Back to Langflow

Oracle

docs/docs/Components/bundles-oracle.mdx

1.11.0.dev447.5 KB
Original Source

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'; import { GraduatedBundleInstall } from '@site/docs/_partial-bundle-graduated-install.mdx';

<GraduatedBundleInstall packageName="oracle" />

<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

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.

<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. :::

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.

<PartialParams /> <PartialConditionalParams />

For more information, see the OracleVS documentation.

NameTypeDescription
userSecretStringInput parameter. Oracle database user. Optional.
passwordSecretStringInput parameter. Oracle database password. Optional.
dsnSecretStringInput parameter. Oracle DSN or connect string. Required.
wallet_passwordSecretStringInput parameter. Wallet password for wallet-based connections. Optional.
connection_paramsDictionaryInput parameter. Non-secret python-oracledb connection options, such as config_dir and wallet_location. Optional.
table_nameStringInput parameter. Table name used by the vector store. Required.
ingest_dataJSONInput parameter. Data to ingest into the vector store. Optional.
search_queryStringInput parameter. Query text for similarity search. Optional.
embeddingEmbeddingsInput parameter. Embedding function to use. Required.
number_of_resultsIntegerInput parameter. Number of results to return in search. Default: 4.
search_typeStringInput parameter. Search mode to use. Options are Similarity (default) and MMR (Max Marginal Relevance).
distance_strategyStringInput parameter. Distance calculation strategy. Options are EUCLIDEAN, DOT, and COSINE. Default: COSINE.
create_indexBooleanInput parameter. If true, creates a vector index after setup. Default: true.
index_paramsDictionaryInput parameter. Parameters for index creation, such as idx_name and idx_type. Optional.
mutate_on_duplicateBooleanInput 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

<PartialParams />

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

NameTypeDescription
userSecretStringInput parameter. Oracle database user. Optional.
passwordSecretStringInput parameter. Oracle database password. Optional.
dsnSecretStringInput parameter. Oracle DSN or connect string. Required.
wallet_passwordSecretStringInput parameter. Wallet password for wallet-based connections. Optional.
connection_paramsDictionaryInput parameter. Non-secret python-oracledb connection options, such as config_dir and wallet_location. Optional.
paramsDictionaryInput 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

<PartialParams />

For more information, see the Oracle Autonomous Database documentation.

NameTypeDescription
queryStringInput parameter. SQL query to execute. Each row in the result becomes a document. Required.
userSecretStringInput parameter. Oracle database user. Optional.
passwordSecretStringInput parameter. Oracle database password. Optional.
dsnSecretStringInput parameter. Oracle DSN or connect string. Required.
wallet_passwordSecretStringInput parameter. Wallet password for wallet-based connections. Optional.
connection_paramsDictionaryInput parameter. Non-secret Oracle options such as schema, config_dir, and wallet_location. Optional.
metadataStringInput parameter. Comma-separated list of result columns to copy into document metadata. Optional.
parameterDictionaryInput 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

<PartialParams />

For more information, see the Oracle embedding documentation.

NameTypeDescription
userSecretStringInput parameter. Oracle database user. Optional.
passwordSecretStringInput parameter. Oracle database password. Optional.
dsnSecretStringInput parameter. Oracle DSN or connect string. Required.
wallet_passwordSecretStringInput parameter. Wallet password for wallet-based connections. Optional.
connection_paramsDictionaryInput parameter. Non-secret python-oracledb connection options, such as config_dir and wallet_location. Optional.
embedding_paramsDictionaryInput parameter. Embedding parameters passed to OracleEmbeddings, such as provider and model. Optional.
proxySecretStringInput parameter. HTTP proxy to reach the embedding provider. Optional.