---
title: Google Gemini 系列 Tools Calling 评测
description: >-
使用 LobeChat 测试 Google Gemini 系列模型（Gemini 1.5 Pro / Gemini 1.5 Flash）的工具调用（Function Calling）能力，并展现评测结果
tags:
- Tools Calling
- Benchmark
- Function Calling 评测
- 工具调用
- 插件
---
# Google Gemini 系列 Tools Calling
Google Gemini 系列模型 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 |
| ---------------- | ---------------- | ----------- | ------------ | ------ | ---- |
| Gemini 1.5 Pro | ✅ | ❌ | ✅ | ⛔ | ⛔ |
| Gemini 1.5 Flash | ❌ | ❌ | ❌ | ⛔ | ⛔ |
根据我们的的实际测试，强烈建议不要给 Gemini 开启插件，因为目前（截止 2024.07.07）它的 Tools
Calling 能力实在太烂了。
## Gemini 1.5 Pro
### 简单调用指令：天气查询
测试指令：指令 ①
Gemini 输出的 json 中，name 是错误的，因此 LobeChat 无法识别到它调用了什么插件。（入参中，天气插件的 name 为 `realtime-weather____fetchCurrentWeather`，而 Gemini 返回的是 `weather____fetchCurrentWeather`）。
Tools Calling 原始输出：
```yml
[stream start] 2024-7-7 17:53:25.647
[chunk 0] 2024-7-7 17:53:25.654
{"candidates":[{"content":{"parts":[{"text":"好的"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":1,"totalTokenCount":96}}
[chunk 1] 2024-7-7 17:53:26.288
{"candidates":[{"content":{"parts":[{"text":"\n\n"}],"role":"model"},"finishReason":"STOP","index":0,"safetyRatings":[{"category":"HARM_CATEGORY_SEXUALLY_EXPLICIT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HATE_SPEECH","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HARASSMENT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_DANGEROUS_CONTENT","probability":"NEGLIGIBLE"}]}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":1,"totalTokenCount":96}}
[chunk 2] 2024-7-7 17:53:26.336
{"candidates":[{"content":{"parts":[{"functionCall":{"name":"weather____fetchCurrentWeather","args":{"city":"杭州"}}},{"functionCall":{"name":"weather____fetchCurrentWeather","args":{"city":"北京"}}}],"role":"model"},"finishReasoSTOP","index":0,"safetyRatings":[{"category":"HARM_CATEGORY_SEXUALLY_EXPLICIT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HATE_SPEECH","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HARASSMENT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_DANGEROUS_CONTENT","probability":"NEGLIGIBLE"}]}],"usageMetadata":{"promptTokenCount":95,"candidatesTokenCount":79,"totalTokenCount":174}}
[stream finished] total chunks: 3
```
### 复杂调用指令：文生图
测试指令：指令 ②
在测试复杂指令集时，Google 直接抛错：
```json
{
"message": "[400 Bad Request] Invalid JSON payload received. Unknown name \"maxItems\" at 'tools[0].function_declarations[0].parameters.properties[0].value': Cannot find field.\nInvalid JSON payload received. Unknown name \"minItems\" at 'tools[0].function_declarations[0].parameters.properties[0].value': Cannot find field.\nInvalid JSON payload received. Unknown name \"default\" at 'tools[0].function_declarations[0].parameters.properties[1].value': Cannot find field.\nInvalid JSON payload received. Unknown name \"default\" at 'tools[0].function_declarations[0].parameters.properties[3].value': Cannot find field.\nInvalid JSON payload received. Unknown name \"default\" at 'tools[0].function_declarations[0].parameters.properties[4].value': Cannot find field. [{\"@type\":\"type.googleapis.com/google.rpc.BadRequest\",\"fieldViolations\":[{\"field\":\"tools[0].function_declarations[0].parameters.properties[0].value\",\"description\":\"Invalid JSON payload received. Unknown name \\\"maxItems\\\" at 'tools[0].function_declarations[0].parameters.properties[0].value': Cannot find field.\"},{\"field\":\"tools[0].function_declarations[0].parameters.properties[0].value\",\"description\":\"Invalid JSON payload received. Unknown name \\\"minItems\\\" at 'tools[0].function_declarations[0].parameters.properties[0].value': Cannot find field.\"},{\"field\":\"tools[0].function_declarations[0].parameters.properties[1].value\",\"description\":\"Invalid JSON payload received. Unknown name \\\"default\\\" at 'tools[0].function_declarations[0].parameters.properties[1].value': Cannot find field.\"},{\"field\":\"tools[0].function_declarations[0].parameters.properties[3].value\",\"description\":\"Invalid JSON payload received. Unknown name \\\"default\\\" at 'tools[0].function_declarations[0].parameters.properties[3].value': Cannot find field.\"},{\"field\":\"tools[0].function_declarations[0].parameters.properties[4].value\",\"description\":\"Invalid JSON payload received. Unknown name \\\"default\\\" at 'tools[0].function_declarations[0].parameters.properties[4].value': Cannot find field.\"}]}]"
}
```
上述抛错中提到并不支持包含 `maxItems` 的 schema，因此 Gemini 1.5 Pro 相当于无法使用 DallE 插件。
相关 issue:
- [Support for minItems and maxItems for FunctionDeclarationSchemaType.ARRAY?](https://github.com/google-gemini/generative-ai-js/issues/200)
- [Gemini Models unusable when dalle plugin is enabled](https://github.com/lobehub/lobe-chat/issues/2537)
综合以上两个测试来看，Google 的 Tool Calling 能力似乎是支持了，但是几乎没法在日常中使用，我个人认为已经等于虚假宣传了。
## Gemini 1.5 Flash
### 简单调用指令：天气查询
测试指令：指令 ①
而 Gemini 1.5 flash 更为抽象，说完调用就结束了。结合以下原始输出可以看到，Gemini 1.5 Flash 并没有输出 Tool Calling 的数据，因此可以说是完全不可用。
```yml
stream start] 2024-7-7 19:4:50.936
[chunk 0] 2024-7-7 19:4:50.943
{"candidates":[{"content":{"parts":[{"text":"好的"}],"role":"model"},"finishReason":"STOP","index":0}],"usageMetadata":{"promptTokenCount":96,"candidatesTokenCount":1,"totalTokenCount":97}}
[chunk 1] 2024-7-7 19:4:52.209
{"candidates":[{"content":{"parts":[{"text":"，请稍等，我正在查询杭州和北京的天气信息。 "}],"role":"model"},"finishReason":"STOP","index":0,"safetyRatings":[{"category":"HARM_CATEGORY_SEXUALLY_EXPLICIT","probability":"NEGLIGIBLE"ATEGORY_HATE_SPEECH","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HARASSMENT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_DANGEROUS_CONTENT","probability":"NEGLIGIBLE"}]}],"usageMetadata":{"promptTokenCount":96,"candidatesTokenCount":16,"totalTokenCount":112}}
[chunk 2] 2024-7-7 19:4:53.288
{"candidates":[{"content":{"parts":[{"text":"\n"}],"role":"model"},"finishReason":"STOP","index":0,"safetyRatings":[{"category":"HARM_CATEGORY_SEXUALLY_EXPLICIT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HATE_SPEECH","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_HARASSMENT","probability":"NEGLIGIBLE"},{"category":"HARM_CATEGORY_DANGEROUS_CONTENT","probability":"NEGLIGIBLE"}]}],"usageMetadata":{"promptTokenCount":96,"candidatesTokenCount":16,"totalTokenCount":112}}
[stream finished] total chunks: 3
```
### 复杂调用指令：文生图
测试指令：指令 ②
该指令和 Gemini 1.5 Pro 的复杂指令一样，直接抛错，因此不再详细展开。