Datasets

Data sources used by agents for context, fine-tuning and retrieval.

Total datasets

8

across 3 agents

Total size

4.7 GB

stored locally

Total records

1.2M

indexed entries

Last sync

12m ago

all up to date

Name Type Used by Records Size Status Last updated
clinical-reports-v3
Medical documents corpus
Vector Summarizer 284,120 1.2 GB Ready 2 min ago
intent-labels-en
English intent classification labels
Text Classifier 42,800 180 MB Ready 1h ago
translation-pairs-es-en
Spanish-English parallel sentences
Text Translator 620,000 850 MB Syncing 12 min ago
validation-rules-v1
Schema and compliance rules
JSON Validator 1,240 4.2 MB Ready 3h ago
sentiment-feedback-q1
User feedback with sentiment labels
Tabular 18,540 72 MB Ready 1 day ago
embeddings-cache-2024
Precomputed document embeddings
Vector Summarizer, Classifier 210,000 1.4 GB Ready 22h ago
error-patterns-log
Historical failure patterns for recovery
JSON Validator 3,820 9.8 MB Error 5h ago
multilang-glossary
Terminology glossary for 12 languages
Text Translator 88,400 310 MB Ready 2 days ago