From 7d3e6389f26da27ef4fcb9466795fe4622ab1e5a Mon Sep 17 00:00:00 2001 From: Tom Dyson Date: Thu, 20 Apr 2023 22:02:20 +0100 Subject: [PATCH] Add DuckDB prompt (#3233) Adds a prompt template for the DuckDB SQL dialect. --- langchain/chains/sql_database/prompt.py | 22 ++++++++++++++++++++++ 1 file changed, 22 insertions(+) diff --git a/langchain/chains/sql_database/prompt.py b/langchain/chains/sql_database/prompt.py index 0ced8a22..8fd3b46a 100644 --- a/langchain/chains/sql_database/prompt.py +++ b/langchain/chains/sql_database/prompt.py @@ -40,6 +40,27 @@ DECIDER_PROMPT = PromptTemplate( 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. + +Use the following format: + +Question: "Question here" +SQLQuery: "SQL Query to run" +SQLResult: "Result of the SQLQuery" +Answer: "Final answer here" + +Only use the following tables: +{table_info} + +Question: {input}""" + +DUCKDB_PROMPT = PromptTemplate( + input_variables=["input", "table_info", "top_k"], + template=_duckdb_prompt, +) _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. @@ -201,6 +222,7 @@ SQLITE_PROMPT = PromptTemplate( SQL_PROMPTS = { + "duckdb": DUCKDB_PROMPT, "googlesql": GOOGLESQL_PROMPT, "mssql": MSSQL_PROMPT, "mysql": MYSQL_PROMPT,