From 4e64aab0a56dbc39d0ba32955cc61a7159135e11 Mon Sep 17 00:00:00 2001 From: LucasDLTG Date: Tue, 28 Apr 2026 18:32:40 +0200 Subject: [PATCH] fix: format + tracing --- .gitea/workflows/release.yml | 5 +- .pre-commit-config.yaml | 2 +- docker-compose.yml | 2 +- readme.md | 79 +++++++++++++++--------------- src/main.rs | 4 +- src/middlewares/auth/middleware.rs | 2 +- src/routes/v1/chat.rs | 2 + 7 files changed, 48 insertions(+), 48 deletions(-) diff --git a/.gitea/workflows/release.yml b/.gitea/workflows/release.yml index 4574912..b90cb26 100644 --- a/.gitea/workflows/release.yml +++ b/.gitea/workflows/release.yml @@ -3,7 +3,7 @@ name: Publish & Deploy on: push: tags: - - 'v*' + - "v*" permissions: contents: write @@ -74,7 +74,7 @@ jobs: script: | REPO_LOWER=$(echo "${{ github.repository }}" | tr '[:upper:]' '[:lower:]') TAG=${{ github.ref_name }} - + echo "${{ secrets.CONTAINER_REGISTRY_TOKEN }}" | docker login gitea.iceberg.black -u "docker-bot" --password-stdin docker pull gitea.iceberg.black/$REPO_LOWER:$TAG docker logout gitea.iceberg.black @@ -86,4 +86,3 @@ jobs: REPO_LOWER=$REPO_LOWER TAG=$TAG docker compose up -d docker image prune -af - diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index ed0f715..2c1f7e0 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -38,4 +38,4 @@ repos: entry: cargo audit language: system pass_filenames: false - stages: [pre-push] \ No newline at end of file + stages: [pre-push] diff --git a/docker-compose.yml b/docker-compose.yml index 1573aa7..10e9e55 100644 --- a/docker-compose.yml +++ b/docker-compose.yml @@ -26,4 +26,4 @@ services: networks: chat-net: - external: true \ No newline at end of file + external: true diff --git a/readme.md b/readme.md index 03a14d6..11efdec 100644 --- a/readme.md +++ b/readme.md @@ -3,23 +3,21 @@ - Race condition on jwks token refresh - Rate Limiting - git tag -d v1.0.0; git push origin :refs/tags/v1.0.0; git tag -a v1.0.0 -m "Release v1.0.0"; git push origin v1.0.0 +curl https://chat.iceberg.black/api/v1/models -H "Authorization: Bearer eyJhbGciOiJSUzI1NiIsInR5cCIgOiAiSldUIiwia2lkIiA6ICJublpLek04TkZHVmpWbGFPRXZpMUtFSTVHQWRwaGlsYjh3RHRLeG5JOENZIn0.eyJleHAiOjE3NzU4MTUyODksImlhdCI6MTc3NTgxNDk4OSwianRpIjoiMTgwYzA2NDUtYzZiMC00MDRmLTgyYjEtMzA3YmY4ZmJlNmJlIiwiaXNzIjoiaHR0cHM6Ly9hdXRoLmljZWJlcmcuYmxhY2svcmVhbG1zL2ljZWJlcmciLCJzdWIiOiJmZGRiN2FjZC1kMmE5LTRmMTctOWIxNi1kZjVlN2EzNDI4YjciLCJ0eXAiOiJCZWFyZXIiLCJhenAiOiJjaGF0LWFwaSIsInNjb3BlIjoiIiwiY2xpZW50SG9zdCI6Ijg2LjIxMi44NC4xOTEiLCJjbGllbnRBZGRyZXNzIjoiODYuMjEyLjg0LjE5MSIsImNsaWVudF9pZCI6ImNoYXQtYXBpIn0.abjHABcjCJNiB6vriRw60nfzabEfD7CXwyRhkahFkC8ATgfy4fn0T8PnFfsaRpsXuhamIhWwNskrA7L9V3mbWWKW-JEOvImDhTc8sIX0E5fDTbk8O5wa_2yzNdLpRxdSjLqgL544rB8I-LZ8bl5SxtdN3gHfrnWr5ef8bbLgPRzZIylT3QUpah0uywDM_cfrrve9SMHHOUUItyzmOHLw0Igit1EzyFNyjbWf6OAU6TMjOF_eFTc5sakyBwsdJnGy0nhj5R-wxLpr1ug3iEd3Y-jDzHO4m6jariXVJ7Vvbz71i7sadDEKdSyOKcCeQbU4T0Tf7IxqW4c2DNnk3BFFuw" -curl https://chat.iceberg.black/api/v1/models -H "Authorization: Bearer eyJhbGciOiJSUzI1NiIsInR5cCIgOiAiSldUIiwia2lkIiA6ICJublpLek04TkZHVmpWbGFPRXZpMUtFSTVHQWRwaGlsYjh3RHRLeG5JOENZIn0.eyJleHAiOjE3NzU4MTUyODksImlhdCI6MTc3NTgxNDk4OSwianRpIjoiMTgwYzA2NDUtYzZiMC00MDRmLTgyYjEtMzA3YmY4ZmJlNmJlIiwiaXNzIjoiaHR0cHM6Ly9hdXRoLmljZWJlcmcuYmxhY2svcmVhbG1zL2ljZWJlcmciLCJzdWIiOiJmZGRiN2FjZC1kMmE5LTRmMTctOWIxNi1kZjVlN2EzNDI4YjciLCJ0eXAiOiJCZWFyZXIiLCJhenAiOiJjaGF0LWFwaSIsInNjb3BlIjoiIiwiY2xpZW50SG9zdCI6Ijg2LjIxMi44NC4xOTEiLCJjbGllbnRBZGRyZXNzIjoiODYuMjEyLjg0LjE5MSIsImNsaWVudF9pZCI6ImNoYXQtYXBpIn0.abjHABcjCJNiB6vriRw60nfzabEfD7CXwyRhkahFkC8ATgfy4fn0T8PnFfsaRpsXuhamIhWwNskrA7L9V3mbWWKW-JEOvImDhTc8sIX0E5fDTbk8O5wa_2yzNdLpRxdSjLqgL544rB8I-LZ8bl5SxtdN3gHfrnWr5ef8bbLgPRzZIylT3QUpah0uywDM_cfrrve9SMHHOUUItyzmOHLw0Igit1EzyFNyjbWf6OAU6TMjOF_eFTc5sakyBwsdJnGy0nhj5R-wxLpr1ug3iEd3Y-jDzHO4m6jariXVJ7Vvbz71i7sadDEKdSyOKcCeQbU4T0Tf7IxqW4c2DNnk3BFFuw" - -curl -X POST "https://auth.iceberg.black/realms/iceberg/protocol/openid-connect/token" -H "Content-Type: application/x-www-form-urlencoded" -d "grant_type=client_credentials" -d "client_id=chat-api" -d "client_secret=5fHUp8Z5GoNM70MVOGuQTfKFkaAE48Za" +curl -X POST "https://auth.iceberg.black/realms/iceberg/protocol/openid-connect/token" -H "Content-Type: application/x-www-form-urlencoded" -d "grant_type=client_credentials" -d "client_id=chat-api" -d "client_secret=5fHUp8Z5GoNM70MVOGuQTfKFkaAE48Za" curl -s -X POST https://chat.iceberg.black/api/v1/chat/completions \ - -H "Content-Type: application/json" \ - -H "Authorization: Bearer eyJhbGciOiJSUzI1NiIsInR5cCIgOiAiSldUIiwia2lkIiA6ICJublpLek04TkZHVmpWbGFPRXZpMUtFSTVHQWRwaGlsYjh3RHRLeG5JOENZIn0.eyJleHAiOjE3NzU4MTU0NTEsImlhdCI6MTc3NTgxNTE1MSwianRpIjoiOGNjMmM5MjUtZmMzNy00MDFhLWE1ZjUtODFlOGJhNjcxNzcwIiwiaXNzIjoiaHR0cHM6Ly9hdXRoLmljZWJlcmcuYmxhY2svcmVhbG1zL2ljZWJlcmciLCJzdWIiOiJmZGRiN2FjZC1kMmE5LTRmMTctOWIxNi1kZjVlN2EzNDI4YjciLCJ0eXAiOiJCZWFyZXIiLCJhenAiOiJjaGF0LWFwaSIsInNjb3BlIjoiIiwiY2xpZW50SG9zdCI6Ijg2LjIxMi44NC4xOTEiLCJjbGllbnRBZGRyZXNzIjoiODYuMjEyLjg0LjE5MSIsImNsaWVudF9pZCI6ImNoYXQtYXBpIn0.Exv34aoAqwzSqQziZH3zScAnK_xiNCXqpOQl54x7NFMdO0gVgacJgMxoW82Ym8aCNfBRMFtWclZJ9RFh1b9uSEUgsdVtqvMX-2kCAhiMSjmIBPU-L0gr5N63c3bScOoAYa37baR4mXQ5LxHjfkLo_rHDJ74adg2JMo359Wbuu1_OR708_q8yjgO_4fQeYbIffxADwRDvPSIwQ8Y2qRjaAIOZs0xmA9p128CUxlUyvhxwfFquYKRaDs5QE9pIAtvm_KuoBydYopm8j8cbm4ixDhUwYjkzniIIapY77NxpmMosfh8BhK0W3ieK2gTKfmiFDhYgkGybU6b1BnJMy1_Kxg" \ - -d '{ - "model": "llama3:latest", - "messages": [ - {"role": "user", "content": "What is Rust?"} - ] - }' | jq . + -H "Content-Type: application/json" \ + -H "Authorization: Bearer eyJhbGciOiJSUzI1NiIsInR5cCIgOiAiSldUIiwia2lkIiA6ICJublpLek04TkZHVmpWbGFPRXZpMUtFSTVHQWRwaGlsYjh3RHRLeG5JOENZIn0.eyJleHAiOjE3NzU4MTU0NTEsImlhdCI6MTc3NTgxNTE1MSwianRpIjoiOGNjMmM5MjUtZmMzNy00MDFhLWE1ZjUtODFlOGJhNjcxNzcwIiwiaXNzIjoiaHR0cHM6Ly9hdXRoLmljZWJlcmcuYmxhY2svcmVhbG1zL2ljZWJlcmciLCJzdWIiOiJmZGRiN2FjZC1kMmE5LTRmMTctOWIxNi1kZjVlN2EzNDI4YjciLCJ0eXAiOiJCZWFyZXIiLCJhenAiOiJjaGF0LWFwaSIsInNjb3BlIjoiIiwiY2xpZW50SG9zdCI6Ijg2LjIxMi44NC4xOTEiLCJjbGllbnRBZGRyZXNzIjoiODYuMjEyLjg0LjE5MSIsImNsaWVudF9pZCI6ImNoYXQtYXBpIn0.Exv34aoAqwzSqQziZH3zScAnK_xiNCXqpOQl54x7NFMdO0gVgacJgMxoW82Ym8aCNfBRMFtWclZJ9RFh1b9uSEUgsdVtqvMX-2kCAhiMSjmIBPU-L0gr5N63c3bScOoAYa37baR4mXQ5LxHjfkLo_rHDJ74adg2JMo359Wbuu1_OR708_q8yjgO_4fQeYbIffxADwRDvPSIwQ8Y2qRjaAIOZs0xmA9p128CUxlUyvhxwfFquYKRaDs5QE9pIAtvm_KuoBydYopm8j8cbm4ixDhUwYjkzniIIapY77NxpmMosfh8BhK0W3ieK2gTKfmiFDhYgkGybU6b1BnJMy1_Kxg" \ + -d '{ +"model": "llama3:latest", +"messages": [ +{"role": "user", "content": "What is Rust?"} +] +}' | jq . # 🦙 Ollama Rust API Wrapper @@ -29,19 +27,20 @@ A high-performance Rust API wrapper around Ollama, providing an OpenAI-compatibl # 🚀 Features -* ✅ OpenAI-compatible API (`/v1/...`) -* ⚡ Streaming (Server-Sent Events) -* 🧠 Model lifecycle management (load/unload) -* 🔐 API key authentication (optional) -* 📊 Usage tracking & observability -* 🔀 Model routing & abstraction -* 🧩 Extensible architecture (multi-provider ready) +- ✅ OpenAI-compatible API (`/v1/...`) +- ⚡ Streaming (Server-Sent Events) +- 🧠 Model lifecycle management (load/unload) +- 🔐 API key authentication (optional) +- 📊 Usage tracking & observability +- 🔀 Model routing & abstraction +- 🧩 Extensible architecture (multi-provider ready) --- # 📡 API Endpoints ## 1. Core LLM API (OpenAI-compatible) + - [x] `POST /v1/chat/completions` + streaming - [x] `POST /v1/completions` + streaming - [ ] `POST /v1/embeddings` @@ -126,16 +125,16 @@ GET /v1/usage Tracks: -* request count -* latency -* per-model usage +- request count +- latency +- per-model usage --- ## 🚦 Rate Limiting -* Requests per minute -* Tokens per minute +- Requests per minute +- Tokens per minute Returns: @@ -158,8 +157,8 @@ Stores conversation history server-side. ## ⚡ Caching -* Embeddings -* Deterministic prompts (temperature = 0) +- Embeddings +- Deterministic prompts (temperature = 0) --- @@ -196,8 +195,8 @@ POST /v1/runtime/evict Strategies: -* LRU -* memory threshold +- LRU +- memory threshold --- @@ -223,10 +222,10 @@ Client → Rust API → Ollama → Response ### Layers: -* HTTP (Axum) -* Service layer (business logic) -* Provider abstraction -* Ollama client +- HTTP (Axum) +- Service layer (business logic) +- Provider abstraction +- Ollama client --- @@ -241,19 +240,19 @@ trait LlmProvider { Supports: -* Ollama (current) -* OpenAI (future) -* Others +- Ollama (current) +- OpenAI (future) +- Others --- # 🎯 Roadmap -* [ ] Full OpenAI compatibility -* [ ] Multi-node routing -* [ ] GPU-aware scheduling -* [ ] Web UI dashboard -* [ ] Distributed inference +- [ ] Full OpenAI compatibility +- [ ] Multi-node routing +- [ ] GPU-aware scheduling +- [ ] Web UI dashboard +- [ ] Distributed inference --- diff --git a/src/main.rs b/src/main.rs index 4dad52e..eece787 100644 --- a/src/main.rs +++ b/src/main.rs @@ -28,13 +28,13 @@ pub fn init_tracing() { #[tokio::main] async fn main() { - init_tracing(); - #[cfg(debug_assertions)] { dotenvy::dotenv().ok(); } + init_tracing(); + let state = AppState { ollama: Arc::new(OllamaProvider::new(OLLAMA_URL.as_str())), }; diff --git a/src/middlewares/auth/middleware.rs b/src/middlewares/auth/middleware.rs index 9fbc7e9..d2831f0 100644 --- a/src/middlewares/auth/middleware.rs +++ b/src/middlewares/auth/middleware.rs @@ -41,7 +41,7 @@ pub async fn auth_middleware(mut request: Request, next: Next) -> Result { - eprintln!("JWT validation failed: {:?}", e); + tracing::error!("JWT validation failed: {:?}", e); Err(StatusCode::UNAUTHORIZED) } } diff --git a/src/routes/v1/chat.rs b/src/routes/v1/chat.rs index 19f6499..90fc1ba 100644 --- a/src/routes/v1/chat.rs +++ b/src/routes/v1/chat.rs @@ -51,6 +51,7 @@ pub async fn completions( State(state): State, Json(body): Json, ) -> Result)> { + tracing::debug!("Received /completion with body {:?}", body); if body.base.stream { let stream = state.ollama.completions_stream(&body).await.map_err(|e| { let (code, msg) = ollama_err(e); @@ -116,6 +117,7 @@ pub async fn chat_completions( State(state): State, Json(body): Json, ) -> Result { + tracing::debug!("Received /completion with body {:?}", body); if body.base.stream { let stream = state .ollama