Application Overview
The VectorAmp dashboard is the operator console for governed retrieval. Use it to create datasets, connect sources, monitor ingestion jobs, inspect search behavior, manage API keys, and keep production knowledge workflows healthy.
Dashboard role
The API is for application traffic. The dashboard is for humans operating the retrieval system: creating keys, checking ingestion health, reviewing datasets, and debugging why an answer did or did not have enough evidence.
What you manage in the dashboard
| Area | What it controls |
|---|---|
| Datasets | Retrieval boundaries backed by SABLE: vectors, metadata, source content, and search behavior. |
| Sources | File uploads and connected content sources that feed ingestion jobs. |
| Pipelines / jobs | Parsing, chunking, embedding, indexing, retries, and processing status. |
| Embeddings | Model/provider choices and embedding behavior for new content. |
| API keys | Server-side access for apps, ingestion automation, SDKs, CLI, REST, and MCP. |
| Organizations | Multi-tenant account boundary for datasets, users, keys, usage, and configuration. |
Core workflow
A typical VectorAmp workflow looks like this:
- Create a dataset for one retrieval boundary, such as product docs, policy knowledge, customer files, or a tenant-specific corpus.
- Connect or upload sources that should become searchable.
- Monitor ingestion jobs while VectorAmp parses, chunks, embeds, and indexes content.
- Test search and cited answers with representative questions.
- Add filters and metadata so application queries are scoped by tenant, role, source, document type, or time window.
- Create API keys for the service or workflow that will query the dataset.
- Ship with observability so operators can tell whether retrieval is fresh, scoped, and source-grounded.
Dashboard vs API
Use both surfaces together.
| Surface | Best for |
|---|---|
| Dashboard | Setup, inspection, demos, troubleshooting, source/job monitoring, key management. |
| REST API | Backend integration, search, ingestion automation, dataset/job/source operations. |
| SDKs | App teams that want language-native helpers. |
| CLI | Repeatable local workflows, smoke tests, and scripted ingestion. |
| MCP | Agent tools that need governed access to enterprise knowledge. |