Documentation Index
Fetch the complete documentation index at: https://docs.knowledgestack.ai/llms.txt
Use this file to discover all available pages before exploring further.
How It Works
When you upload an Excel file, it goes through a specialized conversion and chunking path before joining the shared enrichment and embedding pipeline:
Upload .xlsx/.xlsm
|
v
Step 1: Preparation
-> Download the file from storage
|
v
Step 2: Excel Conversion
-> Parse workbook structure (sheets, cells, formulas, dependencies)
-> Extract embedded images and convert to WEBP
-> Store structured parse result as JSON
|
v
Step 3: Excel Chunking
-> Create one section per sheet
-> Create chunks for each content block (tables, text, images, charts)
-> Build enriched HTML with formula and formatting data
|
v
Steps 4-7: Shared Pipeline
-> Vector cleanup -> Enrichment -> Embedding -> Completion
Content Block to Chunk Mapping
Each block detected in the spreadsheet maps to a specific chunk type:
| Block Type | Chunk Type | Content |
|---|
| Table, calculation block, assumptions, results, label block, data block | TABLE | Plain-text rendering plus enriched HTML with formulas |
| Chart | IMAGE | Structured chart description (type, series, axes) |
| Embedded image | IMAGE | Alt text or placeholder; original image stored in S3 |
| Header, text block, mixed content, sparse cells | TEXT | Plain-text cell content |
| Empty blocks | Skipped | Not chunked |
Enriched HTML for Tables
Every TABLE chunk carries an enriched HTML representation that preserves formulas and cell formatting lost in the plain-text version. This enriched HTML is stored as metadata on the chunk.
<table data-sheet="Sheet1" data-range="A1:D10" data-block-type="table">
<caption>LLM-parsed header: "Q4 Revenue by Region"</caption>
<thead>
<tr>
<th data-cell="A1">Product</th>
<th data-cell="B1">Q1</th>
<th data-cell="C1">Q2</th>
</tr>
</thead>
<tbody>
<tr>
<td data-cell="A2">Widget A</td>
<td data-cell="B2" data-formula="=SUM(B3:B5)" data-fmt="bold"
data-font-color="FF0000">150</td>
<td data-cell="C2" data-formula="=B2*1.1"
data-fill-color="FFFF00">165</td>
</tr>
</tbody>
</table>
Preserved Cell Attributes
| Attribute | When Present | Example |
|---|
data-cell | Always | A1 (cell address) |
data-formula | Cell has a formula | =SUM(B3:B5) |
data-font-color | Non-default font color | FF0000 |
data-fill-color | Non-default background color | FFFF00 |
data-fmt | Cell has formatting | bold, italic, underline |
Auto-Generated Table Titles
Every TABLE chunk gets a human-readable title generated by the LLM enrichment step:
- The LLM receives the enriched HTML plus surrounding context
- It generates a concise title (max 10 words) describing what the table contains
- The title is stored as a
<caption> in the enriched HTML and as metadata on the chunk
This makes every table self-describing for search — the title acts as a semantic anchor that improves both embedding quality and search relevance.
Chart Support
Charts extracted from Excel files are represented as IMAGE chunks with structured text describing the chart:
Chart: "Revenue by Region" (bar, 4 series)
Series 1: "North" -> data: Sheet1!B2:B10, categories: Sheet1!A2:A10
Series 2: "South" -> data: Sheet1!C2:C10, categories: Sheet1!A2:A10
X-Axis: "Region" | Y-Axis: "Revenue ($)"
Anchor: Sheet1!F1:L15
Image and Shape Handling
Embedded images and shapes from Excel files are also extracted:
- Images become IMAGE chunks with alt text. The original image is extracted from the file and uploaded to storage as WEBP. LLM enrichment later generates a full description.
- Text boxes become TEXT chunks with the text box content.
Section Structure
Each Excel sheet becomes a section in the document hierarchy, analogous to a heading in a PDF. This means:
- You can browse a workbook sheet-by-sheet using the standard document navigation
- Each sheet’s content is organized under its own section
- The agent can read individual sheets or search across all sheets
Design Highlights
| Decision | Rationale |
|---|
| One section per sheet | Sheets are the natural structural unit in spreadsheets, analogous to headings in documents |
| Atomic table chunks | Tables are never split — this preserves structural integrity for AI reasoning |
| Formula and formatting preservation | Cell formulas, colors, and formatting are stored as HTML data attributes for full fidelity |
| Plain text for embedding, HTML for display | The plain-text rendering is ideal for vector search; the enriched HTML preserves the full spreadsheet context |
| Separate conversion queue | Excel parsing is CPU-intensive and is isolated to prevent blocking other document processing |
