Skip to content
This repository was archived by the owner on Mar 11, 2026. It is now read-only.

Commit 5df6559

Browse files
authored
Merge pull request #164 from Lanhuace-Wan/outdated-model-names-change
文档: 修复过时的模型描述
2 parents 166deaa + 4c9b55c commit 5df6559

File tree

2 files changed

+17
-13
lines changed

2 files changed

+17
-13
lines changed

en/use/function-calling.md

Lines changed: 9 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -10,16 +10,19 @@ Function calling aims to provide large language models with **the ability to inv
1010

1111
For example, when you ask the LLM: "Help me search for information about cats", the model will call external search tools, such as search engines, and return the search results.
1212

13+
Here is the revised text, updated to reflect your new content while maintaining a formal documentation tone:
14+
1315
Currently, supported models include but are not limited to:
1416

15-
- GPT-4 series (best performance)
16-
- Gemini 2.0 series (excluding thinking-type models) (best performance)
17-
- DeepSeek v3 (deepseek-chat)
18-
- LLaMA 3 series (performance may be poor when deployed locally with smaller parameter counts)
17+
- GPT-5.x series
18+
- Gemini 3.x series
19+
- Claude 4.x series
20+
- DeepSeek v3.2 (deepseek-chat)
21+
- Qwen 3.x series
1922

20-
And more.
23+
Mainstream models released after 2025 typically support function calling.
2124

22-
Commonly unsupported models include DeepSeek-R1, Gemini 2.0 thinking-type models, etc.
25+
Commonly unsupported models include older models such as DeepSeek-R1 and Gemini 2.0 thinking-type models.
2326

2427
In AstrBot, web search, todo reminders, and code interpreter tools are provided by default. Many plugins, such as:
2528

zh/use/function-calling.md

Lines changed: 8 additions & 7 deletions
Original file line numberDiff line numberDiff line change
@@ -10,16 +10,17 @@ outline: deep
1010

1111
比如,问大模型:帮我搜索一下关于“猫”的信息,大模型会调用用于搜索的外部工具,比如搜索引擎,然后返回搜索结果。
1212

13-
目前,支持的模型包括但不限于
13+
目前,支持的模型包括但远不限于
1414

15-
- gpt-4 系列(效果最好)
16-
- gemini 2.0 系列(不包含 thinking 类的模型)(效果最好)
17-
- deepseek v3(deepseek-chat)
18-
- llama3 系列(本地部署参数量较小时效果不好)
15+
- GPT-5.x 系列
16+
- Gemini 3.x 系列
17+
- Claude 4.x 系列
18+
- Deepseek v3.2(deepseek-chat)
19+
- Qwen 3.x 系列
1920

20-
等等
21+
2025年后推出的主流模型通常已支持函数调用
2122

22-
不支持的模型比较常见的有 deepseek-r1, gemini 2.0 的 thinking 类模型等
23+
不支持的模型比较常见的有 Deepseek-R1, Gemini 2.0 的 thinking 类等较老模型
2324

2425
在 AstrBot 中,默认提供了网页搜索、待办提醒、代码执行器这些工具。很多插件,如:
2526

0 commit comments

Comments
 (0)