add bolt guard config (#55)

demos/prompt_guards/bolt_config.yaml

@@ -0,0 +1,48 @@
+default_prompt_endpoint: "127.0.0.1"
+load_balancing: "round_robin"
+timeout_ms: 5000
+
+
+# should not be here
+embedding_provider:
+  name: "bge-large-en-v1.5"
+  model: "BAAI/bge-large-en-v1.5"
+
+llm_providers:
+
+  - name: open-ai-gpt-4
+    api_key: $OPEN_AI_API_KEY
+    model: gpt-4
+    default: true
+
+prompt_guards:
+   input_guard:
+     - name: jailbreak
+       on_exception_message: Looks like you are curious about my abilities…
+     - name: toxic
+       on_exception_message: Looks like you are curious about my toxic detection abilities…
+
+prompt_targets:
+
+  - type: function_resolver
+    name: weather_forecast
+    description: This function resolver provides weather forecast information for a given city.
+    few_shot_examples:
+      - what is the weather in New York?
+      - how is the weather in San Francisco?
+      - what is the forecast in Chicago?
+    parameters:
+      - name: city
+        required: true
+        description: The city for which the weather forecast is requested.
+      - name: days
+        description: The number of days for which the weather forecast is requested.
+      - name: units
+        description: The units in which the weather forecast is requested.
+    endpoint:
+      cluster: weatherhost
+      path: /weather
+    system_prompt: |
+      You are a helpful weather forecaster. Use weater data that is provided to you. Please following following guidelines when responding to user queries:
+      - Use farenheight for temperature
+      - Use miles per hour for wind speed

demos/prompt_guards/docker-compose.yaml

@@ -0,0 +1,82 @@
+
+services:
+
+  config_generator:
+    build:
+      context: ../../
+      dockerfile: config_generator/Dockerfile
+    volumes:
+      - ../../envoyfilter/envoy.template.yaml:/usr/src/app/envoy.template.yaml
+      - ./bolt_config.yaml:/usr/src/app/bolt_config.yaml
+      - ./generated:/usr/src/app/out
+
+  bolt:
+    build:
+      context: ../../
+      dockerfile: envoyfilter/Dockerfile
+    hostname: bolt
+    ports:
+      - "10000:10000"
+      - "19901:9901"
+    volumes:
+      - ./generated/envoy.yaml:/etc/envoy/envoy.yaml
+      - /etc/ssl/cert.pem:/etc/ssl/cert.pem
+    depends_on:
+      config_generator:
+        condition: service_completed_successfully
+      model_server:
+        condition: service_healthy
+    environment:
+      - LOG_LEVEL=debug
+
+  model_server:
+    build:
+      context: ../../model_server
+      dockerfile: Dockerfile
+    ports:
+      - "18081:80"
+    healthcheck:
+        test: ["CMD", "curl" ,"http://localhost:80/healthz"]
+        interval: 5s
+        retries: 20
+    volumes:
+      - ~/.cache/huggingface:/root/.cache/huggingface
+
+  function_resolver:
+    build:
+      context: ../../function_resolver
+      dockerfile: Dockerfile
+    ports:
+      - "18082:80"
+    healthcheck:
+        test: ["CMD", "curl" ,"http://localhost:80/healthz"]
+        interval: 5s
+        retries: 20
+    volumes:
+      - ~/.cache/huggingface:/root/.cache/huggingface
+    environment:
+      # use ollama endpoint that is hosted by host machine (no virtualization)
+      - OLLAMA_ENDPOINT=host.docker.internal
+      # uncomment following line to use ollama endpoint that is hosted by docker
+      # - OLLAMA_ENDPOINT=ollama
+
+  ollama:
+    image: ollama/ollama
+    container_name: ollama
+    volumes:
+      - ./ollama:/root/.ollama
+    restart: unless-stopped
+    ports:
+      - '11434:11434'
+    profiles:
+      - manual
+
+  chatbot_ui:
+    build:
+      context: ../../chatbot_ui
+      dockerfile: Dockerfile
+    ports:
+      - "18080:8080"
+    environment:
+      - OPENAI_API_KEY=${OPENAI_API_KEY}
+      - CHAT_COMPLETION_ENDPOINT=http://bolt:10000/v1/chat/completions