KlicForge Docs

Knowledge sources

Ground your agent's answers in your own documents — creating sources, uploading files, and choosing how content is retrieved.

A knowledge source is a collection of content your agent can retrieve from. When someone sends a message, KlicForge searches the attached sources, pulls the most relevant passages, and gives them to the model before it answers.

This is what makes an agent answer from your content rather than from what the model happens to know.

Creating a knowledge source

Select Knowledge in the sidebar, then New Knowledge Source. You can either:

  • Write or paste content directly in the dashboard. It is stored in the database and is available to agents immediately.
  • Upload a file and let KlicForge extract and index it.

Then open your agent's Knowledge tab and attach the source. A source that is not attached to an agent is never retrieved.

Source types

TypeDescription
db-contentContent stored in the database, written and edited in the dashboard
file-docsContent stored as files on the platform, read-only in the dashboard

Both use the same retrieval interface and can be mixed on one agent.

Retrieval modes

Each source has a retrieval mode that decides how content is matched to a question.

ModeHow it worksBest for
KeywordScores passages by word overlap with the questionSmall collections, straightforward FAQ content
SemanticUses embeddings to find related meaning even when wording differsLarger collections, synonym-heavy content, nuanced questions
HybridCombines both and merges the resultsProduction use where precision and recall both matter

Uploading files

Supported file types

CategoryTypes
DocumentsPDF
Text.txt, .md
SpreadsheetsCSV, Excel (.xlsx, .xls) — rendered as tables
ImagesJPEG, PNG, GIF, WebP — text extracted by OCR or vision

File size limit: 30 MB per file. Your plan's limits on number of sources and total storage are checked before an upload is accepted.

How upload works

  1. Choose Upload a file when creating a source.
  2. The file uploads directly to secure storage.
  3. An ingestion job runs automatically; the source shows a live status.
  4. When status reaches completed, attach it to an agent.

The ingestion pipeline

Each file goes through detect → extract → clean → chunk → embed:

  • Detect — classifies the document and picks an extraction strategy.
  • Extract — PDFs use text extraction, with OCR for scanned pages; visual-heavy PDFs use vision extraction. Spreadsheets become tables. Images use OCR or vision.
  • Clean — removes OCR noise. Already-structured formats skip this.
  • Chunk and embed — content is split and indexed for retrieval.

Limits worth knowing

  • Vision page cap — vision extraction processes the first 50 pages by default; later pages are skipped with a warning.
  • Empty extraction is rejected — if no text can be pulled out, the upload fails rather than creating an empty source.
  • Ingestion uses tokens — cleanup and vision extraction consume tokens recorded against your organization's usage.

You can reprocess an uploaded source from its detail view, which is useful if you want to force a different extraction strategy.

Contact-scoped knowledge

A knowledge source can be classified so that it belongs to a single contact rather than the whole organization. A contact-owned source is only retrievable in conversations with that contact, which is how you give one customer access to their own documents without exposing them to everyone.

Classification controls retrieval. Review it before uploading anything containing personal or customer-specific information.

Troubleshooting retrieval

SymptomLikely cause
Agent says it does not know something in your documentSource not attached to the agent, or still processing
Answers cite the wrong passageTry hybrid retrieval, or split a large document into focused sources
Upload rejectedUnsupported file type, over 30 MB, or no extractable text
Scanned PDF returns nothing usefulReprocess and force vision extraction
Agent ignores knowledge entirelyCheck answer mode is not tools_only

On this page