/
base.py
2028 lines (1640 loc) 路 69.2 KB
/
base.py
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
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
r"""
# Nomenclature
| Prefix | Definition | Examples |
| --- | --- | --- |
| `vn.get_` | Fetch some data | [`vn.get_related_ddl(...)`][vanna.base.base.VannaBase.get_related_ddl] |
| `vn.add_` | Adds something to the retrieval layer | [`vn.add_question_sql(...)`][vanna.base.base.VannaBase.add_question_sql] <br> [`vn.add_ddl(...)`][vanna.base.base.VannaBase.add_ddl] |
| `vn.generate_` | Generates something using AI based on the information in the model | [`vn.generate_sql(...)`][vanna.base.base.VannaBase.generate_sql] <br> [`vn.generate_explanation()`][vanna.base.base.VannaBase.generate_explanation] |
| `vn.run_` | Runs code (SQL) | [`vn.run_sql`][vanna.base.base.VannaBase.run_sql] |
| `vn.remove_` | Removes something from the retrieval layer | [`vn.remove_training_data`][vanna.base.base.VannaBase.remove_training_data] |
| `vn.connect_` | Connects to a database | [`vn.connect_to_snowflake(...)`][vanna.base.base.VannaBase.connect_to_snowflake] |
| `vn.update_` | Updates something | N/A -- unused |
| `vn.set_` | Sets something | N/A -- unused |
# Open-Source and Extending
Vanna.AI is open-source and extensible. If you'd like to use Vanna without the servers, see an example [here](/docs/local.html).
The following is an example of where various functions are implemented in the codebase when using the default "local" version of Vanna. `vanna.base.VannaBase` is the base class which provides a `vanna.base.VannaBase.ask` and `vanna.base.VannaBase.train` function. Those rely on abstract methods which are implemented in the subclasses `vanna.openai_chat.OpenAI_Chat` and `vanna.chromadb_vector.ChromaDB_VectorStore`. `vanna.openai_chat.OpenAI_Chat` uses the OpenAI API to generate SQL and Plotly code. `vanna.chromadb_vector.ChromaDB_VectorStore` uses ChromaDB to store training data and generate embeddings.
If you want to use Vanna with other LLMs or databases, you can create your own subclass of `vanna.base.VannaBase` and implement the abstract methods.
```mermaid
flowchart
subgraph VannaBase
ask
train
end
subgraph OpenAI_Chat
get_sql_prompt
submit_prompt
generate_question
generate_plotly_code
end
subgraph ChromaDB_VectorStore
generate_embedding
add_question_sql
add_ddl
add_documentation
get_similar_question_sql
get_related_ddl
get_related_documentation
end
```
"""
import json
import os
import re
import sqlite3
import traceback
from abc import ABC, abstractmethod
from typing import List, Tuple, Union
from urllib.parse import urlparse
import pandas as pd
import plotly
import plotly.express as px
import plotly.graph_objects as go
import requests
import sqlparse
from ..exceptions import DependencyError, ImproperlyConfigured, ValidationError
from ..types import TrainingPlan, TrainingPlanItem
from ..utils import validate_config_path
class VannaBase(ABC):
def __init__(self, config=None):
if config is None:
config = {}
self.config = config
self.run_sql_is_set = False
self.static_documentation = ""
self.dialect = self.config.get("dialect", "SQL")
self.language = self.config.get("language", None)
def log(self, message: str, title: str = "Info"):
print(message)
def _response_language(self) -> str:
if self.language is None:
return ""
return f"Respond in the {self.language} language."
def generate_sql(self, question: str, allow_llm_to_see_data=False, **kwargs) -> str:
"""
Example:
```python
vn.generate_sql("What are the top 10 customers by sales?")
```
Uses the LLM to generate a SQL query that answers a question. It runs the following methods:
- [`get_similar_question_sql`][vanna.base.base.VannaBase.get_similar_question_sql]
- [`get_related_ddl`][vanna.base.base.VannaBase.get_related_ddl]
- [`get_related_documentation`][vanna.base.base.VannaBase.get_related_documentation]
- [`get_sql_prompt`][vanna.base.base.VannaBase.get_sql_prompt]
- [`submit_prompt`][vanna.base.base.VannaBase.submit_prompt]
Args:
question (str): The question to generate a SQL query for.
allow_llm_to_see_data (bool): Whether to allow the LLM to see the data (for the purposes of introspecting the data to generate the final SQL).
Returns:
str: The SQL query that answers the question.
"""
if self.config is not None:
initial_prompt = self.config.get("initial_prompt", None)
else:
initial_prompt = None
question_sql_list = self.get_similar_question_sql(question, **kwargs)
ddl_list = self.get_related_ddl(question, **kwargs)
doc_list = self.get_related_documentation(question, **kwargs)
prompt = self.get_sql_prompt(
initial_prompt=initial_prompt,
question=question,
question_sql_list=question_sql_list,
ddl_list=ddl_list,
doc_list=doc_list,
**kwargs,
)
self.log(title="SQL Prompt", message=prompt)
llm_response = self.submit_prompt(prompt, **kwargs)
self.log(title="LLM Response", message=llm_response)
if 'intermediate_sql' in llm_response:
if not allow_llm_to_see_data:
return "The LLM is not allowed to see the data in your database. Your question requires database introspection to generate the necessary SQL. Please set allow_llm_to_see_data=True to enable this."
if allow_llm_to_see_data:
intermediate_sql = self.extract_sql(llm_response)
try:
self.log(title="Running Intermediate SQL", message=intermediate_sql)
df = self.run_sql(intermediate_sql)
prompt = self.get_sql_prompt(
initial_prompt=initial_prompt,
question=question,
question_sql_list=question_sql_list,
ddl_list=ddl_list,
doc_list=doc_list+[f"The following is a pandas DataFrame with the results of the intermediate SQL query {intermediate_sql}: \n" + df.to_markdown()],
**kwargs,
)
self.log(title="Final SQL Prompt", message=prompt)
llm_response = self.submit_prompt(prompt, **kwargs)
self.log(title="LLM Response", message=llm_response)
except Exception as e:
return f"Error running intermediate SQL: {e}"
return self.extract_sql(llm_response)
def extract_sql(self, llm_response: str) -> str:
"""
Example:
```python
vn.extract_sql("Here's the SQL query in a code block: ```sql\nSELECT * FROM customers\n```")
```
Extracts the SQL query from the LLM response. This is useful in case the LLM response contains other information besides the SQL query.
Override this function if your LLM responses need custom extraction logic.
Args:
llm_response (str): The LLM response.
Returns:
str: The extracted SQL query.
"""
# If the llm_response contains a CTE (with clause), extract the last sql between WITH and ;
sqls = re.findall(r"WITH.*?;", llm_response, re.DOTALL)
if sqls:
sql = sqls[-1]
self.log(title="Extracted SQL", message=f"{sql}")
return sql
# If the llm_response is not markdown formatted, extract last sql by finding select and ; in the response
sqls = re.findall(r"SELECT.*?;", llm_response, re.DOTALL)
if sqls:
sql = sqls[-1]
self.log(title="Extracted SQL", message=f"{sql}")
return sql
# If the llm_response contains a markdown code block, with or without the sql tag, extract the last sql from it
sqls = re.findall(r"```sql\n(.*)```", llm_response, re.DOTALL)
if sqls:
sql = sqls[-1]
self.log(title="Extracted SQL", message=f"{sql}")
return sql
sqls = re.findall(r"```(.*)```", llm_response, re.DOTALL)
if sqls:
sql = sqls[-1]
self.log(title="Extracted SQL", message=f"{sql}")
return sql
return llm_response
def is_sql_valid(self, sql: str) -> bool:
"""
Example:
```python
vn.is_sql_valid("SELECT * FROM customers")
```
Checks if the SQL query is valid. This is usually used to check if we should run the SQL query or not.
By default it checks if the SQL query is a SELECT statement. You can override this method to enable running other types of SQL queries.
Args:
sql (str): The SQL query to check.
Returns:
bool: True if the SQL query is valid, False otherwise.
"""
parsed = sqlparse.parse(sql)
for statement in parsed:
if statement.get_type() == 'SELECT':
return True
return False
def should_generate_chart(self, df: pd.DataFrame) -> bool:
"""
Example:
```python
vn.should_generate_chart(df)
```
Checks if a chart should be generated for the given DataFrame. By default, it checks if the DataFrame has more than one row and has numerical columns.
You can override this method to customize the logic for generating charts.
Args:
df (pd.DataFrame): The DataFrame to check.
Returns:
bool: True if a chart should be generated, False otherwise.
"""
if len(df) > 1 and df.select_dtypes(include=['number']).shape[1] > 0:
return True
return False
def generate_followup_questions(
self, question: str, sql: str, df: pd.DataFrame, n_questions: int = 5, **kwargs
) -> list:
"""
**Example:**
```python
vn.generate_followup_questions("What are the top 10 customers by sales?", sql, df)
```
Generate a list of followup questions that you can ask Vanna.AI.
Args:
question (str): The question that was asked.
sql (str): The LLM-generated SQL query.
df (pd.DataFrame): The results of the SQL query.
n_questions (int): Number of follow-up questions to generate.
Returns:
list: A list of followup questions that you can ask Vanna.AI.
"""
message_log = [
self.system_message(
f"You are a helpful data assistant. The user asked the question: '{question}'\n\nThe SQL query for this question was: {sql}\n\nThe following is a pandas DataFrame with the results of the query: \n{df.to_markdown()}\n\n"
),
self.user_message(
f"Generate a list of {n_questions} followup questions that the user might ask about this data. Respond with a list of questions, one per line. Do not answer with any explanations -- just the questions. Remember that there should be an unambiguous SQL query that can be generated from the question. Prefer questions that are answerable outside of the context of this conversation. Prefer questions that are slight modifications of the SQL query that was generated that allow digging deeper into the data. Each question will be turned into a button that the user can click to generate a new SQL query so don't use 'example' type questions. Each question must have a one-to-one correspondence with an instantiated SQL query." +
self._response_language()
),
]
llm_response = self.submit_prompt(message_log, **kwargs)
numbers_removed = re.sub(r"^\d+\.\s*", "", llm_response, flags=re.MULTILINE)
return numbers_removed.split("\n")
def generate_questions(self, **kwargs) -> List[str]:
"""
**Example:**
```python
vn.generate_questions()
```
Generate a list of questions that you can ask Vanna.AI.
"""
question_sql = self.get_similar_question_sql(question="", **kwargs)
return [q["question"] for q in question_sql]
def generate_summary(self, question: str, df: pd.DataFrame, **kwargs) -> str:
"""
**Example:**
```python
vn.generate_summary("What are the top 10 customers by sales?", df)
```
Generate a summary of the results of a SQL query.
Args:
question (str): The question that was asked.
df (pd.DataFrame): The results of the SQL query.
Returns:
str: The summary of the results of the SQL query.
"""
message_log = [
self.system_message(
f"You are a helpful data assistant. The user asked the question: '{question}'\n\nThe following is a pandas DataFrame with the results of the query: \n{df.to_markdown()}\n\n"
),
self.user_message(
"Briefly summarize the data based on the question that was asked. Do not respond with any additional explanation beyond the summary." +
self._response_language()
),
]
summary = self.submit_prompt(message_log, **kwargs)
return summary
# ----------------- Use Any Embeddings API ----------------- #
@abstractmethod
def generate_embedding(self, data: str, **kwargs) -> List[float]:
pass
# ----------------- Use Any Database to Store and Retrieve Context ----------------- #
@abstractmethod
def get_similar_question_sql(self, question: str, **kwargs) -> list:
"""
This method is used to get similar questions and their corresponding SQL statements.
Args:
question (str): The question to get similar questions and their corresponding SQL statements for.
Returns:
list: A list of similar questions and their corresponding SQL statements.
"""
pass
@abstractmethod
def get_related_ddl(self, question: str, **kwargs) -> list:
"""
This method is used to get related DDL statements to a question.
Args:
question (str): The question to get related DDL statements for.
Returns:
list: A list of related DDL statements.
"""
pass
@abstractmethod
def get_related_documentation(self, question: str, **kwargs) -> list:
"""
This method is used to get related documentation to a question.
Args:
question (str): The question to get related documentation for.
Returns:
list: A list of related documentation.
"""
pass
@abstractmethod
def add_question_sql(self, question: str, sql: str, **kwargs) -> str:
"""
This method is used to add a question and its corresponding SQL query to the training data.
Args:
question (str): The question to add.
sql (str): The SQL query to add.
Returns:
str: The ID of the training data that was added.
"""
pass
@abstractmethod
def add_ddl(self, ddl: str, **kwargs) -> str:
"""
This method is used to add a DDL statement to the training data.
Args:
ddl (str): The DDL statement to add.
Returns:
str: The ID of the training data that was added.
"""
pass
@abstractmethod
def add_documentation(self, documentation: str, **kwargs) -> str:
"""
This method is used to add documentation to the training data.
Args:
documentation (str): The documentation to add.
Returns:
str: The ID of the training data that was added.
"""
pass
@abstractmethod
def get_training_data(self, **kwargs) -> pd.DataFrame:
"""
Example:
```python
vn.get_training_data()
```
This method is used to get all the training data from the retrieval layer.
Returns:
pd.DataFrame: The training data.
"""
pass
@abstractmethod
def remove_training_data(id: str, **kwargs) -> bool:
"""
Example:
```python
vn.remove_training_data(id="123-ddl")
```
This method is used to remove training data from the retrieval layer.
Args:
id (str): The ID of the training data to remove.
Returns:
bool: True if the training data was removed, False otherwise.
"""
pass
# ----------------- Use Any Language Model API ----------------- #
@abstractmethod
def system_message(self, message: str) -> any:
pass
@abstractmethod
def user_message(self, message: str) -> any:
pass
@abstractmethod
def assistant_message(self, message: str) -> any:
pass
def str_to_approx_token_count(self, string: str) -> int:
return len(string) / 4
def add_ddl_to_prompt(
self, initial_prompt: str, ddl_list: list[str], max_tokens: int = 14000
) -> str:
if len(ddl_list) > 0:
initial_prompt += "\n===Tables \n"
for ddl in ddl_list:
if (
self.str_to_approx_token_count(initial_prompt)
+ self.str_to_approx_token_count(ddl)
< max_tokens
):
initial_prompt += f"{ddl}\n\n"
return initial_prompt
def add_documentation_to_prompt(
self,
initial_prompt: str,
documentation_list: list[str],
max_tokens: int = 14000,
) -> str:
if len(documentation_list) > 0:
initial_prompt += "\n===Additional Context \n\n"
for documentation in documentation_list:
if (
self.str_to_approx_token_count(initial_prompt)
+ self.str_to_approx_token_count(documentation)
< max_tokens
):
initial_prompt += f"{documentation}\n\n"
return initial_prompt
def add_sql_to_prompt(
self, initial_prompt: str, sql_list: list[str], max_tokens: int = 14000
) -> str:
if len(sql_list) > 0:
initial_prompt += "\n===Question-SQL Pairs\n\n"
for question in sql_list:
if (
self.str_to_approx_token_count(initial_prompt)
+ self.str_to_approx_token_count(question["sql"])
< max_tokens
):
initial_prompt += f"{question['question']}\n{question['sql']}\n\n"
return initial_prompt
def get_sql_prompt(
self,
initial_prompt : str,
question: str,
question_sql_list: list,
ddl_list: list,
doc_list: list,
**kwargs,
):
"""
Example:
```python
vn.get_sql_prompt(
question="What are the top 10 customers by sales?",
question_sql_list=[{"question": "What are the top 10 customers by sales?", "sql": "SELECT * FROM customers ORDER BY sales DESC LIMIT 10"}],
ddl_list=["CREATE TABLE customers (id INT, name TEXT, sales DECIMAL)"],
doc_list=["The customers table contains information about customers and their sales."],
)
```
This method is used to generate a prompt for the LLM to generate SQL.
Args:
question (str): The question to generate SQL for.
question_sql_list (list): A list of questions and their corresponding SQL statements.
ddl_list (list): A list of DDL statements.
doc_list (list): A list of documentation.
Returns:
any: The prompt for the LLM to generate SQL.
"""
if initial_prompt is None:
initial_prompt = f"You are a {self.dialect} expert. " + \
"Please help to generate a SQL query to answer the question. Your response should ONLY be based on the given context and follow the response guidelines and format instructions. "
initial_prompt = self.add_ddl_to_prompt(
initial_prompt, ddl_list, max_tokens=14000
)
if self.static_documentation != "":
doc_list.append(self.static_documentation)
initial_prompt = self.add_documentation_to_prompt(
initial_prompt, doc_list, max_tokens=14000
)
initial_prompt += (
"===Response Guidelines \n"
"1. If the provided context is sufficient, please generate a valid SQL query without any explanations for the question. \n"
"2. If the provided context is almost sufficient but requires knowledge of a specific string in a particular column, please generate an intermediate SQL query to find the distinct strings in that column. Prepend the query with a comment saying intermediate_sql \n"
"3. If the provided context is insufficient, please explain why it can't be generated. \n"
"4. Please use the most relevant table(s). \n"
"5. If the question has been asked and answered before, please repeat the answer exactly as it was given before. \n"
)
message_log = [self.system_message(initial_prompt)]
for example in question_sql_list:
if example is None:
print("example is None")
else:
if example is not None and "question" in example and "sql" in example:
message_log.append(self.user_message(example["question"]))
message_log.append(self.assistant_message(example["sql"]))
message_log.append(self.user_message(question))
return message_log
def get_followup_questions_prompt(
self,
question: str,
question_sql_list: list,
ddl_list: list,
doc_list: list,
**kwargs,
) -> list:
initial_prompt = f"The user initially asked the question: '{question}': \n\n"
initial_prompt = self.add_ddl_to_prompt(
initial_prompt, ddl_list, max_tokens=14000
)
initial_prompt = self.add_documentation_to_prompt(
initial_prompt, doc_list, max_tokens=14000
)
initial_prompt = self.add_sql_to_prompt(
initial_prompt, question_sql_list, max_tokens=14000
)
message_log = [self.system_message(initial_prompt)]
message_log.append(
self.user_message(
"Generate a list of followup questions that the user might ask about this data. Respond with a list of questions, one per line. Do not answer with any explanations -- just the questions."
)
)
return message_log
@abstractmethod
def submit_prompt(self, prompt, **kwargs) -> str:
"""
Example:
```python
vn.submit_prompt(
[
vn.system_message("The user will give you SQL and you will try to guess what the business question this query is answering. Return just the question without any additional explanation. Do not reference the table name in the question."),
vn.user_message("What are the top 10 customers by sales?"),
]
)
```
This method is used to submit a prompt to the LLM.
Args:
prompt (any): The prompt to submit to the LLM.
Returns:
str: The response from the LLM.
"""
pass
def generate_question(self, sql: str, **kwargs) -> str:
response = self.submit_prompt(
[
self.system_message(
"The user will give you SQL and you will try to guess what the business question this query is answering. Return just the question without any additional explanation. Do not reference the table name in the question."
),
self.user_message(sql),
],
**kwargs,
)
return response
def _extract_python_code(self, markdown_string: str) -> str:
# Regex pattern to match Python code blocks
pattern = r"```[\w\s]*python\n([\s\S]*?)```|```([\s\S]*?)```"
# Find all matches in the markdown string
matches = re.findall(pattern, markdown_string, re.IGNORECASE)
# Extract the Python code from the matches
python_code = []
for match in matches:
python = match[0] if match[0] else match[1]
python_code.append(python.strip())
if len(python_code) == 0:
return markdown_string
return python_code[0]
def _sanitize_plotly_code(self, raw_plotly_code: str) -> str:
# Remove the fig.show() statement from the plotly code
plotly_code = raw_plotly_code.replace("fig.show()", "")
return plotly_code
def generate_plotly_code(
self, question: str = None, sql: str = None, df_metadata: str = None, **kwargs
) -> str:
if question is not None:
system_msg = f"The following is a pandas DataFrame that contains the results of the query that answers the question the user asked: '{question}'"
else:
system_msg = "The following is a pandas DataFrame "
if sql is not None:
system_msg += f"\n\nThe DataFrame was produced using this query: {sql}\n\n"
system_msg += f"The following is information about the resulting pandas DataFrame 'df': \n{df_metadata}"
message_log = [
self.system_message(system_msg),
self.user_message(
"Can you generate the Python plotly code to chart the results of the dataframe? Assume the data is in a pandas dataframe called 'df'. If there is only one value in the dataframe, use an Indicator. Respond with only Python code. Do not answer with any explanations -- just the code."
),
]
plotly_code = self.submit_prompt(message_log, kwargs=kwargs)
return self._sanitize_plotly_code(self._extract_python_code(plotly_code))
# ----------------- Connect to Any Database to run the Generated SQL ----------------- #
def connect_to_snowflake(
self,
account: str,
username: str,
password: str,
database: str,
role: Union[str, None] = None,
warehouse: Union[str, None] = None,
):
try:
snowflake = __import__("snowflake.connector")
except ImportError:
raise DependencyError(
"You need to install required dependencies to execute this method, run command:"
" \npip install vanna[snowflake]"
)
if username == "my-username":
username_env = os.getenv("SNOWFLAKE_USERNAME")
if username_env is not None:
username = username_env
else:
raise ImproperlyConfigured("Please set your Snowflake username.")
if password == "my-password":
password_env = os.getenv("SNOWFLAKE_PASSWORD")
if password_env is not None:
password = password_env
else:
raise ImproperlyConfigured("Please set your Snowflake password.")
if account == "my-account":
account_env = os.getenv("SNOWFLAKE_ACCOUNT")
if account_env is not None:
account = account_env
else:
raise ImproperlyConfigured("Please set your Snowflake account.")
if database == "my-database":
database_env = os.getenv("SNOWFLAKE_DATABASE")
if database_env is not None:
database = database_env
else:
raise ImproperlyConfigured("Please set your Snowflake database.")
conn = snowflake.connector.connect(
user=username,
password=password,
account=account,
database=database,
client_session_keep_alive=True
)
def run_sql_snowflake(sql: str) -> pd.DataFrame:
cs = conn.cursor()
if role is not None:
cs.execute(f"USE ROLE {role}")
if warehouse is not None:
cs.execute(f"USE WAREHOUSE {warehouse}")
cs.execute(f"USE DATABASE {database}")
cur = cs.execute(sql)
results = cur.fetchall()
# Create a pandas dataframe from the results
df = pd.DataFrame(results, columns=[desc[0] for desc in cur.description])
return df
self.dialect = "Snowflake SQL"
self.run_sql = run_sql_snowflake
self.run_sql_is_set = True
def connect_to_sqlite(self, url: str):
"""
Connect to a SQLite database. This is just a helper function to set [`vn.run_sql`][vanna.base.base.VannaBase.run_sql]
Args:
url (str): The URL of the database to connect to.
Returns:
None
"""
# URL of the database to download
# Path to save the downloaded database
path = os.path.basename(urlparse(url).path)
# Download the database if it doesn't exist
if not os.path.exists(url):
response = requests.get(url)
response.raise_for_status() # Check that the request was successful
with open(path, "wb") as f:
f.write(response.content)
url = path
# Connect to the database
conn = sqlite3.connect(url, check_same_thread=False)
def run_sql_sqlite(sql: str):
return pd.read_sql_query(sql, conn)
self.dialect = "SQLite"
self.run_sql = run_sql_sqlite
self.run_sql_is_set = True
def connect_to_postgres(
self,
host: str = None,
dbname: str = None,
user: str = None,
password: str = None,
port: int = None,
):
"""
Connect to postgres using the psycopg2 connector. This is just a helper function to set [`vn.run_sql`][vanna.base.base.VannaBase.run_sql]
**Example:**
```python
vn.connect_to_postgres(
host="myhost",
dbname="mydatabase",
user="myuser",
password="mypassword",
port=5432
)
```
Args:
host (str): The postgres host.
dbname (str): The postgres database name.
user (str): The postgres user.
password (str): The postgres password.
port (int): The postgres Port.
"""
try:
import psycopg2
import psycopg2.extras
except ImportError:
raise DependencyError(
"You need to install required dependencies to execute this method,"
" run command: \npip install vanna[postgres]"
)
if not host:
host = os.getenv("HOST")
if not host:
raise ImproperlyConfigured("Please set your postgres host")
if not dbname:
dbname = os.getenv("DATABASE")
if not dbname:
raise ImproperlyConfigured("Please set your postgres database")
if not user:
user = os.getenv("PG_USER")
if not user:
raise ImproperlyConfigured("Please set your postgres user")
if not password:
password = os.getenv("PASSWORD")
if not password:
raise ImproperlyConfigured("Please set your postgres password")
if not port:
port = os.getenv("PORT")
if not port:
raise ImproperlyConfigured("Please set your postgres port")
conn = None
try:
conn = psycopg2.connect(
host=host,
dbname=dbname,
user=user,
password=password,
port=port,
)
except psycopg2.Error as e:
raise ValidationError(e)
def run_sql_postgres(sql: str) -> Union[pd.DataFrame, None]:
if conn:
try:
cs = conn.cursor()
cs.execute(sql)
results = cs.fetchall()
# Create a pandas dataframe from the results
df = pd.DataFrame(
results, columns=[desc[0] for desc in cs.description]
)
return df
except psycopg2.Error as e:
conn.rollback()
raise ValidationError(e)
except Exception as e:
conn.rollback()
raise e
self.dialect = "PostgreSQL"
self.run_sql_is_set = True
self.run_sql = run_sql_postgres
def connect_to_mysql(
self,
host: str = None,
dbname: str = None,
user: str = None,
password: str = None,
port: int = None,
):
try:
import pymysql.cursors
except ImportError:
raise DependencyError(
"You need to install required dependencies to execute this method,"
" run command: \npip install PyMySQL"
)
if not host:
host = os.getenv("HOST")
if not host:
raise ImproperlyConfigured("Please set your MySQL host")
if not dbname:
dbname = os.getenv("DATABASE")
if not dbname:
raise ImproperlyConfigured("Please set your MySQL database")
if not user:
user = os.getenv("USER")
if not user:
raise ImproperlyConfigured("Please set your MySQL user")
if not password:
password = os.getenv("PASSWORD")
if not password:
raise ImproperlyConfigured("Please set your MySQL password")
if not port:
port = os.getenv("PORT")
if not port:
raise ImproperlyConfigured("Please set your MySQL port")
conn = None
try:
conn = pymysql.connect(host=host,
user=user,
password=password,
database=dbname,
port=port,
cursorclass=pymysql.cursors.DictCursor)
except pymysql.Error as e:
raise ValidationError(e)
def run_sql_mysql(sql: str) -> Union[pd.DataFrame, None]:
if conn:
try:
cs = conn.cursor()
cs.execute(sql)
results = cs.fetchall()
# Create a pandas dataframe from the results
df = pd.DataFrame(
results, columns=[desc[0] for desc in cs.description]