Archives
/
langchain
mirror of https://github.com/hwchase17/langchain
2
0
Fork 1
Code Issues Packages Projects Releases Wiki Activity

cr

Browse Source
pull/8402/head
Harrison Chase 1 year ago
parent a221a9ced0
commit 1b0bfa54cf
3 changed files with 7 additions and 268 deletions
Show Stats Download Patch File Download Diff File

9
docs/snippets/modules/chains/popular/sqlite.mdx
Unescape Escape View File

@ -5,7 +5,9 @@ To set it up, follow the instructions on https://database.guide/2-sample-databas
```python
from langchain import OpenAI, SQLDatabase, SQLDatabaseChain
from langchain.llms import OpenAI
from langchain.utilities import SQLDatabase
from langchain_experimental.sql import SQLDatabaseChain
```
@ -484,7 +486,7 @@ This is useful in cases where the number of tables in the database is large.
```python
from langchain.chains import SQLDatabaseSequentialChain
from langchain_experimental.sql import SQLDatabaseSequentialChain
db = SQLDatabase.from_uri("sqlite:///../../../../notebooks/Chinook.db")
```
@ -567,7 +569,8 @@ local_llm = HuggingFacePipeline(pipeline=pipe)
```python
from langchain import SQLDatabase, SQLDatabaseChain
from langchain.utilities import SQLDatabase
from langchain_experimental.sql import SQLDatabaseChain
db = SQLDatabase.from_uri("sqlite:///../../../../notebooks/Chinook.db", include_tables=['Customer'])
local_chain = SQLDatabaseChain.from_llm(local_llm, db, verbose=True, return_intermediate_steps=True, use_query_checker=True)

3
libs/experimental/langchain_experimental/sql/base.py
Unescape Escape View File

@ -7,6 +7,7 @@ from typing import Any, Dict, List, Optional
from langchain.callbacks.manager import CallbackManagerForChainRun
from langchain.chains.base import Chain
from langchain.chains.llm import LLMChain
from langchain.chains.sql_database.prompt import DECIDER_PROMPT, PROMPT, SQL_PROMPTS
from langchain.prompts.prompt import PromptTemplate
from langchain.schema import BasePromptTemplate
from langchain.schema.language_model import BaseLanguageModel
@ -14,8 +15,6 @@ from langchain.tools.sql_database.prompt import QUERY_CHECKER
from langchain.utilities.sql_database import SQLDatabase
from pydantic import Extra, Field, root_validator
from langchain_experimental.sql.prompt import DECIDER_PROMPT, PROMPT, SQL_PROMPTS
INTERMEDIATE_STEPS_KEY = "intermediate_steps"

263
libs/experimental/langchain_experimental/sql/prompt.py
Unescape Escape View File

@ -1,263 +0,0 @@
# flake8: noqa
from langchain.output_parsers.list import CommaSeparatedListOutputParser
from langchain.prompts.prompt import PromptTemplate
PROMPT_SUFFIX = """Only use the following tables:
{table_info}
Question: {input}"""
_DEFAULT_TEMPLATE = """Given an input question, first create a syntactically correct {dialect} query to run, then look at the results of the query and return the answer. Unless the user specifies in his question a specific number of examples he wishes to obtain, always limit your query to at most {top_k} results. You can order the results by a relevant column to return the most interesting examples in the database.
Never query for all the columns from a specific table, only ask for a the few relevant columns given the question.
Pay attention to use only the column names that you can see in the schema description. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
Use the following format:
Question: Question here
SQLQuery: SQL Query to run
SQLResult: Result of the SQLQuery
Answer: Final answer here
"""
PROMPT = PromptTemplate(
input_variables=["input", "table_info", "dialect", "top_k"],
template=_DEFAULT_TEMPLATE + PROMPT_SUFFIX,
)
_DECIDER_TEMPLATE = """Given the below input question and list of potential tables, output a comma separated list of the table names that may be necessary to answer this question.
Question: {query}
Table Names: {table_names}
Relevant Table Names:"""
DECIDER_PROMPT = PromptTemplate(
input_variables=["query", "table_names"],
template=_DECIDER_TEMPLATE,
output_parser=CommaSeparatedListOutputParser(),
)
_duckdb_prompt = """You are a DuckDB expert. Given an input question, first create a syntactically correct DuckDB query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per DuckDB. You can order the results to return the most informative data in the database.
Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
Pay attention to use today() function to get the current date, if the question involves "today".
Use the following format:
Question: Question here
SQLQuery: SQL Query to run
SQLResult: Result of the SQLQuery
Answer: Final answer here
"""
DUCKDB_PROMPT = PromptTemplate(
input_variables=["input", "table_info", "top_k"],
template=_duckdb_prompt + PROMPT_SUFFIX,
)
_googlesql_prompt = """You are a GoogleSQL expert. Given an input question, first create a syntactically correct GoogleSQL query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per GoogleSQL. You can order the results to return the most informative data in the database.
Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in backticks (`) to denote them as delimited identifiers.
Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
Pay attention to use CURRENT_DATE() function to get the current date, if the question involves "today".
Use the following format:
Question: Question here
SQLQuery: SQL Query to run
SQLResult: Result of the SQLQuery
Answer: Final answer here
"""
GOOGLESQL_PROMPT = PromptTemplate(
input_variables=["input", "table_info", "top_k"],
template=_googlesql_prompt + PROMPT_SUFFIX,
)
_mssql_prompt = """You are an MS SQL expert. Given an input question, first create a syntactically correct MS SQL query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the TOP clause as per MS SQL. You can order the results to return the most informative data in the database.
Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in square brackets ([]) to denote them as delimited identifiers.
Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
Pay attention to use CAST(GETDATE() as date) function to get the current date, if the question involves "today".
Use the following format:
Question: Question here
SQLQuery: SQL Query to run
SQLResult: Result of the SQLQuery
Answer: Final answer here
"""
MSSQL_PROMPT = PromptTemplate(
input_variables=["input", "table_info", "top_k"],
template=_mssql_prompt + PROMPT_SUFFIX,
)
_mysql_prompt = """You are a MySQL expert. Given an input question, first create a syntactically correct MySQL query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per MySQL. You can order the results to return the most informative data in the database.
Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in backticks (`) to denote them as delimited identifiers.
Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
Pay attention to use CURDATE() function to get the current date, if the question involves "today".
Use the following format:
Question: Question here
SQLQuery: SQL Query to run
SQLResult: Result of the SQLQuery
Answer: Final answer here
"""
MYSQL_PROMPT = PromptTemplate(
input_variables=["input", "table_info", "top_k"],
template=_mysql_prompt + PROMPT_SUFFIX,
)
_mariadb_prompt = """You are a MariaDB expert. Given an input question, first create a syntactically correct MariaDB query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per MariaDB. You can order the results to return the most informative data in the database.
Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in backticks (`) to denote them as delimited identifiers.
Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
Pay attention to use CURDATE() function to get the current date, if the question involves "today".
Use the following format:
Question: Question here
SQLQuery: SQL Query to run
SQLResult: Result of the SQLQuery
Answer: Final answer here
"""
MARIADB_PROMPT = PromptTemplate(
input_variables=["input", "table_info", "top_k"],
template=_mariadb_prompt + PROMPT_SUFFIX,
)
_oracle_prompt = """You are an Oracle SQL expert. Given an input question, first create a syntactically correct Oracle SQL query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the FETCH FIRST n ROWS ONLY clause as per Oracle SQL. You can order the results to return the most informative data in the database.
Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
Pay attention to use TRUNC(SYSDATE) function to get the current date, if the question involves "today".
Use the following format:
Question: Question here
SQLQuery: SQL Query to run
SQLResult: Result of the SQLQuery
Answer: Final answer here
"""
ORACLE_PROMPT = PromptTemplate(
input_variables=["input", "table_info", "top_k"],
template=_oracle_prompt + PROMPT_SUFFIX,
)
_postgres_prompt = """You are a PostgreSQL expert. Given an input question, first create a syntactically correct PostgreSQL query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per PostgreSQL. You can order the results to return the most informative data in the database.
Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
Pay attention to use CURRENT_DATE function to get the current date, if the question involves "today".
Use the following format:
Question: Question here
SQLQuery: SQL Query to run
SQLResult: Result of the SQLQuery
Answer: Final answer here
"""
POSTGRES_PROMPT = PromptTemplate(
input_variables=["input", "table_info", "top_k"],
template=_postgres_prompt + PROMPT_SUFFIX,
)
_sqlite_prompt = """You are a SQLite expert. Given an input question, first create a syntactically correct SQLite query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per SQLite. You can order the results to return the most informative data in the database.
Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
Pay attention to use date('now') function to get the current date, if the question involves "today".
Use the following format:
Question: Question here
SQLQuery: SQL Query to run
SQLResult: Result of the SQLQuery
Answer: Final answer here
"""
SQLITE_PROMPT = PromptTemplate(
input_variables=["input", "table_info", "top_k"],
template=_sqlite_prompt + PROMPT_SUFFIX,
)
_clickhouse_prompt = """You are a ClickHouse expert. Given an input question, first create a syntactically correct Clic query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per ClickHouse. You can order the results to return the most informative data in the database.
Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
Pay attention to use today() function to get the current date, if the question involves "today".
Use the following format:
Question: "Question here"
SQLQuery: "SQL Query to run"
SQLResult: "Result of the SQLQuery"
Answer: "Final answer here"
"""
CLICKHOUSE_PROMPT = PromptTemplate(
input_variables=["input", "table_info", "top_k"],
template=_clickhouse_prompt + PROMPT_SUFFIX,
)
_prestodb_prompt = """You are a PrestoDB expert. Given an input question, first create a syntactically correct PrestoDB query to run, then look at the results of the query and return the answer to the input question.
Unless the user specifies in the question a specific number of examples to obtain, query for at most {top_k} results using the LIMIT clause as per PrestoDB. You can order the results to return the most informative data in the database.
Never query for all columns from a table. You must query only the columns that are needed to answer the question. Wrap each column name in double quotes (") to denote them as delimited identifiers.
Pay attention to use only the column names you can see in the tables below. Be careful to not query for columns that do not exist. Also, pay attention to which column is in which table.
Pay attention to use current_date function to get the current date, if the question involves "today".
Use the following format:
Question: "Question here"
SQLQuery: "SQL Query to run"
SQLResult: "Result of the SQLQuery"
Answer: "Final answer here"
"""
PRESTODB_PROMPT = PromptTemplate(
input_variables=["input", "table_info", "top_k"],
template=_prestodb_prompt + PROMPT_SUFFIX,
)
SQL_PROMPTS = {
"duckdb": DUCKDB_PROMPT,
"googlesql": GOOGLESQL_PROMPT,
"mssql": MSSQL_PROMPT,
"mysql": MYSQL_PROMPT,
"mariadb": MARIADB_PROMPT,
"oracle": ORACLE_PROMPT,
"postgresql": POSTGRES_PROMPT,
"sqlite": SQLITE_PROMPT,
"clickhouse": CLICKHOUSE_PROMPT,
"prestodb": PRESTODB_PROMPT,
}
Write Preview
Loading…
Cancel
Save