try v3

.github/workflows/front-end-release.yml

@@ -3,7 +3,7 @@ name: React.js Build and Release
 on:
   push:
     tags:
-      - 'v*'
+      - 'app-v*'
 
 jobs:
   build:

.github/workflows/ml-service-release.yml

@@ -3,7 +3,7 @@ name: Create Release
 on:
   push:
     tags:
-      - 'v*'
+      - 'ml-v*'
 
 jobs:
   build:

ml_service/emb_serve.py

@@ -71,7 +71,6 @@ async def generate_embedding(self, request: Request) -> JSONResponse:
         elif req_type == "PLAIN_EMBED":
             embedding: List[np.ndarray] = list(self.model.embed(data.get("data")))
 
-        print(embedding)
         embedding = [x.tolist() for x in embedding]
 
         return JSONResponse(content={"embedding": embedding})

ml_service/test/emb_client.py

@@ -1,7 +1,7 @@
 import requests
 import numpy as np
 
-EMBEDDING_URL = "http://172.16.0.57:9999/api/v1/embedder/embed"  # Adjust if your deployment is on a different port
+EMBEDDING_URL = "http://172.16.0.57:5000/api/v1/embedder/embed"  # Adjust if your deployment is on a different port
 
 # Test data
 test_cases = [

ml_service/test/llm_client.py

@@ -55,7 +55,7 @@ async def generate_text(endpoint_url: str, payload: Dict) -> List[str]:
 
 @click.command()
 @click.option("--host", default="localhost", help="Host")
-@click.option("--port", default=9999, help="Port")
+@click.option("--port", default=5000, help="Port")
 @click.option("--stream", default=True, help="Stream")
 @click.option("--max-tokens", default=4096, help="Max tokens")
 @click.option("--temperature", default=0.3, help="Temperature")