memory routers working

llama_stack/examples/router-table-run.yaml

@@ -3,40 +3,40 @@ image_name: local
 docker_image: null
 conda_env: local
 apis_to_serve:
-- inference
-# - memory
+# - inference
+- memory
 - telemetry
 provider_map:
   telemetry:
     provider_id: meta-reference
     config: {}
 provider_routing_table:
-  inference:
-    - routing_key: Meta-Llama3.1-8B-Instruct
-      provider_id: meta-reference
-      config:
-        model: Meta-Llama3.1-8B-Instruct
-        quantization: null
-        torch_seed: null
-        max_seq_len: 4096
-        max_batch_size: 1
-    # - routing_key: Meta-Llama3.1-8B
-    #   provider_id: meta-reference
-    #   config:
-    #     model: Meta-Llama3.1-8B
-    #     quantization: null
-    #     torch_seed: null
-    #     max_seq_len: 4096
-    #     max_batch_size: 1
-  # memory:
-  #   - routing_key: keyvalue
-  #     provider_id: remote::pgvector
-  #     config:
-  #       host: localhost
-  #       port: 5432
-  #       db: vectordb
-  #       user: vectoruser
-  #       password: xxxx
-  #   - routing_key: vector
+  # inference:
+  #   - routing_key: Meta-Llama3.1-8B-Instruct
   #     provider_id: meta-reference
-  #     config: {}
+  #     config:
+  #       model: Meta-Llama3.1-8B-Instruct
+  #       quantization: null
+  #       torch_seed: null
+  #       max_seq_len: 4096
+  #       max_batch_size: 1
+  #   - routing_key: Meta-Llama3.1-8B
+  #     provider_id: meta-reference
+  #     config:
+  #       model: Meta-Llama3.1-8B
+  #       quantization: null
+  #       torch_seed: null
+  #       max_seq_len: 4096
+  #       max_batch_size: 1
+  memory:
+    - routing_key: keyvalue
+      provider_id: remote::pgvector
+      config:
+        host: localhost
+        port: 5432
+        db: vectordb
+        user: vectoruser
+        password: xxxx
+    - routing_key: vector
+      provider_id: meta-reference
+      config: {}

llama_stack/examples/simple-local-run.yaml

@@ -0,0 +1,38 @@
+built_at: '2024-09-19T22:50:36.239761'
+image_name: simple-local
+docker_image: null
+conda_env: simple-local
+apis_to_serve:
+- inference
+- safety
+- agents
+- memory
+provider_map:
+  inference:
+    provider_id: meta-reference
+    config:
+      model: Meta-Llama3.1-8B-Instruct
+      quantization: null
+      torch_seed: null
+      max_seq_len: 4096
+      max_batch_size: 1
+  safety:
+    provider_id: meta-reference
+    config:
+      llama_guard_shield:
+        model: Llama-Guard-3-8B
+        excluded_categories: []
+        disable_input_check: false
+        disable_output_check: false
+      prompt_guard_shield:
+        model: Prompt-Guard-86M
+  agents:
+    provider_id: meta-reference
+    config: {}
+  memory:
+    provider_id: meta-reference
+    config: {}
+  telemetry:
+    provider_id: meta-reference
+    config: {}
+provider_routing_table: {}