config templates restructure, docs (#262)

* wip

* config templates

* readmes

llama_stack/distribution/templates/build_configs/local-gpu-docker-build.yaml

@@ -1,4 +1,4 @@
-name: local
+name: local-gpu
 distribution_spec:
   description: Use code from `llama_stack` itself to serve all llama stack APIs
   providers:
@@ -7,4 +7,4 @@ distribution_spec:
     safety: meta-reference
     agents: meta-reference
     telemetry: meta-reference
-image_type: conda
+image_type: docker

llama_stack/distribution/templates/build_configs/local-tgi-chroma-docker-build.yaml

@@ -1,11 +1,11 @@
-name: local-gpu
+name: local-tgi-chroma
 distribution_spec:
-  description: local meta reference
+  description: remote tgi inference + chromadb memory
   docker_image: null
   providers:
-    inference: meta-reference
+    inference: remote::tgi
     safety: meta-reference
     agents: meta-reference
-    memory: meta-reference
+    memory: remote::chromadb
     telemetry: meta-reference
 image_type: docker

llama_stack/distribution/templates/run_configs/local-run.yaml

@@ -1,16 +1,16 @@
 version: '2'
-built_at: '2024-10-08T17:42:33.690666'
-image_name: local-gpu
-docker_image: local-gpu
-conda_env: null
+built_at: '2024-10-08T17:40:45.325529'
+image_name: local
+docker_image: null
+conda_env: local
 apis:
-- memory
-- inference
-- agents
 - shields
-- safety
+- agents
 - models
+- memory
 - memory_banks
+- inference
+- safety
 providers:
   inference:
   - provider_id: meta-reference
@@ -25,8 +25,13 @@ providers:
   - provider_id: meta-reference
     provider_type: meta-reference
     config:
-      llama_guard_shield: null
-      prompt_guard_shield: null
+      llama_guard_shield:
+        model: Llama-Guard-3-1B
+        excluded_categories: []
+        disable_input_check: false
+        disable_output_check: false
+      prompt_guard_shield:
+        model: Prompt-Guard-86M
   memory:
   - provider_id: meta-reference
     provider_type: meta-reference

llama_stack/distribution/templates/run_configs/local-tgi-run.yaml

@@ -1,29 +1,33 @@
 version: '2'
-built_at: '2024-10-08T17:42:07.505267'
-image_name: local-cpu
-docker_image: local-cpu
-conda_env: null
+built_at: '2024-10-08T17:40:45.325529'
+image_name: local
+docker_image: null
+conda_env: local
 apis:
+- shields
 - agents
-- inference
 - models
 - memory
-- safety
-- shields
 - memory_banks
+- inference
+- safety
 providers:
   inference:
-  - provider_id: remote::ollama
-    provider_type: remote::ollama
+  - provider_id: tgi0
+    provider_type: remote::tgi
     config:
-      host: localhost
-      port: 6000
+      url: http://127.0.0.1:5009
   safety:
   - provider_id: meta-reference
     provider_type: meta-reference
     config:
-      llama_guard_shield: null
-      prompt_guard_shield: null
+      llama_guard_shield:
+        model: Llama-Guard-3-1B
+        excluded_categories: []
+        disable_input_check: false
+        disable_output_check: false
+      prompt_guard_shield:
+        model: Prompt-Guard-86M
   memory:
   - provider_id: meta-reference
     provider_type: meta-reference