File size: 49,013 Bytes
cfd3735
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
{
 "cells": [
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# ClearML Integration\n",
    "\n",
    "In order to properly keep track of your langchain experiments and their results, you can enable the ClearML integration. ClearML is an experiment manager that neatly tracks and organizes all your experiment runs.\n",
    "\n",
    "<a target=\"_blank\" href=\"https://colab.research.google.com/github/hwchase17/langchain/blob/master/docs/ecosystem/clearml_tracking.ipynb\">\n",
    "  <img src=\"https://colab.research.google.com/assets/colab-badge.svg\" alt=\"Open In Colab\"/>\n",
    "</a>"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Getting API Credentials\n",
    "\n",
    "We'll be using quite some APIs in this notebook, here is a list and where to get them:\n",
    "\n",
    "- ClearML: https://app.clear.ml/settings/workspace-configuration\n",
    "- OpenAI: https://platform.openai.com/account/api-keys\n",
    "- SerpAPI (google search): https://serpapi.com/dashboard"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "os.environ[\"CLEARML_API_ACCESS_KEY\"] = \"\"\n",
    "os.environ[\"CLEARML_API_SECRET_KEY\"] = \"\"\n",
    "\n",
    "os.environ[\"OPENAI_API_KEY\"] = \"\"\n",
    "os.environ[\"SERPAPI_API_KEY\"] = \"\""
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Setting Up"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install clearml\n",
    "!pip install pandas\n",
    "!pip install textstat\n",
    "!pip install spacy\n",
    "!python -m spacy download en_core_web_sm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "The clearml callback is currently in beta and is subject to change based on updates to `langchain`. Please report any issues to https://github.com/allegroai/clearml/issues with the tag `langchain`.\n"
     ]
    }
   ],
   "source": [
    "from datetime import datetime\n",
    "from langchain.callbacks import ClearMLCallbackHandler, StdOutCallbackHandler\n",
    "from langchain.llms import OpenAI\n",
    "\n",
    "# Setup and use the ClearML Callback\n",
    "clearml_callback = ClearMLCallbackHandler(\n",
    "    task_type=\"inference\",\n",
    "    project_name=\"langchain_callback_demo\",\n",
    "    task_name=\"llm\",\n",
    "    tags=[\"test\"],\n",
    "    # Change the following parameters based on the amount of detail you want tracked\n",
    "    visualize=True,\n",
    "    complexity_metrics=True,\n",
    "    stream_logs=True\n",
    ")\n",
    "callbacks = [StdOutCallbackHandler(), clearml_callback]\n",
    "# Get the OpenAI model ready to go\n",
    "llm = OpenAI(temperature=0, callbacks=callbacks)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Scenario 1: Just an LLM\n",
    "\n",
    "First, let's just run a single LLM a few times and capture the resulting prompt-answer conversation in ClearML"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a joke'}\n",
      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a poem'}\n",
      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a joke'}\n",
      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a poem'}\n",
      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a joke'}\n",
      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Tell me a poem'}\n",
      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n",
      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n",
      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n",
      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n",
      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nQ: What did the fish say when it hit the wall?\\nA: Dam!', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 109.04, 'flesch_kincaid_grade': 1.3, 'smog_index': 0.0, 'coleman_liau_index': -1.24, 'automated_readability_index': 0.3, 'dale_chall_readability_score': 5.5, 'difficult_words': 0, 'linsear_write_formula': 5.5, 'gunning_fog': 5.2, 'text_standard': '5th and 6th grade', 'fernandez_huerta': 133.58, 'szigriszt_pazos': 131.54, 'gutierrez_polini': 62.3, 'crawford': -0.2, 'gulpease_index': 79.8, 'osman': 116.91}\n",
      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 24, 'token_usage_completion_tokens': 138, 'token_usage_total_tokens': 162, 'model_name': 'text-davinci-003', 'step': 4, 'starts': 2, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 0, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': '\\n\\nRoses are red,\\nViolets are blue,\\nSugar is sweet,\\nAnd so are you.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 83.66, 'flesch_kincaid_grade': 4.8, 'smog_index': 0.0, 'coleman_liau_index': 3.23, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 6.71, 'difficult_words': 2, 'linsear_write_formula': 6.5, 'gunning_fog': 8.28, 'text_standard': '6th and 7th grade', 'fernandez_huerta': 115.58, 'szigriszt_pazos': 112.37, 'gutierrez_polini': 54.83, 'crawford': 1.4, 'gulpease_index': 72.1, 'osman': 100.17}\n",
      "{'action_records':           action    name  step  starts  ends  errors  text_ctr  chain_starts  \\\n",
      "0   on_llm_start  OpenAI     1       1     0       0         0             0   \n",
      "1   on_llm_start  OpenAI     1       1     0       0         0             0   \n",
      "2   on_llm_start  OpenAI     1       1     0       0         0             0   \n",
      "3   on_llm_start  OpenAI     1       1     0       0         0             0   \n",
      "4   on_llm_start  OpenAI     1       1     0       0         0             0   \n",
      "5   on_llm_start  OpenAI     1       1     0       0         0             0   \n",
      "6     on_llm_end     NaN     2       1     1       0         0             0   \n",
      "7     on_llm_end     NaN     2       1     1       0         0             0   \n",
      "8     on_llm_end     NaN     2       1     1       0         0             0   \n",
      "9     on_llm_end     NaN     2       1     1       0         0             0   \n",
      "10    on_llm_end     NaN     2       1     1       0         0             0   \n",
      "11    on_llm_end     NaN     2       1     1       0         0             0   \n",
      "12  on_llm_start  OpenAI     3       2     1       0         0             0   \n",
      "13  on_llm_start  OpenAI     3       2     1       0         0             0   \n",
      "14  on_llm_start  OpenAI     3       2     1       0         0             0   \n",
      "15  on_llm_start  OpenAI     3       2     1       0         0             0   \n",
      "16  on_llm_start  OpenAI     3       2     1       0         0             0   \n",
      "17  on_llm_start  OpenAI     3       2     1       0         0             0   \n",
      "18    on_llm_end     NaN     4       2     2       0         0             0   \n",
      "19    on_llm_end     NaN     4       2     2       0         0             0   \n",
      "20    on_llm_end     NaN     4       2     2       0         0             0   \n",
      "21    on_llm_end     NaN     4       2     2       0         0             0   \n",
      "22    on_llm_end     NaN     4       2     2       0         0             0   \n",
      "23    on_llm_end     NaN     4       2     2       0         0             0   \n",
      "\n",
      "    chain_ends  llm_starts  ...  difficult_words  linsear_write_formula  \\\n",
      "0            0           1  ...              NaN                    NaN   \n",
      "1            0           1  ...              NaN                    NaN   \n",
      "2            0           1  ...              NaN                    NaN   \n",
      "3            0           1  ...              NaN                    NaN   \n",
      "4            0           1  ...              NaN                    NaN   \n",
      "5            0           1  ...              NaN                    NaN   \n",
      "6            0           1  ...              0.0                    5.5   \n",
      "7            0           1  ...              2.0                    6.5   \n",
      "8            0           1  ...              0.0                    5.5   \n",
      "9            0           1  ...              2.0                    6.5   \n",
      "10           0           1  ...              0.0                    5.5   \n",
      "11           0           1  ...              2.0                    6.5   \n",
      "12           0           2  ...              NaN                    NaN   \n",
      "13           0           2  ...              NaN                    NaN   \n",
      "14           0           2  ...              NaN                    NaN   \n",
      "15           0           2  ...              NaN                    NaN   \n",
      "16           0           2  ...              NaN                    NaN   \n",
      "17           0           2  ...              NaN                    NaN   \n",
      "18           0           2  ...              0.0                    5.5   \n",
      "19           0           2  ...              2.0                    6.5   \n",
      "20           0           2  ...              0.0                    5.5   \n",
      "21           0           2  ...              2.0                    6.5   \n",
      "22           0           2  ...              0.0                    5.5   \n",
      "23           0           2  ...              2.0                    6.5   \n",
      "\n",
      "    gunning_fog      text_standard  fernandez_huerta szigriszt_pazos  \\\n",
      "0           NaN                NaN               NaN             NaN   \n",
      "1           NaN                NaN               NaN             NaN   \n",
      "2           NaN                NaN               NaN             NaN   \n",
      "3           NaN                NaN               NaN             NaN   \n",
      "4           NaN                NaN               NaN             NaN   \n",
      "5           NaN                NaN               NaN             NaN   \n",
      "6          5.20  5th and 6th grade            133.58          131.54   \n",
      "7          8.28  6th and 7th grade            115.58          112.37   \n",
      "8          5.20  5th and 6th grade            133.58          131.54   \n",
      "9          8.28  6th and 7th grade            115.58          112.37   \n",
      "10         5.20  5th and 6th grade            133.58          131.54   \n",
      "11         8.28  6th and 7th grade            115.58          112.37   \n",
      "12          NaN                NaN               NaN             NaN   \n",
      "13          NaN                NaN               NaN             NaN   \n",
      "14          NaN                NaN               NaN             NaN   \n",
      "15          NaN                NaN               NaN             NaN   \n",
      "16          NaN                NaN               NaN             NaN   \n",
      "17          NaN                NaN               NaN             NaN   \n",
      "18         5.20  5th and 6th grade            133.58          131.54   \n",
      "19         8.28  6th and 7th grade            115.58          112.37   \n",
      "20         5.20  5th and 6th grade            133.58          131.54   \n",
      "21         8.28  6th and 7th grade            115.58          112.37   \n",
      "22         5.20  5th and 6th grade            133.58          131.54   \n",
      "23         8.28  6th and 7th grade            115.58          112.37   \n",
      "\n",
      "    gutierrez_polini  crawford  gulpease_index   osman  \n",
      "0                NaN       NaN             NaN     NaN  \n",
      "1                NaN       NaN             NaN     NaN  \n",
      "2                NaN       NaN             NaN     NaN  \n",
      "3                NaN       NaN             NaN     NaN  \n",
      "4                NaN       NaN             NaN     NaN  \n",
      "5                NaN       NaN             NaN     NaN  \n",
      "6              62.30      -0.2            79.8  116.91  \n",
      "7              54.83       1.4            72.1  100.17  \n",
      "8              62.30      -0.2            79.8  116.91  \n",
      "9              54.83       1.4            72.1  100.17  \n",
      "10             62.30      -0.2            79.8  116.91  \n",
      "11             54.83       1.4            72.1  100.17  \n",
      "12               NaN       NaN             NaN     NaN  \n",
      "13               NaN       NaN             NaN     NaN  \n",
      "14               NaN       NaN             NaN     NaN  \n",
      "15               NaN       NaN             NaN     NaN  \n",
      "16               NaN       NaN             NaN     NaN  \n",
      "17               NaN       NaN             NaN     NaN  \n",
      "18             62.30      -0.2            79.8  116.91  \n",
      "19             54.83       1.4            72.1  100.17  \n",
      "20             62.30      -0.2            79.8  116.91  \n",
      "21             54.83       1.4            72.1  100.17  \n",
      "22             62.30      -0.2            79.8  116.91  \n",
      "23             54.83       1.4            72.1  100.17  \n",
      "\n",
      "[24 rows x 39 columns], 'session_analysis':     prompt_step         prompts    name  output_step  \\\n",
      "0             1  Tell me a joke  OpenAI            2   \n",
      "1             1  Tell me a poem  OpenAI            2   \n",
      "2             1  Tell me a joke  OpenAI            2   \n",
      "3             1  Tell me a poem  OpenAI            2   \n",
      "4             1  Tell me a joke  OpenAI            2   \n",
      "5             1  Tell me a poem  OpenAI            2   \n",
      "6             3  Tell me a joke  OpenAI            4   \n",
      "7             3  Tell me a poem  OpenAI            4   \n",
      "8             3  Tell me a joke  OpenAI            4   \n",
      "9             3  Tell me a poem  OpenAI            4   \n",
      "10            3  Tell me a joke  OpenAI            4   \n",
      "11            3  Tell me a poem  OpenAI            4   \n",
      "\n",
      "                                               output  \\\n",
      "0   \\n\\nQ: What did the fish say when it hit the w...   \n",
      "1   \\n\\nRoses are red,\\nViolets are blue,\\nSugar i...   \n",
      "2   \\n\\nQ: What did the fish say when it hit the w...   \n",
      "3   \\n\\nRoses are red,\\nViolets are blue,\\nSugar i...   \n",
      "4   \\n\\nQ: What did the fish say when it hit the w...   \n",
      "5   \\n\\nRoses are red,\\nViolets are blue,\\nSugar i...   \n",
      "6   \\n\\nQ: What did the fish say when it hit the w...   \n",
      "7   \\n\\nRoses are red,\\nViolets are blue,\\nSugar i...   \n",
      "8   \\n\\nQ: What did the fish say when it hit the w...   \n",
      "9   \\n\\nRoses are red,\\nViolets are blue,\\nSugar i...   \n",
      "10  \\n\\nQ: What did the fish say when it hit the w...   \n",
      "11  \\n\\nRoses are red,\\nViolets are blue,\\nSugar i...   \n",
      "\n",
      "    token_usage_total_tokens  token_usage_prompt_tokens  \\\n",
      "0                        162                         24   \n",
      "1                        162                         24   \n",
      "2                        162                         24   \n",
      "3                        162                         24   \n",
      "4                        162                         24   \n",
      "5                        162                         24   \n",
      "6                        162                         24   \n",
      "7                        162                         24   \n",
      "8                        162                         24   \n",
      "9                        162                         24   \n",
      "10                       162                         24   \n",
      "11                       162                         24   \n",
      "\n",
      "    token_usage_completion_tokens  flesch_reading_ease  flesch_kincaid_grade  \\\n",
      "0                             138               109.04                   1.3   \n",
      "1                             138                83.66                   4.8   \n",
      "2                             138               109.04                   1.3   \n",
      "3                             138                83.66                   4.8   \n",
      "4                             138               109.04                   1.3   \n",
      "5                             138                83.66                   4.8   \n",
      "6                             138               109.04                   1.3   \n",
      "7                             138                83.66                   4.8   \n",
      "8                             138               109.04                   1.3   \n",
      "9                             138                83.66                   4.8   \n",
      "10                            138               109.04                   1.3   \n",
      "11                            138                83.66                   4.8   \n",
      "\n",
      "    ...  difficult_words  linsear_write_formula  gunning_fog  \\\n",
      "0   ...                0                    5.5         5.20   \n",
      "1   ...                2                    6.5         8.28   \n",
      "2   ...                0                    5.5         5.20   \n",
      "3   ...                2                    6.5         8.28   \n",
      "4   ...                0                    5.5         5.20   \n",
      "5   ...                2                    6.5         8.28   \n",
      "6   ...                0                    5.5         5.20   \n",
      "7   ...                2                    6.5         8.28   \n",
      "8   ...                0                    5.5         5.20   \n",
      "9   ...                2                    6.5         8.28   \n",
      "10  ...                0                    5.5         5.20   \n",
      "11  ...                2                    6.5         8.28   \n",
      "\n",
      "        text_standard  fernandez_huerta  szigriszt_pazos  gutierrez_polini  \\\n",
      "0   5th and 6th grade            133.58           131.54             62.30   \n",
      "1   6th and 7th grade            115.58           112.37             54.83   \n",
      "2   5th and 6th grade            133.58           131.54             62.30   \n",
      "3   6th and 7th grade            115.58           112.37             54.83   \n",
      "4   5th and 6th grade            133.58           131.54             62.30   \n",
      "5   6th and 7th grade            115.58           112.37             54.83   \n",
      "6   5th and 6th grade            133.58           131.54             62.30   \n",
      "7   6th and 7th grade            115.58           112.37             54.83   \n",
      "8   5th and 6th grade            133.58           131.54             62.30   \n",
      "9   6th and 7th grade            115.58           112.37             54.83   \n",
      "10  5th and 6th grade            133.58           131.54             62.30   \n",
      "11  6th and 7th grade            115.58           112.37             54.83   \n",
      "\n",
      "   crawford  gulpease_index   osman  \n",
      "0      -0.2            79.8  116.91  \n",
      "1       1.4            72.1  100.17  \n",
      "2      -0.2            79.8  116.91  \n",
      "3       1.4            72.1  100.17  \n",
      "4      -0.2            79.8  116.91  \n",
      "5       1.4            72.1  100.17  \n",
      "6      -0.2            79.8  116.91  \n",
      "7       1.4            72.1  100.17  \n",
      "8      -0.2            79.8  116.91  \n",
      "9       1.4            72.1  100.17  \n",
      "10     -0.2            79.8  116.91  \n",
      "11      1.4            72.1  100.17  \n",
      "\n",
      "[12 rows x 24 columns]}\n",
      "2023-03-29 14:00:25,948 - clearml.Task - INFO - Completed model upload to https://files.clear.ml/langchain_callback_demo/llm.988bd727b0e94a29a3ac0ee526813545/models/simple_sequential\n"
     ]
    }
   ],
   "source": [
    "# SCENARIO 1 - LLM\n",
    "llm_result = llm.generate([\"Tell me a joke\", \"Tell me a poem\"] * 3)\n",
    "# After every generation run, use flush to make sure all the metrics\n",
    "# prompts and other output are properly saved separately\n",
    "clearml_callback.flush_tracker(langchain_asset=llm, name=\"simple_sequential\")"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "At this point you can already go to https://app.clear.ml and take a look at the resulting ClearML Task that was created.\n",
    "\n",
    "Among others, you should see that this notebook is saved along with any git information. The model JSON that contains the used parameters is saved as an artifact, there are also console logs and under the plots section, you'll find tables that represent the flow of the chain.\n",
    "\n",
    "Finally, if you enabled visualizations, these are stored as HTML files under debug samples."
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Scenario 2: Creating an agent with tools\n",
    "\n",
    "To show a more advanced workflow, let's create an agent with access to tools. The way ClearML tracks the results is not different though, only the table will look slightly different as there are other types of actions taken when compared to the earlier, simpler example.\n",
    "\n",
    "You can now also see the use of the `finish=True` keyword, which will fully close the ClearML Task, instead of just resetting the parameters and prompts for a new conversation."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "\n",
      "\u001b[1m> Entering new AgentExecutor chain...\u001b[0m\n",
      "{'action': 'on_chain_start', 'name': 'AgentExecutor', 'step': 1, 'starts': 1, 'ends': 0, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 0, 'llm_ends': 0, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'input': 'Who is the wife of the person who sang summer of 69?'}\n",
      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 2, 'starts': 2, 'ends': 0, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 0, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'prompts': 'Answer the following questions as best you can. You have access to the following tools:\\n\\nSearch: A search engine. Useful for when you need to answer questions about current events. Input should be a search query.\\nCalculator: Useful for when you need to answer questions about math.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [Search, Calculator]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\nBegin!\\n\\nQuestion: Who is the wife of the person who sang summer of 69?\\nThought:'}\n",
      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 189, 'token_usage_completion_tokens': 34, 'token_usage_total_tokens': 223, 'model_name': 'text-davinci-003', 'step': 3, 'starts': 2, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 0, 'tool_ends': 0, 'agent_ends': 0, 'text': ' I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 91.61, 'flesch_kincaid_grade': 3.8, 'smog_index': 0.0, 'coleman_liau_index': 3.41, 'automated_readability_index': 3.5, 'dale_chall_readability_score': 6.06, 'difficult_words': 2, 'linsear_write_formula': 5.75, 'gunning_fog': 5.4, 'text_standard': '3rd and 4th grade', 'fernandez_huerta': 121.07, 'szigriszt_pazos': 119.5, 'gutierrez_polini': 54.91, 'crawford': 0.9, 'gulpease_index': 72.7, 'osman': 92.16}\n",
      "\u001b[32;1m\u001b[1;3m I need to find out who sang summer of 69 and then find out who their wife is.\n",
      "Action: Search\n",
      "Action Input: \"Who sang summer of 69\"\u001b[0m{'action': 'on_agent_action', 'tool': 'Search', 'tool_input': 'Who sang summer of 69', 'log': ' I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"', 'step': 4, 'starts': 3, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 1, 'tool_ends': 0, 'agent_ends': 0}\n",
      "{'action': 'on_tool_start', 'input_str': 'Who sang summer of 69', 'name': 'Search', 'description': 'A search engine. Useful for when you need to answer questions about current events. Input should be a search query.', 'step': 5, 'starts': 4, 'ends': 1, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 0, 'agent_ends': 0}\n",
      "\n",
      "Observation: \u001b[36;1m\u001b[1;3mBryan Adams - Summer Of 69 (Official Music Video).\u001b[0m\n",
      "Thought:{'action': 'on_tool_end', 'output': 'Bryan Adams - Summer Of 69 (Official Music Video).', 'step': 6, 'starts': 4, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 1, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0}\n",
      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 7, 'starts': 5, 'ends': 2, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 1, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0, 'prompts': 'Answer the following questions as best you can. You have access to the following tools:\\n\\nSearch: A search engine. Useful for when you need to answer questions about current events. Input should be a search query.\\nCalculator: Useful for when you need to answer questions about math.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [Search, Calculator]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\nBegin!\\n\\nQuestion: Who is the wife of the person who sang summer of 69?\\nThought: I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"\\nObservation: Bryan Adams - Summer Of 69 (Official Music Video).\\nThought:'}\n",
      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 242, 'token_usage_completion_tokens': 28, 'token_usage_total_tokens': 270, 'model_name': 'text-davinci-003', 'step': 8, 'starts': 5, 'ends': 3, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 2, 'tool_ends': 1, 'agent_ends': 0, 'text': ' I need to find out who Bryan Adams is married to.\\nAction: Search\\nAction Input: \"Who is Bryan Adams married to\"', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 94.66, 'flesch_kincaid_grade': 2.7, 'smog_index': 0.0, 'coleman_liau_index': 4.73, 'automated_readability_index': 4.0, 'dale_chall_readability_score': 7.16, 'difficult_words': 2, 'linsear_write_formula': 4.25, 'gunning_fog': 4.2, 'text_standard': '4th and 5th grade', 'fernandez_huerta': 124.13, 'szigriszt_pazos': 119.2, 'gutierrez_polini': 52.26, 'crawford': 0.7, 'gulpease_index': 74.7, 'osman': 84.2}\n",
      "\u001b[32;1m\u001b[1;3m I need to find out who Bryan Adams is married to.\n",
      "Action: Search\n",
      "Action Input: \"Who is Bryan Adams married to\"\u001b[0m{'action': 'on_agent_action', 'tool': 'Search', 'tool_input': 'Who is Bryan Adams married to', 'log': ' I need to find out who Bryan Adams is married to.\\nAction: Search\\nAction Input: \"Who is Bryan Adams married to\"', 'step': 9, 'starts': 6, 'ends': 3, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 3, 'tool_ends': 1, 'agent_ends': 0}\n",
      "{'action': 'on_tool_start', 'input_str': 'Who is Bryan Adams married to', 'name': 'Search', 'description': 'A search engine. Useful for when you need to answer questions about current events. Input should be a search query.', 'step': 10, 'starts': 7, 'ends': 3, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 1, 'agent_ends': 0}\n",
      "\n",
      "Observation: \u001b[36;1m\u001b[1;3mBryan Adams has never married. In the 1990s, he was in a relationship with Danish model Cecilie Thomsen. In 2011, Bryan and Alicia Grimaldi, his ...\u001b[0m\n",
      "Thought:{'action': 'on_tool_end', 'output': 'Bryan Adams has never married. In the 1990s, he was in a relationship with Danish model Cecilie Thomsen. In 2011, Bryan and Alicia Grimaldi, his ...', 'step': 11, 'starts': 7, 'ends': 4, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 2, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0}\n",
      "{'action': 'on_llm_start', 'name': 'OpenAI', 'step': 12, 'starts': 8, 'ends': 4, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 2, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0, 'prompts': 'Answer the following questions as best you can. You have access to the following tools:\\n\\nSearch: A search engine. Useful for when you need to answer questions about current events. Input should be a search query.\\nCalculator: Useful for when you need to answer questions about math.\\n\\nUse the following format:\\n\\nQuestion: the input question you must answer\\nThought: you should always think about what to do\\nAction: the action to take, should be one of [Search, Calculator]\\nAction Input: the input to the action\\nObservation: the result of the action\\n... (this Thought/Action/Action Input/Observation can repeat N times)\\nThought: I now know the final answer\\nFinal Answer: the final answer to the original input question\\n\\nBegin!\\n\\nQuestion: Who is the wife of the person who sang summer of 69?\\nThought: I need to find out who sang summer of 69 and then find out who their wife is.\\nAction: Search\\nAction Input: \"Who sang summer of 69\"\\nObservation: Bryan Adams - Summer Of 69 (Official Music Video).\\nThought: I need to find out who Bryan Adams is married to.\\nAction: Search\\nAction Input: \"Who is Bryan Adams married to\"\\nObservation: Bryan Adams has never married. In the 1990s, he was in a relationship with Danish model Cecilie Thomsen. In 2011, Bryan and Alicia Grimaldi, his ...\\nThought:'}\n",
      "{'action': 'on_llm_end', 'token_usage_prompt_tokens': 314, 'token_usage_completion_tokens': 18, 'token_usage_total_tokens': 332, 'model_name': 'text-davinci-003', 'step': 13, 'starts': 8, 'ends': 5, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 3, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 0, 'text': ' I now know the final answer.\\nFinal Answer: Bryan Adams has never been married.', 'generation_info_finish_reason': 'stop', 'generation_info_logprobs': None, 'flesch_reading_ease': 81.29, 'flesch_kincaid_grade': 3.7, 'smog_index': 0.0, 'coleman_liau_index': 5.75, 'automated_readability_index': 3.9, 'dale_chall_readability_score': 7.37, 'difficult_words': 1, 'linsear_write_formula': 2.5, 'gunning_fog': 2.8, 'text_standard': '3rd and 4th grade', 'fernandez_huerta': 115.7, 'szigriszt_pazos': 110.84, 'gutierrez_polini': 49.79, 'crawford': 0.7, 'gulpease_index': 85.4, 'osman': 83.14}\n",
      "\u001b[32;1m\u001b[1;3m I now know the final answer.\n",
      "Final Answer: Bryan Adams has never been married.\u001b[0m\n",
      "{'action': 'on_agent_finish', 'output': 'Bryan Adams has never been married.', 'log': ' I now know the final answer.\\nFinal Answer: Bryan Adams has never been married.', 'step': 14, 'starts': 8, 'ends': 6, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 0, 'llm_starts': 3, 'llm_ends': 3, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 1}\n",
      "\n",
      "\u001b[1m> Finished chain.\u001b[0m\n",
      "{'action': 'on_chain_end', 'outputs': 'Bryan Adams has never been married.', 'step': 15, 'starts': 8, 'ends': 7, 'errors': 0, 'text_ctr': 0, 'chain_starts': 1, 'chain_ends': 1, 'llm_starts': 3, 'llm_ends': 3, 'llm_streams': 0, 'tool_starts': 4, 'tool_ends': 2, 'agent_ends': 1}\n",
      "{'action_records':              action    name  step  starts  ends  errors  text_ctr  \\\n",
      "0      on_llm_start  OpenAI     1       1     0       0         0   \n",
      "1      on_llm_start  OpenAI     1       1     0       0         0   \n",
      "2      on_llm_start  OpenAI     1       1     0       0         0   \n",
      "3      on_llm_start  OpenAI     1       1     0       0         0   \n",
      "4      on_llm_start  OpenAI     1       1     0       0         0   \n",
      "..              ...     ...   ...     ...   ...     ...       ...   \n",
      "66      on_tool_end     NaN    11       7     4       0         0   \n",
      "67     on_llm_start  OpenAI    12       8     4       0         0   \n",
      "68       on_llm_end     NaN    13       8     5       0         0   \n",
      "69  on_agent_finish     NaN    14       8     6       0         0   \n",
      "70     on_chain_end     NaN    15       8     7       0         0   \n",
      "\n",
      "    chain_starts  chain_ends  llm_starts  ...  gulpease_index  osman  input  \\\n",
      "0              0           0           1  ...             NaN    NaN    NaN   \n",
      "1              0           0           1  ...             NaN    NaN    NaN   \n",
      "2              0           0           1  ...             NaN    NaN    NaN   \n",
      "3              0           0           1  ...             NaN    NaN    NaN   \n",
      "4              0           0           1  ...             NaN    NaN    NaN   \n",
      "..           ...         ...         ...  ...             ...    ...    ...   \n",
      "66             1           0           2  ...             NaN    NaN    NaN   \n",
      "67             1           0           3  ...             NaN    NaN    NaN   \n",
      "68             1           0           3  ...            85.4  83.14    NaN   \n",
      "69             1           0           3  ...             NaN    NaN    NaN   \n",
      "70             1           1           3  ...             NaN    NaN    NaN   \n",
      "\n",
      "    tool  tool_input                                                log  \\\n",
      "0    NaN         NaN                                                NaN   \n",
      "1    NaN         NaN                                                NaN   \n",
      "2    NaN         NaN                                                NaN   \n",
      "3    NaN         NaN                                                NaN   \n",
      "4    NaN         NaN                                                NaN   \n",
      "..   ...         ...                                                ...   \n",
      "66   NaN         NaN                                                NaN   \n",
      "67   NaN         NaN                                                NaN   \n",
      "68   NaN         NaN                                                NaN   \n",
      "69   NaN         NaN   I now know the final answer.\\nFinal Answer: B...   \n",
      "70   NaN         NaN                                                NaN   \n",
      "\n",
      "    input_str  description                                             output  \\\n",
      "0         NaN          NaN                                                NaN   \n",
      "1         NaN          NaN                                                NaN   \n",
      "2         NaN          NaN                                                NaN   \n",
      "3         NaN          NaN                                                NaN   \n",
      "4         NaN          NaN                                                NaN   \n",
      "..        ...          ...                                                ...   \n",
      "66        NaN          NaN  Bryan Adams has never married. In the 1990s, h...   \n",
      "67        NaN          NaN                                                NaN   \n",
      "68        NaN          NaN                                                NaN   \n",
      "69        NaN          NaN                Bryan Adams has never been married.   \n",
      "70        NaN          NaN                                                NaN   \n",
      "\n",
      "                                outputs  \n",
      "0                                   NaN  \n",
      "1                                   NaN  \n",
      "2                                   NaN  \n",
      "3                                   NaN  \n",
      "4                                   NaN  \n",
      "..                                  ...  \n",
      "66                                  NaN  \n",
      "67                                  NaN  \n",
      "68                                  NaN  \n",
      "69                                  NaN  \n",
      "70  Bryan Adams has never been married.  \n",
      "\n",
      "[71 rows x 47 columns], 'session_analysis':    prompt_step                                            prompts    name  \\\n",
      "0            2  Answer the following questions as best you can...  OpenAI   \n",
      "1            7  Answer the following questions as best you can...  OpenAI   \n",
      "2           12  Answer the following questions as best you can...  OpenAI   \n",
      "\n",
      "   output_step                                             output  \\\n",
      "0            3   I need to find out who sang summer of 69 and ...   \n",
      "1            8   I need to find out who Bryan Adams is married...   \n",
      "2           13   I now know the final answer.\\nFinal Answer: B...   \n",
      "\n",
      "   token_usage_total_tokens  token_usage_prompt_tokens  \\\n",
      "0                       223                        189   \n",
      "1                       270                        242   \n",
      "2                       332                        314   \n",
      "\n",
      "   token_usage_completion_tokens  flesch_reading_ease  flesch_kincaid_grade  \\\n",
      "0                             34                91.61                   3.8   \n",
      "1                             28                94.66                   2.7   \n",
      "2                             18                81.29                   3.7   \n",
      "\n",
      "   ...  difficult_words  linsear_write_formula  gunning_fog  \\\n",
      "0  ...                2                   5.75          5.4   \n",
      "1  ...                2                   4.25          4.2   \n",
      "2  ...                1                   2.50          2.8   \n",
      "\n",
      "       text_standard  fernandez_huerta  szigriszt_pazos  gutierrez_polini  \\\n",
      "0  3rd and 4th grade            121.07           119.50             54.91   \n",
      "1  4th and 5th grade            124.13           119.20             52.26   \n",
      "2  3rd and 4th grade            115.70           110.84             49.79   \n",
      "\n",
      "  crawford  gulpease_index  osman  \n",
      "0      0.9            72.7  92.16  \n",
      "1      0.7            74.7  84.20  \n",
      "2      0.7            85.4  83.14  \n",
      "\n",
      "[3 rows x 24 columns]}\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Could not update last created model in Task 988bd727b0e94a29a3ac0ee526813545, Task status 'completed' cannot be updated\n"
     ]
    }
   ],
   "source": [
    "from langchain.agents import initialize_agent, load_tools\n",
    "from langchain.agents import AgentType\n",
    "\n",
    "# SCENARIO 2 - Agent with Tools\n",
    "tools = load_tools([\"serpapi\", \"llm-math\"], llm=llm, callbacks=callbacks)\n",
    "agent = initialize_agent(\n",
    "    tools,\n",
    "    llm,\n",
    "    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,\n",
    "    callbacks=callbacks,\n",
    ")\n",
    "agent.run(\n",
    "    \"Who is the wife of the person who sang summer of 69?\"\n",
    ")\n",
    "clearml_callback.flush_tracker(langchain_asset=agent, name=\"Agent with Tools\", finish=True)"
   ]
  },
  {
   "attachments": {},
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Tips and Next Steps\n",
    "\n",
    "- Make sure you always use a unique `name` argument for the `clearml_callback.flush_tracker` function. If not, the model parameters used for a run will override the previous run!\n",
    "\n",
    "- If you close the ClearML Callback using `clearml_callback.flush_tracker(..., finish=True)` the Callback cannot be used anymore. Make a new one if you want to keep logging.\n",
    "\n",
    "- Check out the rest of the open source ClearML ecosystem, there is a data version manager, a remote execution agent, automated pipelines and much more!\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": ".venv",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.10.9"
  },
  "orig_nbformat": 4,
  "vscode": {
   "interpreter": {
    "hash": "a53ebf4a859167383b364e7e7521d0add3c2dbbdecce4edf676e8c4634ff3fbb"
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}