22 lines
937 B
Markdown
22 lines
937 B
Markdown
# ExampleRAG integration
|
|
|
|
```text
|
|
ExampleRAG operator workflow
|
|
-> scoped ExampleRAG service credential
|
|
-> POST /api/v1/capabilities/rag.embedding@1/invoke
|
|
-> Gateway authentication and rate limits
|
|
-> GPU scheduler and lease
|
|
-> outbound GPU Node node agent
|
|
-> typed offline runtime worker
|
|
-> vector plus embedding_space_id
|
|
-> isolated ExampleRAG shadow collection
|
|
```
|
|
|
|
ExampleRAG configuration names only the ModelForge origin, credential-file boundary and
|
|
`rag.embedding@1`. The adapter rejects redirects, public/cloud hosts, invalid credentials,
|
|
non-finite vectors, wrong dimensions, non-normalized output and embedding-space mismatch. Safe
|
|
transient statuses are retried with bounded backoff. There is no cloud or direct-worker fallback.
|
|
|
|
The credential is read for every batch, allowing create → secret-file replacement → validate →
|
|
revoke rotation without logging or persisting the secret in either repository.
|