Overhaul demos directory: cleanup, restructure, and standardize configs (#760)

demos/samples_python/multi_turn_rag_agent/config.yaml

@@ -1,58 +0,0 @@
-version: v0.1.0
-
-listeners:
-  ingress_traffic:
-    address: 0.0.0.0
-    port: 10000
-    message_format: openai
-    timeout: 30s
-
-endpoints:
-  rag_energy_source_agent:
-    endpoint: host.docker.internal:18083
-    connect_timeout: 0.005s
-
-llm_providers:
-  - access_key: $OPENAI_API_KEY
-    model: openai/gpt-4o-mini
-    default: true
-
-system_prompt: |
-  You are a helpful assistant and can offer information about energy sources.
-  You will get a JSON object with energy_source and consideration fields. Focus on answering the querstion using those fields.
-  Keep your responses to just three main points to make it easy for the reader to digest the information
-
-prompt_targets:
-  - name: get_info_for_energy_source
-    description: get information about an energy source
-    parameters:
-      - name: energy_source
-        type: str
-        description: a source of energy
-        required: true
-        enum: [renewable, fossil]
-      - name: consideration
-        type: str
-        description: a specific type of consideration for an energy source
-        enum: [cost, economic, technology]
-    endpoint:
-      name: rag_energy_source_agent
-      path: /agent/energy_source_info
-      http_method: POST
-
-  - name: default_target
-    default: true
-    description: This is the default target for all unmatched prompts.
-    endpoint:
-      name: rag_energy_source_agent
-      path: /default_target
-      http_method: POST
-    system_prompt: |
-      You are a helpful assistant! Summarize the user's request and provide a helpful response.
-    # if it is set to false arch will send response that it received from this prompt target to the user
-    # if true arch will forward the response to the default LLM
-    auto_llm_dispatch_on_response: false
-
-tracing:
-  random_sampling: 100
-  trace_arch_internal: true