IBMDb2EmbeddingRetriever

Retrieve documents from an IBMDb2DocumentStore using IBM Db2's native vector search capabilities.

Embedding Models in Pipelines and Indexes

The embedding model you use to embed documents in your index must be the same as the embedding model you use to embed the query in your pipeline.

This means the embedders for your indexes and pipelines must match. For example, if you use CohereDocumentEmbedder to embed your documents, you should use CohereTextEmbedder with the same model to embed your queries.

Key Features

• Performs vector similarity search using IBM Db2's native VECTOR type and distance functions.
• Supports COSINE, EUCLIDEAN, and MANHATTAN distance metrics configured at the document store level.
• Configurable filter policy to merge or replace filters at query time.
• Works in Haystack pipelines after any text embedder component.

Configuration

1. First, configure an IBMDb2DocumentStore with your Db2 connection details.
2. Drag the IBMDb2EmbeddingRetriever component onto the canvas from the Component Library.
3. Connect a text embedder component to provide query_embedding as input.
4. On the General tab, configure the nested IBMDb2DocumentStore:
   • Set database and hostname for your Db2 server.
   • Set credentials as secrets called DB2_USERNAME and DB2_PASSWORD. For instructions, see Add Secrets.

Connections

IBMDb2EmbeddingRetriever receives a query_embedding (list of floats) from a text embedder. It outputs a list of Document objects you can connect to PromptBuilder or other downstream components.

Source Code

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

Usage Examples

Basic Configuration

  IBMDb2EmbeddingRetriever:
    type: haystack_integrations.components.retrievers.ibm_db.embedding_retriever.IBMDb2EmbeddingRetriever
    init_parameters:
      document_store:
        type: haystack_integrations.document_stores.ibm_db.document_store.IBMDb2DocumentStore
        init_parameters:
          database: mydb
          hostname: localhost
          username:
            type: env_var
            env_vars:
            - DB2_USERNAME
            strict: false
          password:
            type: env_var
            env_vars:
            - DB2_PASSWORD
            strict: false
          embedding_dim: 384
      top_k: 10

Using the Component in a Pipeline

# haystack-pipeline
components:
  text_embedder:
    type: haystack_integrations.components.embedders.sentence_transformers.SentenceTransformersTextEmbedder
    init_parameters:
      model: sentence-transformers/all-MiniLM-L6-v2

  document_store:
    type: haystack_integrations.document_stores.ibm_db.document_store.IBMDb2DocumentStore
    init_parameters:
      database: mydb
      hostname: db2.example.com
      port: 50000
      username:
        type: env_var
        env_vars:
        - DB2_USERNAME
        strict: false
      password:
        type: env_var
        env_vars:
        - DB2_PASSWORD
        strict: false
      embedding_dim: 384
      distance_metric: COSINE

  retriever:
    type: haystack_integrations.components.retrievers.ibm_db.embedding_retriever.IBMDb2EmbeddingRetriever
    init_parameters:
      document_store: document_store
      top_k: 5

connections:
- sender: text_embedder.embedding
  receiver: retriever.query_embedding

inputs:
  query:
  - text_embedder.text

outputs:
  documents: retriever.documents

Parameters

Inputs

Parameter	Type	Description
query_embedding	List[float]	The query embedding vector to search for similar documents.
filters	Optional[Dict[str, Any]]	Filters to apply at query time.
top_k	Optional[int]	Maximum number of documents to retrieve. Overrides the init-time value.

Outputs

Parameter	Type	Description
documents	List[Document]	A list of the most similar documents from the document store.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
document_store	IBMDb2DocumentStore		The IBM Db2 document store to retrieve documents from.
filters	Optional[Dict[str, Any]]	None	Default filters applied to all searches.
top_k	int	10	Maximum number of documents to return.
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_embedding	List[float]		The embedding vector to search with.
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

• Add Secrets
• Pipeline Components