Adding docker-compose.yaml, starting to simplify

distributions/remote-vllm/run.yaml

@@ -6,39 +6,25 @@ conda_env: null
 apis:
 - inference
 - memory
-- safety
 - agents
 - telemetry
 providers:
   inference:
   # serves main inference model
-  - provider_id: vllm-0
+  - provider_id: vllm-inference
     provider_type: remote::vllm
     config:
-      # NOTE: replace with "localhost" if you are running in "host" network mode
-      url: ${env.VLLM_URL:http://host.docker.internal:5100/v1}
-      max_tokens: ${env.MAX_TOKENS:4096}
-      api_token: fake
-  # serves safety llama_guard model
-  - provider_id: vllm-1
-    provider_type: remote::vllm
-    config:
-      # NOTE: replace with "localhost" if you are running in "host" network mode
-      url: ${env.SAFETY_VLLM_URL:http://host.docker.internal:5101/v1}
+      url: ${env.VLLM_URL}
       max_tokens: ${env.MAX_TOKENS:4096}
       api_token: fake
   memory:
-  - provider_id: faiss-0
+  - provider_id: faiss
     provider_type: inline::faiss
     config:
       kvstore:
         namespace: null
         type: sqlite
         db_path: "${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/faiss_store.db"
-  safety:
-  - provider_id: llama-guard
-    provider_type: inline::llama-guard
-    config: {}
   memory:
   - provider_id: meta0
     provider_type: inline::faiss
@@ -60,9 +46,5 @@ metadata_store:
   type: sqlite
   db_path: "${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db"
 models:
-  - model_id: ${env.INFERENCE_MODEL:Llama3.1-8B-Instruct}
-    provider_id: vllm-0
-  - model_id: ${env.SAFETY_MODEL:Llama-Guard-3-1B}
-    provider_id: vllm-1
-shields:
-  - shield_id: ${env.SAFETY_MODEL:Llama-Guard-3-1B}
+  - model_id: ${env.INFERENCE_MODEL}
+    provider_id: vllm-inference