Dynamiq Docs
  • Welcome to Dynamiq
  • Low-Code Builder
    • Chat
    • Basics
    • Connecting Nodes
    • Conditional Nodes and Multiple Outputs
    • Input and Output Transformers
    • Error Handling and Retries
    • LLM Nodes
    • Validator Nodes
    • RAG Nodes
      • Indexing Workflow
        • Pre-processing Nodes
        • Document Splitting
        • Document Embedders
        • Document Writers
      • Inference RAG workflow
        • Text embedders
        • Document retrievers
          • Complex retrievers
        • LLM Answer Generators
    • LLM Agents
      • Basics
      • Guide to Implementing LLM Agents: ReAct and Simple Agents
      • Guide to Agent Orchestration: Linear and Adaptive Orchestrators
      • Guide to Advanced Agent Orchestration: Graph Orchestrator
    • Audio and voice
    • Tools and External Integrations
    • Python Code in Workflows
    • Memory
    • Guardrails
  • Deployments
    • Workflows
      • Tracing Workflow Execution
    • LLMs
      • Fine-tuned Adapters
      • Supported Models
    • Vector Databases
  • Prompts
    • Prompt Playground
  • Connections
  • LLM Fine-tuning
    • Basics
    • Using Adapters
    • Preparing Data
    • Supported Models
    • Parameters Guide
  • Knowledge Bases
  • Evaluations
    • Metrics
      • LLM-as-a-Judge
      • Predefined metrics
        • Faithfulness
        • Context Precision
        • Context Recall
        • Factual Correctness
        • Answer Correctness
      • Python Code Metrics
    • Datasets
    • Evaluation Runs
    • Examples
      • Build Accurate vs. Inaccurate Workflows
  • Examples
    • Building a Search Assistant
      • Approach 1: Single Agent with a Defined Role
      • Approach 2: Adaptive Orchestrator with Multiple Agents
      • Approach 3: Custom Logic Pipeline with a Straightforward Workflow
    • Building a Code Assistant
  • Platform Settings
    • Access Keys
    • Organizations
    • Settings
    • Billing
  • On-premise Deployment
    • AWS
  • Support Center
Powered by GitBook
On this page
  • Available Retrievers
  • Knowledge Base Retriever
  • Configuration
  • Vector Store Retriever
  • Configuration
  • Usage Example
  • Input
  • Output
  1. Low-Code Builder
  2. RAG Nodes
  3. Inference RAG workflow
  4. Document retrievers

Complex retrievers

PreviousDocument retrieversNextLLM Answer Generators

Last updated 6 days ago

Complex retrievers are components that internally combine both an embedder and a retriever. This integrated structure allows them to handle query embedding and retrieval within a single node, eliminating the need for separate configuration or coordination between components. To use them, you simply need to pass the query—you don’t need to set up embedding or retrieval logic separately.

Available Retrievers

Dynamiq offers two custom complex retrievers, each combining an embedder and a retriever into a single node, but with different configuration logic:

Knowledge Base Retriever

To use this node, you must first create a knowledge base based on your configuration. The Knowledge Base Retriever relies on an existing and deployed knowledge base to retrieve relevant information. Therefore, at least one knowledge base must be created and available before this node can be used effectively.

Configuration

  • Name: Provide a name for the retriever.

  • Knowledge Base: Select a knowledge base to automatically generate the appropriate retrieval logic.

  • Max Documents: Set the maximum number of documents to retrieve.

  • Filters: Apply filters to refine search results.

  • Description: Short description of the node’s functionality.

  • Options:

    • Use hybrid search: Enables hybrid search.

      • Alpha: Adjusts the balance between keyword and vector search.

Vector Store Retriever

This node allows you to dynamically specify both the embedder and the retriever to suit your use case. It parses and applies all provided parameters through an internal manager, enabling flexible configuration without hardcoding. This design makes it easy to integrate custom retrieval logic tailored to your specific requirements.

Configuration

  • Name: Provide a name for the retriever.

  • Text Embedder: Choose an embedder to convert the query into vector form for retrieval.

  • Document Retriever: Choose a retriever to find and return relevant documents based on the embedded query.

  • Max Documents: Set the maximum number of documents to retrieve.

  • Filters: Apply filters to refine search results.

  • Description: Short description of the node’s functionality.

  • Options:

    • Use hybrid search: Enables hybrid search.

      • Alpha: Adjusts the balance between keyword and vector search.

Usage Example

The input and output structure is identical for both of these retrievers. Below is an example illustrating the expected format:

Input

  • query: A string containing the search query to execute.

Output

  • Content: content off all retrieved documents in string format

    • Example:

      Source 1
Content: Artificial Intelligence continues to evolve rapidly, with key 
developments in machine learning and natural language processing.

Source 2
Content: Advancements in Artificial Intelligence are accelerating, 
especially in areas like deep learning and language understanding, 
driving innovation across various industries.

  • Documents- list of retrieved documents