AzureDocumentDBFullTextRetriever

Retrieve documents from an AzureDocumentDBDocumentStore using BM25 full-text search. This component is useful for keyword-based retrieval pipelines that rely on lexical matching rather than dense vector similarity. Azure DocumentDB is Azure Cosmos DB for MongoDB (vCore), so this component is also relevant if you're searching for "Cosmos DB" or "vCore".

note

Full-text search in Azure DocumentDB is currently a gated preview and must be enabled on the cluster before using this retriever. You must also configure a full_text_search_index on the document store.

Key Features

• Performs BM25 full-text search using Azure DocumentDB's gated-preview text search capability.
• Accepts a single query string or a list of query strings.
• Supports optional fuzzy matching with configurable maxEdits for typo tolerance.
• Configurable filter policy to merge or replace filters at query time.
• Supports both synchronous and asynchronous execution.

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. Make sure full-text search is enabled on your Azure DocumentDB cluster (gated preview).
2. Set the AZURE_DOCUMENTDB_CLUSTER_NAME environment variable with your cluster name, or provide a mongo_connection_string for local development.
3. Configure an AzureDocumentDBDocumentStore with a full_text_search_index pointing to your text search index.
4. Drag the AzureDocumentDBFullTextRetriever component onto the canvas from the Component Library.
5. Connect the retriever output to downstream components such as PromptBuilder.

Connections

AzureDocumentDBFullTextRetriever receives a query string (or list of strings) as input. It outputs a list of Document objects ranked by BM25 relevance that you can connect to PromptBuilder or other downstream components.

Source Code

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

Usage Examples

Basic Configuration

  AzureDocumentDBFullTextRetriever:
    type: haystack_integrations.components.retrievers.azure_documentdb.full_text_retriever.AzureDocumentDBFullTextRetriever
    init_parameters:
      document_store: AzureDocumentDBDocumentStore
      top_k: 5

Using the Component in a Pipeline

# haystack-pipeline
components:
  document_store:
    type: haystack_integrations.document_stores.azure_documentdb.document_store.AzureDocumentDBDocumentStore
    init_parameters:
      database_name: haystack
      collection_name: documents
      full_text_search_index: haystack_fts_index

  retriever:
    type: haystack_integrations.components.retrievers.azure_documentdb.full_text_retriever.AzureDocumentDBFullTextRetriever
    init_parameters:
      document_store: document_store
      top_k: 5

inputs:
  query:
  - retriever.query

outputs:
  documents: retriever.documents

Parameters

Inputs

Parameter	Type	Description
query	str | List[str]	The keyword query string or list of strings to search for.
fuzzy	Optional[Dict[str, int]]	Azure DocumentDB fuzzy search options, for example {"maxEdits": 1} for typo tolerance.
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 BM25 relevance from the document store.

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
document_store	AzureDocumentDBDocumentStore		The Azure DocumentDB document store to retrieve documents from. Requires full_text_search_index to be set.
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 | List[str]		The keyword query string or list of strings.
fuzzy	Optional[Dict[str, int]]	None	Fuzzy search options such as {"maxEdits": 1}.
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

• AzureDocumentDBEmbeddingRetriever
• Pipeline Components