Workflow: Run Model Inference

# List and inspect models
dodil ignite models list
dodil ignite models get kimi-k2-5
 
# Embeddings
dodil ignite models embed kimi-k2-5 --input "hello world"
 
# Generic infer
dodil ignite models infer kimi-k2-5 --prompt '{"input":"hello"}'

curl -sS https://api.dev.dodil.io/v1/chat/completions \
  -H "Authorization: Bearer ${TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "model":"kimi-k2-5",
    "messages":[{"role":"user","content":"Summarize this text"}]
  }'

curl -sS https://api.dev.dodil.io/v1/rerank \
  -H "Authorization: Bearer ${TOKEN}" \
  -H "Content-Type: application/json" \
  -d '{
    "model":"bge-reranker-v2",
    "query":"ignite gateway architecture",
    "documents":["doc A","doc B"]
  }'