Spark SQL 代理

本笔记本展示了如何使用代理与 Spark SQL 进行交互。与 SQL 数据库代理类似，它旨在解答关于 Spark SQL 的通用问题并促进错误恢复。

注意：请注意，由于该代理正在积极开发中，所有答案可能不一定正确。此外，不保证代理不会在某些问题上对您的 Spark 集群执行 DML 语句。在敏感数据上运行时要小心！

初始化

from langchain.agents import create_spark_sql_agent
from langchain.agents.agent_toolkits import SparkSQLToolkit
from langchain.chat_models import ChatOpenAI
from langchain.utilities.spark_sql import SparkSQL

from pyspark.sql import SparkSession

spark = SparkSession.builder.getOrCreate()
schema = "langchain_example"
spark.sql(f"CREATE DATABASE IF NOT EXISTS {schema}")
spark.sql(f"USE {schema}")
csv_file_path = "titanic.csv"
table = "titanic"
spark.read.csv(csv_file_path, header=True, inferSchema=True).write.saveAsTable(table)
spark.table(table).show()

Setting default log level to "WARN".
To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).
23/05/18 16:03:10 WARN NativeCodeLoader: Unable to load native-hadoop library for your platform... using builtin-java classes where applicable


+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+
|PassengerId|Survived|Pclass|                Name|   Sex| Age|SibSp|Parch|          Ticket|   Fare|Cabin|Embarked|
+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+
|          1|       0|     3|Braund, Mr. Owen ...|  male|22.0|    1|    0|       A/5 21171|   7.25| null|       S|
|          2|       1|     1|Cumings, Mrs. Joh...|female|38.0|    1|    0|        PC 17599|71.2833|  C85|       C|
|          3|       1|     3|Heikkinen, Miss. ...|female|26.0|    0|    0|STON/O2. 3101282|  7.925| null|       S|
|          4|       1|     1|Futrelle, Mrs. Ja...|female|35.0|    1|    0|          113803|   53.1| C123|       S|
|          5|       0|     3|Allen, Mr. Willia...|  male|35.0|    0|    0|          373450|   8.05| null|       S|
|          6|       0|     3|    Moran, Mr. James|  male|null|    0|    0|          330877| 8.4583| null|       Q|
|          7|       0|     1|McCarthy, Mr. Tim...|  male|54.0|    0|    0|           17463|51.8625|  E46|       S|
|          8|       0|     3|Palsson, Master. ...|  male| 2.0|    3|    1|          349909| 21.075| null|       S|
|          9|       1|     3|Johnson, Mrs. Osc...|female|27.0|    0|    2|          347742|11.1333| null|       S|
|         10|       1|     2|Nasser, Mrs. Nich...|female|14.0|    1|    0|          237736|30.0708| null|       C|
|         11|       1|     3|Sandstrom, Miss. ...|female| 4.0|    1|    1|         PP 9549|   16.7|   G6|       S|
|         12|       1|     1|Bonnell, Miss. El...|female|58.0|    0|    0|          113783|  26.55| C103|       S|
|         13|       0|     3|Saundercock, Mr. ...|  male|20.0|    0|    0|       A/5. 2151|   8.05| null|       S|
|         14|       0|     3|Andersson, Mr. An...|  male|39.0|    1|    5|          347082| 31.275| null|       S|
|         15|       0|     3|Vestrom, Miss. Hu...|female|14.0|    0|    0|          350406| 7.8542| null|       S|
|         16|       1|     2|Hewlett, Mrs. (Ma...|female|55.0|    0|    0|          248706|   16.0| null|       S|
|         17|       0|     3|Rice, Master. Eugene|  male| 2.0|    4|    1|          382652| 29.125| null|       Q|
|         18|       1|     2|Williams, Mr. Cha...|  male|null|    0|    0|          244373|   13.0| null|       S|
|         19|       0|     3|Vander Planke, Mr...|female|31.0|    1|    0|          345763|   18.0| null|       S|
|         20|       1|     3|Masselmani, Mrs. ...|female|null|    0|    0|            2649|  7.225| null|       C|
+-----------+--------+------+--------------------+------+----+-----+-----+----------------+-------+-----+--------+
only showing top 20 rows

# Note, you can also connect to Spark via Spark connect. For example:
# db = SparkSQL.from_uri("sc://localhost:15002", schema=schema)
spark_sql = SparkSQL(schema=schema)
llm = ChatOpenAI(temperature=0)
toolkit = SparkSQLToolkit(db=spark_sql, llm=llm)
agent_executor = create_spark_sql_agent(llm=llm, toolkit=toolkit, verbose=True)

Example: describing a table

agent_executor.run("Describe the titanic table")

[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: list_tables_sql_db
Action Input: [0m
Observation: [38;5;200m[1;3mtitanic[0m
Thought:[32;1m[1;3mI found the titanic table. Now I need to get the schema and sample rows for the titanic table.
Action: schema_sql_db
Action Input: titanic[0m
Observation: [33;1m[1;3mCREATE TABLE langchain_example.titanic (
  PassengerId INT,
  Survived INT,
  Pclass INT,
  Name STRING,
  Sex STRING,
  Age DOUBLE,
  SibSp INT,
  Parch INT,
  Ticket STRING,
  Fare DOUBLE,
  Cabin STRING,
  Embarked STRING)
;

/*
3 rows from titanic table:
PassengerId Survived    Pclass  Name    Sex Age SibSp   Parch   Ticket  Fare    Cabin   Embarked
1   0   3   Braund, Mr. Owen Harris male    22.0    1   0   A/5 21171   7.25    None    S
2   1   1   Cumings, Mrs. John Bradley (Florence Briggs Thayer) female  38.0    1   0   PC 17599    71.2833 C85 C
3   1   3   Heikkinen, Miss. Laina  female  26.0    0   0   STON/O2. 3101282    7.925   None    S
*/[0m
Thought:[32;1m[1;3mI now know the schema and sample rows for the titanic table.
Final Answer: The titanic table has the following columns: PassengerId (INT), Survived (INT), Pclass (INT), Name (STRING), Sex (STRING), Age (DOUBLE), SibSp (INT), Parch (INT), Ticket (STRING), Fare (DOUBLE), Cabin (STRING), and Embarked (STRING). Here are some sample rows from the table: 

1. PassengerId: 1, Survived: 0, Pclass: 3, Name: Braund, Mr. Owen Harris, Sex: male, Age: 22.0, SibSp: 1, Parch: 0, Ticket: A/5 21171, Fare: 7.25, Cabin: None, Embarked: S
2. PassengerId: 2, Survived: 1, Pclass: 1, Name: Cumings, Mrs. John Bradley (Florence Briggs Thayer), Sex: female, Age: 38.0, SibSp: 1, Parch: 0, Ticket: PC 17599, Fare: 71.2833, Cabin: C85, Embarked: C
3. PassengerId: 3, Survived: 1, Pclass: 3, Name: Heikkinen, Miss. Laina, Sex: female, Age: 26.0, SibSp: 0, Parch: 0, Ticket: STON/O2. 3101282, Fare: 7.925, Cabin: None, Embarked: S[0m

[1m> Finished chain.[0m





'The titanic table has the following columns: PassengerId (INT), Survived (INT), Pclass (INT), Name (STRING), Sex (STRING), Age (DOUBLE), SibSp (INT), Parch (INT), Ticket (STRING), Fare (DOUBLE), Cabin (STRING), and Embarked (STRING). Here are some sample rows from the table: \n\n1. PassengerId: 1, Survived: 0, Pclass: 3, Name: Braund, Mr. Owen Harris, Sex: male, Age: 22.0, SibSp: 1, Parch: 0, Ticket: A/5 21171, Fare: 7.25, Cabin: None, Embarked: S\n2. PassengerId: 2, Survived: 1, Pclass: 1, Name: Cumings, Mrs. John Bradley (Florence Briggs Thayer), Sex: female, Age: 38.0, SibSp: 1, Parch: 0, Ticket: PC 17599, Fare: 71.2833, Cabin: C85, Embarked: C\n3. PassengerId: 3, Survived: 1, Pclass: 3, Name: Heikkinen, Miss. Laina, Sex: female, Age: 26.0, SibSp: 0, Parch: 0, Ticket: STON/O2. 3101282, Fare: 7.925, Cabin: None, Embarked: S'

Example: running queries

agent_executor.run("whats the square root of the average age?")

[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: list_tables_sql_db
Action Input: [0m
Observation: [38;5;200m[1;3mtitanic[0m
Thought:[32;1m[1;3mI should check the schema of the titanic table to see if there is an age column.
Action: schema_sql_db
Action Input: titanic[0m
Observation: [33;1m[1;3mCREATE TABLE langchain_example.titanic (
  PassengerId INT,
  Survived INT,
  Pclass INT,
  Name STRING,
  Sex STRING,
  Age DOUBLE,
  SibSp INT,
  Parch INT,
  Ticket STRING,
  Fare DOUBLE,
  Cabin STRING,
  Embarked STRING)
;

/*
3 rows from titanic table:
PassengerId Survived    Pclass  Name    Sex Age SibSp   Parch   Ticket  Fare    Cabin   Embarked
1   0   3   Braund, Mr. Owen Harris male    22.0    1   0   A/5 21171   7.25    None    S
2   1   1   Cumings, Mrs. John Bradley (Florence Briggs Thayer) female  38.0    1   0   PC 17599    71.2833 C85 C
3   1   3   Heikkinen, Miss. Laina  female  26.0    0   0   STON/O2. 3101282    7.925   None    S
*/[0m
Thought:[32;1m[1;3mThere is an Age column in the titanic table. I should write a query to calculate the average age and then find the square root of the result.
Action: query_checker_sql_db
Action Input: SELECT SQRT(AVG(Age)) as square_root_of_avg_age FROM titanic[0m
Observation: [31;1m[1;3mThe original query seems to be correct. Here it is again:

SELECT SQRT(AVG(Age)) as square_root_of_avg_age FROM titanic[0m
Thought:[32;1m[1;3mThe query is correct, so I can execute it to find the square root of the average age.
Action: query_sql_db
Action Input: SELECT SQRT(AVG(Age)) as square_root_of_avg_age FROM titanic[0m
Observation: [36;1m[1;3m[('5.449689683556195',)][0m
Thought:[32;1m[1;3mI now know the final answer
Final Answer: The square root of the average age is approximately 5.45.[0m

[1m> Finished chain.[0m





'The square root of the average age is approximately 5.45.'

agent_executor.run("What's the name of the oldest survived passenger?")

[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3mAction: list_tables_sql_db
Action Input: [0m
Observation: [38;5;200m[1;3mtitanic[0m
Thought:[32;1m[1;3mI should check the schema of the titanic table to see what columns are available.
Action: schema_sql_db
Action Input: titanic[0m
Observation: [33;1m[1;3mCREATE TABLE langchain_example.titanic (
  PassengerId INT,
  Survived INT,
  Pclass INT,
  Name STRING,
  Sex STRING,
  Age DOUBLE,
  SibSp INT,
  Parch INT,
  Ticket STRING,
  Fare DOUBLE,
  Cabin STRING,
  Embarked STRING)
;

/*
3 rows from titanic table:
PassengerId Survived    Pclass  Name    Sex Age SibSp   Parch   Ticket  Fare    Cabin   Embarked
1   0   3   Braund, Mr. Owen Harris male    22.0    1   0   A/5 21171   7.25    None    S
2   1   1   Cumings, Mrs. John Bradley (Florence Briggs Thayer) female  38.0    1   0   PC 17599    71.2833 C85 C
3   1   3   Heikkinen, Miss. Laina  female  26.0    0   0   STON/O2. 3101282    7.925   None    S
*/[0m
Thought:[32;1m[1;3mI can use the titanic table to find the oldest survived passenger. I will query the Name and Age columns, filtering by Survived and ordering by Age in descending order.
Action: query_checker_sql_db
Action Input: SELECT Name, Age FROM titanic WHERE Survived = 1 ORDER BY Age DESC LIMIT 1[0m
Observation: [31;1m[1;3mSELECT Name, Age FROM titanic WHERE Survived = 1 ORDER BY Age DESC LIMIT 1[0m
Thought:[32;1m[1;3mThe query is correct. Now I will execute it to find the oldest survived passenger.
Action: query_sql_db
Action Input: SELECT Name, Age FROM titanic WHERE Survived = 1 ORDER BY Age DESC LIMIT 1[0m
Observation: [36;1m[1;3m[('Barkworth, Mr. Algernon Henry Wilson', '80.0')][0m
Thought:[32;1m[1;3mI now know the final answer.
Final Answer: The oldest survived passenger is Barkworth, Mr. Algernon Henry Wilson, who was 80 years old.[0m

[1m> Finished chain.[0m





'The oldest survived passenger is Barkworth, Mr. Algernon Henry Wilson, who was 80 years old.'

Spark SQL 代理

初始化​

Example: describing a table​

Example: running queries​

初始化

Example: describing a table

Example: running queries