[建议] 接入deepseek的API示例 - 专家坐堂 - Foxtable(狐表) - 新一代数据库软件，完美融合Access、Foxpro、Excel、vb.net之优势，人人都能掌握的快速软件开发工具!

老师，是否可以做一个foxtable接入deepseek的示例。

http://www.foxtable.com/bbs/dispbbs.asp?boardid=2&Id=194892&page=2

试试

Dim hc As New HttpClient("https://api.deepseek.com/v1/chat/completions")

hc.ContentType = "application/json"

dim API_KEY As String = "your_api_key_here"

hc.Headers.Add("Authorization", "Bearer " & API_KEY)

Dim jo As New JObject
jo("model") = "deepseek-chat"
jo("messages") = new JArray

jo("messages").Add(New Jobject)

jo("messages")(0)("role") = "user"

jo("messages")(0)("content") = "某某prompt"

hc.Content = jo.tostring
Dim ret As String = hc.GetData()
MessageBox.Show(ret)

用deepseek给出的vue代码对接成功,就是有点卡

<!DOCTYPE html>

<html>

<head>

</head>

<body>

<div>

<h1>DeepSeek 流式输出示例</h1>

<div>

<h2>生成的文本：</h2>

<pre>{{ generatedText }}</pre>

</div>

var data = {

prompt: '', // 用户输入的提示内容

generatedText: '', // 生成的文本

};

var methods = {

async generateText() {

// 清空之前的生成结果

this.generatedText = '';

// DeepSeek API 的 URL 和 API 密钥

const API_URL = 'https://api.deepseek.com/v1/chat/completions';

const API_KEY = 'your key';

try {

// 使用 Fetch API 发送请求

const response = await fetch(API_URL, {

method: 'POST',

headers: {

'Content-Type': 'application/json',

Authorization: `Bearer ${API_KEY}`,

body: JSON.stringify({

model: 'deepseek-chat',

messages: [{ role: 'user', content: this.prompt }],

stream: true, // 开启流式输出

}),

});

// 检查响应是否成功

if (!response.ok) {

throw new Error(`HTTP error! status: ${response.status}`);

}

// 获取流式响应的读取器

const reader = response.body.getReader();

const decoder = new TextDecoder('utf-8');

// 读取流式数据

while (true) {

const { done, value } = await reader.read();

if (done) break;

// 解码流式数据

const chunk = decoder.decode(value, { stream: true });

const lines = chunk.split('\n').filter((line) => line.trim() !== '');

// 处理每一行数据

lines.forEach((line) => {

try {

if(line!==': keep-alive' && line.includes('data:')){

const json = JSON.parse(line.replace('data: ', ''));

const content = json.choices[0].delta.content;

if (content) {

// 将生成的文本片段追加到结果中

this.generatedText += content;

}

} catch (error) {

console.error('Error parsing JSON:', error);

}

});

}

} catch (error) {

console.error('Error calling DeepSeek API:', error);

}

var app = Vue.createApp({

data: function() {

return data;

methods:methods,

});

app.mount("#app");

</script>

<style>

[v-cloak] {

display: none;

}

</style>

</body>

</html>

[此贴子已经被作者于2025/2/7 12:18:52编辑过]

'http://www.foxtable.com/bbs/dispbbs.asp?BoardID=2&ID=191179
Net.ServicePointManager.SecurityProtocol = Net.SecurityProtocolType.Tls12 '选择一个协议Tls11，不行就Tls12、Tls13都试一遍

Dim hc As New HttpClient("https://api.deepseek.com/v1/chat/completions")
hc.ContentType = "application/json"
Dim API_KEY As String = "your_api_key_here"
hc.Headers.Add("Authorization", "Bearer " & API_KEY)
Dim jo As New JObject
Dim ja As New JArray
jo("model") = "deepseek-chat"
jo("messages") = ja
ja.Add(New JObject)
ja(0)("role") = "user"
ja(0)("content") = "某某prompt"
hc.Content = jo.ToString
Dim ret As String = hc.GetData()
MessageBox.Show(ret)

[此贴子已经被作者于2025/2/7 13:58:35编辑过]

这个可用，谢谢！

作一个实例出来

用阿里云百炼DeepSeek-V3 api 接口测试成功（请有水平狐友接龙将foxtable格式及HTML格式回传后数据解析整理方便阅读，这方面本人技不如人）：

此主题相关图片如下：微信截图_20250212094609.png

Dim hc As New HttpClient("https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions")

hc.ContentType = "application/json"

Dim API_KEY As String = "sk-88888888888888888888888888"

hc.Headers.Add("Authorization", "Bearer " & API_KEY)

Dim jo As New JObject

Dim ja As New JArray

jo("model") = "deepseek-r1"

jo("messages") = ja

ja.Add(New JObject)

ja(0)("role") = "user"

ja(0)("content") = "9.9和9.11谁大"

hc.Content = jo.ToString

Dim ret As String = hc.GetData()

MessageBox.Show(ret)

此主题相关图片如下：微信截图_20250212092513.png

<!DOCTYPE html>

<html>

<head>

<title>DeepSeek Chat</title>

<style>

body { background-color: #f5f5f5; }

.container { margin: 20px auto; max-width: 1200px; }

.chat-box { background: #fff; border-radius: 10px; box-shadow: 0 2px 12px rgba(0,0,0,.1); }

.chat-history { height: 70vh; overflow-y: auto; padding: 20px; }

.message { margin-bottom: 20px; }

.user-message { text-align: right; }

.bot-message { text-align: left; }

.message-content {

display: inline-block;

max-width: 80%;

padding: 12px 20px;

border-radius: 20px;

word-break: break-word;

}

.user-message .message-content { background: #1890ff; color: #fff; }

.bot-message .message-content { background: #f0f2f5; }

.input-box { border-top: 1px solid #eee; padding: 20px; position: relative; }

.layui-textarea { border: none; resize: none; }

.send-btn { position: absolute; right: 30px; bottom: 30px; }

</style>

</head>

<body>

</div>

</div>

</form>

</div>

let isGenerating = false;

let controller = null;

// 初始化

layui.use(['form', 'util'], function(){

const form = layui.form;

const util = layui.util;

// 绑定Enter键

util.event('keydown', '#input-area', function(e){

if(e.key === 'Enter' && !e.shiftKey) {

e.preventDefault();

sendMessage();

}

});

async function sendMessage() {

if (isGenerating) return;

const input = document.getElementById('input-area');

const question = input.value.trim();

if (!question) return;

isGenerating = true;

input.value = '';

controller = new AbortController();

// 添加用户消息

appendMessage(question, 'user');

const API_URL = 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions';

const API_KEY = 'sk-888888888888888888888888888';

try {

const response = await fetch(API_URL, {

method: 'POST',

headers: {

'Content-Type': 'application/json',

'Authorization': `Bearer ${API_KEY}`

body: JSON.stringify({

model: "deepseek-r1",

messages: [{ role: "user", content: question }],

stream: true

}),

signal: controller.signal

});

const reader = response.body.getReader();

const decoder = new TextDecoder();

let buffer = '';

let partialLine = '';

while (true) {

const { done, value } = await reader.read();

if (done) break;

buffer += decoder.decode(value, { stream: true });

let lines = buffer.split('\n');

// 保留最后不完整的行

buffer = lines.pop() || '';

for (const line of lines) {

try {

// 处理可能存在的data:前缀

const cleanLine = line.replace(/^data: /, '').trim();

if (!cleanLine) continue;

if (cleanLine === '[DONE]') break;

const data = JSON.parse(cleanLine);

const content = data.choices[0]?.delta?.content || '';

if (content) {

appendMessage(content, 'bot', true);

}

} catch (e) {

console.error('解析错误:', e, '原始数据:', line);

}

} catch (error) {

if (error.name !== 'AbortError') {

appendMessage('请求出错，请重试', 'bot');

}

} finally {

isGenerating = false;

controller = null;

}

function appendMessage(content, role, isAppend = false) {

const container = document.getElementById('chat-container');

let messageElement;

if (isAppend && container.lastElementChild?.classList.contains('bot-message')) {

messageElement = container.lastElementChild.querySelector('.message-content');

messageElement.innerHTML += content;

} else {

const messageDiv = document.createElement('div');

messageDiv.className = `message ${role}-message`;

messageDiv.innerHTML = `

${content.replace(/\n/g, '<br>')}

</div>

container.appendChild(messageDiv);

messageElement = messageDiv.querySelector('.message-content');

}

// 自动滚动

container.scrollTop = container.scrollHeight;

}

// 停止生成

function stopGenerate() {

if (controller) {

controller.abort();

isGenerating = false;

}

</script>

</body>

</html>

此主题相关图片如下：微信截图_20250212094548.png

[此贴子已经被作者于2025/2/12 21:25:43编辑过]

楼上的兄弟，你把代码复制出来给我们大家试试啊

foxtable接入deepseek代码可用，但是不能流式显示，要全部生成后才能显示，会有一段时间卡死，不适用。最好的方法还是用网页对接比较好，可流式显示无卡顿

这个功能可接入foxtable，方便用户使用了。

主题：[建议] 接入deepseek的API示例