889c594" />
+
+<Image alt="Mixtral-8x7B 复杂指令的 Tools Calling" src="https://github.com/lobehub/lobe-chat/assets/28616219/815b2792-adaf-4315-9014-f20531a3978b" />
 
 <details>
   <summary>Tools Calling 原始输出：</summary>
 
-```yml
-[no stream response] 2024-7-9 12:6:38.11
-
-{"id":"chatcmpl-a90069f3-b119-41b9-b8d7-c7f97373529e","object":"chat.completion","created":1720497998,"model":"mixtral-8x7b-32768","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_hw8t","type":"function","function":{"name":"lobe-image-designer____text2image____builtin","arguments":"{\"prompts\":[\"A colorful and playful illustration of a friendly small dog, looking directly at the viewer with a wagging tail and bright, expressive eyes. The dog's fur is glossy and well-groomed, with a mix of black, white, and brown colors. The background is a lush, green park with a clear blue sky and a few fluffy clouds.\",\"An oil painting of a small, energetic dog in a sunlit park, chasing a frisbee. The dog is a mix of black and white fur, with a distinct brown spot above its left eye. The park features tall trees, providing dappled shade across the grassy landscape. The frisbee is bright orange and stands out against the natural surroundings.\",\"A realistic watercolor painting of a small, fluffy white dog curled up next to a warm fireplace during a cozy winter evening. The dog's eyes are closed in contentment, and a single red bow is tied around its neck. The background includes a plush armchair, a stack of books, and a softly lit room.\",\"A fun and engaging cartoon of a small dog sitting at a café table, enjoying a cup of coffee and a croissant. The dog has a expressive face and a blue scarf around its neck. The café has a vintage, 1920's style and a red awning, with a bustling city background.\"],\"quality\":\"standard\",\"size\":\"1024x1024\",\"style\":\"vivid\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":2920,"prompt_time":0.228639219,"completion_tokens":465,"completion_time":0.755757988,"total_tokens":3385,"total_time":0.984397207},"system_fingerprint":"fp_c5f20b5bb1","x_groq":{"id":"req_01j2atr155f0nv8rmfk448e2at"}}
+  ```yml
+  [no stream response] 2024-7-9 12:6:38.11
 
-POST /api/chat/groq 200 in 6216ms
+  {"id":"chatcmpl-a90069f3-b119-41b9-b8d7-c7f97373529e","object":"chat.completion","created":1720497998,"model":"mixtral-8x7b-32768","choices":[{"index":0,"message":{"role":"assistant","tool_calls":[{"id":"call_hw8t","type":"function","function":{"name":"lobe-image-designer____text2image____builtin","arguments":"{\"prompts\":[\"A colorful and playful illustration of a friendly small dog, looking directly at the viewer with a wagging tail and bright, expressive eyes. The dog's fur is glossy and well-groomed, with a mix of black, white, and brown colors. The background is a lush, green park with a clear blue sky and a few fluffy clouds.\",\"An oil painting of a small, energetic dog in a sunlit park, chasing a frisbee. The dog is a mix of black and white fur, with a distinct brown spot above its left eye. The park features tall trees, providing dappled shade across the grassy landscape. The frisbee is bright orange and stands out against the natural surroundings.\",\"A realistic watercolor painting of a small, fluffy white dog curled up next to a warm fireplace during a cozy winter evening. The dog's eyes are closed in contentment, and a single red bow is tied around its neck. The background includes a plush armchair, a stack of books, and a softly lit room.\",\"A fun and engaging cartoon of a small dog sitting at a café table, enjoying a cup of coffee and a croissant. The dog has a expressive face and a blue scarf around its neck. The café has a vintage, 1920's style and a red awning, with a bustling city background.\"],\"quality\":\"standard\",\"size\":\"1024x1024\",\"style\":\"vivid\"}"}}]},"logprobs":null,"finish_reason":"tool_calls"}],"usage":{"prompt_tokens":2920,"prompt_time":0.228639219,"completion_tokens":465,"completion_time":0.755757988,"total_tokens":3385,"total_time":0.984397207},"system_fingerprint":"fp_c5f20b5bb1","x_groq":{"id":"req_01j2atr155f0nv8rmfk448e2at"}}
 
-```
+  POST /api/chat/groq 200 in 6216ms
 
+  ```
 </details>

package/docs/usage/tools-calling/moonshot.mdx

@@ -1 +1,10 @@
+---
+title: ''
+description: 学习如何有效管理待办事项，提高工作效率和生产力。
+tags:
+  - 待办事项
+  - 工作效率
+  - 生产力
+---
+
 TODO

package/docs/usage/tools-calling/openai.mdx

@@ -15,11 +15,11 @@ tags:
 
 Overview of the Tool Calling capabilities of OpenAI GPT series models:
 
-| Model | Tool Calling Support | Streaming | Parallel | Simple Instruction Score | Complex Instruction Score |
-| --- | --- | --- | --- | --- | --- |
-| GPT-3.5-turbo | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟 |
-| GPT-4-turbo | ✅ | ✅ | ✅ | 🌟🌟 | 🌟🌟 |
-| GPT-4o | ✅ | ✅ | ✅ | 🌟🌟🌟 | 🌟🌟 |
+| Model         | Tool Calling Support | Streaming | Parallel | Simple Instruction Score | Complex Instruction Score |
+| ------------- | -------------------- | --------- | -------- | ------------------------ | ------------------------- |
+| GPT-3.5-turbo | ✅                    | ✅         | ✅        | 🌟🌟🌟                   | 🌟                        |
+| GPT-4-turbo   | ✅                    | ✅         | ✅        | 🌟🌟                     | 🌟🌟                      |
+| GPT-4o        | ✅                    | ✅         | ✅        | 🌟🌟🌟                   | 🌟🌟                      |
 
 <Callout type={'info'}>
   For testing instructions, see [Tools Calling - Evaluation Task
@@ -34,14 +34,10 @@ Test Instruction: Instruction ①
 
 <Video src="https://github.com/lobehub/lobe-chat/assets/28616219/65901ee2-78b8-4f56-9e0d-6407c484f434" />
 
-<Image
-  alt="Tool Calling for Simple Instruction in GPT 3.5 Turbo"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/1251dfc0-d1c4-4c3d-825e-dd6205793d53"
-/>
+<Image alt="Tool Calling for Simple Instruction in GPT 3.5 Turbo" src="https://github.com/lobehub/lobe-chat/assets/28616219/1251dfc0-d1c4-4c3d-825e-dd6205793d53" />
 
 <details>
-<summary>Streaming Tool Calling Raw Output:</summary>
-
+  <summary>Streaming Tool Calling Raw Output:</summary>
 </details>
 
 ### Complex Instruction Call: Wenshengtu
@@ -50,14 +46,10 @@ Test Instruction: Instruction ②
 
 <Video src="https://github.com/lobehub/lobe-chat/assets/28616219/2047665f-ab22-4da7-a390-0fb4ec5a2a14" />
 
-<Image
-  alt="Tool Calling for Complex Instruction in GPT 3.5 Turbo"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/125ad028-a621-4433-b5fa-321f8fd76302"
-/>
+<Image alt="Tool Calling for Complex Instruction in GPT 3.5 Turbo" src="https://github.com/lobehub/lobe-chat/assets/28616219/125ad028-a621-4433-b5fa-321f8fd76302" />
 
 <details>
-<summary>Streaming Tool Calling Raw Output:</summary>
-
+  <summary>Streaming Tool Calling Raw Output:</summary>
 </details>
 
 ## GPT-4 Turbo
@@ -72,14 +64,10 @@ Of course, it is also possible that GPT-4 Turbo's model has more "autonomy" and
 
 <Video src="https://github.com/lobehub/lobe-chat/assets/28616219/f865d91b-b84a-4258-ae09-9d1e15eeb43d" />
 
-<Image
-  alt="Tool Calling for Simple Instruction in GPT-4 Turbo"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/19298693-7a9b-4b54-9e28-c46b541b4f41"
-/>
+<Image alt="Tool Calling for Simple Instruction in GPT-4 Turbo" src="https://github.com/lobehub/lobe-chat/assets/28616219/19298693-7a9b-4b54-9e28-c46b541b4f41" />
 
 <details>
-<summary>Streaming Tool Calling Raw Output:</summary>
-
+  <summary>Streaming Tool Calling Raw Output:</summary>
 </details>
 
 ### Complex Instruction Call: Wenshengtu
@@ -88,14 +76,10 @@ Test Instruction: Instruction ②
 
 <Video src="https://github.com/lobehub/lobe-chat/assets/28616219/69989faf-9b98-41ec-ba51-40cc3545d8d1" />
 
-<Image
-  alt="Tool Calling for Complex Instruction in GPT-4 Turbo"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/8329c1b2-5e36-4457-946c-ce3781b05afd"
-/>
+<Image alt="Tool Calling for Complex Instruction in GPT-4 Turbo" src="https://github.com/lobehub/lobe-chat/assets/28616219/8329c1b2-5e36-4457-946c-ce3781b05afd" />
 
 <details>
-<summary>Streaming Tool Calling Raw Output:</summary>
-
+  <summary>Streaming Tool Calling Raw Output:</summary>
 </details>
 
 ## GPT-4o
@@ -108,14 +92,10 @@ Similar to GPT-3.5, GPT-4o performs very well in following compound instructions
 
 <Video src="https://github.com/lobehub/lobe-chat/assets/28616219/c77b65ab-0854-4e1f-a25b-ff43275bd318" />
 
-<Image
-  alt="Tool Calling for Simple Instruction in GPT-4o"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/e5d6214f-f628-4064-a330-cbd7c5d474ac"
-/>
+<Image alt="Tool Calling for Simple Instruction in GPT-4o" src="https://github.com/lobehub/lobe-chat/assets/28616219/e5d6214f-f628-4064-a330-cbd7c5d474ac" />
 
 <details>
-    <summary>Streaming Tool Calling Raw Output:</summary>
-
+  <summary>Streaming Tool Calling Raw Output:</summary>
 </details>
 
 ### Complex Instruction Call: Wenshengtu
@@ -124,16 +104,11 @@ Test Instruction: Instruction ②
 
 <Video src="https://github.com/lobehub/lobe-chat/assets/28616219/714bd86a-3b58-4941-8323-186c3fa4c6ea" />
 
-<Image
-  alt="Tool Calling for Complex Instruction in GPT-4o"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/8329c1b2-5e36-4457-946c-ce3781b05afd"
-/>
+<Image alt="Tool Calling for Complex Instruction in GPT-4o" src="https://github.com/lobehub/lobe-chat/assets/28616219/8329c1b2-5e36-4457-946c-ce3781b05afd" />
 
 <details>
-    <summary>Streaming Tool Calling Raw Output:</summary>
-
-```yml
-
-```
+  <summary>Streaming Tool Calling Raw Output:</summary>
 
+  ```yml
+  ```
 </details>

package/docs/usage/tools-calling/openai.zh-CN.mdx

@@ -15,11 +15,11 @@ tags:
 
 OpenAI GPT 系列模型 Tool Calling 能力一览：
 
-| 模型          | 支持 Tool Calling | 流式 （Stream） | 并发（Parallel） | 简单指令得分 | 复杂指令 |
-| ------------- | ----------------- | --------------- | ---------------- | ------------ | -------- |
-| GPT-3.5-turbo | ✅                | ✅              | ✅               | 🌟🌟🌟       | 🌟       |
-| GPT-4-turbo   | ✅                | ✅              | ✅               | 🌟🌟         | 🌟🌟     |
-| GPT-4o        | ✅                | ✅              | ✅               | 🌟🌟🌟       | 🌟🌟     |
+| 模型            | 支持 Tool Calling | 流式 （Stream） | 并发（Parallel） | 简单指令得分 | 复杂指令 |
+| ------------- | --------------- | ----------- | ------------ | ------ | ---- |
+| GPT-3.5-turbo | ✅               | ✅           | ✅            | 🌟🌟🌟 | 🌟   |
+| GPT-4-turbo   | ✅               | ✅           | ✅            | 🌟🌟   | 🌟🌟 |
+| GPT-4o        | ✅               | ✅           | ✅            | 🌟🌟🌟 | 🌟🌟 |
 
 <Callout type={'info'}>
   关于测试指令，详见 [工具调用 Tools Calling -
@@ -34,14 +34,10 @@ OpenAI GPT 系列模型 Tool Calling 能力一览：
 
 <Video src="https://github.com/lobehub/lobe-chat/assets/28616219/65901ee2-78b8-4f56-9e0d-6407c484f434" />
 
-<Image
-  alt="GPT 3.5 Turbo 简单指令的 Tool Calling"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/1251dfc0-d1c4-4c3d-825e-dd6205793d53"
-/>
+<Image alt="GPT 3.5 Turbo 简单指令的 Tool Calling" src="https://github.com/lobehub/lobe-chat/assets/28616219/1251dfc0-d1c4-4c3d-825e-dd6205793d53" />
 
 <details>
-<summary>流式 Tool Calling 原始输出：</summary>
-
+  <summary>流式 Tool Calling 原始输出：</summary>
 </details>
 
 ### 复杂调用指令：文生图
@@ -50,14 +46,10 @@ OpenAI GPT 系列模型 Tool Calling 能力一览：
 
 <Video src="https://github.com/lobehub/lobe-chat/assets/28616219/2047665f-ab22-4da7-a390-0fb4ec5a2a14" />
 
-<Image
-  alt="GPT 3.5 Turbo 复杂指令的 Tool Calling"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/125ad028-a621-4433-b5fa-321f8fd76302"
-/>
+<Image alt="GPT 3.5 Turbo 复杂指令的 Tool Calling" src="https://github.com/lobehub/lobe-chat/assets/28616219/125ad028-a621-4433-b5fa-321f8fd76302" />
 
 <details>
-<summary>流式 Tool Calling 原始输出：</summary>
-
+  <summary>流式 Tool Calling 原始输出：</summary>
 </details>
 
 ## GPT-4 Turbo
@@ -68,18 +60,14 @@ OpenAI GPT 系列模型 Tool Calling 能力一览：
 
 GPT-4 Turbo 在调用 Tool Calling 时并没有像 GPT-3.5 Turbo 一样回复「好的」，且经过多次测试始终一样，因此在这一条复合指令的跟随中反而不如 GPT-3.5 Turbo，但剩余两项能力均不错。
 
-当然，也有可能是因为 GPT-4 Turbo 的模型更加有“自主意识”，认为不需要输出这一句“好的”。
+当然，也有可能是因为 GPT-4 Turbo 的模型更加有 “自主意识”，认为不需要输出这一句 “好的”。
 
 <Video src="https://github.com/lobehub/lobe-chat/assets/28616219/f865d91b-b84a-4258-ae09-9d1e15eeb43d" />
 
-<Image
-  alt="GPT-4 Turbo 简单指令的 Tool Calling"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/19298693-7a9b-4b54-9e28-c46b541b4f41"
-/>
+<Image alt="GPT-4 Turbo 简单指令的 Tool Calling" src="https://github.com/lobehub/lobe-chat/assets/28616219/19298693-7a9b-4b54-9e28-c46b541b4f41" />
 
 <details>
-<summary>流式 Tool Calling 原始输出：</summary>
-
+  <summary>流式 Tool Calling 原始输出：</summary>
 </details>
 
 ### 复杂调用指令：文生图
@@ -88,14 +76,10 @@ GPT-4 Turbo 在调用 Tool Calling 时并没有像 GPT-3.5 Turbo 一样回复「
 
 <Video src="https://github.com/lobehub/lobe-chat/assets/28616219/69989faf-9b98-41ec-ba51-40cc3545d8d1" />
 
-<Image
-  alt="GPT-4o 复杂指令的 Tool Calling"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/8329c1b2-5e36-4457-946c-ce3781b05afd"
-/>
+<Image alt="GPT-4o 复杂指令的 Tool Calling" src="https://github.com/lobehub/lobe-chat/assets/28616219/8329c1b2-5e36-4457-946c-ce3781b05afd" />
 
 <details>
-<summary>流式 Tool Calling 原始输出：</summary>
-
+  <summary>流式 Tool Calling 原始输出：</summary>
 </details>
 
 ## GPT 4o
@@ -108,14 +92,10 @@ GPT-4o 和 3.5 一样，在简单调用指令中，能够达到非常不错的
 
 <Video src="https://github.com/lobehub/lobe-chat/assets/28616219/c77b65ab-0854-4e1f-a25b-ff43275bd318" />
 
-<Image
-  alt="GPT-4o 简单指令的 Tool Calling"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/e5d6214f-f628-4064-a330-cbd7c5d474ac"
-/>
+<Image alt="GPT-4o 简单指令的 Tool Calling" src="https://github.com/lobehub/lobe-chat/assets/28616219/e5d6214f-f628-4064-a330-cbd7c5d474ac" />
 
 <details>
-    <summary>流式 Tool Calling 原始输出：</summary>
-
+  <summary>流式 Tool Calling 原始输出：</summary>
 </details>
 
 ### 复杂调用指令：文生图
@@ -124,16 +104,11 @@ GPT-4o 和 3.5 一样，在简单调用指令中，能够达到非常不错的
 
 <Video src="https://github.com/lobehub/lobe-chat/assets/28616219/714bd86a-3b58-4941-8323-186c3fa4c6ea" />
 
-<Image
-  alt="GPT-4o 复杂指令的 Tool Calling"
-  src="https://github.com/lobehub/lobe-chat/assets/28616219/8329c1b2-5e36-4457-946c-ce3781b05afd"
-/>
+<Image alt="GPT-4o 复杂指令的 Tool Calling" src="https://github.com/lobehub/lobe-chat/assets/28616219/8329c1b2-5e36-4457-946c-ce3781b05afd" />
 
 <details>
-    <summary>流式 Tool Calling 原始输出：</summary>
-
-```yml
-
-```
+  <summary>流式 Tool Calling 原始输出：</summary>
 
+  ```yml
+  ```
 </details>

package/docs/usage/tools-calling.mdx

@@ -1,3 +1,12 @@
+---
+title: Tools Calling
+description: Discover the best tools to enhance your calling experience and productivity.
+tags:
+  - Calling Tools
+  - Productivity
+  - Communication
+---
+
 # Tools Calling
 
 TODO