Oracle

tip

If you installed lfx directly (not as part of langflow), install the Oracle bundle separately:

1. Run uv pip install lfx-oracle.
2. Restart Langflow.
3. To confirm the bundle loaded, run lfx extension list.

If you installed Langflow with uv pip install langflow, these bundle components are already included.

For more information, see Install LFX with bundle components.

Bundles contain custom components that support specific third-party integrations with Langflow.

This page describes the components that are available in the Oracle bundle.

Prerequisites

• An Oracle Database and its python-oracledb connection values. For more information, see Connecting to Oracle Database.

Oracle Vector Store

The Oracle Vector Store component reads and writes to Oracle vector stores using an instance of OracleVS from langchain_oracledb. Use it to ingest documents and perform similarity and MMR searches.

About vector store instances

Because Langflow is based on LangChain, vector store components use an instance of LangChain vector store to drive the underlying read and write functions. These instances are provider-specific and configured according to the component's parameters, such as the connection string, index name, and schema.

In component code, this is often instantiated as vector_store, but some vector store components use a different name, such as the provider name.

Some LangChain classes don't expose all possible options as component parameters. Depending on the provider, these options might use default values or allow modification through environment variables, if they are supported in Langflow. For information about specific options, see the LangChain API reference and vector store provider's documentation.

If you use a vector store component to query your vector database, it produces search results that you can pass to downstream components in your flow as a list of JSON objects or a tabular Table. If both types are supported, you can set the format near the vector store component's output port in the visual editor.

tip

For a tutorial using a vector database in a flow, see Create a vector RAG chatbot.

Oracle Vector Store parameters

You can inspect a vector store component's parameters to learn more about the inputs it accepts, the features it supports, and how to configure it.

Some parameters are hidden by default in the visual editor. You can modify all component parameters through the component inspection panel that appears when you select a component.

Some parameters are conditional, and they are only available after you set other parameters or select specific options for other parameters. Conditional parameters may not be visible on the Controls pane until you set the required dependencies.

For more information, see the OracleVS documentation.

Name	Type	Description
user	SecretString	Input parameter. Oracle database user. Optional.
password	SecretString	Input parameter. Oracle database password. Optional.
dsn	SecretString	Input parameter. Oracle DSN or connect string. Required.
wallet_password	SecretString	Input parameter. Wallet password for wallet-based connections. Optional.
connection_params	Dictionary	Input parameter. Non-secret python-oracledb connection options, such as config_​dir and wallet_​location. Optional.
table_name	String	Input parameter. Table name used by the vector store. Required.
ingest_data	JSON	Input parameter. Data to ingest into the vector store. Optional.
search_query	String	Input parameter. Query text for similarity search. Optional.
embedding	Embeddings	Input parameter. Embedding function to use. Required.
number_of_results	Integer	Input parameter. Number of results to return in search. Default: 4.
search_type	String	Input parameter. Search mode to use. Options are Similarity (default) and MMR (Max Marginal Relevance).
distance_strategy	String	Input parameter. Distance calculation strategy. Options are EUCLIDEAN, DOT, and COSINE. Default: COSINE.
create_index	Boolean	Input parameter. If true, creates a vector index after setup. Default: true.
index_params	Dictionary	Input parameter. Parameters for index creation, such as idx_​name and idx_​type. Optional.
mutate_on_duplicate	Boolean	Input parameter. When supported by your langchain_​oracledb version, controls mutation behavior on duplicate inserts. Default: false.

Oracle Doc Loader

The Oracle Doc Loader component reads documents from Oracle Database using OracleDocLoader from langchain_oracledb.document_loaders. It returns a list of JSON objects converted from Document.

Oracle Doc Loader parameters

Some parameters are hidden by default in the visual editor. You can modify all component parameters through the component inspection panel that appears when you select a component.

For information, see the Oracle AI Vector Search Document Processing documentation.

Name	Type	Description
user	SecretString	Input parameter. Oracle database user. Optional.
password	SecretString	Input parameter. Oracle database password. Optional.
dsn	SecretString	Input parameter. Oracle DSN or connect string. Required.
wallet_password	SecretString	Input parameter. Wallet password for wallet-based connections. Optional.
connection_params	Dictionary	Input parameter. Non-secret python-oracledb connection options, such as config_​dir and wallet_​location. Optional.
params	Dictionary	Input parameter. Loader-specific options passed to OracleDocLoader, such as owner, tablename, and colname. Required.

Oracle Autonomous Database Loader

The Oracle Autonomous Database Loader component loads data from Oracle Autonomous Database (ADB) by running a SQL query and converting each row into a document, then into JSON.

Oracle Autonomous Database Loader parameters

Some parameters are hidden by default in the visual editor. You can modify all component parameters through the component inspection panel that appears when you select a component.

For more information, see the Oracle Autonomous Database documentation.

Name	Type	Description
query	String	Input parameter. SQL query to execute. Each row in the result becomes a document. Required.
user	SecretString	Input parameter. Oracle database user. Optional.
password	SecretString	Input parameter. Oracle database password. Optional.
dsn	SecretString	Input parameter. Oracle DSN or connect string. Required.
wallet_password	SecretString	Input parameter. Wallet password for wallet-based connections. Optional.
connection_params	Dictionary	Input parameter. Non-secret Oracle options such as schema, config_​dir, and wallet_​location. Optional.
metadata	String	Input parameter. Comma-separated list of result columns to copy into document metadata. Optional.
parameter	Dictionary	Input parameter. Bind parameters for the SQL query. Optional.

Oracle Embeddings

The Oracle Embeddings component generates embeddings using Oracle AI Vector Search via langchain_oracledb.OracleEmbeddings. Use this component to create an embeddings function for the vector store or other downstream components.

For more information, see Embedding model components.

Oracle Embeddings parameters

Some parameters are hidden by default in the visual editor. You can modify all component parameters through the component inspection panel that appears when you select a component.

For more information, see the Oracle embedding documentation.

Name	Type	Description
user	SecretString	Input parameter. Oracle database user. Optional.
password	SecretString	Input parameter. Oracle database password. Optional.
dsn	SecretString	Input parameter. Oracle DSN or connect string. Required.
wallet_password	SecretString	Input parameter. Wallet password for wallet-based connections. Optional.
connection_params	Dictionary	Input parameter. Non-secret python-oracledb connection options, such as config_​dir and wallet_​location. Optional.
embedding_params	Dictionary	Input parameter. Embedding parameters passed to OracleEmbeddings, such as provider and model. Optional.
proxy	SecretString	Input parameter. HTTP proxy to reach the embedding provider. Optional.