一、ollama的连通性测试
参考文档:API 参考 - Ollama中文网
1.使用api测试ollama qwen大模型的连通性
curl --location --request POST 'http://192.168.110.216:11434/api/generate' \
--header 'User-Agent: Apifox/1.0.0 (https://apifox.com)' \
--header 'Content-Type: application/json' \
--data-raw '{
"model": "qwen:7b",
"prompt": "你好!",
"stream": false
}'
输出信息:
{
"model": "qwen:7b",
"created_at": "2024-07-16T09:50:46.903797271Z",
"response": "你好!有什么我能帮你的吗?",
"done": true,
"done_reason": "stop",
"context": [
151644,
872,
......
11319
],
"total_duration": 1200826373,
"load_duration": 2290434,
"prompt_eval_duration": 129797000,
"eval_count": 9,
"eval_duration": 1021756000
}
2.使用api测试ollama m3e索引模型的连通性
注意:地址后缀要更改为/api/embeddings
curl --location --request POST 'http://192.168.110.216:11434/api/embeddings' \
--header 'User-Agent: Apifox/1.0.0 (https://apifox.com)' \
--header 'Content-Type: application/json' \
--data-raw '{
"model": "milkey/m3e:small-f16",
"prompt": "你好!"
}'
输出信息:
{
"embedding": [
0.001690375036559999,
-0.5071032643318176,
0.618750274181366,
0.8972500562667847,
-0.8042110800743103,
...省略...
-1.357832431793213,
-0.8816344141960144,
0.8974659442901611,
0.5146898627281189
]
}
二、oneAPi的连通性测试
参考文章:
一站式多模型管理:One API实用指南 (gameapp.club)
1.使用api测试one Api索引模型的连通性
注意:ip、Authorization、model需要换成自己的
请求信息:
curl --location --request POST 'http://ip:3001/v1/embeddings' \
--header 'Authorization: Bearer sk-uvkdLvi96pAwjpfv8a53EaCb20Eb4f69B483B388D7656b03' \
--header 'User-Agent: Apifox/1.0.0 (https://apifox.com)' \
--header 'Content-Type: application/json' \
--data-raw '{
"model":"milkey/m3e:small-f16",
"input":"你好你好"
}'
输出信息:
{
"object": "list",
"data": [
{
"object": "embedding",
"index": 0,
"embedding": [
-0.1644720584154129,
-0.3401753604412079,
0.4924147427082062,
0.7944067120552063,
-1.106508731842041,
-0.6042813658714294,
-0.135698601603508,
1.1983524560928345,
1.0502504110336304,
0.39524030685424805,
......
1.7453641891479492,
0.753643810749054,
-1.10323965549469,
-0.452385276556015,
0.9913195371627808,
0.6946268677711487
]
}
],
"model": "text-embedding-v1",
"usage": {
"prompt_tokens": 0,
"completion_tokens": 0,
"total_tokens": 0
}
}
2.使用api测试oneApi大模型的连通性
注意:ip、Authorization、model需要换成自己的
model可以换成本地部署的模型,确认模型名称是否正确
curl --location --request POST 'http://ip:3001/v1/chat/completions' \
--header 'Authorization: Bearer sk-uvkdLvi96pAwjpfv8a53EaCb20Eb4f69B483B388D7656b03' \
--header 'User-Agent: Apifox/1.0.0 (https://apifox.com)' \
--header 'Content-Type: application/json' \
--data-raw '{
"model":"qwen:7b",
"messages": [{"role": "user", "content": "你是哪个公司的大模型"}]
}'
输出信息:
{
"id": "chatcmpl-8dc2c903ffe34d7a87becd127cdf6971",
"model": "qwen:7b",
"object": "chat.completion",
"created": 1721122587,
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "我是阿里云研发的语言模型,名叫通义千问。"
},
"finish_reason": "stop"
}
],
"usage": {
"prompt_tokens": 10,
"completion_tokens": 14,
"total_tokens": 24
}
}
三、fastgpt的连通性测试
参考文章:FastGPT Open API
以下引用官方文档示例
1.使用api测试fastgpt 应用模型的连通性
curl --location --request POST 'http://localhost:3000/api/v1/chat/completions' \
--header 'Authorization: Bearer test-xxxxx' \
--header 'Content-Type: application/json' \
--data-raw '{
"stream": false,
"chatId": "test",
"variables": {
"query":"你好" # 我的插件输入有一个参数,变量名叫 query
}
}'
正确输出:
{
"responseData": [
{
"nodeId": "fdDgXQ6SYn8v",
"moduleName": "AI 对话",
"moduleType": "chatNode",
"totalPoints": 0.685,
"model": "FastAI-3.5",
"tokens": 685,
"query": "你好",
"maxToken": 2000,
"historyPreview": [
{
"obj": "Human",
"value": "你好"
},
{
"obj": "AI",
"value": "你好!有什么可以帮助你的吗?欢迎向我提问。"
}
],
"contextTotalLen": 14,
"runningTime": 1.73
},
{
"nodeId": "pluginOutput",
"moduleName": "自定义插件输出",
"moduleType": "pluginOutput",
"totalPoints": 0,
"pluginOutput": {
"result": "你好!有什么可以帮助你的吗?欢迎向我提问。"
},
"runningTime": 0
}
],
"newVariables": {
"query": "你好"
},
"id": "safsafsa",
"model": "",
"usage": {
"prompt_tokens": 1,
"completion_tokens": 1,
"total_tokens": 1
},
"choices": [
{
"message": {
"role": "assistant",
"content": "你好!有什么可以帮助你的吗?欢迎向我提问。"
},
"finish_reason": "stop",
"index": 0
}
]
}