Skip to main content
GET
/
health
curl -X GET "http://localhost:8080/health"

{
  "status": "ok",
  "embedding_provider": "ollama",
  "model": "nomic-embed-text",
  "llm_provider": "ollama",
  "llm_model": "llama3.2",
  "items": 1500,
  "max_items": 100000,
  "remaining": 98500
}

​
Overview

Returns whether the server is running, which embedding and LLM providers and models are configured, and how many items are stored versus the global cap (default 100,000). 
curl -X GET "http://localhost:8080/health"

{
  "status": "ok",
  "embedding_provider": "ollama",
  "model": "nomic-embed-text",
  "llm_provider": "ollama",
  "llm_model": "llama3.2",
  "items": 1500,
  "max_items": 100000,
  "remaining": 98500
}

​
Response fields

FieldTypeDescription
statusstring"ok" when the server is up
embedding_providerstringollama, openai, or cohere
modelstringEmbedding model id for the configured provider
llm_providerstringLLM provider for /answer
llm_modelstringDefault LLM model id
itemsnumberCurrent item count (all namespaces)
max_itemsnumberGlobal item limit
remainingnumbermax_items - items
Use the same quota fields when uploads return 409 - see Upload documents.