Workshop
Case 4: A RAG Workflow

Case 4: A RAG Workflow


🟡 Demo:

1. Create a File block → upload your file → Create a load edge.

eg3f

2. Run the edge to load the file.

eg3f

3. Edit Structured Text.

eg3f

4. Create Convert to Text edge.

eg3f

5. Generate the text.

eg3f

6. Create a Chunking Edge.

eg3f
  • Auto
    • Easiest and fastest option.
    • Automatically splits content by line breaks.
    • No additional configuration needed.
    • Best for pre-formatted content like lists or short paragraph.
  • By length
    • Splits content strictly by character count without using any semantic rules.
    • Configurable:
      • Chunk Size: Max characters per chunk.
      • Overlap: Repeated characters between chunks.
      • Handle Half Word: Prevents breaking words in half .(set to True if using English or similar languages)
    • Ideal when uniform chunk length is needed.
  • By character
    • Uses custom user-defined delimiters to split content.
    • Configurable:
      • Delimiters: Choose one or more. (e.g., comma, period, space)
    • Suitable for data with predictable formatting, like CSV or semicolon-separated values.

7. Run the Chunking Edge and create Retrieve Edge.

eg3f

8. Create a Text Block to describe your question and connect to the Retrieve edge.

eg3f

9. Modify your Retrieve Edge:

eg3f
  • Query: The text or structured query from user or workflow
  • Data source with Vector indexing: The indexed structured content (chunks with embedding vectors)
  • Settings:
    • Result Number: Number of top results to return (default: 5)
    • Threshold: Minimum similarity score (0–1). Default is 0.7. Results below this value will be filtered out.

10. Run the Retrieve Edge.

eg3f

11. Generate the Answer.

eg3f