fix(ai): correct bge embedding model name to hosted_vllm/openai prefix

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

ai/litellm-config.yaml

@@ -58,7 +58,7 @@ model_list:
   # Embeddings - BGE Large (Port 8002)
   - model_name: bge-large-en-v1.5
     litellm_params:
-      model: hosted_vllm/BAAI/bge-large-en-v1.5
+      model: hosted_vllm/openai/bge-large-en-v1.5
       api_base: os.environ/GPU_VLLM_EMBED_URL  # Direct to vLLM embedding server
       api_key: "EMPTY"
       rpm: 1000