reafctor: all code without stream

readme.md

@@ -19,6 +19,17 @@ curl -s -X POST https://chat.iceberg.black/api/v1/chat/completions \
 ]
 }' | jq .
 
+curl -X POST http://localhost:3001/v1/completions \
+  -H "Content-Type: application/json" \
+  -H "x-api-key: UXVqi1Jazl_-A0TuBudw2Y3PeUiNwCMYayXwBWwuMf0" \
+  -H "Accept: text/event-stream" \
+  -d '{"model": "llama3:latest", "prompt": "hello", "stream": true}'
+
+
+providers → LlmError ┐
+                     ├── services → ServiceError → api → HTTP
+databases → DbError  ┘
+
 # 🦙 Ollama Rust API Wrapper
 
 A high-performance Rust API wrapper around Ollama, providing an OpenAI-compatible interface, model lifecycle management, and advanced runtime features.
@@ -266,3 +277,5 @@ This project turns Ollama into:
 
 # TODO
 - open api doc for bearer token
+- Unify check before sending to ollama payload
+- load/unload model functions