Defining Parameters in YAML and in the REST API

Parameters in pipeline YAML are the init parameters you can specify for the components, either when creating a pipeline in deepset Cloud or when uploading a ready-made YAML through a REST API endpoint.

Runtime parameters in the REST API are request body parameters you define when making a request with the Search REST API endpoint. You can configure these parameters for all the components in the pipeline, or you can target specific components. See the reference documentation for a particular component in this section to check the parameters you can modify. If no REST API parameters are listed for a component, it means you can't define any runtime parameters for it.

Passing YAML Parameters

You customize these parameters in the components section of the YAML, in the init_parameters object for a particular component, like this:

components:
  componentName:
    type: componentType
    init_parameters:
      param1: value1
      param2: value2

The name is a custom name you give to a pipeline component. The type is the path to the component, you can check it on the component's documentation page.

Examples

This example shows how to customize OpenSearchEmbeddingRetriever in the YAML:

embedding_retriever: # Selects the most similar documents from the document store
    type: haystack_integrations.components.retrievers.opensearch.embedding_retriever.OpenSearchEmbeddingRetriever
    init_parameters:
      document_store:
        init_parameters:
          use_ssl: True
          verify_certs: False
          http_auth:
            - "${OPENSEARCH_USER}"
            - "${OPENSEARCH_PASSWORD}"
        type: haystack_integrations.document_stores.opensearch.document_store.OpenSearchDocumentStore
      top_k: 20 # The number of results to return

Passing Runtime Parameters to the REST API

You can pass runtime parameters to influence the behavior of nodes in a pipeline when it's executed. To do this, pass the name of the node whose parameter you want to change together with the dictionary of the parameters, like this:

payload = {
    "init_parameters": {
        "node_name":{
          "param1": value1,
          "param2": value2
        },
    },
}

You can also do this for multiple nodes at once. Simply pass the names of the nodes and the parameters you want to modify:

payload = {
    "params": {
        "node1_name":{
          "param1": value1,
          "param2": value2
        },
        "node2_name":{
          "param": value
        },
        "node3_name":{
          "param3": value3
        },
    },
}

To pass a parameter to all nodes in a pipeline, use the parameter name and value without listing node names:

payload = {
    "params": {
        "param": value,
        "param2": value2
    }
}

The parameters are applied to all nodes that accept them and are ignored for all other nodes.

Examples

Customizing a Single Node

In this example, we're changing the EmbeddingRetriever's top_k parameter that determines the number of documents the retriever fetches from the document store:

payload = {
    "debug": True,
    "params": {
        "EmbeddingRetriever":{
          "top_k": 2
        },
    },
    "queries": ["Where does Horned sungem live?"]
}

Customizing Multiple Nodes

This example passes different parameters to the EmbeddingRetriever, Reranker, and PromptNode nodes:

payload = {
    "debug": True,
    "params": {
        "EmbeddingRetriever":{
          "top_k": 10
        },
        "Reranker":{
          "top_k": 4
        },
        "PromptNode":{
          "max_tokens": 500
        },
    },
    "queries": ["Where does Horned sungem live?"]
}