> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.cohere.com/llms.txt.
> For full documentation content, see https://docs.cohere.com/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.cohere.com/_mcp/server.
# Build a SQL Agent with Cohere's LLM Platform
> This page contains a tutorial on how to build a SQL agent with Cohere's LLM platform.
## Motivation
Enterprise customers often store and handle information in relational databases but querying such databases effectively requires bespoke knowledge of the underlying database structure as well as strong SQL coding skills. One way to address these challenges is to build an LLM agent capable of generating and executing SQL queries based on natural language. For example, if a user asks: `what are the top 4 rows in table X`, the agent should be able to generate `SELECT * FROM X LIMIT 4`, execute this query and return the output to the user.
## Objective
In this notebook we explore how to setup a [Cohere ReAct Agent](https://github.com/langchain-ai/langchain-cohere/blob/main/libs/cohere/langchain_cohere/cohere_agent.py) to answer questions over SQL Databases. We show how this can be done seamlessly with langchain's existing [SQLDBToolkit](https://python.langchain.com/v0.1/docs/integrations/toolkits/sql_database/).
# Toolkit Setup \[#sec\_step0]
```python PYTHON
from langchain.agents import AgentExecutor
from langchain_cohere.react_multi_hop.agent import create_cohere_react_agent
from langchain_core.prompts import ChatPromptTemplate
from langchain_cohere.chat_models import ChatCohere
from langchain_community.utilities.sql_database import SQLDatabase
from langchain_community.agent_toolkits import SQLDatabaseToolkit
import os
import json
```
```python PYTHON
# Uncomment if you need to install the following packages
#!pip install --quiet langchain langchain_cohere langchain_experimental --upgrade
```
Langchain already has a SQLDBToolkit that consists of 4 tools to handle SQL query generation, execution and validation. To use this, you simply need to define your LLM and DB and pass these into the Toolkit.
These are the following tools:
* 'sql\_db\_query': executes SQL code on the database
* 'sql\_db\_schema': returns the schema of tables given the list of tables
* 'sql\_db\_list\_tables': lists the tables in the database
* 'sql\_db\_query\_checker': validates the SQL query
```python PYTHON
# load the cohere api key
os.environ["COHERE_API_KEY"] = ""
```
```python PYTHON
DB_NAME='Chinook.db'
MODEL="command-a-03-2025"
llm = ChatCohere(model=MODEL, temperature=0.1,verbose=True)
db = SQLDatabase.from_uri(f"sqlite:///{DB_NAME}")
toolkit = SQLDatabaseToolkit(db=db, llm=llm)
context = toolkit.get_context()
tools = toolkit.get_tools()
print('**List of pre-defined Langchain Tools**')
print([tool.name for tool in tools])
```
```txt title="Output"
**List of pre-defined Langchain Tools**
['sql_db_query', 'sql_db_schema', 'sql_db_list_tables', 'sql_db_query_checker']
```
# SQL Agent \[#sec\_step1]
We follow the general cohere react agent setup in Langchain to build our SQL agent.
```python PYTHON
# define the prompt template
prompt = ChatPromptTemplate.from_template("{input}")
# instantiate the ReAct agent
agent = create_cohere_react_agent(
llm=llm,
tools=tools,
prompt=prompt,
)
agent_executor = AgentExecutor(agent=agent,
tools=tools,
verbose=True,
return_intermediate_steps=True
)
```
```python PYTHON
output=agent_executor.invoke({
"input": 'what tables are available?',
})
```
```txt title="Output"
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
I will use the sql_db_list_tables tool to find out which tables are available.
{'tool_name': 'sql_db_list_tables', 'parameters': {'tool_input': ''}}
[0m[38;5;200m[1;3mAlbum, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track[0m[32;1m[1;3mRelevant Documents: 0
Cited Documents: 0
Answer: The following tables are available: Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track.
Grounded answer: The following tables are available: Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track.[0m
[1m> Finished chain.[0m
```
```python PYTHON
print(output['output'])
```
```txt title="Output"
The following tables are available: Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track.
```
The agent uses the list\_tables tool to effectively highlight all the tables in the DB.
```python PYTHON
output=agent_executor.invoke({
"input": 'show the first row of the Playlist and Genre tables?',
})
```
```txt title="Output"
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
I will use the sql_db_schema tool to find the first row of the Playlist and Genre tables.
{'tool_name': 'sql_db_schema', 'parameters': {'table_names': 'Playlist, Genre'}}
[0m[33;1m[1;3m
CREATE TABLE "Genre" (
"GenreId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("GenreId")
)
/*
3 rows from Genre table:
GenreId Name
1 Rock
2 Jazz
3 Metal
*/
CREATE TABLE "Playlist" (
"PlaylistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("PlaylistId")
)
/*
3 rows from Playlist table:
PlaylistId Name
1 Music
2 Movies
3 TV Shows
*/[0m[32;1m[1;3mRelevant Documents: 0
Cited Documents: 0
Answer: Here is the first row of the Genre table:
| GenreId | Name |
|---|---|
| 1 | Rock |
Here is the first row of the Playlist table:
| PlaylistId | Name |
|---|---|
| 1 | Music |
Grounded answer: Here is the first row of the Genre table:
| GenreId | Name |
|---|---|
| 1 | Rock |
Here is the first row of the Playlist table:
| PlaylistId | Name |
|---|---|
| 1 | Music |[0m
[1m> Finished chain.[0m
```
```python PYTHON
print(output['output'])
```
```txt title="Output"
Here is the first row of the Genre table:
| GenreId | Name |
|---|---|
| 1 | Rock |
Here is the first row of the Playlist table:
| PlaylistId | Name |
|---|---|
| 1 | Music |
```
Here we see that the tool takes a list of tables to query the sql\_db\_schema tool to retrieve the various schemas.
```python PYTHON
output=agent_executor.invoke({
"input": 'which countries have the most invoices?',
})
```
```txt title="Output"
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
I will search for the number of invoices per country and then write an answer.
{'tool_name': 'sql_db_query', 'parameters': {'query': 'SELECT country, COUNT(*) AS invoice_count FROM invoices GROUP BY country ORDER BY invoice_count DESC'}}
[0m[36;1m[1;3mError: (sqlite3.OperationalError) no such table: invoices
[SQL: SELECT country, COUNT(*) AS invoice_count FROM invoices GROUP BY country ORDER BY invoice_count DESC]
(Background on this error at: https://sqlalche.me/e/20/e3q8)[0m[32;1m[1;3m
I received an error message. I will now use the sql_db_list_tables tool to find out the correct table name.
{'tool_name': 'sql_db_list_tables', 'parameters': {'tool_input': ''}}
[0m[38;5;200m[1;3mAlbum, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track[0m[32;1m[1;3m
I found out that the correct table name is 'Invoice'. I will now rewrite my query and run it again.
{'tool_name': 'sql_db_query', 'parameters': {'query': 'SELECT country, COUNT(*) AS invoice_count FROM Invoice GROUP BY country ORDER BY invoice_count DESC'}}
[0m[36;1m[1;3mError: (sqlite3.OperationalError) no such column: country
[SQL: SELECT country, COUNT(*) AS invoice_count FROM Invoice GROUP BY country ORDER BY invoice_count DESC]
(Background on this error at: https://sqlalche.me/e/20/e3q8)[0m[32;1m[1;3m
I received another error message. I will now use the sql_db_schema tool to find out the correct column name.
{'tool_name': 'sql_db_schema', 'parameters': {'table_names': 'Invoice'}}
[0m[33;1m[1;3m
CREATE TABLE "Invoice" (
"InvoiceId" INTEGER NOT NULL,
"CustomerId" INTEGER NOT NULL,
"InvoiceDate" DATETIME NOT NULL,
"BillingAddress" NVARCHAR(70),
"BillingCity" NVARCHAR(40),
"BillingState" NVARCHAR(40),
"BillingCountry" NVARCHAR(40),
"BillingPostalCode" NVARCHAR(10),
"Total" NUMERIC(10, 2) NOT NULL,
PRIMARY KEY ("InvoiceId"),
FOREIGN KEY("CustomerId") REFERENCES "Customer" ("CustomerId")
)
/*
3 rows from Invoice table:
InvoiceId CustomerId InvoiceDate BillingAddress BillingCity BillingState BillingCountry BillingPostalCode Total
1 2 2021-01-01 00:00:00 Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 1.98
2 4 2021-01-02 00:00:00 Ullevålsveien 14 Oslo None Norway 0171 3.96
3 8 2021-01-03 00:00:00 Grétrystraat 63 Brussels None Belgium 1000 5.94
*/[0m[32;1m[1;3m
I found out that the correct column name is 'BillingCountry'. I will now rewrite my query and run it again.
{'tool_name': 'sql_db_query', 'parameters': {'query': 'SELECT BillingCountry AS country, COUNT(*) AS invoice_count FROM Invoice GROUP BY BillingCountry ORDER BY invoice_count DESC'}}
[0m[36;1m[1;3m[('USA', 91), ('Canada', 56), ('France', 35), ('Brazil', 35), ('Germany', 28), ('United Kingdom', 21), ('Portugal', 14), ('Czech Republic', 14), ('India', 13), ('Sweden', 7), ('Spain', 7), ('Poland', 7), ('Norway', 7), ('Netherlands', 7), ('Italy', 7), ('Ireland', 7), ('Hungary', 7), ('Finland', 7), ('Denmark', 7), ('Chile', 7), ('Belgium', 7), ('Austria', 7), ('Australia', 7), ('Argentina', 7)][0m[32;1m[1;3mRelevant Documents: 1,3,4
Cited Documents: 4
Answer: The countries with the most invoices are the USA (91), Canada (56), and France (35).
Grounded answer: The countries with the most invoices are the USA (91), Canada (56), and France (35).[0m
[1m> Finished chain.[0m
```
```python PYTHON
print(output['output'])
```
```txt title="Output"
The countries with the most invoices are the USA (91), Canada (56), and France (35).
```
The agent initially makes some errors as it jumps to answer the question using the db\_query tool, but it then realizes it needs to figure out what tables it has access to and what they look like. It then fixes the SQL code and is able to generate the right answer.
```python PYTHON
output=agent_executor.invoke({
"input": 'who is the best customer? The customer who has spent the most money is the best.',
})
```
```txt title="Output"
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
I will run a SQL query to find the customer who has spent the most money.
{'tool_name': 'sql_db_query', 'parameters': {'query': 'SELECT customer_name, SUM(total_cost) AS total_spent FROM orders GROUP BY customer_name ORDER BY total_spent DESC LIMIT 1;'}}
[0m[36;1m[1;3mError: (sqlite3.OperationalError) no such table: orders
[SQL: SELECT customer_name, SUM(total_cost) AS total_spent FROM orders GROUP BY customer_name ORDER BY total_spent DESC LIMIT 1;]
(Background on this error at: https://sqlalche.me/e/20/e3q8)[0m[32;1m[1;3m
I received an error message saying that there is no table called 'orders'. I will now use the sql_db_list_tables tool to find out what tables are available.
{'tool_name': 'sql_db_list_tables', 'parameters': {'tool_input': ''}}
[0m[38;5;200m[1;3mAlbum, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track[0m[32;1m[1;3m
I found that there is a table called 'Customer'. I will now use the sql_db_schema tool to find out what columns are in the 'Customer' table.
{'tool_name': 'sql_db_schema', 'parameters': {'table_names': 'Customer'}}
[0m[33;1m[1;3m
CREATE TABLE "Customer" (
"CustomerId" INTEGER NOT NULL,
"FirstName" NVARCHAR(40) NOT NULL,
"LastName" NVARCHAR(20) NOT NULL,
"Company" NVARCHAR(80),
"Address" NVARCHAR(70),
"City" NVARCHAR(40),
"State" NVARCHAR(40),
"Country" NVARCHAR(40),
"PostalCode" NVARCHAR(10),
"Phone" NVARCHAR(24),
"Fax" NVARCHAR(24),
"Email" NVARCHAR(60) NOT NULL,
"SupportRepId" INTEGER,
PRIMARY KEY ("CustomerId"),
FOREIGN KEY("SupportRepId") REFERENCES "Employee" ("EmployeeId")
)
/*
3 rows from Customer table:
CustomerId FirstName LastName Company Address City State Country PostalCode Phone Fax Email SupportRepId
1 Luís Gonçalves Embraer - Empresa Brasileira de Aeronáutica S.A. Av. Brigadeiro Faria Lima, 2170 São José dos Campos SP Brazil 12227-000 +55 (12) 3923-5555 +55 (12) 3923-5566 luisg@embraer.com.br 3
2 Leonie Köhler None Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 +49 0711 2842222 None leonekohler@surfeu.de 5
3 François Tremblay None 1498 rue Bélanger Montréal QC Canada H2G 1A7 +1 (514) 721-4711 None ftremblay@gmail.com 3
*/[0m[32;1m[1;3m
I found that the 'Customer' table does not contain any information about how much money a customer has spent. I will now use the sql_db_schema tool to find out what columns are in the 'Invoice' table.
{'tool_name': 'sql_db_schema', 'parameters': {'table_names': 'Invoice'}}
[0m[33;1m[1;3m
CREATE TABLE "Invoice" (
"InvoiceId" INTEGER NOT NULL,
"CustomerId" INTEGER NOT NULL,
"InvoiceDate" DATETIME NOT NULL,
"BillingAddress" NVARCHAR(70),
"BillingCity" NVARCHAR(40),
"BillingState" NVARCHAR(40),
"BillingCountry" NVARCHAR(40),
"BillingPostalCode" NVARCHAR(10),
"Total" NUMERIC(10, 2) NOT NULL,
PRIMARY KEY ("InvoiceId"),
FOREIGN KEY("CustomerId") REFERENCES "Customer" ("CustomerId")
)
/*
3 rows from Invoice table:
InvoiceId CustomerId InvoiceDate BillingAddress BillingCity BillingState BillingCountry BillingPostalCode Total
1 2 2021-01-01 00:00:00 Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 1.98
2 4 2021-01-02 00:00:00 Ullevålsveien 14 Oslo None Norway 0171 3.96
3 8 2021-01-03 00:00:00 Grétrystraat 63 Brussels None Belgium 1000 5.94
*/[0m[32;1m[1;3m
I found that the 'Invoice' table contains a 'Total' column, which is likely to be the total amount spent by the customer on that invoice. I will now use the sql_db_query tool to find the customer who has spent the most money.
{'tool_name': 'sql_db_query', 'parameters': {'query': 'SELECT c.FirstName, c.LastName, SUM(i.Total) AS total_spent FROM Customer c JOIN Invoice i ON c.CustomerId = i.CustomerId GROUP BY c.CustomerId ORDER BY total_spent DESC LIMIT 1;'}}
[0m[36;1m[1;3m[('Helena', 'Holý', 49.62)][0m[32;1m[1;3mRelevant Documents: 1,2,3,4
Cited Documents: 4
Answer: The best customer is Helena Holý, who has spent a total of 49.62.
Grounded answer: The best customer is Helena Holý, who has spent a total of 49.62.[0m
[1m> Finished chain.[0m
```
```python PYTHON
print(output['output'])
```
```txt title="Output"
The best customer is Helena Holý, who has spent a total of 49.62.
```
As you can see, the agent makes an error, but is able to rectify itself. It also manages to generate a SQL query over two tables in the database.
# SQL Agent with context \[#sec\_step2]
Generally, passing in additional context to the system instruction (preamble) can help reduce the initial failures. This context is provided by the SQLDBToolkit and contains the first 3 rows of the tables in the Database.
```python PYTHON
print('**Context to pass to LLM on tables**')
print('Table Names')
print(context['table_names'])
print('Table Schemas')
print(context['table_info'])
```
```sql title="Output"
**Context to pass to LLM on tables**
Table Names
Album, Artist, Customer, Employee, Genre, Invoice, InvoiceLine, MediaType, Playlist, PlaylistTrack, Track
Table Schemas
CREATE TABLE "Album" (
"AlbumId" INTEGER NOT NULL,
"Title" NVARCHAR(160) NOT NULL,
"ArtistId" INTEGER NOT NULL,
PRIMARY KEY ("AlbumId"),
FOREIGN KEY("ArtistId") REFERENCES "Artist" ("ArtistId")
)
/*
3 rows from Album table:
AlbumId Title ArtistId
1 For Those About To Rock We Salute You 1
2 Balls to the Wall 2
3 Restless and Wild 2
*/
CREATE TABLE "Artist" (
"ArtistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("ArtistId")
)
/*
3 rows from Artist table:
ArtistId Name
1 AC/DC
2 Accept
3 Aerosmith
*/
CREATE TABLE "Customer" (
"CustomerId" INTEGER NOT NULL,
"FirstName" NVARCHAR(40) NOT NULL,
"LastName" NVARCHAR(20) NOT NULL,
"Company" NVARCHAR(80),
"Address" NVARCHAR(70),
"City" NVARCHAR(40),
"State" NVARCHAR(40),
"Country" NVARCHAR(40),
"PostalCode" NVARCHAR(10),
"Phone" NVARCHAR(24),
"Fax" NVARCHAR(24),
"Email" NVARCHAR(60) NOT NULL,
"SupportRepId" INTEGER,
PRIMARY KEY ("CustomerId"),
FOREIGN KEY("SupportRepId") REFERENCES "Employee" ("EmployeeId")
)
/*
3 rows from Customer table:
CustomerId FirstName LastName Company Address City State Country PostalCode Phone Fax Email SupportRepId
1 Luís Gonçalves Embraer - Empresa Brasileira de Aeronáutica S.A. Av. Brigadeiro Faria Lima, 2170 São José dos Campos SP Brazil 12227-000 +55 (12) 3923-5555 +55 (12) 3923-5566 luisg@embraer.com.br 3
2 Leonie Köhler None Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 +49 0711 2842222 None leonekohler@surfeu.de 5
3 François Tremblay None 1498 rue Bélanger Montréal QC Canada H2G 1A7 +1 (514) 721-4711 None ftremblay@gmail.com 3
*/
CREATE TABLE "Employee" (
"EmployeeId" INTEGER NOT NULL,
"LastName" NVARCHAR(20) NOT NULL,
"FirstName" NVARCHAR(20) NOT NULL,
"Title" NVARCHAR(30),
"ReportsTo" INTEGER,
"BirthDate" DATETIME,
"HireDate" DATETIME,
"Address" NVARCHAR(70),
"City" NVARCHAR(40),
"State" NVARCHAR(40),
"Country" NVARCHAR(40),
"PostalCode" NVARCHAR(10),
"Phone" NVARCHAR(24),
"Fax" NVARCHAR(24),
"Email" NVARCHAR(60),
PRIMARY KEY ("EmployeeId"),
FOREIGN KEY("ReportsTo") REFERENCES "Employee" ("EmployeeId")
)
/*
3 rows from Employee table:
EmployeeId LastName FirstName Title ReportsTo BirthDate HireDate Address City State Country PostalCode Phone Fax Email
1 Adams Andrew General Manager None 1962-02-18 00:00:00 2002-08-14 00:00:00 11120 Jasper Ave NW Edmonton AB Canada T5K 2N1 +1 (780) 428-9482 +1 (780) 428-3457 andrew@chinookcorp.com
2 Edwards Nancy Sales Manager 1 1958-12-08 00:00:00 2002-05-01 00:00:00 825 8 Ave SW Calgary AB Canada T2P 2T3 +1 (403) 262-3443 +1 (403) 262-3322 nancy@chinookcorp.com
3 Peacock Jane Sales Support Agent 2 1973-08-29 00:00:00 2002-04-01 00:00:00 1111 6 Ave SW Calgary AB Canada T2P 5M5 +1 (403) 262-3443 +1 (403) 262-6712 jane@chinookcorp.com
*/
CREATE TABLE "Genre" (
"GenreId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("GenreId")
)
/*
3 rows from Genre table:
GenreId Name
1 Rock
2 Jazz
3 Metal
*/
CREATE TABLE "Invoice" (
"InvoiceId" INTEGER NOT NULL,
"CustomerId" INTEGER NOT NULL,
"InvoiceDate" DATETIME NOT NULL,
"BillingAddress" NVARCHAR(70),
"BillingCity" NVARCHAR(40),
"BillingState" NVARCHAR(40),
"BillingCountry" NVARCHAR(40),
"BillingPostalCode" NVARCHAR(10),
"Total" NUMERIC(10, 2) NOT NULL,
PRIMARY KEY ("InvoiceId"),
FOREIGN KEY("CustomerId") REFERENCES "Customer" ("CustomerId")
)
/*
3 rows from Invoice table:
InvoiceId CustomerId InvoiceDate BillingAddress BillingCity BillingState BillingCountry BillingPostalCode Total
1 2 2021-01-01 00:00:00 Theodor-Heuss-Straße 34 Stuttgart None Germany 70174 1.98
2 4 2021-01-02 00:00:00 Ullevålsveien 14 Oslo None Norway 0171 3.96
3 8 2021-01-03 00:00:00 Grétrystraat 63 Brussels None Belgium 1000 5.94
*/
CREATE TABLE "InvoiceLine" (
"InvoiceLineId" INTEGER NOT NULL,
"InvoiceId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
"UnitPrice" NUMERIC(10, 2) NOT NULL,
"Quantity" INTEGER NOT NULL,
PRIMARY KEY ("InvoiceLineId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("InvoiceId") REFERENCES "Invoice" ("InvoiceId")
)
/*
3 rows from InvoiceLine table:
InvoiceLineId InvoiceId TrackId UnitPrice Quantity
1 1 2 0.99 1
2 1 4 0.99 1
3 2 6 0.99 1
*/
CREATE TABLE "MediaType" (
"MediaTypeId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("MediaTypeId")
)
/*
3 rows from MediaType table:
MediaTypeId Name
1 MPEG audio file
2 Protected AAC audio file
3 Protected MPEG-4 video file
*/
CREATE TABLE "Playlist" (
"PlaylistId" INTEGER NOT NULL,
"Name" NVARCHAR(120),
PRIMARY KEY ("PlaylistId")
)
/*
3 rows from Playlist table:
PlaylistId Name
1 Music
2 Movies
3 TV Shows
*/
CREATE TABLE "PlaylistTrack" (
"PlaylistId" INTEGER NOT NULL,
"TrackId" INTEGER NOT NULL,
PRIMARY KEY ("PlaylistId", "TrackId"),
FOREIGN KEY("TrackId") REFERENCES "Track" ("TrackId"),
FOREIGN KEY("PlaylistId") REFERENCES "Playlist" ("PlaylistId")
)
/*
3 rows from PlaylistTrack table:
PlaylistId TrackId
1 3402
1 3389
1 3390
*/
CREATE TABLE "Track" (
"TrackId" INTEGER NOT NULL,
"Name" NVARCHAR(200) NOT NULL,
"AlbumId" INTEGER,
"MediaTypeId" INTEGER NOT NULL,
"GenreId" INTEGER,
"Composer" NVARCHAR(220),
"Milliseconds" INTEGER NOT NULL,
"Bytes" INTEGER,
"UnitPrice" NUMERIC(10, 2) NOT NULL,
PRIMARY KEY ("TrackId"),
FOREIGN KEY("MediaTypeId") REFERENCES "MediaType" ("MediaTypeId"),
FOREIGN KEY("GenreId") REFERENCES "Genre" ("GenreId"),
FOREIGN KEY("AlbumId") REFERENCES "Album" ("AlbumId")
)
/*
3 rows from Track table:
TrackId Name AlbumId MediaTypeId GenreId Composer Milliseconds Bytes UnitPrice
1 For Those About To Rock (We Salute You) 1 1 1 Angus Young, Malcolm Young, Brian Johnson 343719 11170334 0.99
2 Balls to the Wall 2 2 1 U. Dirkschneider, W. Hoffmann, H. Frank, P. Baltes, S. Kaufmann, G. Hoffmann 342562 5510424 0.99
3 Fast As a Shark 3 2 1 F. Baltes, S. Kaufman, U. Dirkscneider & W. Hoffman 230619 3990994 0.99
*/
```
We can pass this context into the system instruction (preamble) and re-run a query to see how it performs.
```python PYTHON
preamble="""## Task And Context
You use your advanced complex reasoning capabilities to help people by answering their questions and other requests interactively. You will be asked a very wide array of requests on all kinds of topics. You will be equipped with a wide range of search engines or similar tools to help you, which you use to research your answer. You may need to use multiple tools in parallel or sequentially to complete your task. You should focus on serving the user's needs as best you can, which will be wide-ranging.
## Style Guide
Unless the user asks for a different style of answer, you should answer in full sentences, using proper grammar and spelling.
## Additional Information
You are an expert who answers the user's question by creating SQL queries and executing them.
You are equipped with a number of relevant SQL tools.
Here is information about the database:
{schema_info}
""".format(schema_info=context)
```
```python PYTHON
output=agent_executor.invoke({
"input": 'provide the name of the best customer? The customer who has spent the most money is the best.',
"preamble": preamble
})
```
```txt title="Output"
[1m> Entering new AgentExecutor chain...[0m
[32;1m[1;3m
I will write a SQL query to find the customer who has spent the most money.
{'tool_name': 'sql_db_query', 'parameters': {'query': 'SELECT c.FirstName, c.LastName, SUM(i.Total) AS TotalSpent FROM Customer c JOIN Invoice i ON c.CustomerId = i.CustomerId GROUP BY c.CustomerId ORDER BY TotalSpent DESC LIMIT 1;'}}
[0m[36;1m[1;3m[('Helena', 'Holý', 49.62)][0m[32;1m[1;3mRelevant Documents: 0
Cited Documents: 0
Answer: The customer who has spent the most money is Helena Holý.
Grounded answer: The customer who has spent the most money is Helena Holý.[0m
[1m> Finished chain.[0m
```
```python PYTHON
print(output['output'])
```
```txt title="Output"
The customer who has spent the most money is Helena Holý.
```
We can see that passing that additional context actually avoids the error seen in the previous section and gets to the answer in one tool call. This works as long as you have a few tables and a few columns per table. We will follow up with more techniques to improve stability and scalability in future work.