Run the script to produce vllm outputs

distributions/remote-vllm/run-with-safety.yaml

@@ -1,68 +1,71 @@
 version: '2'
-built_at: '2024-11-11T20:09:45.988375'
+built_at: 2024-11-17 14:07:24.568750
 image_name: remote-vllm
-docker_image: remote-vllm
+docker_image: llamastack/distribution-remote-vllm:test-0.0.52rc3
 conda_env: null
 apis:
-- inference
-- memory
-- safety
 - agents
 - telemetry
+- safety
+- inference
+- memory
 providers:
   inference:
-  # serves main inference model
   - 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}
-      max_tokens: ${env.MAX_TOKENS:4096}
-      api_token: fake
-  # serves safety llama_guard model
+      max_tokens: ${env.VLLM_MAX_TOKENS:4096}
+      api_token: ${env.VLLM_API_TOKEN:fake}
   - provider_id: vllm-safety
     provider_type: remote::vllm
     config:
-      # NOTE: replace with "localhost" if you are running in "host" network mode
       url: ${env.SAFETY_VLLM_URL}
-      max_tokens: ${env.MAX_TOKENS:4096}
-      api_token: fake
+      max_tokens: ${env.VLLM_MAX_TOKENS:4096}
+      api_token: ${env.VLLM_API_TOKEN:fake}
   memory:
-  - provider_id: faiss-0
+  - provider_id: faiss
     provider_type: inline::faiss
     config:
       kvstore:
-        namespace: null
         type: sqlite
-        db_path: "${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/faiss_store.db"
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/faiss_store.db
   safety:
   - provider_id: llama-guard
     provider_type: inline::llama-guard
     config: {}
-  memory:
-  - provider_id: meta0
-    provider_type: inline::faiss
-    config: {}
   agents:
-  - provider_id: meta0
+  - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
       persistence_store:
-        namespace: null
         type: sqlite
-        db_path: "${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/agents_store.db"
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/agents_store.db
   telemetry:
-  - provider_id: meta0
+  - provider_id: meta-reference
     provider_type: inline::meta-reference
     config: {}
 metadata_store:
   namespace: null
   type: sqlite
-  db_path: "${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db"
+  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/remote-vllm}/registry.db
 models:
-  - model_id: ${env.INFERENCE_MODEL}
-    provider_id: vllm-inference
-  - model_id: ${env.SAFETY_MODEL}
-    provider_id: vllm-safety
+- metadata: {}
+  model_id: ${env.INFERENCE_MODEL}
+  provider_id: vllm-inference
+  provider_model_id: null
+- metadata: {}
+  model_id: ${env.SAFETY_MODEL}
+  provider_id: vllm-safety
+  provider_model_id: null
 shields:
-  - shield_id: ${env.SAFETY_MODEL}
+- params: null
+  shield_id: ${env.SAFETY_MODEL}
+  provider_id: null
+  provider_shield_id: null
+memory_banks: []
+datasets: []
+scoring_fns: []
+eval_tasks: []