Dynamiq Docs
  • Welcome to Dynamiq
  • Low-Code Builder
    • Extractors and Transformers
    • 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
    • IBM
    • Red Hat OpenShift
  • Support Center
Powered by GitBook
On this page
  • Why is the Inference Workflow Needed?
  • Important Steps in the Inference Workflow
  1. Low-Code Builder
  2. RAG Nodes

Inference RAG workflow

PreviousDocument WritersNextText embedders

Last updated 7 months ago

Why is the Inference Workflow Needed?

The inference workflow is a critical phase in building a Retrieval-Augmented Generation (RAG) application. It involves processing user queries to retrieve relevant information and generate responses. This phase ensures that the application can deliver accurate and contextually relevant answers by leveraging the indexed data and external knowledge sources.

Key Reasons for Inference

  • Real-Time Response: The inference workflow enables the application to process queries and generate responses in real-time, providing users with timely and relevant information.

  • Dynamic Interaction: By integrating external knowledge sources, the inference workflow allows the application to handle dynamic and informed interactions, essential for applications like customer support and knowledge management.

  • Enhanced Accuracy: By utilizing components like retrievers and generators, the inference workflow ensures that the responses are precise and contextually appropriate.

Important Steps in the Inference Workflow

  1. Input Node

    • Purpose: Captures the user's query or question.

    • Importance: Serves as the entry point for user interactions, ensuring that queries are accurately received and processed.

  2. Text Embedder

    • Purpose: Converts the input query into a vector representation.

    • Importance: Facilitates similarity searches by transforming text into a format that can be efficiently matched with relevant data.

  3. Documents Retriever

    • Purpose: Searches for relevant documents based on the query's vector.

    • Importance: Ensures that the most pertinent information is retrieved, forming the basis for generating accurate responses.

  4. LLM Answer Generator

    • Purpose: Uses the retrieved documents to generate a response.

    • Importance: Synthesizes information to create coherent and contextually relevant answers for the user.

  5. Output Node

    • Purpose: Displays the generated response to the user.

    • Importance: Provides a user-friendly interface for delivering responses, completing the interaction loop.

By following these steps, the inference workflow ensures that the RAG application can deliver precise and timely responses to user queries. In the next sections, we will explore each of these components in detail, providing guidance on how to implement them effectively within Dynamiq's Workflow Builder.