Add support for local llm (mistral 7b) (#31)

demos/weather-forecast-local-llm/docker-compose.yaml

@@ -0,0 +1,88 @@
+services:
+  config-generator:
+    build:
+      context: ../../
+      dockerfile: config_generator/Dockerfile
+    volumes:
+      - ./katanemo-config.yaml:/usr/src/app/katanemo-config.yaml
+      - ./generated:/usr/src/app/out
+  envoy:
+    build:
+      context: ../../
+      dockerfile: envoyfilter/Dockerfile
+    hostname: envoy
+    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
+      embeddingserver:
+        condition: service_healthy
+
+  embeddingserver:
+    build:
+      context: ../../embedding-server
+      dockerfile: Dockerfile
+    ports:
+      - "18081:80"
+    healthcheck:
+        test: ["CMD", "curl" ,"http://localhost:80/healthz"]
+        interval: 5s
+        retries: 20
+    volumes:
+      - ~/.cache/huggingface:/root/.cache/huggingface
+  qdrant:
+    image: qdrant/qdrant
+    hostname: vector-db
+    ports:
+      - 16333:6333
+      - 16334:6334
+
+  chatbot-ui:
+    build:
+      context: ../../chatbot-ui
+      dockerfile: Dockerfile
+    ports:
+      - "18080:8080"
+    environment:
+      - OPENAI_API_KEY=${OPENAI_API_KEY}
+      - CHAT_COMPLETION_ENDPOINT=http://envoy:10000/v1/chat/completions
+
+  prometheus:
+    image: prom/prometheus
+    container_name: prometheus
+    command:
+      - '--config.file=/etc/prometheus/prometheus.yaml'
+    ports:
+      - 9090:9090
+    restart: unless-stopped
+    volumes:
+      - ./prometheus:/etc/prometheus
+      - ./prom_data:/prometheus
+
+  grafana:
+    image: grafana/grafana
+    container_name: grafana
+    ports:
+      - 3000:3000
+    restart: unless-stopped
+    environment:
+      - GF_SECURITY_ADMIN_USER=admin
+      - GF_SECURITY_ADMIN_PASSWORD=grafana
+    volumes:
+      - ./grafana:/etc/grafana/provisioning/datasources
+      - ./grafana/dashboard.yaml:/etc/grafana/provisioning/dashboards/main.yaml
+      - ./grafana/dashboards:/var/lib/grafana/dashboards
+
+  mistral_7b_instruct:
+    image: ghcr.io/ggerganov/llama.cpp:server
+    hostname: mistral_7b_instruct
+    ports:
+      - "10001:10001"
+    volumes:
+      - ./mistral-7b-instruct-v0.2.Q4_K_M.gguf:/models/model.gguf
+    command: ["--host", "0.0.0.0", "--port", "10001", "-m", "/models/model.gguf"]