fix cli models and logs (#196)

* removing unnecessar setup.py files

* updated the cli for debug and access logs

* ran the pre-commit locally to fix pull request

* fixed bug where if archgw_process is None we didn't handle it gracefully

* Apply suggestions from code review

Co-authored-by: Adil Hafeez <[email protected]>

* fixed changes based on PR

* fixed version not found message

* fixed message based on PR feedback

* adding poetry lock

* fixed pre-commit

---------

Co-authored-by: Salman Paracha <[email protected]>
Co-authored-by: Adil Hafeez <[email protected]>

README.md

@@ -25,9 +25,9 @@ Engineered with purpose-built LLMs, Arch handles the critical but undifferentiat
 To get in touch with us, please join our [discord server](https://discord.gg/rSRQ9fv7). We will be monitoring that actively and offering support there.
 
 ## Demos
-* [Function Calling](demos/function_calling/README.md) - Walk through of critical function calling capabilities
-* [Insurance Agent](demos/insurance_agent/README.md) - Build a full insurance agent with arch
-* [Network Agent](demos/network_agent/README.md) - Build a networking co-pilot/agent agent with arch
+* [Function Calling](demos/function_calling/README.md) - Walk through of the core function calling capabilities Arch offers
+* [Insurance Agent](demos/insurance_agent/README.md) - Build a full insurance agent with Arch
+* [Network Agent](demos/network_agent/README.md) - Build a networking co-pilot/agent agent with Arch
 
 ## Quickstart
 
@@ -111,9 +111,9 @@ Make outbound calls via Arch
 import openai
 
 # Set the OpenAI API base URL to the Arch gateway endpoint
-openai.api_base = "http://127.0.0.1:51001/v1"
-
-# No need to set openai.api_key since it's configured in Arch's gateway
+openai.api_base = "http://127.0.0.1:12000/v1"
+# No need to set a specific openai.api_key since it's configured in Arch's gateway
+openai.api_key = "null"
 
 # Use the OpenAI client as usual
 response = openai.Completion.create(

arch/tools/cli/consts.py

@@ -1 +1,11 @@
 KATANEMO_DOCKERHUB_REPO = "katanemo/archgw"
+KATANEMO_LOCAL_MODEL_LIST = [
+    "katanemo/Arch-Guard-cpu",
+    "katanemo/Arch-Guard",
+    "katanemo/bge-large-en-v1.5",
+]
+SERVICE_NAME_ARCHGW = "archgw"
+SERVICE_NAME_MODEL_SERVER = "model_server"
+SERVICE_ALL = "all"
+MODEL_SERVER_LOG_FILE = "~/archgw_logs/modelserver.log"
+ACCESS_LOG_FILES = "~/archgw_logs/access*"

arch/tools/cli/core.py

@@ -3,9 +3,16 @@
 import time
 import pkg_resources
 import select
+import sys
+import glob
 from cli.utils import run_docker_compose_ps, print_service_status, check_services_state
 from cli.utils import getLogger
-import sys
+from cli.consts import (
+    KATANEMO_LOCAL_MODEL_LIST,
+    MODEL_SERVER_LOG_FILE,
+    ACCESS_LOG_FILES,
+)
+from huggingface_hub import snapshot_download
 
 log = getLogger(__name__)
 
@@ -37,6 +44,45 @@ def stream_gateway_logs(follow):
         log.info(f"Failed to stream logs: {str(e)}")
 
 
+def stream_model_server_logs(follow):
+    """
+    Get the model server logs, check if the user wants to follow/tail them.
+    """
+    log_file_expanded = os.path.expanduser(MODEL_SERVER_LOG_FILE)
+
+    stream_command = ["tail"]
+    if follow:
+        stream_command.append("-f")
+
+    stream_command.append(log_file_expanded)
+    subprocess.run(
+        stream_command,
+        check=True,
+        stdout=sys.stdout,
+        stderr=sys.stderr,
+    )
+
+
+def stream_access_logs(follow):
+    """
+    Get the archgw access logs
+    """
+    log_file_pattern_expanded = os.path.expanduser(ACCESS_LOG_FILES)
+    log_files = glob.glob(log_file_pattern_expanded)
+
+    stream_command = ["tail"]
+    if follow:
+        stream_command.append("-f")
+
+    stream_command.extend(log_files)
+    subprocess.run(
+        stream_command,
+        check=True,
+        stdout=sys.stdout,
+        stderr=sys.stderr,
+    )
+
+
 def start_arch(arch_config_file, env, log_timeout=120):
     """
     Start Docker Compose in detached mode and stream logs until services are healthy.
@@ -164,6 +210,12 @@ def stop_arch():
         log.info(f"Failed to shut down services: {str(e)}")
 
 
+def download_models_from_hf():
+    for model in KATANEMO_LOCAL_MODEL_LIST:
+        log.info(f"Downloading model: {model}")
+        snapshot_download(repo_id=model)
+
+
 def start_arch_modelserver():
     """
     Start the model server. This assumes that the archgw_modelserver package is installed locally