> ## Documentation Index
> Fetch the complete documentation index at: https://docs.langchain.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Oracle autonomous database integration

> Integrate with the Oracle autonomous database document loader using LangChain Python.

Oracle Autonomous Database is a cloud database that uses machine learning to automate database tuning, security, backups, updates, and other routine management tasks traditionally performed by DBAs.

This notebook covers how to load documents from Oracle Autonomous Database.

## Prerequisites

A database that `python-oracledb`'s default `'Thin'` mode can connected to. This is true of Oracle Autonomous Database, see [`python-oracledb` Architecture](https://python-oracledb.readthedocs.io/en/latest/user_guide/introduction.html#architecture).

You'll need to install `langchain-oracledb` to use this integration.

The `python-oracledb` driver is installed automatically as a dependency of langchain-oracledb.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
# python -m pip install -U langchain-oracledb
```

## Instructions

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
from langchain_oracledb.document_loaders import OracleAutonomousDatabaseLoader
from settings import s
```

With mutual TLS authentication (mTLS), wallet\_location and wallet\_password parameters are required to create the connection. See python-oracledb documentation [Connecting to Oracle Cloud Autonomous Databases](https://python-oracledb.readthedocs.io/en/latest/user_guide/connection_handling.html#connecting-to-oracle-cloud-autonomous-databases).

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
SQL_QUERY = "select prod_id, time_id from sh.costs fetch first 5 rows only"

doc_loader_1 = OracleAutonomousDatabaseLoader(
    query=SQL_QUERY,
    user=s.USERNAME,
    password=s.PASSWORD,
    schema=s.SCHEMA,
    config_dir=s.CONFIG_DIR,
    wallet_location=s.WALLET_LOCATION,
    wallet_password=s.PASSWORD,
    dsn=s.DSN,
)
doc_1 = doc_loader_1.load()

doc_loader_2 = OracleAutonomousDatabaseLoader(
    query=SQL_QUERY,
    user=s.USERNAME,
    password=s.PASSWORD,
    schema=s.SCHEMA,
    dsn=s.DSN,
    wallet_location=s.WALLET_LOCATION,
    wallet_password=s.PASSWORD,
)
doc_2 = doc_loader_2.load()
```

With 1-way TLS authentication, only the database credentials and connection string are required to establish a connection. The example below also shows passing bind variable values with the argument `parameters`.

```python theme={"theme":{"light":"catppuccin-latte","dark":"catppuccin-mocha"}}
SQL_QUERY = "select channel_id, channel_desc from sh.channels where channel_desc = :1 fetch first 5 rows only"

doc_loader_3 = OracleAutonomousDatabaseLoader(
    query=SQL_QUERY,
    user=s.USERNAME,
    password=s.PASSWORD,
    schema=s.SCHEMA,
    config_dir=s.CONFIG_DIR,
    dsn=s.DSN,
    parameters=["Direct Sales"],
)
doc_3 = doc_loader_3.load()

doc_loader_4 = OracleAutonomousDatabaseLoader(
    query=SQL_QUERY,
    user=s.USERNAME,
    password=s.PASSWORD,
    schema=s.SCHEMA,
    dsn=s.DSN,
    parameters=["Direct Sales"],
)
doc_4 = doc_loader_4.load()
```

***

<div className="source-links">
  <Callout icon="terminal-2">
    [Connect these docs](/use-these-docs) to Claude, VSCode, and more via MCP for real-time answers.
  </Callout>

  <Callout icon="edit">
    [Edit this page on GitHub](https://github.com/langchain-ai/docs/edit/main/src/oss/python/integrations/document_loaders/oracleadb_loader.mdx) or [file an issue](https://github.com/langchain-ai/docs/issues/new/choose).
  </Callout>
</div>