CALIBER
Quickstart
Use CALIBER

Knowledge bases

The practical guide for ingesting knowledge, improving retrieval quality, and connecting grounded content to assistant or workflow behavior.

System userDeveloperEvaluatorHow ToGA
PrerequisitesA CALIBER deployment with knowledge-base access
Reviewed 2026-08-10 · current main branch docs contract

Use this page when the question is practical: ingest source material, verify retrieval quality, and connect grounded knowledge to assistant or workflow behavior.

At a glance

TaskStart hereDeep reference
ingest documentsconfirm storage and extraction pathKnowledge bases architecture
improve retrieval qualityinspect chunking, embeddings, and rerankingKnowledge bases architecture
use knowledge in assistant answersconnect retrieval to the consuming surfaceAria assistant
evaluate grounded answersscore citation quality and answer faithfulnessEvaluation and test sets

1. What knowledge bases are for in CALIBER

Knowledge bases give CALIBER a governed retrieval surface: versioned corpora, ingestion, chunking, embeddings, optional graph extraction, and retrieval that can be measured rather than assumed.

2. Common tasks

You want to...Read this next
upload and ingest contentKnowledge bases architecture
improve search or answer qualityEvaluation and test sets
debug a missing source or file pathStorage and state
reason about grounded-answer trustTrust and governance

3. Common failure modes

SymptomFirst thing to check
Files uploaded, but answers are weakchunking, embeddings, reranking, or evaluation coverage
Sources exist, but retrieval cannot find themingestion status, storage path, or project scope
Answers cite the wrong materialretrieval quality, prompt instructions, or judge coverage

CALIBER : Contextual Adaptive Lifecycle for Intelligent Build, Evaluation, and Refinement — this page is generated from the authoritative Markdown sources in docs/ and the repository-level ARCHITECTURE.md.