# Database Tool
This tool connects to a database (using SQLAlchemy under the hood) and allows an Agent to query the database and get information about the tables.
## Usage
This tool has more extensive example usage documented in a Jupyter notebook [here](https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/tools/llama-index-tools-database/examples/database.ipynb).
Here's an example usage of the DatabaseToolSpec.
```python
from llama_index.tools.database import DatabaseToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI
db_tools = DatabaseToolSpec(
scheme="postgresql", # Database Scheme
host="localhost", # Database Host
port="5432", # Database Port
user="postgres", # Database User
password="FakeExamplePassword", # Database Password
dbname="postgres", # Database Name
)
agent = FunctionAgent(
tools=db_tools.to_tool_list(),
llm=OpenAI(model="gpt-4.1"),
)
print(await agent.run("What tables does this database contain"))
print(await agent.run("Describe the first table"))
print(await agent.run("Retrieve the first row of that table"))
```
The tools available are:
`list_tables`: A tool to list the tables in the database schema
`describe_tables`: A tool to describe the schema of a table
`load_data`: A tool that accepts an SQL query and returns the result
This loader is designed to be used as a way to load data as a Tool in a Agent.
Raw data
{
"_id": null,
"home_page": null,
"name": "llama-index-tools-database",
"maintainer": "ajhofmann",
"docs_url": null,
"requires_python": "<4.0,>=3.9",
"maintainer_email": null,
"keywords": "aws rds, postgres, snowflake, sql",
"author": null,
"author_email": "Your Name <you@example.com>",
"download_url": "https://files.pythonhosted.org/packages/f0/89/7689dd218ecf927616f0c21d5b79fbc4bc2ddb4c91d05deb41827694f23b/llama_index_tools_database-0.4.0.tar.gz",
"platform": null,
"description": "# Database Tool\n\nThis tool connects to a database (using SQLAlchemy under the hood) and allows an Agent to query the database and get information about the tables.\n\n## Usage\n\nThis tool has more extensive example usage documented in a Jupyter notebook [here](https://github.com/run-llama/llama_index/blob/main/llama-index-integrations/tools/llama-index-tools-database/examples/database.ipynb).\n\nHere's an example usage of the DatabaseToolSpec.\n\n```python\nfrom llama_index.tools.database import DatabaseToolSpec\nfrom llama_index.core.agent.workflow import FunctionAgent\nfrom llama_index.llms.openai import OpenAI\n\ndb_tools = DatabaseToolSpec(\n scheme=\"postgresql\", # Database Scheme\n host=\"localhost\", # Database Host\n port=\"5432\", # Database Port\n user=\"postgres\", # Database User\n password=\"FakeExamplePassword\", # Database Password\n dbname=\"postgres\", # Database Name\n)\nagent = FunctionAgent(\n tools=db_tools.to_tool_list(),\n llm=OpenAI(model=\"gpt-4.1\"),\n)\n\nprint(await agent.run(\"What tables does this database contain\"))\nprint(await agent.run(\"Describe the first table\"))\nprint(await agent.run(\"Retrieve the first row of that table\"))\n```\n\nThe tools available are:\n\n`list_tables`: A tool to list the tables in the database schema\n`describe_tables`: A tool to describe the schema of a table\n`load_data`: A tool that accepts an SQL query and returns the result\n\nThis loader is designed to be used as a way to load data as a Tool in a Agent.\n",
"bugtrack_url": null,
"license": null,
"summary": "llama-index tools database integration",
"version": "0.4.0",
"project_urls": null,
"split_keywords": [
"aws rds",
" postgres",
" snowflake",
" sql"
],
"urls": [
{
"comment_text": null,
"digests": {
"blake2b_256": "ca36967075e153a30a3886d2ebf54110964180a4eccdb07379fccc798dec36c4",
"md5": "bda8daf5a335ab04b5a420e9f37de470",
"sha256": "c31ac502f9d639960d125b632b5aef1f39e49104f174bc26fd3b3fd3544ceaf9"
},
"downloads": -1,
"filename": "llama_index_tools_database-0.4.0-py3-none-any.whl",
"has_sig": false,
"md5_digest": "bda8daf5a335ab04b5a420e9f37de470",
"packagetype": "bdist_wheel",
"python_version": "py3",
"requires_python": "<4.0,>=3.9",
"size": 4529,
"upload_time": "2025-07-30T20:50:24",
"upload_time_iso_8601": "2025-07-30T20:50:24.592594Z",
"url": "https://files.pythonhosted.org/packages/ca/36/967075e153a30a3886d2ebf54110964180a4eccdb07379fccc798dec36c4/llama_index_tools_database-0.4.0-py3-none-any.whl",
"yanked": false,
"yanked_reason": null
},
{
"comment_text": null,
"digests": {
"blake2b_256": "f0897689dd218ecf927616f0c21d5b79fbc4bc2ddb4c91d05deb41827694f23b",
"md5": "523e588ae9810c2db350f3e1ba8f2a4d",
"sha256": "932c13fc0451e05ff2b5166e6c99414f89409f6df490eb439bb3efd46d64361e"
},
"downloads": -1,
"filename": "llama_index_tools_database-0.4.0.tar.gz",
"has_sig": false,
"md5_digest": "523e588ae9810c2db350f3e1ba8f2a4d",
"packagetype": "sdist",
"python_version": "source",
"requires_python": "<4.0,>=3.9",
"size": 4891,
"upload_time": "2025-07-30T20:50:25",
"upload_time_iso_8601": "2025-07-30T20:50:25.328631Z",
"url": "https://files.pythonhosted.org/packages/f0/89/7689dd218ecf927616f0c21d5b79fbc4bc2ddb4c91d05deb41827694f23b/llama_index_tools_database-0.4.0.tar.gz",
"yanked": false,
"yanked_reason": null
}
],
"upload_time": "2025-07-30 20:50:25",
"github": false,
"gitlab": false,
"bitbucket": false,
"codeberg": false,
"lcname": "llama-index-tools-database"
}
JSON