DeepsetAnswerBuilder

Use DeepsetAnswerBuilder combined with a Generator instructed to produce references to its replies to convert these replies into a format you can visualize in deepset AI Platform

Basic Information

• Type: deepset_cloud_custom_nodes.augmenters.deepset_answer_builder.DeepsetAnswerBuilder
• Components it can connect with:
  • Rankers: It can receive documents from Rankers and add them to the generated answers.
  • Generators: It receives replies from a Generator and transforms them into GeneratedAnswer objects.

Inputs

Parameter	Type	Default	Description
query	str		The query used in the prompts for the Generator. If DeepsetAnswerBuilder doesn't receive the query from a component it's connected to, you must list it in the inputs section of the pipeline YAML under query. You can see an example in the Usage Examples section below.
replies	List[str]		The output of the Generator.
meta	Optional[List[Dict[str, Any]]]	None	The metadata returned by the Generator. If not specified, the generated answer contains no metadata.
documents	Optional[List[Document]]	None	The documents used as input to the Generator. If documents are specified, they are added to the Answer objects. If both documents and reference_pattern are specified, the documents referenced in the Generator's output are extracted from the input documents and added to the Answer objects.
pattern	Optional[str]	None	The regular expression pattern to use to extract the answer text from the generator output. If not specified, the whole string is used as the answer. The regular expression can have at most one capture group. If a capture group is present, the text matched by the capture group is used as the answer. If no capture group is present, the whole match is used as the answer. Examples: [^\n]+$ finds "this is an answer" in a string "this is an argument.\nthis is an answer". Answer: (.*) finds "this is an answer" in a string "this is an argument. Answer: this is an answer".
reference_pattern	Optional[str]	None	The regular expression pattern to use for parsing the document references. It's assumed that references are specified as indices of the input documents and that indices start at 1. Example: \[(\d+)\] finds "1" in a string "this is an answer[1]". If not specified, no parsing is done, and all documents are referenced. You can use the following shortcuts: - "acm": \[(?:(\d+),?\s*)+\] finds "1" and "2" in a string "this is an answer[1, 2]".
prompt	Optional[str]	None	The prompt used in the Generator. If specified, it is added to the metadata of the Answer objects.

Outputs

Parameter	Type	Default	Description
answers	List[GeneratedAnswer]		A dictionary with the following keys: - answers: The answers obtained from the output of the Generator

Overview

DeepsetAnswerBuilder takes a query and the replies from a Generator as input and turns them into GeneratedAnswer objects. Optionally, Optionally, you can configure it to enhance the generated answer with documents and metadata from the Generator.

DeepsetAnswerBuilder is used in RAG pipelines to enhance generated responses with references. You use it after a Generator instructed to produce references. DeepsetAnswerBuilder then takes the replies from such Generator as input and adds the references to the answer's _references metadata field so that they can be displayed in deepset's user interface.

The difference between ReferencePredictor and DeepsetAnswerBuilder is that ReferencePredictor uses a dedicated model that filters for documents' ID to create references, while DeepsetAnswerBuilder is used with an LLM (through a Generator) instructed to create the references. If reference_pattern is specified, references are parsed and added to _references in the metadata of the GeneratedAnswer objects.

Usage Example

Inititating the Component

This is how you initiate DeepsetAnswerBuilder:

components:
  DeepsetAnswerBuilder:
    type: augmenters.deepset_answer_builder.DeepsetAnswerBuilder
    init_parameters:

Using the Component in a Pipeline

In this example, DeepsetAnswerBuilder receives documents from the Ranker so that it can attach these documents to the generated answers, and it receives replies from the Generator so that it can convert them into the GeneratedAnswer objects with references that the deepset interface can display.

query_yaml: |
  components:
  ...
    ranker:
      type: haystack.components.rankers.transformers_similarity.TransformersSimilarityRanker
      init_parameters:
        model: "svalabs/cross-electra-ms-marco-german-uncased"
        top_k: 8
        device: null
        model_kwargs:
          torch_dtype: "torch.float16"
          
    generator:
      type: haystack.components.generators.openai.OpenAIGenerator
      init_parameters:
        api_key: {"type": "env_var", "env_vars": ["OPENAI_API_KEY"], "strict": False}
        model: "gpt-4-turbo-preview"
        generation_kwargs:
          max_tokens: 400
          temperature: 0.0
          seed: 0
          
    answer_builder:
      type: deepset_cloud_custom_nodes.augmenters.deepset_answer_builder.DeepsetAnswerBuilder
      init_parameters: 
        reference_pattern: acm
      ...
      
  connections:  # Defines how the components are connected
  ...
  - sender: ranker.documents
    receiver: answer_builder.documents # DeepsetAnswerBuilder receives documents from ranker
  - sender: generator.replies
    receiver: answer_builder.replies # DeepsetAnswerBuilder receives replies from the generator
    ...
    
  inputs:
   query:
   ..
   - "ranker.query"
   - "answer_builder.query" # We're listing AnswerBuilder here because it needs "query" as input and it's not
														# getting it from any other component it's connected to. This means AnswerBuilder
														# will receive "query" as input from the pipeline.
   ...
   
   outputs:
    answers: "answer_builder.answers" # This means we want AnswerBuilder's answers to be the output of the pipeline
  

Parameters

Init Parameters

These are the parameters you can configure in Pipeline Builder:

Parameter	Type	Default	Description
pattern	Optional[str]	None	The regular expression pattern to use to extract the answer text from the generator output. If not specified, the whole string is used as the answer. The regular expression can have at most one capture group. If a capture group is present, the text matched by the capture group is used as the answer. If no capture group is present, the whole match is used as the answer. Examples: [^\n]+$ finds "this is an answer" in a string "this is an argument.\nthis is an answer". Answer: (.*) finds "this is an answer" in a string "this is an argument. Answer: this is an answer".
reference_pattern	Optional[str]	None	The regular expression pattern to use for parsing the document references. We assume that references are specified as indices of the input documents and that indices start at 1. Example: \[(\d+)\] finds "1" in a string "this is an answer[1]". If not specified, no parsing is done, and all documents are referenced. You can use the following shortcuts: - "acm": \[(?:(\d+),?\s*)+\] finds "1" and "2" in a string "this is an answer[1, 2]".
extract_xml_tags	Optional[List[str]]	None	A list of XML tags to extract content

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 query used in the prompts for the Generator.
replies	List[str]		The output of the Generator.
meta	Optional[List[Dict[str, Any]]]	None	The metadata returned by the Generator. If not specified, the generated answer will contain no metadata.
documents	Optional[List[Document]]	None	The documents used as input to the Generator. If documents are specified, they are added to the Answer objects. If both documents and reference_pattern are specified, the documents referenced in the Generator output are extracted from the input documents and added to the Answer objects.
pattern	Optional[str]	None	The regular expression pattern to use to extract the answer text from the generator output. If not specified, the whole string is used as the answer. The regular expression can have at most one capture group. If a capture group is present, the text matched by the capture group is used as the answer. If no capture group is present, the whole match is used as the answer. Examples: [^\n]+$ finds "this is an answer" in a string "this is an argument.\nthis is an answer". Answer: (.*) finds "this is an answer" in a string "this is an argument. Answer: this is an answer".
reference_pattern	Optional[str]	None	The regular expression pattern to use for parsing the document references. We assume that references are specified as indices of the input documents and that indices start at 1. Example: \[(\d+)\] finds "1" in a string "this is an answer[1]". If not specified, no parsing is done, and all documents are referenced. You can use the following shortcuts: - "acm": \[(?:(\d+),?\s*)+\] finds "1" and "2" in a string "this is an answer[1, 2]".
prompt	Optional[str]	None	The prompt used in the Generator. If specified, it is added to the metadata of the Answer objects.