updating the network agent to work agin (#425)

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

Author: salmanap

demos/samples_python/network_switch_operator_agent/arch_config.yaml

@@ -11,7 +11,7 @@ llm_providers:
   - name: OpenAI
     provider_interface: openai
     access_key: $OPENAI_API_KEY
-    model: gpt-3.5-turbo
+    model: gpt-4o
     default: true
 
 # default system prompt used by all prompt targets
@@ -26,25 +26,26 @@ prompt_targets:
       path: /agent/device_summary
       http_method: POST
     parameters:
-      - name: device_ids
-        type: list
-        description: A list of device identifiers (IDs) to retrieve statistics for.
+      - name: device_id
+        type: str
+        description: A device identifier to retrieve statistics for.
         required: true # device_ids are required to get device statistics
       - name: days
         type: int
         description: The number of days for which to gather device statistics.
-        default: "7"
-  - name: reboot_devices
-    description: Reboot a list of devices
+        default: 7
+  - name: reboot_device
+    description: Reboot a device
     endpoint:
       name: app_server
       path: /agent/device_reboot
       http_method: POST
     parameters:
-      - name: device_ids
-        type: list
-        description: A list of device identifiers (IDs).
+      - name: device_id
+        type: str
+        description: the device identifier
         required: true
+    system_prompt: You will get a status JSON object. Simply summarize it
 
 # Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.
 endpoints:
@@ -55,3 +56,8 @@ endpoints:
     endpoint: host.docker.internal:18083
     # max time to wait for a connection to be established
     connect_timeout: 0.005s
+
+
+tracing:
+  random_sampling: 100
+  trace_arch_internal: true

demos/samples_python/network_switch_operator_agent/docker-compose.yaml

@@ -18,3 +18,11 @@ services:
       - "host.docker.internal:host-gateway"
     volumes:
       - ./arch_config.yaml:/app/arch_config.yaml
+
+  jaeger:
+    build:
+      context: ../../shared/jaeger
+    ports:
+      - "16686:16686"
+      - "4317:4317"
+      - "4318:4318"

demos/samples_python/network_switch_operator_agent/main.py

@@ -13,15 +13,15 @@
 
 # Define the request model
 class DeviceSummaryRequest(BaseModel):
-    device_ids: List[int]
+    device_id: str
     time_range: Optional[int] = Field(
         default=7, description="Time range in days, defaults to 7"
     )
 
 
 # Define the response model
 class DeviceStatistics(BaseModel):
-    device_id: int
+    device_id: str
     time_range: str
     data: str
 
@@ -33,7 +33,7 @@ class DeviceSummaryResponse(BaseModel):
 
 
 class DeviceRebootRequest(BaseModel):
-    device_ids: List[int]
+    device_id: str
 
 
 # Response model for the device reboot
@@ -49,24 +49,21 @@ def reboot_network_device(request_data: DeviceRebootRequest):
     """
 
     # Access data from the Pydantic model
-    device_ids = request_data.device_ids
+    device_id = request_data.device_id
 
-    # Validate 'device_ids'
+    # Validate 'device_id'
     # (This is already validated by Pydantic, but additional logic can be added if needed)
-    if not device_ids:
-        raise HTTPException(
-            status_code=400, detail="'device_ids' parameter is required"
-        )
+    if not device_id:
+        raise HTTPException(status_code=400, detail="'device_id' parameter is required")
 
     # Simulate reboot operation and return the response
     statistics = []
-    for device_id in device_ids:
-        # Placeholder for actual data retrieval or device reboot logic
-        stats = {"data": f"Device {device_id} has been successfully rebooted."}
-        statistics.append(stats)
+    # Placeholder for actual data retrieval or device reboot logic
+    stats = {"data": f"Device {device_id} has been successfully rebooted."}
+    statistics.append(stats)
 
     # Return the response with a summary
-    return CoverageResponse(status="success", summary={"device_ids": device_ids})
+    return CoverageResponse(status="success", summary={"device_id": device_id})
 
 
 # Post method for device summary
@@ -76,28 +73,20 @@ def get_device_summary(request: DeviceSummaryRequest):
     Endpoint to retrieve device statistics based on device IDs and an optional time range.
     """
 
-    # Extract 'device_ids' and 'time_range' from the request
-    device_ids = request.device_ids
+    # Extract 'device_id' and 'time_range' from the request
+    device_id = request.device_id
     time_range = request.time_range
 
     # Simulate retrieving statistics for the given device IDs and time range
     statistics = []
-    minutes = 1
-    for device_id in device_ids:
-        stats = {
-            "device_id": device_id,
-            "time_range": f"Last {time_range} days",
-            "data": f"""Device {device_id} over the last {time_range} days experienced {minutes}
-             minutes of downtime.""",
-        }
-        minutes += 1
-        statistics.append(DeviceStatistics(**stats))
-
-    return DeviceSummaryResponse(statistics=statistics)
+    minutes = 4
+    stats = {
+        "device_id": device_id,
+        "time_range": f"Last {time_range} days",
+        "data": f"""Device {device_id} over the last {time_range} days experienced {minutes}
+        minutes of downtime.""",
+    }
 
+    statistics.append(DeviceStatistics(**stats))
 
-CHAT_COMPLETION_ENDPOINT = os.getenv("CHAT_COMPLETION_ENDPOINT")
-client = OpenAI(
-    api_key="--",
-    base_url=CHAT_COMPLETION_ENDPOINT,
-)
+    return DeviceSummaryResponse(statistics=statistics)

demos/samples_python/network_switch_operator_agent/run_demo.sh

@@ -22,9 +22,8 @@ start_demo() {
   echo "Starting Arch with arch_config.yaml..."
   archgw up arch_config.yaml
 
-  # Step 4: Start Network Agent
+  # Step 4: Start developer services
   echo "Starting Network Agent using Docker Compose..."
-  cd build
   docker compose up -d  # Run in detached mode
 }