[api_updates_3] fix CLI for routing_table, bug fixes for memory & safety (#90)

* fix llama stack build

* fix configure

* fix configure for simple case

* configure w/ routing

* move examples config

* fix memory router naming

* issue w/ safety

* fix config w/ safety

* update memory endpoints

* allow providers in api_providers

* configure script works

* all endpoints w/ build->configure->run simple local works

* new example run.yaml

* run openapi generator

tests/examples/local-run.yaml

@@ -0,0 +1,87 @@
+built_at: '2024-09-23T00:54:40.551416'
+image_name: test-2
+docker_image: null
+conda_env: test-2
+apis_to_serve:
+- shields
+- agents
+- models
+- memory
+- memory_banks
+- inference
+- safety
+api_providers:
+  inference:
+    providers:
+    - meta-reference
+  safety:
+    providers:
+    - meta-reference
+  agents:
+    provider_id: meta-reference
+    config:
+      persistence_store:
+        namespace: null
+        type: sqlite
+        db_path: /home/xiyan/.llama/runtime/kvstore.db
+  memory:
+    providers:
+    - meta-reference
+  telemetry:
+    provider_id: meta-reference
+    config: {}
+routing_table:
+  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
+    routing_key: Meta-Llama3.1-8B-Instruct
+  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
+    routing_key: llama_guard
+  - 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
+    routing_key: code_scanner_guard
+  - 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
+    routing_key: injection_shield
+  - 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
+    routing_key: jailbreak_shield
+  memory:
+  - provider_id: meta-reference
+    config: {}
+    routing_key: vector

tests/examples/router-local-run.yaml

@@ -1,50 +0,0 @@
-built_at: '2024-09-18T13:41:17.656743'
-image_name: local
-docker_image: null
-conda_env: local
-apis_to_serve:
-- inference
-- memory
-- telemetry
-- agents
-- safety
-- models
-provider_map:
-  telemetry:
-    provider_id: meta-reference
-    config: {}
-  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: {}
-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: vector
-      provider_id: meta-reference
-      config: {}

tests/examples/simple-local-run.yaml

@@ -1,40 +0,0 @@
-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
-- models
-- telemetry
-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: {}