Oracle

import Icon from "@site/src/components/icon"; import PartialParams from '@site/docs/_partial-hidden-params.mdx'; import PartialConditionalParams from '@site/docs/_partial-conditional-params.mdx'; import PartialVectorSearchResults from '@site/docs/_partial-vector-search-results.mdx'; import PartialVectorStoreInstance from '@site/docs/_partial-vector-store-instance.mdx';

<Icon name="Blocks" aria-hidden="true" /> 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 reachable from the Langflow server/runtime.
• The python-oracledb connection values, such as user, password, DSN, and optional wallet settings. See the official guide: https://python-oracledb.readthedocs.io/en/latest/user_guide/connection_handling.html

---

Oracle Vector Store (OracleVectorStoreComponent)

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

<details> <summary>About vector store instances</summary> <PartialVectorStoreInstance /> </details> <PartialVectorSearchResults />

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

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.

<PartialParams /> <PartialConditionalParams />

Name	Type	Description
user	Secret	Optional. Oracle database user.
password	Secret	Optional. Oracle database password.
dsn	Secret	Required. Oracle DSN or connect string.
wallet_password	Secret	Optional. Wallet password for wallet-based connections (advanced).
connection_params	Dict	Optional non-secret python-oracledb connection options, such as config_dir and wallet_location.
table_name	String	Required. Table name used by the vector store.
ingest_data	Data	Optional. Data to ingest (converted to Document).
embedding	Embeddings	Required. Embedding function/provider to use.
search_query	String	Optional. Query text for search.
number_of_results	Integer	Optional. Number of results to return (default: 4).
search_type	Dropdown	Optional. Search mode to use. Supported values are Similarity and MMR (Max Marginal Relevance) (default: Similarity).
distance_strategy	Dropdown	Optional. One of EUCLIDEAN, DOT, COSINE (default: COSINE).
create_index	Boolean	Optional. If true, will create a vector index after setup (default: true).
index_params	Dict	Optional. Parameters for index creation (e.g., idx_name, idx_type, etc.).
mutate_on_duplicate	Boolean	Optional. When supported by your langchain_oracledb version, control mutation behavior on duplicate inserts.

---

Oracle Doc Loader (OracleDocLoaderComponent)

The OracleDocLoaderComponent reads documents from Oracle Database using OracleDocLoader from langchain_oracledb.document_loaders. It returns a list of Data objects converted from Document.

Parameters

Name	Type	Description
user	Secret	Optional. Oracle database user.
password	Secret	Optional. Oracle database password.
dsn	Secret	Required. Oracle DSN or connect string.
wallet_password	Secret	Optional. Wallet password for wallet-based connections (advanced).
connection_params	Dict	Optional non-secret python-oracledb connection options, such as config_dir and wallet_location.
params	Dict	Required. Loader-specific options passed to OracleDocLoader (for example, owner, tablename, colname, etc.). See Oracle AI docs.

Check Oracle AI Vector Search Document Processing for more information.

Oracle Autonomous Database Loader (OracleAutonomousDatabaseLoaderComponent)

OracleAutonomousDatabaseLoaderComponent loads data from Oracle Autonomous Database (ADB) by running a SQL query and converting each row into a Document, then into Data.

Parameters

Name	Type	Description
query	String	Required. SQL query to execute. Each row in the result becomes a document.
user	Secret	Optional. Oracle database user.
password	Secret	Optional. Oracle database password.
dsn	Secret	Required. Oracle DSN or connect string.
wallet_password	Secret	Optional. Wallet password for wallet-based connections (advanced).
connection_params	Dict	Optional non-secret Oracle options such as schema, config_dir, and wallet_location.
metadata	String	Optional. Comma-separated list of result columns to copy into document metadata.
parameter	Dict	Optional. Bind parameters for the SQL query.

:::note This component is designed for Oracle ADB environments. Ensure your wallet and TLS configuration are set up if required by your environment, for example with config_dir and wallet_location in connection_params, and wallet_password in the dedicated secret field. :::

Check Oracle Autonomous Database for more information.

---

Oracle Embeddings (OracleEmbeddingsComponent)

The OracleEmbeddingsComponent builds 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.

Parameters

Name	Type	Description
user	Secret	Optional. Oracle database user.
password	Secret	Optional. Oracle database password.
dsn	Secret	Required. Oracle DSN or connect string.
wallet_password	Secret	Optional. Wallet password for wallet-based connections (advanced).
connection_params	Dict	Optional non-secret python-oracledb connection options, such as config_dir and wallet_location.
embedding_params	Dict	Optional. Embedding parameters passed to OracleEmbeddings (for example, provider, model, etc.). See the Oracle embedding docs for accepted values.
proxy	Secret	Optional. HTTP proxy to reach the embedding provider (advanced).