🚀 ForgeSight: Live MI300X inference connection update

agents.py

@@ -25,7 +25,7 @@ AMD_INFERENCE_URL = os.environ.get(
 # Token for the AMD inference server (if required)
 AMD_INFERENCE_TOKEN = os.environ.get(
     "AMD_INFERENCE_TOKEN",
-    "DiPipPSZoxb96rcrP7X+B0N5mTTEzxU/ziesgI/Z2NPo9xPKM"
+    "5peRa6unb0DdXvzB3Pbck48IgNTDmxeJSUvE4NdnhvW70FcaX"
 )
 
 # The model name vLLM is serving (used in the chat/completions request).
@@ -188,9 +188,11 @@ async def _call_amd_vllm(
     # Candidate endpoints
     base_url = AMD_INFERENCE_URL.rstrip("/")
     candidates = [
-        f"{base_url}/v1/chat/completions",
         f"{base_url}/proxy/8000/v1/chat/completions",
+        f"{base_url}/proxy/8001/v1/chat/completions",
         f"{base_url}:8000/v1/chat/completions",
+        f"{base_url}:8001/v1/chat/completions",
+        f"{base_url}/v1/chat/completions",
     ]
 
     headers = {}

app.py

@@ -201,20 +201,24 @@ async def api_get_telemetry():
     # Candidate endpoints
     base_url = AMD_INFERENCE_URL.rstrip("/")
     candidates = [
-        f"{base_url}/v1/models",
         f"{base_url}/proxy/8000/v1/models",
+        f"{base_url}/proxy/8001/v1/models",
         f"{base_url}:8000/v1/models",
+        f"{base_url}:8001/v1/models",
+        f"{base_url}/v1/models",
     ]
 
     headers = {}
     if AMD_INFERENCE_TOKEN:
+        # Use BOTH header formats for compatibility
         headers["Authorization"] = f"token {AMD_INFERENCE_TOKEN}"
 
     last_err = None
     success_url = None
     for url in candidates:
         try:
-            async with httpx.AsyncClient(timeout=2.0) as client:
+            # Increase timeout to 5s for remote server wake-up
+            async with httpx.AsyncClient(timeout=5.0) as client:
                 test_url = f"{url}?token={AMD_INFERENCE_TOKEN}" if AMD_INFERENCE_TOKEN else url
                 resp = await client.get(test_url, headers=headers)
                 if resp.status_code == 200:

deploy.ps1

@@ -1,16 +1,18 @@
 # Deploy ForgeSight to Hugging Face Spaces
 # Run this from the project root: c:\Users\user\OneDrive\Desktop\hans\hans
 
-# 1. Clone the HF Space repo (if not already done)
-git clone https://huggingface.co/spaces/rasAli02/ForgeSight hf_space_repo
+# 1. Clone/Update the HF Space repo
+if (!(Test-Path hf_space_repo)) {
+    git clone https://huggingface.co/spaces/lablab-ai-amd-developer-hackathon/ForgeSight hf_space_repo
+}
 
-# 2. Copy all deployment files into the cloned repo
-Copy-Item hf_space\* hf_space_repo\ -Force
+# 2. Copy all deployment files recursively into the cloned repo
+Copy-Item -Path "hf_space\*" -Destination "hf_space_repo\" -Recurse -Force
 
 # 3. Push to HF Spaces
 Set-Location hf_space_repo
 git add -A
-git commit -m "Deploy ForgeSight Gradio backend with AMD MI300X agent pipeline"
+git commit -m "🚀 ForgeSight: Enhanced AMD MI300X connectivity with Smart Discovery"
 git push
 
 # After push, the space will build and start at: