OracleKeywordRetriever

Retrieve documents from an OracleDocumentStore using keyword-based search. Use this component in query pipelines that rely on lexical matching using Oracle Database 23ai's DBMS_SEARCH index.

Key Features

• Performs keyword search using Oracle's DBMS_SEARCH full-text index with CONTAINS queries.
• Ranks results by relevance using Oracle's built-in SCORE() function.
• Supports both thin (direct TCP) and thick (wallet/ADB-S) Oracle connection modes.
• Configurable filter policy to merge or replace filters at query time.
• Requires Oracle Database 23ai or later with DBMS_SEARCH enabled.

Configuration

Add Workspace-Level Integration

1. Click your profile icon and choose Settings.
2. Go to Workspace>Integrations.
3. Find the provider you want to connect and click Connect next to them.
4. Enter the API key and any other required details.
5. Click Connect. You can use this integration in pipelines and indexes in the current workspace.

Add Organization-Level Integration

1. Click your profile icon and choose Settings.
2. Go to Organization>Integrations.
3. Find the provider you want to connect and click Connect next to them.
4. Enter the API key and any other required details.
5. Click Connect. You can use this integration in pipelines and indexes in all workspaces in the current organization.

1. Set environment variables for your Oracle credentials: ORACLE_USER, ORACLE_PASSWORD, and ORACLE_DSN.
2. Configure an OracleDocumentStore in your pipeline. The DBMS_SEARCH keyword index is created automatically when create_table_if_not_exists is True (the default). For pre-existing tables, call create_keyword_index() manually.
3. Drag the OracleKeywordRetriever component onto the canvas from the Component Library.
4. Connect the retriever output to downstream components such as PromptBuilder.

Connections

OracleKeywordRetriever receives a query string as input. It outputs a list of Document objects ranked by keyword relevance that you can connect to PromptBuilder or other downstream components.

Source Code

To check this component's source code, open keyword_retriever.py in the Haystack Core Integrations repository.

Usage Examples

Basic Configuration

  OracleKeywordRetriever:
    type: haystack_integrations.components.retrievers.oracle.keyword_retriever.OracleKeywordRetriever
    init_parameters:
      document_store: OracleDocumentStore
      top_k: 5

Using the Component in a Pipeline

# haystack-pipeline
components:
  document_store:
    type: haystack_integrations.document_stores.oracle.document_store.OracleDocumentStore
    init_parameters:
      connection_config:
        user:
          type: haystack.utils.Secret
          init_parameters:
            env_vars: ["ORACLE_USER"]
        password:
          type: haystack.utils.Secret
          init_parameters:
            env_vars: ["ORACLE_PASSWORD"]
        dsn:
          type: haystack.utils.Secret
          init_parameters:
            env_vars: ["ORACLE_DSN"]
      embedding_dim: 1536

  retriever:
    type: haystack_integrations.components.retrievers.oracle.keyword_retriever.OracleKeywordRetriever
    init_parameters:
      document_store: document_store
      top_k: 5

inputs:
  query:
  - retriever.query

outputs:
  documents: retriever.documents

Parameters

Inputs

Parameter	Type	Description
query	str	The keyword query string to search for.
filters	Optional[Dict[str, Any]]	Filters to apply when retrieving documents.
top_k	Optional[int]	The maximum number of documents to retrieve. Overrides the init-time value.

Outputs

Parameter	Type	Description
documents	List[Document]	A list of documents ranked by keyword relevance from the document store.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
document_store	OracleDocumentStore		The Oracle document store to retrieve documents from.
filters	Optional[Dict[str, Any]]	None	Default filters to apply when retrieving documents.
top_k	int	10	The maximum number of documents to retrieve.
filter_policy	FilterPolicy	FilterPolicy.REPLACE	How to handle filters passed at query time. REPLACE replaces init-time filters; MERGE combines them.

Run Method Parameters

These are the parameters you can configure for the component's run() method. This means you can pass these parameters at query time through the API, in Playground, or when running a job. For details, see Modify Pipeline Parameters at Query Time.

Parameter	Type	Default	Description
query	str		The keyword query string.
filters	Optional[Dict[str, Any]]	None	Runtime filters to apply.
top_k	Optional[int]	None	Maximum number of documents to retrieve. Overrides the init-time value.

Related Information

• OracleEmbeddingRetriever
• Pipeline Components