mirror of
https://github.com/labring/FastGPT.git
synced 2025-10-15 07:31:19 +00:00
Test parse cite and add tool call parallel (#4737)
* add quote response filter (#4727) * chatting * add quote response filter * add test * remove comment * perf: cite hidden * perf: format llm response * feat: comment * update default chunk size * update default chunk size --------- Co-authored-by: heheer <heheer@sealos.io>
This commit is contained in:
Archer
@@ -16,7 +16,7 @@ describe('Markdown utils', () => {
|
||||
|
||||
it('should convert quote references to proper markdown links', () => {
|
||||
const input = '[123456789012345678901234]';
|
||||
const expected = '[123456789012345678901234](QUOTE)';
|
||||
const expected = '[123456789012345678901234](CITE)';
|
||||
expect(mdTextFormat(input)).toBe(expected);
|
||||
});
|
||||
|
||||
@@ -35,7 +35,7 @@ describe('Markdown utils', () => {
|
||||
const input =
|
||||
'Math \\[x^2\\] with link https://test.com，and quote [123456789012345678901234]';
|
||||
const expected =
|
||||
'Math $$x^2$$ with link https://test.com ，and quote [123456789012345678901234](QUOTE)';
|
||||
'Math $$x^2$$ with link https://test.com ，and quote [123456789012345678901234](CITE)';
|
||||
expect(mdTextFormat(input)).toBe(expected);
|
||||
});
|
||||
});
|
||||
|
||||
@@ -1,5 +0,0 @@
|
||||
[
|
||||
"测试的呀,第一个表格\n\n| 序号 | 姓名 | 年龄 | 职业 | 城市 |\n| --- | --- | --- | --- | --- |\n| 1 | 张三 | 25 | 工程师 | 北京 |\n| 2 | 李四 | 30 | 教师 | 上海 |\n| 3 | 王五 | 28 | 医生 | 广州 |\n| 6 | 周八 | 32 | 会计 | 成都 |\n| 4 | 赵六 | 35 | 律师 | 深圳 |\n| 5 | 孙七 | 27 | 设计师 | 杭州 |\n| 6 | 周八 | 32 | 会计 | 成都 |\n| 6 | 周八 | 32 | 会计 | 成都 |\n| 7 | 吴九 | 29 | 销售 | 武汉 |\n| 8 | 郑十 | 31 | 记者 | 南京 |\n| 9 | 刘一 | 33 | 建筑师 | 天津 |\n| 10 | 陈二 | 26 | 程序员 | 重庆 |\n| 1000 | 黄末 | 28 | 作家 | 厦门 |\n| 1001 | 杨一 | 34 | 程序员 | 厦门 |\n| 1002 | 杨二 | 34 | 程序员 | 厦门 |\n| 1003 | 杨三 | 34 | 程序员 | 厦门 |",
|
||||
"| 序号 | 姓名 | 年龄 | 职业 | 城市 |\n| --- | --- | --- | --- | --- |\n| 6 | 周八 | 32 | 会计 | 成都 |\n| 1004 | 杨四 | 34 | 程序员 | 厦门 |\n| 1005 | 杨五 | 34 | 程序员 | 厦门 |\n| 1000 | 黄末 | 28 | 作家 | 厦门 |\n| 1000 | 黄末 | 28 | 作家 | 厦门 |\n| 1000 | 黄末 | 28 | 作家 | 厦门 |\n| 9 | 刘一 | 33 | 建筑师 | 天津 |\n| 10 | 陈二 | 26 | 程序员 | 重庆 |\n| 1000 | 黄末 | 28 | 作家 | 厦门 |\n| 1001 | 杨一 | 34 | 程序员 | 厦门 |\n| 1002 | 杨二 | 34 | 程序员 | 厦门 |\n| 1003 | 杨三 | 34 | 程序员 | 厦门 |\n| 1004 | 杨四 | 34 | 程序员 | 厦门 |\n| 1005 | 杨五 | 34 | 程序员 | 厦门 |\n\n| 序号 | 姓名 | 年龄 | 职业 | 城市 |\n| --- | --- | --- | --- | --- |\n| 6 | 周八 | 32 | 会计 | 成都 |\n| 1000 | 黄末 | 28 | 作家 | 厦门 |\n| 1000 | 黄末 | 28 | 作家 | 厦门 |\n| 1000 | 黄末 | 28 | 作家 | 厦门 |",
|
||||
"这是第二段了，第二表格\n\n| 序号 | 姓名 | 年龄 | 职业 | 城市 |\n| --- | --- | --- | --- | --- |\n| 1 | 张三 | 25 | 工程师 | 北京 |\n| 6 | 周八 | 32 | 会计 | 成都 |\n| 2 | 李四 | 30 | 教师 | 上海 |\n| 3 | 王五 | 28 | 医生 | 广州 |\n| 4 | 赵六 | 35 | 律师 | 深圳 |\n| 5 | 孙七 | 27 | 设计师 | 杭州 |\n| 6 | 周八 | 32 | 会计 | 成都 |\n| 7 | 吴九 | 29 | 销售 | 武汉 |\n| 8 | 郑十 | 31 | 记者 | 南京 |\n| 9 | 刘一 | 33 | 建筑师 | 天津 |\n| 10 | 陈二 | 26 | 程序员 | 重庆 |\n| 10004 | 黄末 | 28 | 作家 | 厦门 |\n| 10013 | 杨一 | 34 | 程序员 | 厦门 |\n\n\n结束了\n\n| 序号22 | 姓名 | 年龄 | 职业 | 城市 |\n| --- | --- | --- | --- | --- |\n| 1 | 张三 | 25 | 工程师 | 北京 |\n| 2 | 李四 | 30 | 教师 | 上海 |\n| 3 | 王五 | 28 | 医生 | 广州 |\n| 4 | 赵六 | 35 | 律师 | 深圳 |\n| 5 | 孙七 | 27 | 设计师 | 杭州 |\n| 6 | 周八 | 32 | 会计 | 成都 |\n| 6 | 周八 | 32 | 会计 | 成都 |\n| 7 | 吴九 | 29 | 销售 | 武汉 |\n| 8 | 郑十 | 31 | 记者 | 南京 |\n| 9 | 刘一 | 33 | 建筑师 | 天津 |\n| 10 | 陈二 | 26 | 程序员 | 重庆 |\n| 10002 | 黄末 | 28 | 作家 | 厦门 |\n| 10012 | 杨一 | 34 | 程序员 | 厦门 |"
|
||||
]
|
||||
@@ -1,5 +1,5 @@
|
||||
import { describe, expect, it } from 'vitest';
|
||||
import { checkPasswordRule } from '@/web/support/user/login/constants';
|
||||
import { checkPasswordRule } from '@fastgpt/global/common/string/password';
|
||||
|
||||
describe('PasswordRule', () => {
|
||||
it('should be a valid password', () => {
|
||||
@@ -1,6 +1,5 @@
|
||||
import { it, expect } from 'vitest'; // 必须显式导入
|
||||
import { splitText2Chunks } from '@fastgpt/global/common/string/textSplitter';
|
||||
import * as fs from 'fs';
|
||||
|
||||
const simpleChunks = (chunks: string[]) => {
|
||||
return chunks.map((chunk) => chunk.replace(/\s+/g, ''));
|
||||
|
||||
@@ -0,0 +1,340 @@
|
||||
import { CompletionFinishReason } from '@fastgpt/global/core/ai/type';
|
||||
import { parseLLMStreamResponse } from '@fastgpt/service/core/ai/utils';
|
||||
import { describe, expect, it } from 'vitest';
|
||||
|
||||
describe('Parse reasoning stream content test', async () => {
|
||||
const partList = [
|
||||
{
|
||||
data: [{ content: '你好1' }, { content: '你好2' }, { content: '你好3' }],
|
||||
correct: { answer: '你好1你好2你好3', reasoning: '' }
|
||||
},
|
||||
{
|
||||
data: [
|
||||
{ reasoning_content: '这是' },
|
||||
{ reasoning_content: '思考' },
|
||||
{ reasoning_content: '过程' },
|
||||
{ content: '你好1' },
|
||||
{ content: '你好2' },
|
||||
{ content: '你好3' }
|
||||
],
|
||||
correct: { answer: '你好1你好2你好3', reasoning: '这是思考过程' }
|
||||
},
|
||||
{
|
||||
data: [
|
||||
{ content: '<t' },
|
||||
{ content: 'hink>' },
|
||||
{ content: '这是' },
|
||||
{ content: '思考' },
|
||||
{ content: '过程' },
|
||||
{ content: '</think>' },
|
||||
{ content: '你好1' },
|
||||
{ content: '你好2' },
|
||||
{ content: '你好3' }
|
||||
],
|
||||
correct: { answer: '你好1你好2你好3', reasoning: '这是思考过程' }
|
||||
},
|
||||
{
|
||||
data: [
|
||||
{ content: '<think>' },
|
||||
{ content: '这是' },
|
||||
{ content: '思考' },
|
||||
{ content: '过程' },
|
||||
{ content: '</think>' },
|
||||
{ content: '你好1' },
|
||||
{ content: '你好2' },
|
||||
{ content: '你好3' }
|
||||
],
|
||||
correct: { answer: '你好1你好2你好3', reasoning: '这是思考过程' }
|
||||
},
|
||||
{
|
||||
data: [
|
||||
{ content: '<think>这是' },
|
||||
{ content: '思考' },
|
||||
{ content: '过程' },
|
||||
{ content: '</think>' },
|
||||
{ content: '你好1' },
|
||||
{ content: '你好2' },
|
||||
{ content: '你好3' }
|
||||
],
|
||||
correct: { answer: '你好1你好2你好3', reasoning: '这是思考过程' }
|
||||
},
|
||||
{
|
||||
data: [
|
||||
{ content: '<think>这是' },
|
||||
{ content: '思考' },
|
||||
{ content: '过程</' },
|
||||
{ content: 'think>' },
|
||||
{ content: '你好1' },
|
||||
{ content: '你好2' },
|
||||
{ content: '你好3' }
|
||||
],
|
||||
correct: { answer: '你好1你好2你好3', reasoning: '这是思考过程' }
|
||||
},
|
||||
{
|
||||
data: [
|
||||
{ content: '<think>这是' },
|
||||
{ content: '思考' },
|
||||
{ content: '过程</think>' },
|
||||
{ content: '你好1' },
|
||||
{ content: '你好2' },
|
||||
{ content: '你好3' }
|
||||
],
|
||||
correct: { answer: '你好1你好2你好3', reasoning: '这是思考过程' }
|
||||
},
|
||||
{
|
||||
data: [
|
||||
{ content: '<think>这是' },
|
||||
{ content: '思考' },
|
||||
{ content: '过程</think>你好1' },
|
||||
{ content: '你好2' },
|
||||
{ content: '你好3' }
|
||||
],
|
||||
correct: { answer: '你好1你好2你好3', reasoning: '这是思考过程' }
|
||||
},
|
||||
{
|
||||
data: [
|
||||
{ content: '<think>这是' },
|
||||
{ content: '思考' },
|
||||
{ content: '过程</th' },
|
||||
{ content: '假的' },
|
||||
{ content: '你好2' },
|
||||
{ content: '你好3' },
|
||||
{ content: '过程</think>你好1' },
|
||||
{ content: '你好2' },
|
||||
{ content: '你好3' }
|
||||
],
|
||||
correct: { answer: '你好1你好2你好3', reasoning: '这是思考过程</th假的你好2你好3过程' }
|
||||
},
|
||||
{
|
||||
data: [
|
||||
{ content: '<think>这是' },
|
||||
{ content: '思考' },
|
||||
{ content: '过程</th' },
|
||||
{ content: '假的' },
|
||||
{ content: '你好2' },
|
||||
{ content: '你好3' }
|
||||
],
|
||||
correct: { answer: '', reasoning: '这是思考过程</th假的你好2你好3' }
|
||||
}
|
||||
];
|
||||
|
||||
// Remove think
|
||||
partList.forEach((part, index) => {
|
||||
it(`Reasoning test:${index}`, () => {
|
||||
const { parsePart } = parseLLMStreamResponse();
|
||||
|
||||
let answer = '';
|
||||
let reasoning = '';
|
||||
part.data.forEach((item) => {
|
||||
const formatPart = {
|
||||
choices: [
|
||||
{
|
||||
delta: {
|
||||
role: 'assistant',
|
||||
content: item.content,
|
||||
reasoning_content: item.reasoning_content
|
||||
}
|
||||
}
|
||||
]
|
||||
};
|
||||
const { reasoningContent, content } = parsePart({
|
||||
part: formatPart,
|
||||
parseThinkTag: true,
|
||||
retainDatasetCite: false
|
||||
});
|
||||
answer += content;
|
||||
reasoning += reasoningContent;
|
||||
});
|
||||
expect(answer).toBe(part.correct.answer);
|
||||
expect(reasoning).toBe(part.correct.reasoning);
|
||||
});
|
||||
});
|
||||
});
|
||||
|
||||
describe('Parse dataset cite content test', async () => {
|
||||
const partList = [
|
||||
{
|
||||
// 完整的
|
||||
data: [
|
||||
{ content: '知识库' },
|
||||
{ content: '问答系统' },
|
||||
{ content: '[67e517e747' },
|
||||
{ content: '67063e882d' },
|
||||
{ content: '6861](CITE)' }
|
||||
],
|
||||
correct: {
|
||||
content: '知识库问答系统[67e517e74767063e882d6861](CITE)',
|
||||
responseContent: '知识库问答系统'
|
||||
}
|
||||
},
|
||||
{
|
||||
// 缺失结尾
|
||||
data: [
|
||||
{ content: '知识库问答系统' },
|
||||
{ content: '[67e517e747' },
|
||||
{ content: '67063e882d' },
|
||||
{ content: '6861](CITE' }
|
||||
],
|
||||
correct: {
|
||||
content: '知识库问答系统[67e517e74767063e882d6861](CITE',
|
||||
responseContent: '知识库问答系统[67e517e74767063e882d6861](CITE'
|
||||
}
|
||||
},
|
||||
{
|
||||
// ObjectId 不正确
|
||||
data: [
|
||||
{ content: '知识库问答系统' },
|
||||
{ content: '[67e517e747' },
|
||||
{ content: '67882d' },
|
||||
{ content: '6861](CITE)' }
|
||||
],
|
||||
correct: {
|
||||
content: '知识库问答系统[67e517e74767882d6861](CITE)',
|
||||
responseContent: '知识库问答系统[67e517e74767882d6861](CITE)'
|
||||
}
|
||||
},
|
||||
{
|
||||
// 其他链接
|
||||
data: [{ content: '知识库' }, { content: '问答系统' }, { content: '[](https://fastgpt.cn)' }],
|
||||
correct: {
|
||||
content: '知识库问答系统[](https://fastgpt.cn)',
|
||||
responseContent: '知识库问答系统[](https://fastgpt.cn)'
|
||||
}
|
||||
},
|
||||
{
|
||||
// 不完整的其他链接
|
||||
data: [{ content: '知识库' }, { content: '问答系统' }, { content: '[](https://fastgp' }],
|
||||
correct: {
|
||||
content: '知识库问答系统[](https://fastgp',
|
||||
responseContent: '知识库问答系统[](https://fastgp'
|
||||
}
|
||||
},
|
||||
{
|
||||
// 开头
|
||||
data: [{ content: '[知识库' }, { content: '问答系统' }, { content: '[](https://fastgp' }],
|
||||
correct: {
|
||||
content: '[知识库问答系统[](https://fastgp',
|
||||
responseContent: '[知识库问答系统[](https://fastgp'
|
||||
}
|
||||
},
|
||||
{
|
||||
// 结尾
|
||||
data: [{ content: '知识库' }, { content: '问答系统' }, { content: '[' }],
|
||||
correct: {
|
||||
content: '知识库问答系统[',
|
||||
responseContent: '知识库问答系统['
|
||||
}
|
||||
},
|
||||
{
|
||||
// 中间
|
||||
data: [
|
||||
{ content: '知识库' },
|
||||
{ content: '问答系统' },
|
||||
{ content: '[' },
|
||||
{ content: '问答系统]' }
|
||||
],
|
||||
correct: {
|
||||
content: '知识库问答系统[问答系统]',
|
||||
responseContent: '知识库问答系统[问答系统]'
|
||||
}
|
||||
},
|
||||
{
|
||||
// 双链接
|
||||
data: [
|
||||
{ content: '知识库' },
|
||||
{ content: '问答系统' },
|
||||
{ content: '[](https://fastgpt.cn)' },
|
||||
{ content: '[67e517e747' },
|
||||
{ content: '67063e882d' },
|
||||
{ content: '6861](CITE)' }
|
||||
],
|
||||
correct: {
|
||||
content: '知识库问答系统[](https://fastgpt.cn)[67e517e74767063e882d6861](CITE)',
|
||||
responseContent: '知识库问答系统[](https://fastgpt.cn)'
|
||||
}
|
||||
},
|
||||
{
|
||||
// 双链接缺失部分
|
||||
data: [
|
||||
{ content: '知识库' },
|
||||
{ content: '问答系统' },
|
||||
{ content: '[](https://fastgpt.cn)' },
|
||||
{ content: '[67e517e747' },
|
||||
{ content: '67063e882d' },
|
||||
{ content: '6861](CIT' }
|
||||
],
|
||||
correct: {
|
||||
content: '知识库问答系统[](https://fastgpt.cn)[67e517e74767063e882d6861](CIT',
|
||||
responseContent: '知识库问答系统[](https://fastgpt.cn)[67e517e74767063e882d6861](CIT'
|
||||
}
|
||||
},
|
||||
{
|
||||
// 双Cite
|
||||
data: [
|
||||
{ content: '知识库' },
|
||||
{ content: '问答系统' },
|
||||
{ content: '[67e517e747' },
|
||||
{ content: '67063e882d' },
|
||||
{ content: '6861](CITE)' },
|
||||
{ content: '[67e517e747' },
|
||||
{ content: '67063e882d' },
|
||||
{ content: '6861](CITE)' }
|
||||
],
|
||||
correct: {
|
||||
content: '知识库问答系统[67e517e74767063e882d6861](CITE)[67e517e74767063e882d6861](CITE)',
|
||||
responseContent: '知识库问答系统'
|
||||
}
|
||||
},
|
||||
{
|
||||
// 双Cite-第一个假Cite
|
||||
data: [
|
||||
{ content: '知识库' },
|
||||
{ content: '问答系统' },
|
||||
{ content: '[67e517e747' },
|
||||
{ content: '6861](CITE)' },
|
||||
{ content: '[67e517e747' },
|
||||
{ content: '67063e882d' },
|
||||
{ content: '6861](CITE)' }
|
||||
],
|
||||
correct: {
|
||||
content: '知识库问答系统[67e517e7476861](CITE)[67e517e74767063e882d6861](CITE)',
|
||||
responseContent: '知识库问答系统[67e517e7476861](CITE)'
|
||||
}
|
||||
}
|
||||
];
|
||||
|
||||
partList.forEach((part, index) => {
|
||||
it(`Dataset cite test: ${index}`, () => {
|
||||
const { parsePart } = parseLLMStreamResponse();
|
||||
|
||||
let answer = '';
|
||||
let responseContent = '';
|
||||
part.data.forEach((item, index) => {
|
||||
const formatPart = {
|
||||
choices: [
|
||||
{
|
||||
delta: {
|
||||
role: 'assistant',
|
||||
content: item.content,
|
||||
reasoning_content: ''
|
||||
},
|
||||
finish_reason: (index === part.data.length - 1
|
||||
? 'stop'
|
||||
: null) as CompletionFinishReason
|
||||
}
|
||||
]
|
||||
};
|
||||
const { content, responseContent: newResponseContent } = parsePart({
|
||||
part: formatPart,
|
||||
parseThinkTag: false,
|
||||
retainDatasetCite: false
|
||||
});
|
||||
answer += content;
|
||||
responseContent += newResponseContent;
|
||||
});
|
||||
|
||||
expect(answer).toEqual(part.correct.content);
|
||||
expect(responseContent).toEqual(part.correct.responseContent);
|
||||
});
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user