1
00:00:00,200 --> 00:00:02,480
So I have good news and bad news for you.
所以我有好消息和坏消息要告诉你。

2
00:00:02,480 --> 00:00:09,840
The good news is that today, the last day of week two, it's going to be quick and easy and satisfying.
好消息是，今天，第二周的最后一天，这将是快速、简单和令人满意的。

3
00:00:09,840 --> 00:00:11,920
So there's going to be fun stuff right away.
所以马上就会有有趣的事情。

4
00:00:12,040 --> 00:00:14,960
The bad news is there's going to be a really hard challenge at the end of it.
坏消息是最终将面临一个非常艰巨的挑战。

5
00:00:14,960 --> 00:00:18,320
It's going to be hard, but really big and juicy and good.
这会很难，但真的又大又多汁又好吃。

6
00:00:18,360 --> 00:00:21,680
So I do hope that you will take on the challenge that's coming up.
因此，我真诚地希望您能够接受即将到来的挑战。

7
00:00:21,680 --> 00:00:24,400
But first, let's just talk about what we're going to do today.
但首先，我们来谈谈今天要做什么。

8
00:00:24,400 --> 00:00:26,800
We're going to take our deep research.
我们将进行深入研究。

9
00:00:27,080 --> 00:00:29,920
The agent that we built last time in a notebook.
我们上次在笔记本中构建的代理。

10
00:00:29,920 --> 00:00:33,880
And we're going to turn it into proper Python code in modules.
我们将把它转换成模块中正确的 Python 代码。

11
00:00:33,920 --> 00:00:36,760
Yes, with a user interface featuring Gradio.
是的，具有具有 Gradio 功能的用户界面。

12
00:00:36,920 --> 00:00:38,240
Let's go and do that right now.
我们现在就去做吧。

13
00:00:38,680 --> 00:00:42,800
And so here we are in cursor and we're going into the OpenAI folder.
现在我们的光标位于 OpenAI 文件夹中。

14
00:00:42,800 --> 00:00:48,960
But now we're going into another folder into the deep research folder that is beneath it.
但现在我们要进入另一个文件夹，进入其下方的深度研究文件夹。

15
00:00:49,160 --> 00:00:52,840
And you will see that there are some Python modules you'll be happy to see.
您会发现有一些您会很高兴看到的 Python 模块。

16
00:00:52,880 --> 00:00:57,440
Because I know you like Python modules, and I'm going to just talk you through them, and I hope going
因为我知道你喜欢 Python 模块，我将向你介绍它们，我希望

17
00:00:57,480 --> 00:01:03,800
to be pleasantly surprised how easy it is, and also how natural it is to move from a notebook world
令人惊喜的是，它是多么容易，而且从笔记本世界转移是多么自然

18
00:01:03,800 --> 00:01:05,320
into proper modules.
进入适当的模块。

19
00:01:05,320 --> 00:01:07,080
And again, one more sales pitch.
又是一次推销。

20
00:01:07,120 --> 00:01:12,600
It's where I like to work experimentally, first in a notebook and then turn it into modules.
这是我喜欢进行实验性工作的地方，首先在笔记本中，然后将其变成模块。

21
00:01:12,640 --> 00:01:17,720
As you've built out your prompts, as you've experimented and refined your agent architecture.
当您构建了提示时，当您试验并完善了代理架构时。

22
00:01:18,040 --> 00:01:24,520
So what we've got in here are some agent classes, some agent modules with a single agent class, and
所以我们这里有一些代理类、一些具有单个代理类的代理模块，以及

23
00:01:24,520 --> 00:01:26,920
then a manager that packages it all together.
然后是一个将所有这些打包在一起的经理。

24
00:01:26,960 --> 00:01:32,200
And then finally, deep research is the user interface, which is a very simple user interface.
最后，深入研究的是用户界面，这是一个非常简单的用户界面。

25
00:01:32,240 --> 00:01:36,280
So let's start with the classes that represent the agents.
那么让我们从代表代理的类开始。

26
00:01:36,280 --> 00:01:37,760
And it's going to be really simple.
这将非常简单。

27
00:01:37,760 --> 00:01:42,680
We will start with the planner agent, which is exactly where we started when we were in the notebook
我们将从 planner 代理开始，这正是我们在笔记本中开始的地方

28
00:01:42,840 --> 00:01:44,520
the planner agent.
规划代理人。

29
00:01:44,560 --> 00:01:45,200
We've got this.
我们有这个。

30
00:01:45,200 --> 00:01:46,320
How many searches?
有多少次搜索？

31
00:01:46,320 --> 00:01:52,240
I've got it set to 20 now, but I'll turn it back to three before I check this in so that no one racks
我现在已将其设置为 20，但在签入之前我会将其调回 3，这样就不会有人占用了

32
00:01:52,240 --> 00:01:53,000
up a big bill.
涨了一大笔钱。

33
00:01:53,000 --> 00:01:59,800
If you use it, and you'll recognize the same old instructions and the same pedantic objects for a web
如果您使用它，您将认识到网络上相同的旧说明和相同的迂腐对象

34
00:01:59,800 --> 00:02:06,760
search item and a web search plan, which is the list of web search items in the single field searches.
搜索项和网页搜索计划，即单字段搜索中网页搜索项的列表。

35
00:02:06,920 --> 00:02:14,760
And here is our planner agent that takes our instructions and it uses the web search plan.
这是我们的规划代理，它接受我们的指示并使用网络搜索计划。

36
00:02:15,320 --> 00:02:16,200
There we go.
我们开始吧。

37
00:02:16,520 --> 00:02:22,040
Okay, next up, the search agent and I need to make one little change to this guy.
好吧，接下来，搜索代理和我需要对这个人做一点改变。

38
00:02:22,400 --> 00:02:25,000
So this is the search agent.
这就是搜索代理。

39
00:02:25,120 --> 00:02:29,320
The instructions you'll see here your research assistant.
您将在此处看到您的研究助理的说明。

40
00:02:29,560 --> 00:02:31,600
And it's got got this this format.
它有这样的格式。

41
00:02:31,600 --> 00:02:35,760
You'll remember that we stole that format from OpenAI's documentation.
您会记得我们从 OpenAI 的文档中窃取了该格式。

42
00:02:35,800 --> 00:02:38,920
A very nice set of instructions right there.
那里有一套非常好的说明。

43
00:02:39,160 --> 00:02:44,480
I don't know if you spot the little change I have to make, but the tools in here, I need to add in
我不知道你是否发现我必须做的小改变，但是这里的工具，我需要添加

44
00:02:44,480 --> 00:02:46,560
that parameter to make it nice and cheap.
该参数使其变得又好又便宜。

45
00:02:46,560 --> 00:02:47,840
So let's go and do that together.
那么让我们一起去做吧。

46
00:02:47,840 --> 00:02:55,280
If we go to this lab, if we look at what that parameter was, that parameter was actually near the
如果我们去这个实验室，如果我们看看那个参数是什么，那个参数实际上接近

47
00:02:55,280 --> 00:02:55,560
top.
顶部。

48
00:02:55,560 --> 00:02:57,840
I think we did at the very beginning.
我想我们一开始就这么做了。

49
00:02:57,840 --> 00:02:58,760
There we go.
我们开始吧。

50
00:02:59,000 --> 00:03:02,880
It is that the search context size is low.
这是搜索上下文大小较低。

51
00:03:03,160 --> 00:03:08,910
Let's go and put that in there right now so that no one spends unexpected amounts there.
我们现在就去把它放在那里，这样就不会有人在那里花费意外的金额。

52
00:03:08,910 --> 00:03:10,390
We have it done.
我们已经完成了。

53
00:03:10,830 --> 00:03:15,910
Okay, so that is the search agent class in the search agent module.
好的，这就是搜索代理模块中的搜索代理类。

54
00:03:16,190 --> 00:03:22,270
And now we've got a couple more, two more agents to talk about the writer agent again.
现在我们又多了两个经纪人来再次谈论作家经纪人。

55
00:03:22,430 --> 00:03:26,710
And you know, the benefit of having these in Python modules, it looks very crisp and simple.
你知道，将这些放在 Python 模块中的好处是，它看起来非常清晰和简单。

56
00:03:26,710 --> 00:03:28,550
You can see exactly what's going on.
您可以清楚地看到发生了什么。

57
00:03:28,590 --> 00:03:30,190
We've got our instructions.
我们已经得到了指示。

58
00:03:30,310 --> 00:03:38,110
We've got the pedantic report data that has a short summary, a markdown report and follow up questions.
我们已经得到了迂腐的报告数据，其中有简短的摘要、降价报告和后续问题。

59
00:03:38,430 --> 00:03:45,430
And then our writer agent, which is the agent that will take all of the information from all of the
然后是我们的作家代理，该代理将从所有的信息中获取所有信息

60
00:03:45,430 --> 00:03:49,990
searches and turn it into a report data object.
搜索并将其转换为报表数据对象。

61
00:03:50,510 --> 00:03:53,790
And the final agent, if you remember, is of course, the email agent.
如果您还记得的话，最后一个代理当然是电子邮件代理。

62
00:03:53,790 --> 00:03:54,630
Here it is.
这里是。

63
00:03:54,750 --> 00:03:57,150
This is stuff that you will recognize.
这是你会认出的东西。

64
00:03:57,270 --> 00:04:01,990
This is just the same thing that is going to send the email.
这与发送电子邮件相同。

65
00:04:02,030 --> 00:04:10,870
You must remember, please to change this to be your verified sender here, not make put your verified
您一定要记住，请在此处将其更改为您已验证的发件人，而不是输入您已验证的发件人

66
00:04:10,870 --> 00:04:14,990
sender here and then put some other email here.
发件人在这里，然后在这里输入一些其他电子邮件。

67
00:04:15,030 --> 00:04:17,550
Put your recipient here, not me.
把你的收件人放在这里，而不是我。

68
00:04:17,590 --> 00:04:20,790
I think I might change this before I check it in because otherwise someone's going to forget.
我想我可能会在签入之前更改此设置，否则有人会忘记。

69
00:04:20,830 --> 00:04:24,550
Well, many people will forget and I'll be overloaded with spam email.
好吧，很多人会忘记，我也会被垃圾邮件淹没。

70
00:04:24,910 --> 00:04:26,990
All right, so this is the tool.
好吧，这就是工具。

71
00:04:26,990 --> 00:04:37,310
And actually it's good to have a comment in here because that will send an email with the given subject
实际上，在这里发表评论是很好的，因为这将发送一封包含给定主题的电子邮件

72
00:04:37,310 --> 00:04:38,270
in HTML body.
在 HTML 正文中。

73
00:04:38,310 --> 00:04:39,310
Very nice.
很不错。

74
00:04:39,710 --> 00:04:40,430
Okay.
好的。

75
00:04:40,630 --> 00:04:45,390
So that is our email agent and that is all four of our agents.
这是我们的电子邮件代理，也是我们的所有四个代理。

76
00:04:45,390 --> 00:04:48,670
What's coming next is research manager.
接下来是研究经理。

77
00:04:49,070 --> 00:04:49,430
Okay.
好的。

78
00:04:49,470 --> 00:04:51,790
So research manager is a class.
所以研究经理是一个类。

79
00:04:51,790 --> 00:04:59,150
And this contains those short functions that we had last time with a little bit of a twist spiced it
这包含了我们上次使用的那些简短的函数，并对其进行了一些修改

80
00:04:59,150 --> 00:04:59,550
up.
向上。

81
00:04:59,790 --> 00:05:05,310
So first of all there is a single method here run or it's a coroutine.
所以首先这里有一个方法运行或者它是一个协程。

82
00:05:05,350 --> 00:05:11,590
If you want to be pedantic with me, this coroutine run an async def run.
如果你想跟我学究气，这个协程运行 async def run。

83
00:05:11,830 --> 00:05:16,830
And this is just the same as the as the code that I had before.
这和我之前的代码是一样的。

84
00:05:16,830 --> 00:05:23,470
We've got a little trick here to, to generate a trace ID so that we can, we can print where to go
我们这里有一个小技巧，生成一个跟踪 ID，以便我们可以打印要去的地方

85
00:05:23,470 --> 00:05:27,310
to look at the precise trace that we're looking at here.
查看我们在这里看到的精确轨迹。

86
00:05:27,710 --> 00:05:31,670
Now you may wonder why we've got all of this yielding going on.
现在您可能想知道为什么我们会产生所有这些收益。

87
00:05:31,870 --> 00:05:38,630
We, uh, we're treating this as a generator that is going to yield various bits of text along the way.
我们，呃，我们将其视为一个生成器，它将在此过程中生成各种文本。

88
00:05:38,990 --> 00:05:43,670
So that is going to become clear in a bit, but just take a look at what's going on here.
稍后这一点就会变得清楚，但看看这里发生了什么。

89
00:05:43,670 --> 00:05:47,590
I print some updates and I also yield those updates.
我打印了一些更新，并且也生成了这些更新。

90
00:05:47,630 --> 00:05:51,150
And I end by yielding the full markdown report.
最后我提供了完整的降价报告。

91
00:05:51,350 --> 00:05:53,950
Now hopefully you've done your intermediate.
现在希望你已经完成了中间任务。

92
00:05:53,950 --> 00:05:58,710
Either you already know all about generators or if you don't, then you've taken a look at the guide
要么您已经了解有关生成器的所有信息，要么如果您不了解，那么您已经查看了指南

93
00:05:58,710 --> 00:06:02,230
that explains generators so that there's no surprise.
这解释了生成器，所以也就不足为奇了。

94
00:06:03,070 --> 00:06:03,510
Okay.
好的。

95
00:06:03,550 --> 00:06:10,670
And then I've just got each of these functions plan searches, perform searches, search and write,
然后我刚刚获得了每个功能来计划搜索、执行搜索、搜索和写入，

96
00:06:10,670 --> 00:06:12,630
report and send email.
报告并发送电子邮件。

97
00:06:12,910 --> 00:06:17,950
These are the five functions that are exactly the same as the five functions we talked through before,
这五个函数与我们之前讨论过的五个函数完全相同，

98
00:06:17,990 --> 00:06:19,950
except a little bit beefed up.
除了稍微加强一点。

99
00:06:19,950 --> 00:06:26,150
They've got more type hints put in, as one should do for proper checked in Python modules.
它们添加了更多类型提示，就像正确检查 Python 模块所应该做的那样。

100
00:06:26,310 --> 00:06:28,670
And there's a bit more exception handling.
还有更多的异常处理。

101
00:06:28,790 --> 00:06:34,950
And this is a little bit fancier to handle the being able to print a status update while it's going
这对于处理能够在运行时打印状态更新来说有点花哨

102
00:06:34,950 --> 00:06:39,390
through the different searches, but otherwise it is much the same.
通过不同的搜索，但除此之外都大同小异。

103
00:06:39,590 --> 00:06:45,670
So it's just a bit tidied up, which is the kind of practice you should do when you move from the notebook
所以只是稍微整理了一下，这是你从笔记本上移开时应该做的练习

104
00:06:45,710 --> 00:06:51,310
environment, when you're being more experimental into something that's more well baked code, but it's
环境，当你对一些更完善的代码进行更多实验时，但它是

105
00:06:51,310 --> 00:06:52,590
the same functionality.
相同的功能。

106
00:06:53,230 --> 00:06:56,550
And that finally brings us to Deepresearch.
这最终让我们进入了深度研究。

107
00:06:57,630 --> 00:06:58,350
Here we are.
我们到了。

108
00:06:58,390 --> 00:07:00,430
This is our Gradio app.
这是我们的 Gradio 应用程序。

109
00:07:00,750 --> 00:07:03,550
This is where the magic happens.
这就是奇迹发生的地方。

110
00:07:03,710 --> 00:07:05,630
So Gradio which we import here.
所以我们在这里导入的Gradio。

111
00:07:05,950 --> 00:07:12,550
This is the the the package which you may know I love, which lets data scientists build great UIs without
这是您可能知道我喜欢的软件包，它可以让数据科学家构建出色的 UI，而无需

112
00:07:12,550 --> 00:07:14,430
needing to know anything about front end.
需要了解有关前端的任何知识。

113
00:07:14,740 --> 00:07:20,100
And I'm going to give you just some, some insights into how this works without I'm not giving you a
我将向您提供一些有关其工作原理的见解，但我不会向您提供

114
00:07:20,100 --> 00:07:21,220
full radio lesson here.
完整的广播课程在这里。

115
00:07:21,260 --> 00:07:22,420
And radio has great docs.
广播电台有很棒的文档。

116
00:07:22,420 --> 00:07:25,220
It's really easy to read up about it and build build your own.
阅读并构建您自己的内容非常容易。

117
00:07:25,220 --> 00:07:29,220
But just very briefly, this this code here is where the user interface is defined.
但非常简单地说，这里的代码是定义用户界面的地方。

118
00:07:29,260 --> 00:07:37,380
And we're used to using things like chat interface which is the super canned simple one where you just
我们习惯于使用诸如聊天界面之类的东西，这是一个超级简单的界面，您只需

119
00:07:37,380 --> 00:07:39,300
you can create an interface out of nothing.
你可以从无到有创建一个界面。

120
00:07:39,300 --> 00:07:44,500
If you want to actually build your own user interface from scratch, then you have to use a slightly
如果您想从头开始实际构建自己的用户界面，那么您必须使用稍微

121
00:07:44,500 --> 00:07:52,580
more detailed version when you do with great blocks as and then something like UI, and then you put
更详细的版本，当你使用伟大的块作为然后像 UI 之类的东西，然后你把

122
00:07:52,580 --> 00:07:58,540
your your code in there and then you say UI dot launch at the end and that that's the way to do it,
你的代码在那里，然后你在最后说 UI 点启动，这就是这样做的方法，

123
00:07:58,580 --> 00:08:00,740
that that will then build your user interface.
然后将构建您的用户界面。

124
00:08:00,740 --> 00:08:02,740
So that is exactly what we've got here.
这正是我们现在所得到的。

125
00:08:02,740 --> 00:08:04,980
We say with great blocks.
我们说有大块。

126
00:08:05,340 --> 00:08:10,100
And then you can pass in a theme if you want to have a different theme to the to the standard theme,
然后，如果您想要与标准主题不同的主题，则可以传入一个主题，

127
00:08:10,100 --> 00:08:12,820
and you can find the different colors that you can have in here.
您可以在这里找到不同的颜色。

128
00:08:13,100 --> 00:08:16,700
And then you simply put down the fields that you want.
然后您只需写下您想要的字段即可。

129
00:08:16,740 --> 00:08:21,940
So we're going to start with a heading GR markdown gives us a heading and we want to have the word deep
所以我们将从一个标题开始 GR markdown 给了我们一个标题，我们想要让这个词深入

130
00:08:21,940 --> 00:08:23,340
research as a big heading.
研究作为一个大标题。

131
00:08:23,340 --> 00:08:27,140
Then we want a text box that says what topic would you like to research.
然后我们需要一个文本框来说明您想要研究的主题。

132
00:08:27,300 --> 00:08:31,660
And we're associating that text box with a field called query.
我们将该文本框与一个名为“查询”的字段关联起来。

133
00:08:31,780 --> 00:08:34,220
So this this is a is a field.
所以这是一个字段。

134
00:08:34,260 --> 00:08:38,100
It might be a bit query clearer if we call this query text box.
如果我们调用这个查询文本框，查询可能会更清晰一些。

135
00:08:38,460 --> 00:08:40,180
Let's say that query text box.
假设查询文本框。

136
00:08:40,740 --> 00:08:46,140
And then here the next field we're going to put on a user interface is called run button.
然后，我们要在用户界面上放置的下一个字段称为“运行”按钮。

137
00:08:46,140 --> 00:08:47,700
It's a button.
这是一个按钮。

138
00:08:47,700 --> 00:08:50,580
It says run on it and it's a primary button.
它说运行它，它是一个主按钮。

139
00:08:50,580 --> 00:08:55,020
So it'll be nice and blue because blue is the sky, blue is the color we've chosen.
所以它会很漂亮，是蓝色的，因为蓝色是天空，蓝色是我们选择的颜色。

140
00:08:55,580 --> 00:09:01,180
And then the next one is going to be report, which is going to be our actual report text.
然后下一篇将是报告，这将是我们实际的报告文本。

141
00:09:01,220 --> 00:09:04,740
It's a markdown and its label is report.
这是一个markdown，它的标签是report。

142
00:09:05,460 --> 00:09:08,940
Okay I'm going to change this here to query text box.
好的，我将在这里更改它以查询文本框。

143
00:09:09,380 --> 00:09:13,660
So what we can now do is register an event.
所以我们现在能做的就是注册一个事件。

144
00:09:13,940 --> 00:09:17,900
We want to register an event with the run button.
我们想用运行按钮注册一个事件。

145
00:09:18,220 --> 00:09:23,380
We're going to say if the run button is clicked and we register that event by calling a function, click
我们会说，如果单击运行按钮，并且我们通过调用函数来注册该事件，请单击

146
00:09:23,380 --> 00:09:28,380
on run button and we just have to tell Gradio we want you to call us back.
按“运行”按钮，我们只需告诉 Gradio 我们希望您给我们回电。

147
00:09:28,420 --> 00:09:31,340
If that run button is clicked, then call this callback.
如果单击该运行按钮，则调用此回调。

148
00:09:31,420 --> 00:09:34,620
And that callback is going to be something called run.
这个回调将被称为 run。

149
00:09:34,940 --> 00:09:37,620
And spoiler alert, run is right up here.
剧透警告，奔跑就在这里。

150
00:09:38,180 --> 00:09:42,060
So if if run button is clicked then call that callback.
因此，如果单击运行按钮，则调用该回调。

151
00:09:42,060 --> 00:09:42,580
Run.
跑步。

152
00:09:42,820 --> 00:09:48,900
The inputs that you should use should be the contents of the query text box.
您应该使用的输入应该是查询文本框的内容。

153
00:09:49,780 --> 00:09:55,980
So the inputs to this callback should be whatever's in the text box when they press the run button,
因此，当按下运行按钮时，此回调的输入应该是文本框中的任何内容，

154
00:09:56,020 --> 00:09:58,140
when they click the run button, and the outputs.
当他们单击运行按钮时，以及输出。

155
00:09:58,140 --> 00:10:04,180
Whatever comes out of this callback should go into, I want you to hook that up Gradio hook it up into
无论此回调产生什么结果都应该进入，我希望你将其连接起来 Gradio 将其连接到

156
00:10:04,180 --> 00:10:06,020
this report markdown.
本报告降价。

157
00:10:06,540 --> 00:10:09,780
And then for the this, this next one is really the same thing.
然后对于这个，下一个实际上是同一件事。

158
00:10:09,900 --> 00:10:15,380
It's, it's saying that if they're in the query text box and they hit the enter key to submit, then
它是说，如果他们在查询文本框中并按回车键提交，那么

159
00:10:15,380 --> 00:10:16,740
again call the run.
再次调用运行。

160
00:10:17,100 --> 00:10:22,860
The input should be the contents of the query text box, and the output should be the report.
输入应该是查询文本框的内容，输出应该是报告。

161
00:10:23,220 --> 00:10:30,540
So this is a way that you can hook up gradio so that the widgets that you've constructed here get associated
因此，这是一种连接 gradio 的方法，以便您在此处构建的小部件关联起来

162
00:10:30,540 --> 00:10:35,340
with inputs and outputs of a callback function that's getting called.
带有被调用的回调函数的输入和输出。

163
00:10:35,540 --> 00:10:40,740
And this this method here is going to generate front end code that's going to run in a browser.
这里的这个方法将生成将在浏览器中运行的前端代码。

164
00:10:40,740 --> 00:10:46,500
And when they press that button it's actually going to call back this Python code in our class populating
当他们按下那个按钮时，它实际上会在我们的类中回调这个Python代码来填充

165
00:10:46,500 --> 00:10:48,300
it with the right the right fields.
它与正确的字段。

166
00:10:48,940 --> 00:10:54,660
So it doesn't matter if you didn't follow all of that, or you don't get or even care how Gradio hooks
因此，如果您没有遵循所有这些，或者您不了解甚至不关心 Gradio 如何挂钩，也没关系

167
00:10:54,660 --> 00:11:00,700
things up together, just have some general intuition for it and know that UI launch is the thing that
一切都放在一起，只需对此有一些一般的直觉，并知道 UI 启动是最重要的事情

168
00:11:00,700 --> 00:11:06,100
is then going to generate the front end code based on that, and figure out how to make sure that our
然后将基于此生成前端代码，并找出如何确保我们的

169
00:11:06,100 --> 00:11:11,580
callback gets called in browser equals true means that it's going to bring up a browser window right
在浏览器中调用回调等于 true 意味着它将正确打开浏览器窗口

170
00:11:11,580 --> 00:11:11,900
away.
离开。

171
00:11:11,940 --> 00:11:13,740
You don't need to have that if you don't wish.
如果您不愿意，则无​​需拥有它。

172
00:11:14,220 --> 00:11:18,820
So the only remaining thing for me to mention is what then is this?
所以我唯一要提的是，这是什么？

173
00:11:18,820 --> 00:11:22,100
What is going on with the with the run up here?
这里的跑步是怎么回事？

174
00:11:22,220 --> 00:11:30,610
So This is the callback that gets called, and you can see that as part of this I am calling the research
这是被调用的回调，您可以看到，作为其中的一部分，我将研究称为

175
00:11:30,650 --> 00:11:37,130
manager Dot run, and that is the the long function that we looked at a moment ago that had lots of
manager Dot run，这就是我们刚才看到的长函数，其中有很多

176
00:11:37,130 --> 00:11:38,330
yields in there.
那里有产量。

177
00:11:38,450 --> 00:11:43,010
And that brings me to the final part of the puzzle, which is normally in Gradio.
这让我想到了谜题的最后一部分，通常是在 Gradio 中。

178
00:11:43,010 --> 00:11:48,490
With these callbacks, you just return a result, the chat function that we've worked on in the past,
通过这些回调，您只需返回一个结果，即我们过去开发的聊天功能，

179
00:11:48,530 --> 00:11:50,610
that's an example of a callback.
这是回调的一个例子。

180
00:11:50,770 --> 00:11:57,530
Chat just returns the result, but you can also, instead of doing that, have your callback functions
聊天只返回结果，但您也可以使用回调函数来代替这样做

181
00:11:57,570 --> 00:12:03,530
be generators that Gradio needs to needs to iterate over and they will yield back results.
是 Gradio 需要迭代的生成器，它们将返回结果。

182
00:12:03,530 --> 00:12:09,010
And if you do that, then Gradio will show that incrementally in the user interface, so that you don't
如果您这样做，Gradio 将在用户界面中逐步显示，这样您就不会

183
00:12:09,010 --> 00:12:12,170
have to sit there and wait for a long time and suddenly see an output.
必须坐在那里等待很长时间，然后突然看到输出。

184
00:12:12,210 --> 00:12:14,610
You can see interim results as well.
您还可以看到中期结果。

185
00:12:14,610 --> 00:12:20,530
And that is why we had a bunch of yields, and that is why we have them here in our callback.
这就是为什么我们有很多收益率，这就是为什么我们在回调中拥有它们。

186
00:12:20,890 --> 00:12:24,370
I hope that makes some sense, but it certainly will do when we actually see it.
我希望这是有道理的，但当我们真正看到它时，它肯定会起作用。

187
00:12:24,410 --> 00:12:26,170
If it works, let's find out.
如果有效的话，让我们来看看。