kalavai-client 0.5.2__py3-none-any.whl → 0.5.12__py3-none-any.whl

kalavai_client/__init__.py

@@ -1,2 +1,2 @@
 
-__version__ = "0.5.2"
+__version__ = "0.5.12"

kalavai_client/assets/apps.yaml

@@ -139,7 +139,7 @@ releases:
     - name: replicas
       value: 2
     - name: image_tag
-      value: "v2025.01"
+      value: "v2025.01.1"
     - name: deployment.in_cluster
       value: "True"
     - name: deployment.use_auth_key
@@ -189,13 +189,13 @@ releases:
       value: "1"
     - name: devicePlugin.deviceSplitCount
       value: "1"
-    - name: scheduler.customWebhook.port
-      value: "30498"
-    - name: scheduler.service.schedulerPort
-      value: "30498"
-    - name: scheduler.service.monitorPort
-      value: "30493"
-    - name: devicePlugin.service.httpPort
-      value: "30492"
+    # - name: scheduler.customWebhook.port
+    #   value: "30498"
+    # - name: scheduler.service.schedulerPort
+    #   value: "30498"
+    # - name: scheduler.service.monitorPort
+    #   value: "30493"
+    # - name: devicePlugin.service.httpPort
+    #   value: "30492"
     
 

kalavai_client/assets/docker-compose-template.yaml

@@ -1,55 +1,107 @@
 services:
-   {{service_name}}-{{command}}:
-      image: bundenth/kalavai-runner:gpu-latest
-      container_name: {{service_name}}
-      hostname: {{hostname}}
-      privileged: true
-      restart: unless-stopped
-      ports:
-      - "6443:6443" # kube server
-      - "8472:8472" # flannel vxlan
-      - "51820:51820" # flannel wireguard
-{% if command == "server" %}
-      - "30000-30500:30000-30500"
+{% if vpn %}
+  {{vpn_name}}:
+    image: gravitl/netclient:v0.24.3
+    container_name: {{vpn_name}}
+    #privileged: true
+    cap_add:
+      - NET_ADMIN
+      - SYS_MODULE
+    network_mode: host
+    # networks:
+    # - custom-network
+    # ports:
+    # # https://docs.k3s.io/installation/requirements#inbound-rules-for-k3s-nodes
+    # - "6443:6443" # kube server
+    # - "10250:10250" # worker balancer
+    # - "8472:8472/udp" # flannel vxlan
+    # - "51820-51830:51820-51830" # flannel wireguard
+    # {% if command == "server" %}
+    # - "30000-30500:30000-30500"
+    # {% endif %}
+    environment:
+      - HOST_NAME={{node_name}}
+      - IFACE_NAME={{flannel_iface}}
+      - TOKEN={{vpn_token}}
+    volumes:
+      - /dev/net/tun:/dev/net/tun
+    restart: unless-stopped
+#   nginx:
+#     image: nginx:latest
+#     ports:
+#       - "{{redirect_source_port}}:{{redirect_source_port}}"
+#     restart: unless-stopped
+#     networks:
+#       - custom-network
+#     volumes:
+#       - {{nginx_path}}/nginx.conf:/etc/nginx/nginx.conf
 {% endif %}
-      networks:
-      - custom-network
-      command: >
-        {{command}}
-{% if command == "server" %}
-        --flannel-backend wireguard-native
-        --service-node-port-range "30000-30500"
-{% else %}
-        --server {{pool_ip}}
-        --token {{token}}
-{% endif %}
-        --node-label role={{command}}
-{% if node_labels %}
-        {{node_labels}}
-{% endif %}
-{% if num_gpus and num_gpus > 0 %}
-        --node-label gpu=on
-{% else %}
-        --node-label gpu=off
-{% endif %}
-        --node-ip {{ip_address}}
-        --node-external-ip {{ip_address}}
-{% if flannel_iface %}
-        --flannel-iface {{flannel_iface}}
-{% endif %}
-      volumes:
-      - {{k3s_path}}:/var/lib/rancher/k3s # Persist data
-      - {{etc_path}}:/etc/rancher/k3s # Config files
-{% if num_gpus and num_gpus > 0 %}
-      deploy:
-        resources:
-          reservations:
-            devices:
-            - driver: nvidia
-              count: {{num_gpus}}
-              capabilities: [gpu]
+
+# run worker only if command is set
+{%if command %}
+  {{service_name}}:
+    image: docker.io/bundenth/kalavai-runner:gpu-latest
+    container_name: {{service_name}}
+  {% if vpn %}
+    depends_on:
+    - {{vpn_name}}
+    network_mode: "service:{{vpn_name}}"
+  {% else %}
+    network_mode: host
+    # hostname: {{node_name}}
+    # networks:
+    # - custom-network
+    # ports:
+    # - "6443:6443" # kube server
+    # - "2379-2380:2379-2380" # etcd server
+    # - "10259:10259" # kube scheduler
+    # - "10257:10257" # kube controller manager
+    # - "10250:10250" # worker balancer
+    # - "8285:8285" # flannel
+    # - "8472:8472" # flannel vxlan
+    # - "51820:51820" # flannel wireguard
+    # {% if command == "server" %}
+    # - "30000-32767:30000-32767"
+    # {% endif %}
+  {% endif %}
+    privileged: true
+    restart: unless-stopped
+    command: >
+      --command={{command}}
+      {% if command == "server" %}
+      --port_range="30000-32767"
+      {% else %}
+      --server_ip={{pool_ip}}
+      --token={{pool_token}}
+      {% endif %}
+      {%if vpn %}
+      --flannel_iface={{flannel_iface}}
+      {% endif %}
+      {% if num_gpus and num_gpus > 0 %}
+      --gpu=on
+      {% else %}
+      --gpu=off
+      {% endif %}
+      {% if node_labels %}
+      --extra="{{node_labels}}"
+      {% endif %}
+
+    volumes:
+    - {{k3s_path}}:/var/lib/rancher/k3s # Persist data
+    - {{etc_path}}:/etc/rancher/k3s # Config files
+
+  {% if num_gpus and num_gpus > 0 %}
+    deploy:
+      resources:
+        reservations:
+          devices:
+          - driver: nvidia
+            count: {{num_gpus}}
+            capabilities: [gpu]
+  {% endif %}
 {% endif %}
 
 networks:
   custom-network:
-    driver: bridge
+    driver: bridge
+

kalavai_client/assets/nginx.conf

@@ -0,0 +1,12 @@
+events {}
+
+http {
+    server {
+        listen {{redirect_source_port}};
+        server_name localhost;
+
+        location / {
+                proxy_pass http://{{redirect_container}}:{{redirect_target_port}};
+        }
+    }
+}

kalavai_client/cli.py

@@ -31,6 +31,7 @@ from kalavai_client.utils import (
     safe_remove,
     leave_vpn,
     join_vpn,
+    get_vpn_details,
     load_server_info,
     user_login,
     user_logout,
@@ -81,15 +82,17 @@ STORAGE_ACCESS_MODE = ["ReadWriteOnce"]
 STORAGE_CLASS_LABEL = "kalavai.storage.enabled"
 DEFAULT_STORAGE_NAME = "pool-cache"
 DEFAULT_STORAGE_SIZE = 20
+DEFAULT_WATCHER_PORT = 30001
 USER_NODE_LABEL = "kalavai.cluster.user"
 KUBE_VERSION = os.getenv("KALAVAI_KUBE_VERSION", "v1.31.1+k3s1")
-DEFAULT_FLANNEL_IFACE = os.getenv("KALAVAI_FLANNEL_IFACE", "netmaker")
+DEFAULT_FLANNEL_IFACE = os.getenv("KALAVAI_FLANNEL_IFACE", "netmaker-1")
 FORBIDEDEN_IPS = ["127.0.0.1"]
 # kalavai templates
 HELM_APPS_FILE = resource_path("kalavai_client/assets/apps.yaml")
 HELM_APPS_VALUES = resource_path("kalavai_client/assets/apps_values.yaml")
 # user specific config files
-DEFAULT_CONTAINER_NAME = "kalavai-seed"
+DEFAULT_CONTAINER_NAME = "kalavai"
+DEFAULT_VPN_CONTAINER_NAME = "kalavai-vpn"
 CONTAINER_HOST_PATH = user_path("pool/", create_path=True)
 USER_COMPOSE_FILE = user_path("docker-compose-worker.yaml")
 USER_VPN_COMPOSE_FILE = user_path("docker-compose-vpn.yaml")
@@ -115,27 +118,6 @@ CLUSTER = dockerCluster(
 ######################
 ## HELPER FUNCTIONS ##
 ######################
-
-def check_vpn_compatibility():
-    """Check required packages to join VPN"""
-    logs = []
-    console.log("[white]Checking system requirements...")
-    # netclient
-    try:
-        run_cmd("sudo netclient version >/dev/null 2>&1")
-    except:
-        logs.append("[red]Netmaker not installed. Install instructions:\n")
-        logs.append("   Linux: https://docs.netmaker.io/docs/netclient#linux\n")
-        logs.append("   Windows: https://docs.netmaker.io/docs/netclient#windows\n")
-        logs.append("   MacOS: https://docs.netmaker.io/docs/netclient#mac\n")
-    
-    if len(logs) == 0:
-        console.log("[green]System is ready to join a pool")
-        return True
-    else:
-        for log in logs:
-            console.log(log)
-        return False
     
 def check_seed_compatibility():
     """Check required packages to start pools"""
@@ -179,16 +161,6 @@ def check_worker_compatibility():
 
 
 def cleanup_local():
-    # disconnect from private network
-    console.log("Disconnecting from VPN...")
-    try:
-        vpns = leave_vpn()
-        if vpns is not None:
-            for vpn in vpns:
-                console.log(f"You have left {vpn} VPN")
-    except:
-        # no vpn
-        pass
     console.log("Removing local cache files...")
     safe_remove(CONTAINER_HOST_PATH)
     safe_remove(USER_COMPOSE_FILE)
@@ -365,32 +337,37 @@ def select_token_type():
             break
     return {"admin": choice == 0, "user": choice == 1, "worker": choice == 2}
 
-def generate_compose_config(role, node_name, ip_address, node_labels, is_public, server=None, token=None):
+def generate_compose_config(role, node_name, is_public, use_gpus=True, node_labels=None, pool_ip=None, vpn_token=None, pool_token=None):
     num_gpus = 0
-    try:
-        has_gpus = check_gpu_drivers()
-        if has_gpus:
-            max_gpus = int(run_cmd("nvidia-smi -L | wc -l").decode())
-            num_gpus = user_confirm(
-                question=f"{max_gpus} NVIDIA GPU(s) detected. How many GPUs would you like to include?",
-                options=range(max_gpus+1)
-            ) 
-    except:
-        console.log(f"[red]WARNING: error when fetching NVIDIA GPU info. GPUs will not be used on this local machine")
+    if use_gpus:
+        try:
+            has_gpus = check_gpu_drivers()
+            if has_gpus:
+                max_gpus = int(run_cmd("nvidia-smi -L | wc -l").decode())
+                num_gpus = user_confirm(
+                    question=f"{max_gpus} NVIDIA GPU(s) detected. How many GPUs would you like to include?",
+                    options=range(max_gpus+1)
+                ) 
+        except:
+            console.log(f"[red]WARNING: error when fetching NVIDIA GPU info. GPUs will not be used on this local machine")
+    if node_labels is not None:
+        node_labels = " ".join([f"--node-label {key}={value}" for key, value in node_labels.items()])
     compose_values = {
         "user_path": user_path(""),
         "service_name": DEFAULT_CONTAINER_NAME,
-        "pool_ip": server,
-        "token": token,
-        "hostname": node_name,
+        "vpn": is_public,
+        "vpn_name": DEFAULT_VPN_CONTAINER_NAME,
+        "pool_ip": pool_ip,
+        "pool_token": pool_token,
+        "vpn_token": vpn_token,
+        "node_name": node_name,
         "command": role,
         "storage_enabled": "True",
-        "ip_address": ip_address,
         "num_gpus": num_gpus,
         "k3s_path": f"{CONTAINER_HOST_PATH}/k3s",
         "etc_path": f"{CONTAINER_HOST_PATH}/etc",
-        "node_labels": " ".join([f"--node-label {key}={value}" for key, value in node_labels.items()]),
-        "flannel_iface": DEFAULT_FLANNEL_IFACE if is_public else None
+        "node_labels": node_labels,
+        "flannel_iface": DEFAULT_FLANNEL_IFACE if is_public else ""
     }
     # generate local config files
     compose_yaml = load_template(
@@ -585,35 +562,56 @@ def pool__start(cluster_name, *others,  only_registered_users: bool=False, ip_ad
         STORAGE_CLASS_LABEL: is_storage_compatible()
     }
     if location is not None:
-        console.log("Joining private network")
+        console.log("Fetching VPN credentials")
         try:
-            if not check_vpn_compatibility():
-                return
-            vpn = join_vpn(
+            vpn = get_vpn_details(
                 location=location,
                 user_cookie=USER_COOKIE)
             node_labels[USER_NODE_LABEL] = user["username"]
         except Exception as e:
             console.log(f"[red]Error when joining network: {str(e)}")
             return
-
-    if ip_address is None:
-        console.log(f"Scanning for valid IPs (subnet {vpn['subnet']})...")
-        ip_address = select_ip_address(subnet=vpn["subnet"])
+    
+    # Generate docker compose recipe
+    generate_compose_config(
+        role="server",
+        vpn_token=vpn["key"],
+        node_name=socket.gethostname(),
+        node_labels=node_labels,
+        is_public=location is not None
+    )
+    
+    # start server
+    console.log("Deploying seed...")
+    CLUSTER.start_seed_node()
+    
+    while not CLUSTER.is_agent_running():
+        console.log("Waiting for seed to start...")
+        time.sleep(10)
+    
+    # select IP address (for external discovery)
+    if ip_address is None and location is None:
+        # local IP
+        console.log(f"Scanning for valid IPs")
+        ip_address = select_ip_address()
+    else:
+        # load VPN ip
+        ip_address = CLUSTER.get_vpn_ip()
     console.log(f"Using {ip_address} address for server")
 
+    # populate local cred files
     auth_key = str(uuid.uuid4())
     write_auth_key = str(uuid.uuid4())
     readonly_auth_key = str(uuid.uuid4())
-    watcher_port = 30001
-    watcher_service = f"{ip_address}:{watcher_port}"
+    
+    watcher_service = f"{ip_address}:{DEFAULT_WATCHER_PORT}"
     values = {
         CLUSTER_NAME_KEY: cluster_name,
         CLUSTER_IP_KEY: ip_address,
         AUTH_KEY: auth_key,
         READONLY_AUTH_KEY: readonly_auth_key,
         WRITE_AUTH_KEY: write_auth_key,
-        WATCHER_PORT_KEY: watcher_port,
+        WATCHER_PORT_KEY: DEFAULT_WATCHER_PORT,
         WATCHER_SERVICE_KEY: watcher_service,
         USER_NODE_LABEL_KEY: USER_NODE_LABEL,
         ALLOW_UNREGISTERED_USER_KEY: not only_registered_users
@@ -630,15 +628,6 @@ def pool__start(cluster_name, *others,  only_registered_users: bool=False, ip_ad
         cluster_name=cluster_name,
         public_location=location,
         user_api_key=user["api_key"])
-
-    # 1. Generate docker compose recipe
-    compose_yaml = generate_compose_config(
-        role="server",
-        node_name=socket.gethostname(),
-        ip_address=ip_address,
-        node_labels=node_labels,
-        is_public=location is not None
-    )
     
     # Generate helmfile recipe
     helm_yaml = load_template(
@@ -650,14 +639,6 @@ def pool__start(cluster_name, *others,  only_registered_users: bool=False, ip_ad
         f.write(helm_yaml)
     
     console.log("[green]Config files have been generated in your local machine\n")
-
-    # # 1. start server
-    console.log("Deploying seed...")
-    CLUSTER.start_seed_node()
-    
-    while not CLUSTER.is_agent_running():
-        console.log("Waiting for seed to start...")
-        time.sleep(10)
     
     console.log("Setting pool dependencies...")
     # set template values in helmfile
@@ -691,7 +672,6 @@ def pool__start(cluster_name, *others,  only_registered_users: bool=False, ip_ad
 
     return None
 
-
 @arguably.command
 def pool__token(*others, admin=False, user=False, worker=False):
     """
@@ -773,6 +753,7 @@ def pool__join(token, *others, node_name=None, ip_address: str=None):
     if CLUSTER.is_agent_running():
         console.log(f"[white] You are already connected to {load_server_info(data_key=CLUSTER_NAME_KEY, file=USER_LOCAL_SERVER_FILE)}. Enter [yellow]kalavai pool stop[white] to exit and join another one.")
         return
+    
     # check that is not attached to another instance
     if os.path.exists(USER_LOCAL_SERVER_FILE):
         option = user_confirm(
@@ -810,20 +791,20 @@ def pool__join(token, *others, node_name=None, ip_address: str=None):
     }
     user = defaultdict(lambda: None)
     if public_location is not None:
-        console.log("Joining private network")
+        user = user_login(user_cookie=USER_COOKIE)
+        if user is None:
+            console.log("[red]Must be logged in to join public pools. Run [yellow]kalavai login[red] to authenticate")
+            exit()
+        console.log("Fetching VPN credentials")
         try:
-            if not check_vpn_compatibility():
-                return
-            vpn = join_vpn(
+            vpn = get_vpn_details(
                 location=public_location,
                 user_cookie=USER_COOKIE)
-            user = user_login(user_cookie=USER_COOKIE)
             node_labels[USER_NODE_LABEL] = user["username"]
         except Exception as e:
             console.log(f"[red]Error when joining network: {str(e)}")
             console.log("Are you authenticated? Try [yellow]kalavai login")
             return
-        # validate public seed
         try:
             validate_join_public_seed(
                 cluster_name=cluster_name,
@@ -832,31 +813,29 @@ def pool__join(token, *others, node_name=None, ip_address: str=None):
             )
         except Exception as e:
             console.log(f"[red]Error when joining network: {str(e)}")
-            leave_vpn(vpn_file=USER_VPN_COMPOSE_FILE)
             return
 
     # send note to server to let them know the node is coming online
-    if not pre_join_check(node_name=node_name, server_url=watcher_service, server_key=auth_key):
-        console.log(f"[red] Failed pre join checks. Server offline or node '{node_name}' may already exist. Please specify a different one with '--node-name'")
-        leave_vpn(vpn_file=USER_VPN_COMPOSE_FILE)
-        return
-
-    if ip_address is None:
-        console.log(f"Scanning for valid IPs (subnet {vpn['subnet']})...")
-        ip_address = select_ip_address(subnet=vpn["subnet"])
-    console.log(f"Using {ip_address} address for worker")
+    # TODO: won't be able to check for VPN pools...
+    # if not pre_join_check(node_name=node_name, server_url=watcher_service, server_key=auth_key):
+    #     console.log(f"[red] Failed pre join checks. Server offline or node '{node_name}' may already exist. Please specify a different one with '--node-name'")
+    #     leave_vpn(container_name=DEFAULT_VPN_CONTAINER_NAME)
+    #     return
         
     # local agent join
     # 1. Generate local cache files
     console.log("Generating config files...")
-    compose_yaml = generate_compose_config(
+    
+    # Generate docker compose recipe
+    generate_compose_config(
         role="agent",
-        server=f"https://{kalavai_seed_ip}:6443",
-        token=kalavai_token,
-        node_name=socket.gethostname(),
-        ip_address=ip_address,
+        pool_ip=f"https://{kalavai_seed_ip}:6443",
+        pool_token=kalavai_token,
+        vpn_token=vpn["key"],
+        node_name=node_name,
         node_labels=node_labels,
         is_public=public_location is not None)
+    
     store_server_info(
         server_ip=kalavai_seed_ip,
         auth_key=auth_key,
@@ -866,8 +845,6 @@ def pool__join(token, *others, node_name=None, ip_address: str=None):
         cluster_name=cluster_name,
         public_location=public_location,
         user_api_key=user["api_key"])
-    
-    init_user_workspace()
 
     option = user_confirm(
         question="Docker compose ready. Would you like Kalavai to deploy it?",
@@ -883,18 +860,23 @@ def pool__join(token, *others, node_name=None, ip_address: str=None):
         CLUSTER.start_worker_node()
     except Exception as e:
         console.log(f"[red] Error connecting to {cluster_name} @ {kalavai_seed_ip}. Check with the admin if the token is still valid.")
-        leave_vpn(vpn_file=USER_VPN_COMPOSE_FILE)
+        leave_vpn(container_name=DEFAULT_VPN_CONTAINER_NAME)
         exit()
 
-    while not CLUSTER.is_agent_running():
-        console.log("Waiting for worker to start...")
-        time.sleep(10)
+    # ensure we are connected
+    while True:
+        console.log("Waiting for core services to be ready, may take a few minutes...")
+        time.sleep(30)
+        if is_watcher_alive(server_creds=USER_LOCAL_SERVER_FILE, user_cookie=USER_COOKIE):
+            break
+    
+    init_user_workspace()
     
     # set status to schedulable
     console.log(f"[green] You are connected to {cluster_name}")
 
 @arguably.command
-def pool__stop(*others):
+def pool__stop(*others, skip_node_deletion=False):
     """
     Stop sharing your device and clean up. DO THIS ONLY IF YOU WANT TO REMOVE KALAVAI-CLIENT from your device.
 
@@ -903,7 +885,8 @@ def pool__stop(*others):
     """
     console.log("[white] Stopping kalavai app...")
     # delete local node from server
-    node__delete(load_server_info(data_key=NODE_NAME_KEY, file=USER_LOCAL_SERVER_FILE))
+    if not skip_node_deletion:
+        node__delete(load_server_info(data_key=NODE_NAME_KEY, file=USER_LOCAL_SERVER_FILE))
     # unpublish event (only if seed node)
     # TODO: no, this should be done via the platform!!!
     # try:
@@ -916,7 +899,20 @@ def pool__stop(*others):
     #     console.log(f"[red][WARNING]: (ignore if not a public pool) Error when unpublishing cluster. {str(e)}")
     # remove local node agent
     console.log("Removing agent and local cache")
+    
+    # disconnect from VPN first, then remove agent, then remove local files
+    console.log("Disconnecting from VPN...")
+    try:
+        vpns = leave_vpn(container_name=DEFAULT_VPN_CONTAINER_NAME)
+        if vpns is not None:
+            for vpn in vpns:
+                console.log(f"You have left {vpn} VPN")
+    except:
+        # no vpn
+        pass
+
     CLUSTER.remove_agent()
+
     # clean local files
     cleanup_local()
     console.log("[white] Kalavai has stopped sharing your resources. Use [yellow]kalavai pool start[white] or [yellow]kalavai pool join[white] to start again!")
@@ -1107,6 +1103,11 @@ def pool__attach(token, *others, node_name=None):
     """
     Set creds in token on the local instance
     """
+
+    if node_name is None:
+        node_name = socket.gethostname()
+    
+    # check that is not attached to another instance
     if os.path.exists(USER_LOCAL_SERVER_FILE):
         option = user_confirm(
             question="You seem to be connected to an instance already. Are you sure you want to join a new one?",
@@ -1115,34 +1116,39 @@ def pool__attach(token, *others, node_name=None):
         if option == 0:
             console.log("[green]Nothing happened.")
             return
+    
+    # check token
+    if not pool__check_token(token):
+        return
+
     try:
         data = decode_dict(token)
         kalavai_seed_ip = data[CLUSTER_IP_KEY]
-        kalavai_token = data[CLUSTER_TOKEN_KEY]
         cluster_name = data[CLUSTER_NAME_KEY]
         auth_key = data[AUTH_KEY]
         watcher_service = data[WATCHER_SERVICE_KEY]
         public_location = data[PUBLIC_LOCATION_KEY]
-    except:
-        console.log("[red]Error when parsing token. Invalid token")
+        vpn = defaultdict(lambda: None)
+    except Exception as e:
+        console.log(str(e))
+        console.log("[red] Invalid token")
         return
-
+    
     user = defaultdict(lambda: None)
     if public_location is not None:
-        console.log("Joining private network")
+        user = user_login(user_cookie=USER_COOKIE)
+        if user is None:
+            console.log("[red]Must be logged in to join public pools. Run [yellow]kalavai login[red] to authenticate")
+            exit()
+        console.log("Fetching VPN credentials")
         try:
-            if not check_vpn_compatibility():
-                return
-            vpn = join_vpn(
+            vpn = get_vpn_details(
                 location=public_location,
                 user_cookie=USER_COOKIE)
-            user = user_login(user_cookie=USER_COOKIE)
-            time.sleep(5)
         except Exception as e:
             console.log(f"[red]Error when joining network: {str(e)}")
             console.log("Are you authenticated? Try [yellow]kalavai login")
             return
-        # validate public seed
         try:
             validate_join_public_seed(
                 cluster_name=cluster_name,
@@ -1151,9 +1157,20 @@ def pool__attach(token, *others, node_name=None):
             )
         except Exception as e:
             console.log(f"[red]Error when joining network: {str(e)}")
-            leave_vpn(vpn_file=USER_VPN_COMPOSE_FILE)
             return
-
+        
+    # local agent join
+    # 1. Generate local cache files
+    console.log("Generating config files...")
+    
+    # Generate docker compose recipe
+    generate_compose_config(
+        use_gpus=False,
+        role="",
+        vpn_token=vpn["key"],
+        node_name=node_name,
+        is_public=public_location is not None)
+    
     store_server_info(
         server_ip=kalavai_seed_ip,
         auth_key=auth_key,
@@ -1164,7 +1181,26 @@ def pool__attach(token, *others, node_name=None):
         public_location=public_location,
         user_api_key=user["api_key"])
 
-    console.log(f"[green]You are now connected to {cluster_name} @ {kalavai_seed_ip}")
+    option = user_confirm(
+        question="Docker compose ready. Would you like Kalavai to deploy it?",
+        options=["no", "yes"]
+    )
+    if option == 0:
+        console.log("Manually deploy the worker with the following command:\n")
+        print(f"docker compose -f {USER_COMPOSE_FILE} up -d")
+        return
+    
+    console.log(f"[white] Connecting to {cluster_name} @ {kalavai_seed_ip} (this may take a few minutes)...")
+    run_cmd(f"docker compose -f {USER_COMPOSE_FILE} up -d")
+    # ensure we are connected
+    while True:
+        console.log("Waiting for core services to be ready, may take a few minutes...")
+        time.sleep(30)
+        if is_watcher_alive(server_creds=USER_LOCAL_SERVER_FILE, user_cookie=USER_COOKIE):
+            break
+    
+    # set status to schedulable
+    console.log(f"[green] You are connected to {cluster_name}")
 
 
 @arguably.command
@@ -1480,6 +1516,62 @@ def job__run(template_name, *others, values: str=None, force_namespace: str=None
         console.log(f"[red]Error when connecting to kalavai service: {str(e)}")
         return
 
+@arguably.command
+def job__test(local_template_dir, *others, values, defaults, force_namespace: str=None):
+    """
+    Helper to test local templates, useful for development
+    """
+    try:
+        CLUSTER.validate_cluster()
+    except Exception as e:
+        console.log(f"[red]Problems with your pool: {str(e)}")
+        return
+    
+    if not os.path.isdir(local_template_dir):
+        console.log(f"[red]--local_template_dir ({local_template_dir}) is not a directory")
+        return
+    
+    # load template
+    with open(os.path.join(local_template_dir, "template.yaml"), "r") as f:
+        template_str = f.read()
+    
+    # load values
+    if not os.path.isfile(values):
+        console.log(f"[red]--values ({values}) is not a valid local file")
+        return
+    with open(values, "r") as f:
+        values_dict = yaml.safe_load(f)
+    # load defaults
+    if not os.path.isfile(defaults):
+        console.log(f"[red]--defaults ({defaults}) is not a valid local file")
+        return
+    with open(defaults, "r") as f:
+        defaults = f.read()
+    
+    # submit custom deployment
+    data = {
+        "template": template_str,
+        "template_values": values_dict,
+        "default_values": defaults
+    }
+    if force_namespace is not None:
+        data["force_namespace"] = force_namespace
+
+    try:
+        result = request_to_server(
+            method="post",
+            endpoint="/v1/deploy_custom_job",
+            data=data,
+            server_creds=USER_LOCAL_SERVER_FILE,
+            user_cookie=USER_COOKIE
+        )
+        console.log("Deployment result:")
+        print(
+            json.dumps(result,indent=3)
+        )
+    except Exception as e:
+        console.log(f"[red]Error when connecting to kalavai service: {str(e)}")
+
 
 @arguably.command
 def job__defaults(template_name, *others):

kalavai_client/cluster.py

@@ -7,7 +7,8 @@ from kalavai_client.utils import (
     run_cmd,
     check_gpu_drivers,
     validate_poolconfig,
-    user_path
+    user_path,
+    populate_template
 )
 
 
@@ -20,6 +21,9 @@ class Cluster(ABC):
     def start_worker_node(self, url, token, node_name, auth_key, watcher_service, ip_address, labels, flannel_iface):
         raise NotImplementedError()
 
+    @abstractmethod
+    def get_vpn_ip(self):
+        raise NotImplementedError()
 
     @abstractmethod
     def update_dependencies(self, dependencies_files):
@@ -79,11 +83,23 @@ class dockerCluster(Cluster):
     def start_seed_node(self):
         
         run_cmd(f"docker compose -f {self.compose_file} up -d")
-        time.sleep(5)
-        run_cmd(f"docker cp {self.container_name}:/etc/rancher/k3s/k3s.yaml {self.kubeconfig_file}")
+        # wait for container to be setup
+        while True:
+            try:
+                run_cmd(f"docker cp {self.container_name}:/etc/rancher/k3s/k3s.yaml {self.kubeconfig_file} >/dev/null 2>&1")
+                break
+            except:
+                pass
+            time.sleep(5)
 
     def start_worker_node(self):
         run_cmd(f"docker compose -f {self.compose_file} up -d")
+    
+    def get_vpn_ip(self):
+        command = populate_template(
+            template_str="docker exec -it {{container_name}} ifconfig {{iface_name}} | grep 'inet ' | awk '{gsub(/^addr:/, \"\", $2); print $2}'",
+            values_dict={"container_name": self.container_name, "iface_name": self.default_flannel_iface})
+        return run_cmd(command).decode().strip()
         
 
     def update_dependencies(self, dependencies_file=None, debug=False, retries=3):
@@ -122,8 +138,13 @@ class dockerCluster(Cluster):
     def is_seed_node(self):
         if not os.path.isfile(self.compose_file):
             return False
-        status = "server" in run_cmd(f"docker compose -f {self.compose_file} ps --services --status=running").decode()
-        return status
+        if not self.is_agent_running():
+            return False
+        try:
+            run_cmd(f"docker container exec {self.container_name} cat /var/lib/rancher/k3s/server/node-token >/dev/null 2>&1")
+            return True
+        except:
+            return False
     
     def is_cluster_init(self):
         if not os.path.isfile(self.compose_file):

kalavai_client/utils.py

@@ -2,7 +2,6 @@ import json, base64
 import os
 import requests
 from pathlib import Path
-from urllib.parse import urljoin
 import shutil
 import subprocess
 import re
@@ -12,10 +11,7 @@ from jinja2 import Template
 
 from rich.table import Table
 import yaml
-import platform
-import psutil
 
-import GPUtil
 
 from kalavai_client.auth import KalavaiAuthClient
 
@@ -245,12 +241,12 @@ def join_vpn(location, user_cookie):
     run_cmd(f"sudo netclient join -t {token} >/dev/null 2>&1")
     return vpn
 
-def leave_vpn():
+def leave_vpn(container_name):
     try:
-        vpns = json.loads(run_cmd("sudo netclient list").decode())
+        vpns = json.loads(run_cmd(f"docker exec {container_name} netclient list").decode())
         left_vpns = [vpn['network'] for vpn in vpns]
         for vpn in left_vpns:
-            run_cmd(f"sudo netclient leave {vpn}")
+            run_cmd(f"docker exec {container_name} netclient leave {vpn}")
         return left_vpns
     except:
         return None
@@ -288,8 +284,11 @@ def request_to_server(
         json=data,
         headers=headers
     )
-    result = response.json()
-    return result
+    try:
+        result = response.json()
+        return result
+    except Exception as e:
+        raise ValueError(f"Error with HTTP request: {response.text}\n{str(e)}")
 
 
 def generate_table(columns, rows, end_sections=None):
@@ -387,48 +386,13 @@ def encode_dict(data: dict):
 def decode_dict(str_data: str):
     return json.loads(base64.b64decode(str_data.encode()))
 
-def get_gpus():
-    GPUs = GPUtil.getGPUs()
-    gpus = []
-    for gpu in GPUs:
-        name = "nvidia" if "nvidia" in gpu.name.lower() else None
-        if name is None:
-            continue
-        mem = int(gpu.memoryTotal / 1000) # in GBs
-        gpus.append(f"{name}-{mem}GB")
-    return ",".join(gpus)
-
-def system_uptick_request(username, node_name, backend_endpoint, backend_api_key, local_version=0):
-    gpus = get_gpus()
-    data = {
-        "username": username,
-        "system_info": {
-            "os": platform.system(),
-            "cpu_count": os.cpu_count(),
-            "cpu": platform.processor(),
-            "platform": platform.platform(),
-            "ram": round(psutil.virtual_memory().total / (1024.0 **3)),
-            "hostname": node_name,
-            "gpus": gpus
-        },
-        "version": local_version
-    }
-
-    response = requests.post(
-        url=urljoin(backend_endpoint, "/uptick"),
-        json=data,
-        headers={'X-API-KEY': backend_api_key}
-    )
-    response.raise_for_status()
-    return response.json()
-
 def resource_path(relative_path: str):
     """ Get absolute path to resource """
     try:
         last_slash = relative_path.rfind("/") 
         path = relative_path[:last_slash].replace("/", ".")
         filename = relative_path[last_slash+1:]
-        resource = importlib.resources.path(path, filename)
+        resource = str(importlib.resources.files(path).joinpath(filename))
     except Exception as e:
         return None
     return resource

{kalavai_client-0.5.2.dist-info → kalavai_client-0.5.12.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: kalavai-client
-Version: 0.5.2
+Version: 0.5.12
 Summary: Client app for kalavai platform
 License: Apache-2.0
 Keywords: LLM,platform
@@ -8,9 +8,13 @@ Author: Carlos Fernandez Musoles
 Author-email: carlos@kalavai.net
 Maintainer: Carlos Fernandez Musoles
 Maintainer-email: carlos@kalavai.net
-Requires-Python: >=3.8
+Requires-Python: >=3.4
 Classifier: License :: OSI Approved :: Apache Software License
 Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.4
+Classifier: Programming Language :: Python :: 3.5
+Classifier: Programming Language :: Python :: 3.6
+Classifier: Programming Language :: Python :: 3.7
 Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
@@ -22,7 +26,6 @@ Requires-Dist: Pillow (==10.3.0)
 Requires-Dist: anvil-uplink (==0.5.1)
 Requires-Dist: arguably (>=1.2.5)
 Requires-Dist: build ; extra == "dev"
-Requires-Dist: gputil (==1.4.0)
 Requires-Dist: importlib_resources (==6.5.2)
 Requires-Dist: jinja2 (==3.1.4)
 Requires-Dist: netifaces (==0.11.0)
@@ -32,7 +35,7 @@ Requires-Dist: pyinstaller (==6.5.0) ; extra == "dev"
 Requires-Dist: pyyaml (==6.0.2)
 Requires-Dist: requests (>=2.25)
 Requires-Dist: rich (==13.7.1)
-Requires-Dist: setuptools (<70.0.0)
+Requires-Dist: setuptools (>75.0.0)
 Requires-Dist: twine ; extra == "dev"
 Project-URL: Homepage, https://platform.kalavai.net
 Project-URL: Website, https://kalavai.net
@@ -47,7 +50,7 @@ Description-Content-Type: text/markdown
 
 </div>
 
-⭐⭐⭐ **Kalavai and our LLM pools are open source, and free to use in both commercial and non-commercial purposes. If you find it useful, consider supporting us by [staring our GitHub project](https://github.com/kalavai-net/kalavai-client), joining our [discord channel](https://discord.gg/HJ8FNapQ), follow our [Substack](https://kalavainet.substack.com/) and give us a [review on Product Hunt](https://www.producthunt.com/products/kalavai/reviews/new).**
+⭐⭐⭐ **Kalavai and our LLM pools are open source, and free to use in both commercial and non-commercial purposes. If you find it useful, consider supporting us by [giving a star to our GitHub project](https://github.com/kalavai-net/kalavai-client), joining our [discord channel](https://discord.gg/HJ8FNapQ), follow our [Substack](https://kalavainet.substack.com/) and give us a [review on Product Hunt](https://www.producthunt.com/products/kalavai/reviews/new).**
 
 
 # Kalavai: turn your devices into a scalable LLM platform
@@ -86,6 +89,7 @@ https://github.com/user-attachments/assets/0d2316f3-79ea-46ac-b41e-8ef720f52672
 
 ### News updates
 
+- 31 January 2025: `kalavai-client` is now a [PyPI package](https://pypi.org/project/kalavai-client/), easier to install than ever!
 - 27 January 2025: Support for accessing pools from remote computers
 - 9 January 2025: Added support for [Aphrodite Engine](https://github.com/aphrodite-engine/aphrodite-engine) models
 - 8 January 2025: Release of [a free, public, shared pool](/docs/docs/public_llm_pool.md) for community LLM deployment
@@ -126,21 +130,47 @@ Not what you were looking for? [Tell us](https://github.com/kalavai-net/kalavai-
 
 ## Getting started
 
-The `kalavai` client is the main tool to interact with the Kalavai platform, to create and manage both local and public pools and also to interact with them (e.g. deploy models). Let's go over its installation. 
+The `kalavai-client` is the main tool to interact with the Kalavai platform, to create and manage both local and public pools and also to interact with them (e.g. deploy models). Let's go over its installation. 
 
-From release **v0.5.0, you can now install `kalavai` client in non-worker computers**. You can run a pool on a set of machines and have the client on a remote computer from which you access the LLM pool. Because the client only requires having python installed, this means more computers are now supported to run it.
+From release **v0.5.0, you can now install `kalavai-client` in non-worker computers**. You can run a pool on a set of machines and have the client on a remote computer from which you access the LLM pool. Because the client only requires having python installed, this means more computers are now supported to run it.
 
 
-### Requirements for a worker machine
+### Requirements
+
+For workers sharing resources with the pool:
 
 - A laptop, desktop or Virtual Machine
 - Docker engine installed (for [linux](https://docs.docker.com/engine/install/), [Windows and MacOS](https://docs.docker.com/desktop/)) with [privilege access](https://docs.docker.com/engine/containers/run/#runtime-privilege-and-linux-capabilities).
 
+> **Support for Windows and MacOS workers is experimental**: kalavai workers run on docker containers that require access to the host network interfaces, thus systems that do not support containers natively (Windows and MacOS) may have difficulties finding each other.
+
+Any system that runs python 3.6+ is able to run the `kalavai-client` and therefore connect and operate an LLM pool, [without sharing with the pool](). Your computer won't be adding its capacity to the pool, but it wil be able to deploy jobs and interact with models.
+
+
+#### Common issues
+
+If you see the following error:
 
-### Requirements to run the client
+```bash
+fatal error: Python.h: No such file or directory | #include <Python.h>
+```
 
-- Python 3.10+
+Make sure you also install python3-dev package. For ubuntu distros:
 
+```bash
+sudo apt install python3-dev
+```
+
+If you see:
+```bash
+AttributeError: install_layout. Did you mean: 'install_platlib'?
+      [end of output]
+```
+
+Upgrade your setuptools:
+```bash
+pip install -U setuptools
+```
 
 ### Install the client
 
@@ -186,6 +216,17 @@ Copy the joining token. On the worker node, run:
 kalavai pool join <token>
 ```
 
+### 3. Attach more clients
+
+You can now connect to an existing pool from any computer -not just from worker nodes. To connect to a pool, run:
+
+```bash
+kalavai pool attach <token>
+```
+
+This won't add the machine as a worker, but you will be able to operate in the pool as if you were. This is ideal for remote access to the pool, and to use the pool from machines that cannot run workers (docker container limitations).
+
+
 ### Enough already, let's run stuff!
 
 Check our [examples](examples/) to put your new AI pool to good use!
@@ -250,12 +291,16 @@ Anything missing here? Give us a shout in the [discussion board](https://github.
 
 ### Requirements
 
-Python version <= 3.12.
+Python version >= 3.6.
 
 ```bash
-virtualenv -p python3 env
+sudo add-apt-repository ppa:deadsnakes/ppa
+sudo apt update
+sudo apt install python3.10 python3.10-dev python3-virtualenv
+virtualenv -p python3.10 env
 source env/bin/activate
 sudo apt install  python3.10-venv python3.10-dev -y
+pip install -U setuptools
 pip install -e .[dev]
 ```
 
@@ -273,3 +318,4 @@ To run the unit tests, use:
 python -m unittest
 ```
 
+docker run --rm --net=host -v   /root/.cache/kalavai/:/root/.cache/kalavai/  ghcr.io/helmfile/helmfile:v0.169.2 helmfile sync --file  /root/.cache/kalavai/apps.yaml --kubeconfig /root/.cache/kalavai/kubeconfig

kalavai_client-0.5.12.dist-info/RECORD

@@ -0,0 +1,20 @@
+kalavai_client/__init__.py,sha256=mqDZCSDdo4jyvGQ0x29B1roX6bl4-uTP0d3CclCa2oo,23
+kalavai_client/__main__.py,sha256=WQUfxvRsBJH5gsCJg8pLz95QnZIj7Ol8psTO77m0QE0,73
+kalavai_client/assets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
+kalavai_client/assets/apps.yaml,sha256=LKLF315cBJG0Ts8oShl6WdKaJlM6Ewk_P_XyPVcApP8,5981
+kalavai_client/assets/apps_values.yaml,sha256=CjKVelPQHd-hm-DTMEuya92feKiphU9mh3HrosLYYPE,1676
+kalavai_client/assets/docker-compose-template.yaml,sha256=mo8LUam9-AzB_0w72wTyMyreKr4Ns-pxZGc4GVWcUHA,2747
+kalavai_client/assets/nginx.conf,sha256=drVVCg8GHucz7hmt_BI6giAhK92OV71257NTs3LthwM,225
+kalavai_client/assets/pool_config_template.yaml,sha256=fFz4w2-fMKD5KvyzFdfcWD_jSneRlmnjLc8hCctweX0,576
+kalavai_client/assets/pool_config_values.yaml,sha256=VrM3XHQfQo6QLZ68qvagooUptaYgl1pszniY_JUtemk,233
+kalavai_client/assets/user_workspace.yaml,sha256=wDvlMYknOPABAEo0dsQwU7bac8iubjAG9tdkFbJZ5Go,476
+kalavai_client/assets/user_workspace_values.yaml,sha256=G0HOzQUxrDMCwuW9kbWUZaKMzDDPVwDwzBHCL2Xi2ZM,542
+kalavai_client/auth.py,sha256=QsBh28L2LwjBBK6pTUE4Xu36lLDTyetyU1YfS1Hbb6g,1717
+kalavai_client/cli.py,sha256=KVWQI2FOAU7km6hXNTs4PXw9Q24G4QqxujQL2pySEY0,70817
+kalavai_client/cluster.py,sha256=fULTAad4KXEGeWZmp4_VBoBwT5eED_HOBUsXIKmf0CU,12119
+kalavai_client/utils.py,sha256=7Cr2wXm2mXGJoseKbFdIVMuMBkqmzSgbwaCLHYoGOn0,12544
+kalavai_client-0.5.12.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+kalavai_client-0.5.12.dist-info/METADATA,sha256=631MQR4FQ5pcMwbLKDucI8gy7qVylzhqmkKhohEBN8c,14101
+kalavai_client-0.5.12.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
+kalavai_client-0.5.12.dist-info/entry_points.txt,sha256=9T6D45gxwzfVbglMm1r6XPdXuuZdHfy_7fCeu2jUphc,50
+kalavai_client-0.5.12.dist-info/RECORD,,

kalavai_client/assets/vpn-template.yaml

@@ -1,13 +0,0 @@
-# https://docs.netmaker.io/docs/netclient#docker
-services:
-    {{service_name}}:
-        network_mode: host
-        privileged: true
-        restart: always
-        environment:
-        - TOKEN={{vpn_token}}
-        - IFACE_NAME={{flannel_iface}}
-        volumes:
-        - '{{etc_path}}/netclient:/etc/netclient'
-        container_name: {{service_name}}
-        image: 'gravitl/netclient:latest'

kalavai_client-0.5.2.dist-info/RECORD

@@ -1,20 +0,0 @@
-kalavai_client/__init__.py,sha256=Ihhobsu68mjIUrgtsfOab7vjkNbLMm1uv7WvMKrKu8c,22
-kalavai_client/__main__.py,sha256=WQUfxvRsBJH5gsCJg8pLz95QnZIj7Ol8psTO77m0QE0,73
-kalavai_client/assets/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-kalavai_client/assets/apps.yaml,sha256=aW9wKyvZhZFMHzBkZOsgVq-kpntED6U8B9XoHkm5F9Y,5963
-kalavai_client/assets/apps_values.yaml,sha256=CjKVelPQHd-hm-DTMEuya92feKiphU9mh3HrosLYYPE,1676
-kalavai_client/assets/docker-compose-template.yaml,sha256=qDv0og338clLobDDPEJ-HiGlMcCMMx2NOi5R_hdhKvw,1442
-kalavai_client/assets/pool_config_template.yaml,sha256=fFz4w2-fMKD5KvyzFdfcWD_jSneRlmnjLc8hCctweX0,576
-kalavai_client/assets/pool_config_values.yaml,sha256=VrM3XHQfQo6QLZ68qvagooUptaYgl1pszniY_JUtemk,233
-kalavai_client/assets/user_workspace.yaml,sha256=wDvlMYknOPABAEo0dsQwU7bac8iubjAG9tdkFbJZ5Go,476
-kalavai_client/assets/user_workspace_values.yaml,sha256=G0HOzQUxrDMCwuW9kbWUZaKMzDDPVwDwzBHCL2Xi2ZM,542
-kalavai_client/assets/vpn-template.yaml,sha256=Hm7sevtrsakSxSKMJwl68hzOEWCaxwYytwkTgKhe_MM,397
-kalavai_client/auth.py,sha256=QsBh28L2LwjBBK6pTUE4Xu36lLDTyetyU1YfS1Hbb6g,1717
-kalavai_client/cli.py,sha256=qBOe4IULIX7pzKUhHoR1JppWrbUeV1aslxQLMWrRGpU,67913
-kalavai_client/cluster.py,sha256=C7uofrpSEj4PUhF_VLfwH4k9BhJMTkuKRWHxDYu1OD0,11345
-kalavai_client/utils.py,sha256=XO-fTrl8vudAOYK9QwuR-C5enzXORIs5A4sFIk3eA9k,13476
-kalavai_client-0.5.2.dist-info/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
-kalavai_client-0.5.2.dist-info/METADATA,sha256=K-7NcUKhmWlkGyYmQ9hrnbKqN7UuGHUV6lQPnqxdSLg,12077
-kalavai_client-0.5.2.dist-info/WHEEL,sha256=IYZQI976HJqqOpQU6PHkJ8fb3tMNBFjg-Cn-pwAbaFM,88
-kalavai_client-0.5.2.dist-info/entry_points.txt,sha256=9T6D45gxwzfVbglMm1r6XPdXuuZdHfy_7fCeu2jUphc,50
-kalavai_client-0.5.2.dist-info/RECORD,,