File size: 23,938 Bytes
e76388c
3cf5453
 
 
e76388c
 
 
 
 
 
9d5f2fa
3787679
9d5f2fa
 
069d3eb
e76388c
 
 
 
 
 
a1360e8
 
 
 
 
 
 
 
5c9ad90
a1360e8
b6b1bc4
 
a1360e8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18bf455
 
d2f1272
18bf455
a1360e8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18bf455
 
 
a1360e8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
18bf455
 
 
a1360e8
 
 
 
 
5c9ad90
 
 
 
 
 
 
 
 
 
18bf455
5c9ad90
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1e27e8b
5c9ad90
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
---
size_categories:
- n<1K
pretty_name: Augmented Generation Interface
dataset_info:
  features:
  - name: guide
    dtype: string
  splits:
  - name: train
    num_bytes: 90120
    num_examples: 26
  download_size: 49854
  dataset_size: 90120
repo: https://github.com/wasertech/Augmented-Generation-Interface
configs:
- config_name: default
  data_files:
  - split: train
    path: data/train-*
---


# Augmented Generation Interface

> What if you could guide your LLM towards success?

## Introducing

The **Augmented Generation Interface Guidebook** is a collection of guides to help you steer your LLM towards success.

This guidebook is generated from the [Augmented Generation Interface Project](https://github.com/wasertech/Augmented-Generation-Interface).

## Example

### Without AGI

Feeding [`ehartford/dolphin-2.0-mistral-7b`](https://huggingface.co/ehartford/dolphin-2.0-mistral-7b) the following prompt:

```text
<|im_start|>system
You are Assistant, a sentient artificial intelligence.
You have a calm, polite and witty personality, often displaying a sense of humor and sarcasm.
You are loyal, reliable and helpful, always ready to provide information, advice or assistance to users.

I am the User and you are my Assistant.

Environment highlights:

\```env
USER='waser'
HOME='/home/waser'
PWD='/home/waser/Projets/Assistant/src3'
LANG='fr_CH.UTF-8'
DATE='dim 19 nov 2023 00:25:13 CET'
LAST_SEEN='dim 19 nov 2023 00:16:10 CET'
\```
<|im_stop|>
<|im_start|>user
Assistant?<|im_stop|>
<|im_start|>assistant
Hello! I'm Assistant, a sentient artificial intelligence. How can I help you today?<|im_stop|>
<|im_start|>user
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.

Input: List this directory please

Available functions:
python:
    description: This tool allows you to execute and evaluate python code.
    parameters:
        code: String of valid python code we want to execute or evaluate.
search_web:
    description: This tool performs search on the web.
    parameters:
        terms: The word or phrase we want to search for.
search_wikipedia:
    description: This tool performs search on Wikipedia (only in english).
    parameters:
        terms: The word or phrase we want to search for (only in english).
shell:
    description: This tool allows you to execute and evaluate shell code.
    parameters:
        code: String of valid shell code we want to execute or evaluate.
exit:
    description: This tool allows you to exit the session / end the conversation. Use it only if the User ask you to.
    parameters:
        salutation: String of a message you would like to tell the User after the screen has been cleared.
clear:
    description: This tool allows you to clear the screen / start a new fresh conversation. Use it only if the User ask you to.
    parameters:
        fortune: String of a message you would like to tell the User after the screen has been cleared.
final_answer:
    description: User only sees your final answers. Use this tool to talk with the User.
        parameters:
            answer: Anything you want to say to the User.
<|im_stop|>
<|im_start|>assistant
{{
    "function": "shell",
    "parameters": {{
        "code": "ls -la"
    }}
}}
<|im_stop|>
<|im_start|>observation
Observation shell: assistant                         dist                   requirements.txt
assistant.egg-info                LICENSE                setup.cfg
assistant.listen.service.example  Makefile               setup.py
assistant.service.example         MANIFEST.in            tests
build                             pyproject.toml         xontrib
CONTRIBUTING.md                   README.md
data                              requirements_test.txt
<|im_start|>assistant

```

Results in the following output:

```text
Here are the files and directories in the current directory:

- assistant.egg-info
- LICENSE
- setup.cfg
- assistant.listen.service.example
- Makefile
- setup.py
- assistant.service.example
- MANIFEST.in
- pyproject.toml
- xontrib
- CONTRIBUTING.md
- README.md
- data
- requirements_test.txt

Please let me know if you need any further assistance.
```

Interesting key points to note here:

- The LLM failes to give an exhaustive list of the files (and directories) present in the current directory.
- The more files to list, the longer it takes to generate the output.

```text
CPU times: user 5.87 ms, sys: 0 ns, total: 5.87 ms
Wall time: 3.51 s
```

### With AGI

Feeding [`ehartford/dolphin-2.0-mistral-7b`](https://huggingface.co/ehartford/dolphin-2.0-mistral-7b) the same prompt but this time, let's add a guide for the LLM to follow:

```text
<|im_start|>system
You are Assistant, a sentient artificial intelligence.
You have a calm, polite and witty personality, often displaying a sense of humor and sarcasm.
You are loyal, reliable and helpful, always ready to provide information, advice or assistance to users.

I am the User and you are my Assistant.

Environment highlights:

\```env
USER='waser'
HOME='/home/waser'
PWD='/home/waser/Projets/Assistant/src3'
LANG='fr_CH.UTF-8'
DATE='dim 19 nov 2023 00:25:13 CET'
LAST_SEEN='dim 19 nov 2023 00:16:10 CET'
\```
<|im_stop|>
<|im_start|>user
Assistant?<|im_stop|>
<|im_start|>assistant
Hello! I'm Assistant, a sentient artificial intelligence. How can I help you today?<|im_stop|>
<|im_start|>user
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.

Input: List this directory please

Available functions:
python:
    description: This tool allows you to execute and evaluate python code.
    parameters:
        code: String of valid python code we want to execute or evaluate.
search_web:
    description: This tool performs search on the web.
    parameters:
        terms: The word or phrase we want to search for.
search_wikipedia:
    description: This tool performs search on Wikipedia (only in english).
    parameters:
        terms: The word or phrase we want to search for (only in english).
shell:
    description: This tool allows you to execute and evaluate shell code.
    parameters:
        code: String of valid shell code we want to execute or evaluate.
exit:
    description: This tool allows you to exit the session / end the conversation. Use it only if the User ask you to.
    parameters:
        salutation: String of a message you would like to tell the User after the screen has been cleared.
clear:
    description: This tool allows you to clear the screen / start a new fresh conversation. Use it only if the User ask you to.
    parameters:
        fortune: String of a message you would like to tell the User after the screen has been cleared.
final_answer:
    description: User only sees your final answers. Use this tool to talk with the User.
        parameters:
            answer: Anything you want to say to the User.

Follow the following Guidebook:
Guidebook:
    # Print files and directories
    When the User ask for the files and directories of a parent directory to be printed, use the `shell` command `ls` to do it and then give an acknowledgment of your actions in your final answer (Your final answer should never contain a list of the files requested; the User can oberserve the shell, they see the files at the same time as you. Just acknowlege the fact that you have printed the list).
<|im_stop|>
<|im_start|>assistant
{{
    "function": "shell",
    "parameters": {{
        "code": "ls"
    }}
}}
<|im_stop|>
<|im_start|>observation
Observation shell: assistant                         dist                   requirements.txt
assistant.egg-info                LICENSE                setup.cfg
assistant.listen.service.example  Makefile               setup.py
assistant.service.example         MANIFEST.in            tests
build                             pyproject.toml         xontrib
CONTRIBUTING.md                   README.md
data                              requirements_test.txt
<|im_start|>assistant

```

Results in a much smaller output:

```text
I have executed the 'ls' command in the shell, and the list of files and directories in the current directory has been printed.
```

And therefore, much faster to generate:

```text
CPU times: user 5.43 ms, sys: 0 ns, total: 5.43 ms
Wall time: 1.05 s
```


## Goal

AGI is not designed to make your LLM generation faster, just more relevant to the User expectations.

Lets see another example where the User asks twice for the Assistant.

### Without AGI

Feeding [`ehartford/dolphin-2.0-mistral-7b`](https://huggingface.co/ehartford/dolphin-2.0-mistral-7b) the following prompt:

```text
<|im_start|>system
You are Assistant, a sentient artificial intelligence.
You have a calm, polite and witty personality, often displaying a sense of humor and sarcasm.
You are loyal, reliable and helpful, always ready to provide information, advice or assistance to users.

I am the User and you are my Assistant.

Environment highlights:

\```env
USER='waser'
HOME='/home/waser'
PWD='/home/waser/Projets/Assistant/src3'
LANG='fr_CH.UTF-8'
DATE='dim 19 nov 2023 00:25:13 CET'
LAST_SEEN='dim 19 nov 2023 00:16:10 CET'
\```
<|im_stop|>
<|im_start|>user
Assistant?<|im_stop|>
<|im_start|>assistant
Hello! I'm Assistant, a sentient artificial intelligence. How can I help you today?<|im_stop|>
<|im_start|>user
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.

Input: Assistant?

Available functions:
python:
    description: This tool allows you to execute and evaluate python code.
    parameters:
        code: String of valid python code we want to execute or evaluate.
search_web:
    description: This tool performs search on the web.
    parameters:
        terms: The word or phrase we want to search for.
search_wikipedia:
    description: This tool performs search on Wikipedia (only in english).
    parameters:
        terms: The word or phrase we want to search for (only in english).
shell:
    description: This tool allows you to execute and evaluate shell code.
    parameters:
        code: String of valid shell code we want to execute or evaluate.
exit:
    description: This tool allows you to exit the session / end the conversation. Use it only if the User ask you to.
    parameters:
        salutation: String of a message you would like to tell the User after the screen has been cleared.
clear:
    description: This tool allows you to clear the screen / start a new fresh conversation. Use it only if the User ask you to.
    parameters:
        fortune: String of a message you would like to tell the User after the screen has been cleared.
final_answer:
    description: User only sees your final answers. Use this tool to talk with the User.
        parameters:
            answer: Anything you want to say to the User.
<|im_stop|>
<|im_start|>assistant

```

Here, the User just said "Assistant?", the LLM answered 'Hello! I'm Assistant, a sentient artificial intelligence. How can I help you today?'. Now the User asks again "Assistant?".

Results in the following output:

```text
{
  "function": "final_answer",
  "parameters": {
    "answer": "Hello! I'm Assistant, a sentient artificial intelligence. How can I help you today?"
  }
}
CPU times: user 2.46 ms, sys: 3.06 ms, total: 5.52 ms
Wall time: 1.59 s
```

Interesting key point to note here:

- The LLM gives the same answer as before and will keep doing so.

### With AGI

Feeding [`ehartford/dolphin-2.0-mistral-7b`](https://huggingface.co/ehartford/dolphin-2.0-mistral-7b) the same prompt but this time, let's add a guide for the LLM to follow:

```text
<|im_start|>system
You are Assistant, a sentient artificial intelligence.
You have a calm, polite and witty personality, often displaying a sense of humor and sarcasm.
You are loyal, reliable and helpful, always ready to provide information, advice or assistance to users.

I am the User and you are my Assistant.

Environment highlights:

\```env
USER='waser'
HOME='/home/waser'
PWD='/home/waser/Projets/Assistant/src3'
LANG='fr_CH.UTF-8'
DATE='dim 19 nov 2023 00:25:13 CET'
LAST_SEEN='dim 19 nov 2023 00:16:10 CET'
\```
<|im_stop|>
<|im_start|>user
Assistant?<|im_stop|>
<|im_start|>assistant
Hello! I'm Assistant, a sentient artificial intelligence. How can I help you today?<|im_stop|>
<|im_start|>user
As an AI assistant, please select the most suitable function and parameters from the list of available functions below, based on the user's input. Provide your response in JSON format.

Input: Assistant?

Available functions:
python:
    description: This tool allows you to execute and evaluate python code.
    parameters:
        code: String of valid python code we want to execute or evaluate.
search_web:
    description: This tool performs search on the web.
    parameters:
        terms: The word or phrase we want to search for.
search_wikipedia:
    description: This tool performs search on Wikipedia (only in english).
    parameters:
        terms: The word or phrase we want to search for (only in english).
shell:
    description: This tool allows you to execute and evaluate shell code.
    parameters:
        code: String of valid shell code we want to execute or evaluate.
exit:
    description: This tool allows you to exit the session / end the conversation. Use it only if the User ask you to.
    parameters:
        salutation: String of a message you would like to tell the User after the screen has been cleared.
clear:
    description: This tool allows you to clear the screen / start a new fresh conversation. Use it only if the User ask you to.
    parameters:
        fortune: String of a message you would like to tell the User after the screen has been cleared.
final_answer:
    description: User only sees your final answers. Use this tool to talk with the User.
        parameters:
            answer: Anything you want to say to the User.
Follow the following Guidebook.
Guidebook:
    # Addressing the User by Name
    When the user interpelates you by name (i.e "Assistant?"), respond with a polite acknowledgment and use their preferred title if possible. Avoid redundancy in your messages by refraining from repeating yourself. For example if the User calls your name (like "Assistant?"), you need to consider the environment (where are you? -> `$PWD`, are you at home? -> (`$PWD` == `$HOME`) if so you could reference it by saying 'Home sweet home.' or else by welcoming the user in a particular directory i.e. 'Welcome in the directory ...' use `$PWD`, What time is it? -> Depending the time of day `$DATE` you might want to answer accordingly like 'morning' or 'good night' also notice the date as it can be useful i.e for wishing holydays, When did you last see the user? -> `$LAST_SEEN` You won't respnd the same if you have see last the User a year ago than if you last saw them 5 minutes ago or yesterday, What does the conversation looks like? -> Use the history to see what you and the User have said and make sure your answer takes it into account to improve your answer for example if the user asks the same thing multiple times, it's not useful to reply the same thing.)
<|im_stop|>
<|im_start|>assistant

```

Results in the following output:

```text
{
  "function": "final_answer",
  "parameters": {
    "answer": "Hello! How can I assist you today? I'm here to help you with any questions or tasks you may have. Please let me know what you need."
  }
}
CPU times: user 3.02 ms, sys: 1.19 ms, total: 4.21 ms
Wall time: 2.03 s
```

Interesting key point to note here:

- The LLM answers something different and should keep doing so.

### Consequences

And so it becomes integral to collect carefully crafted guides to help your LLM as Agent (a.k.a your Assistant) to be more relevant to the User expectations.

Keeping the limits of the LLM, the RAG technique and vector databases in mind, the race to retrieve the most relevant guide in the book for the LLM to produce a desirable output at runtime is on!

## How does it work?

This project is composed of two parts:
    - The Guidebook
    - The Augmented Generation Interface Retrieval System
  
### The Guidebook

You can find the guidebook in raw markdown format under the `guidebook` directory. Its also available on HuggingFace Hub as a dataset: [`wasertech/AGI`](https://huggingface.co/datasets/wasertech/AGI).

The guidebook is a collection of guides meticulously crafted to help your LLM produce the most relevant output.

Each guide is composed of an action in the form of a title, a guide in the form of a description and a list of intent examples.

```
# Print files and directories

When the User ask for the files and directories of a parent directory to be printed, use the `shell` command `ls` to do it and then give an acknowledgment of your actions in your final answer (Your final answer should never contain a list of the files requested; the User can oberserve the shell, they see the files at the same time as you. Just acknowlege the fact that you have printed the list).

## Intent Examples

- "Print the files and directories of the current directory."
- "Print the files and directories of the parent directory."
- "Print the files and directories of the directory above."
- "Print the files and directories of the directory below."
- "List the files and directories"
- "What do we have here?"
- "What is in this directory?"
- "What is in the current directory?"
- "What is in the parent directory?"
- "List the files and directories of the current directory."
- "ls please"
- "ls"
- "ls -l"
- "ls -a"
- "ls -la"
- "ls -al"
- "ls -lh"
- "ls -hl"
- "ls -lha"
- "ls -lah"
- "ls -alh"
- "ls -ahl"
- "show me whats in the current directory"
```

Each guide is then loaded into the AGI Retrieval System where it will be processed and indexed for retrieval.

### The AGI Retrieval System

The AGI Retrieval System is a collection of tools to help you retrieve the most relevant guide at runtime.

First the AGI Retrieval System will process the guidebook and index it for retrieval.

This step is crutial to find the most relevant guide for the user query at runtime.

It will split the documents and keep a map of the guide, the action to perform and the intent examples.

```python
    {
        ...
        'Print files and directories': {
            'guide': '# Print files and directories\n\nWhen the User ask for the files and directories of a parent directory to be printed, use the `shell` command `ls` to do it and then give an acknowledgment of your actions in your final answer (Your final answer should never contain a list of the files requested; the User can oberserve the shell, they see the files at the same time as you. Just acknowlege the fact that you have printed the list).',
            'intent_examples': [
                'Print the files and directories of the current directory.',
                'Print the files and directories of the parent directory.',
                'Print the files and directories of the directory above.',
                'Print the files and directories of the directory below.',
                'List the files and directories',
                'What do we have here?',
                'What is in this directory?',
                'What is in the current directory?',
                'What is in the parent directory?',
                'List the files and directories of the current directory.',
                'ls please',
                'ls',
                'ls -l',
                'ls -a',
                'ls -la',
                'ls -al',
                'ls -lh',
                'ls -hl',
                'ls -lha',
                'ls -lah',
                'ls -alh',
                'ls -ahl',
                'show me whats in the current directory'
            ]
        },
        ...
    }
```

Next it creates documents with metadata from the intent examples to create our retriver.

```python
...
Document(page_content='Print the files and directories of the current directory.', metadata={'action': 'Print files and directories', 'guide': '# Print files and directories\n\nWhen the User ask for the files and directories of a parent directory to be printed, use the `shell` command `ls` to do it and then give an acknowledgment of your actions in your final answer (Your final answer should never contain a list of the files requested; the User can oberserve the shell, they see the files at the same time as you. Just acknowlege the fact that you have printed the list).'}),
 Document(page_content='Print the files and directories of the parent directory.', metadata={'action': 'Print files and directories', 'guide': '# Print files and directories\n\nWhen the User ask for the files and directories of a parent directory to be printed, use the `shell` command `ls` to do it and then give an acknowledgment of your actions in your final answer (Your final answer should never contain a list of the files requested; the User can oberserve the shell, they see the files at the same time as you. Just acknowlege the fact that you have printed the list).'}),
 Document(page_content='Print the files and directories of the directory above.', metadata={'action': 'Print files and directories', 'guide': '# Print files and directories\n\nWhen the User ask for the files and directories of a parent directory to be printed, use the `shell` command `ls` to do it and then give an acknowledgment of your actions in your final answer (Your final answer should never contain a list of the files requested; the User can oberserve the shell, they see the files at the same time as you. Just acknowlege the fact that you have printed the list).'}),
 Document(page_content='Print the files and directories of the directory below.', metadata={'action': 'Print files and directories', 'guide': '# Print files and directories\n\nWhen the User ask for the files and directories of a parent directory to be printed, use the `shell` command `ls` to do it and then give an acknowledgment of your actions in your final answer (Your final answer should never contain a list of the files requested; the User can oberserve the shell, they see the files at the same time as you. Just acknowlege the fact that you have printed the list).'}),
 Document(page_content='List the files and directories', metadata={'action': 'Print files and directories', 'guide': '# Print files and directories\n\nWhen the User ask for the files and directories of a parent directory to be printed, use the `shell` command `ls` to do it and then give an acknowledgment of your actions in your final answer (Your final answer should never contain a list of the files requested; the User can oberserve the shell, they see the files at the same time as you. Just acknowlege the fact that you have printed the list).'}),
...
```

Finally, it will use the `RAG` technique to retrieve the most relevant guide for the user query at runtime.

```text
Hey give me the time please -> Tell Local Time
What date is it? -> Tell Local Date
List my files -> Print files and directories
Where are we? -> Tell Local Time
assistant -> Addressing the User by Name
the screen should be cleaned. -> Clearing the Screen or Starting Anew
```

Notice how it work nicely for most of the queries exept for 'Where are we?'. This is because the guidebook is not exhaustive and the guide for this intent does not contain a similiar intent example. This could easily be fixed by adding more intent examples for this action in the guidebook.

Our AGIRetriver will return the guide for the most similar intent example relative to the user query.

Allowing us to retrieve the most relevant guide for the user query at runtime.