Overview
This node inserts vector embeddings and their associated documents into an Oracle Database table configured as a vector store. It is designed to work with AI-generated documents and embeddings, enabling efficient storage and retrieval of vectorized data within Oracle databases.
Common scenarios include:
- Storing document embeddings for semantic search or similarity queries.
- Managing vector data in Oracle DB for AI applications such as recommendation systems or natural language processing.
- Clearing existing data in the target table before inserting new vectors to maintain up-to-date datasets.
For example, you might use this node to insert embeddings generated from customer feedback documents into an Oracle database, then later perform similarity searches on that data.
Properties
| Name | Meaning |
|---|---|
| Table Name | The name of the Oracle database table where the vector embeddings and documents will be inserted. This property is required. |
| Clear Table | Whether to clear (delete) all existing data in the specified table before inserting the new data. Options: true or false. Default is false. |
Output
The node outputs an array of JSON objects representing the processed documents after insertion. Each output item corresponds to a serialized version of the input documents enriched or transformed during processing.
No binary data output is produced by this node.
Dependencies
- Requires an Oracle Database accessible via network with proper credentials.
- Needs an API key credential for authenticating to the Oracle Database.
- Uses the
oracledbNode.js package to connect and interact with the Oracle DB. - Relies on internal helper modules for processing documents and managing the vector store logic.
Troubleshooting
- Connection errors: Ensure the Oracle DB host, port, service name, username, and password are correctly configured. Network accessibility and firewall rules must allow connections.
- Table not found or permission denied: Verify that the specified table exists in the Oracle DB and that the user has sufficient privileges to read/write and optionally clear the table.
- Clearing table issues: If "Clear Table" is enabled but fails, check for locks or constraints preventing deletion.
- Input data mismatches: The node expects AI Document and AI Embedding inputs; ensure these are connected and properly formatted.
- Credential errors: Confirm that the provided API key credential is valid and has access rights to the Oracle DB.