model server build (#127)

* first commit to have model_server not be dependent on Docker

* making changes to fix the docker-compose file for archgw to set DNS_V4 and minor fixes with the build

* additional fixes for model server to be separated out in the build

* additional fixes for model server to be separated out in the build

* fix to get model_server to be built as a separate python process. TODO: fix the embeddings logs after cli completes

* fixing init to pull tempfile using the tempfile python package

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-261.local>

arch/docker-compose.yaml

@@ -7,24 +7,5 @@ services:
     volumes:
       - ${ARCH_CONFIG_FILE:-./demos/function_calling/arch_confg.yaml}:/config/arch_config.yaml
       - /etc/ssl/cert.pem:/etc/ssl/cert.pem
-    depends_on:
-      model_server:
-        condition: service_healthy
     env_file:
       - stage.env
-
-  model_server:
-    image: model_server:latest
-    ports:
-      - "18081:80"
-    healthcheck:
-        test: ["CMD", "curl" ,"http://localhost/healthz"]
-        interval: 5s
-        retries: 20
-    volumes:
-      - ~/.cache/huggingface:/root/.cache/huggingface
-    environment:
-      - OLLAMA_ENDPOINT=${OLLAMA_ENDPOINT:-host.docker.internal}
-      - OLLAMA_MODEL=Arch-Function-Calling-3B-Q4_K_M
-      - MODE=${MODE:-cloud}
-      - FC_URL=${FC_URL:-https://arch-fc-free-trial-4mzywewe.uc.gateway.dev/v1}