mirror of
https://github.com/katanemo/plano.git
synced 2026-04-25 16:56:24 +02:00
Update docs to Plano (#639)
This commit is contained in:
Salman Paracha
GitHub
parent
15fbb6c3af
commit
e224cba3e3
139 changed files with 4407 additions and 24735 deletions
|
|
@ -26,12 +26,6 @@ endpoints:
|
|||
system_prompt: |
|
||||
You are a helpful assistant. Only respond to queries related to currency exchange. If there are any other questions, I can't help you.
|
||||
|
||||
prompt_guards:
|
||||
input_guards:
|
||||
jailbreak:
|
||||
on_exception:
|
||||
message: Looks like you're curious about my abilities, but I can only provide assistance for currency exchange.
|
||||
|
||||
prompt_targets:
|
||||
- name: currency_exchange
|
||||
description: Get currency exchange rate from USD to other currencies
|
||||
|
|
|
|||
|
|
@ -1,16 +0,0 @@
|
|||
FROM python:3.12 AS base
|
||||
|
||||
FROM base AS builder
|
||||
|
||||
WORKDIR /src
|
||||
|
||||
COPY requirements.txt /src/
|
||||
RUN pip install --prefix=/runtime --force-reinstall -r requirements.txt
|
||||
|
||||
FROM python:3.12-slim AS output
|
||||
COPY --from=builder /runtime /usr/local
|
||||
|
||||
WORKDIR /app
|
||||
COPY . /app
|
||||
|
||||
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "80", "--log-level", "info"]
|
||||
|
|
@ -1,29 +0,0 @@
|
|||
# HR Agent Demo
|
||||
|
||||
This demo showcases how the **Arch** can be used to build an HR agent to manage workforce-related inquiries, workforce planning, and communication via Slack. It intelligently routes incoming prompts to the correct targets, providing concise and useful responses tailored for HR and workforce decision-making.
|
||||
|
||||
## Available Functions:
|
||||
|
||||
- **HR Q/A**: Handles general Q&A related to insurance policies.
|
||||
- **Endpoint**: `/agent/hr_qa`
|
||||
|
||||
- **Workforce Data Retrieval**: Retrieves data related to workforce metrics like headcount, satisfaction, and staffing.
|
||||
- **Endpoint**: `/agent/workforce`
|
||||
- Parameters:
|
||||
- `staffing_type` (str, required): Type of staffing (e.g., `contract`, `fte`, `agency`).
|
||||
- `region` (str, required): Region for which the data is requested (e.g., `asia`, `europe`, `americas`).
|
||||
- `point_in_time` (int, optional): Time point for data retrieval (e.g., `0 days ago`, `30 days ago`).
|
||||
|
||||
- **Initiate Policy**: Sends messages to a Slack channel
|
||||
- **Endpoint**: `/agent/slack_message`
|
||||
- Parameters:
|
||||
- `slack_message` (str, required): The message content to be sent
|
||||
|
||||
# Starting the demo
|
||||
1. Please make sure the [pre-requisites](https://github.com/katanemo/arch/?tab=readme-ov-file#prerequisites) are installed correctly
|
||||
2. Start Arch
|
||||
```sh
|
||||
sh run_demo.sh
|
||||
```
|
||||
3. Navigate to http://localhost:18080/agent/chat
|
||||
4. "Can you give me workforce data for asia?"
|
||||
|
|
@ -1,63 +0,0 @@
|
|||
version: v0.1.0
|
||||
|
||||
listeners:
|
||||
ingress_traffic:
|
||||
address: 0.0.0.0
|
||||
port: 10000
|
||||
message_format: openai
|
||||
timeout: 30s
|
||||
|
||||
# Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way
|
||||
llm_providers:
|
||||
- access_key: $OPENAI_API_KEY
|
||||
model: openai/gpt-4o-mini
|
||||
default: true
|
||||
|
||||
# Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.
|
||||
endpoints:
|
||||
app_server:
|
||||
# value could be ip address or a hostname with port
|
||||
# this could also be a list of endpoints for load balancing
|
||||
# for example endpoint: [ ip1:port, ip2:port ]
|
||||
endpoint: host.docker.internal:18083
|
||||
# max time to wait for a connection to be established
|
||||
connect_timeout: 0.005s
|
||||
|
||||
# default system prompt used by all prompt targets
|
||||
system_prompt: |
|
||||
You are a Workforce assistant that helps on workforce planning and HR decision makers with reporting and workforce planning. Use following rules when responding,
|
||||
- when you get data in json format, offer some summary but don't be too verbose
|
||||
- be concise, to the point and do not over analyze the data
|
||||
|
||||
prompt_targets:
|
||||
- name: workforce
|
||||
description: Get workforce data like headcount and satisfaction levels by region and staffing type
|
||||
endpoint:
|
||||
name: app_server
|
||||
path: /agent/workforce
|
||||
http_method: POST
|
||||
parameters:
|
||||
- name: staffing_type
|
||||
type: str
|
||||
description: specific category or nature of employment used by an organization like fte, contract and agency
|
||||
required: true
|
||||
enum: [fte, contract, agency]
|
||||
- name: region
|
||||
type: str
|
||||
required: true
|
||||
description: Geographical region for which you want workforce data like asia, europe, americas.
|
||||
- name: data_snapshot_days_ago
|
||||
type: int
|
||||
required: false
|
||||
description: the snapshot day for which you want workforce data.
|
||||
- name: slack_message
|
||||
endpoint:
|
||||
name: app_server
|
||||
path: /agent/slack_message
|
||||
http_method: POST
|
||||
description: sends a slack message on a channel
|
||||
parameters:
|
||||
- name: slack_message
|
||||
type: string
|
||||
required: true
|
||||
description: the message that should be sent to a slack channel
|
||||
|
|
@ -1,29 +0,0 @@
|
|||
services:
|
||||
api_server:
|
||||
build:
|
||||
context: .
|
||||
environment:
|
||||
- SLACK_BOT_TOKEN=${SLACK_BOT_TOKEN:-None}
|
||||
- OPENAI_API_KEY=${OPENAI_API_KEY:?error}
|
||||
- CHAT_COMPLETION_ENDPOINT=http://host.docker.internal:10000/v1
|
||||
volumes:
|
||||
- ./arch_config.yaml:/app/arch_config.yaml
|
||||
ports:
|
||||
- "18083:80"
|
||||
healthcheck:
|
||||
test: ["CMD", "curl" ,"http://localhost:80/healthz"]
|
||||
interval: 5s
|
||||
retries: 20
|
||||
|
||||
chatbot_ui:
|
||||
build:
|
||||
context: ../../shared/chatbot_ui
|
||||
dockerfile: Dockerfile
|
||||
ports:
|
||||
- "18080:8080"
|
||||
environment:
|
||||
- CHAT_COMPLETION_ENDPOINT=http://host.docker.internal:10000/v1
|
||||
extra_hosts:
|
||||
- "host.docker.internal:host-gateway"
|
||||
volumes:
|
||||
- ./arch_config.yaml:/app/arch_config.yaml
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 549 KiB |
|
|
@ -1,94 +0,0 @@
|
|||
import os
|
||||
import json
|
||||
import pandas as pd
|
||||
import gradio as gr
|
||||
import logging
|
||||
|
||||
from fastapi import FastAPI, HTTPException
|
||||
from pydantic import BaseModel, Field
|
||||
from enum import Enum
|
||||
from typing import List, Optional, Tuple
|
||||
from slack_sdk import WebClient
|
||||
from slack_sdk.errors import SlackApiError
|
||||
from openai import OpenAI
|
||||
|
||||
app = FastAPI()
|
||||
workforce_data_df = None
|
||||
|
||||
with open("workforce_data.json") as file:
|
||||
workforce_data = json.load(file)
|
||||
workforce_data_df = pd.json_normalize(
|
||||
workforce_data,
|
||||
record_path=["regions"],
|
||||
meta=["data_snapshot_days_ago", "satisfaction"],
|
||||
)
|
||||
|
||||
|
||||
# Define the request model
|
||||
class WorkforceRequest(BaseModel):
|
||||
region: str
|
||||
staffing_type: str
|
||||
data_snapshot_days_ago: Optional[int] = None
|
||||
|
||||
|
||||
class SlackRequest(BaseModel):
|
||||
slack_message: str
|
||||
|
||||
|
||||
class WorkforceResponse(BaseModel):
|
||||
region: str
|
||||
staffing_type: str
|
||||
headcount: int
|
||||
satisfaction: float
|
||||
|
||||
|
||||
@app.post("/agent/slack_message")
|
||||
def send_slack_message(request: SlackRequest):
|
||||
"""
|
||||
Endpoint that sends slack message
|
||||
"""
|
||||
slack_message = request.slack_message
|
||||
|
||||
# Load the bot token from an environment variable or replace it directly
|
||||
slack_token = os.getenv(
|
||||
"SLACK_BOT_TOKEN"
|
||||
) # Replace with your token if needed: 'xoxb-your-token'
|
||||
|
||||
if slack_token is None:
|
||||
print(f"Message for slack: {slack_message}")
|
||||
else:
|
||||
client = WebClient(token=slack_token)
|
||||
channel = "hr_agent_demo"
|
||||
try:
|
||||
# Send the message
|
||||
response = client.chat_postMessage(channel=channel, text=slack_message)
|
||||
return f"Message sent to {channel}: {response['message']['text']}"
|
||||
except SlackApiError as e:
|
||||
print(f"Error sending message: {e.response['error']}")
|
||||
|
||||
|
||||
# Post method for device summary
|
||||
@app.post("/agent/workforce")
|
||||
def get_workforce(request: WorkforceRequest):
|
||||
"""
|
||||
Endpoint to workforce data by region, staffing type at a given point in time.
|
||||
"""
|
||||
region = request.region.lower()
|
||||
staffing_type = request.staffing_type.lower()
|
||||
data_snapshot_days_ago = (
|
||||
request.data_snapshot_days_ago
|
||||
if request.data_snapshot_days_ago
|
||||
else 0 # this param is not required.
|
||||
)
|
||||
|
||||
response = {
|
||||
"region": region,
|
||||
"staffing_type": f"Staffing agency: {staffing_type}",
|
||||
"headcount": f"Headcount: {int(workforce_data_df[(workforce_data_df['region']==region) & (workforce_data_df['data_snapshot_days_ago']==data_snapshot_days_ago)][staffing_type].values[0])}",
|
||||
"satisfaction": f"Satisfaction: {float(workforce_data_df[(workforce_data_df['region']==region) & (workforce_data_df['data_snapshot_days_ago']==data_snapshot_days_ago)]['satisfaction'].values[0])}",
|
||||
}
|
||||
return response
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
app.run(debug=True)
|
||||
|
|
@ -1,14 +0,0 @@
|
|||
fastapi
|
||||
uvicorn
|
||||
slack-sdk
|
||||
typing
|
||||
pandas
|
||||
gradio==5.3.0
|
||||
huggingface_hub<1.0.0
|
||||
async_timeout==4.0.3
|
||||
loguru==0.7.2
|
||||
asyncio==3.4.3
|
||||
httpx==0.27.0
|
||||
python-dotenv==1.0.1
|
||||
pydantic==2.8.2
|
||||
openai==1.51.0
|
||||
|
|
@ -1,47 +0,0 @@
|
|||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
# Function to start the demo
|
||||
start_demo() {
|
||||
# Step 1: Check if .env file exists
|
||||
if [ -f ".env" ]; then
|
||||
echo ".env file already exists. Skipping creation."
|
||||
else
|
||||
# Step 2: Create `.env` file and set OpenAI key
|
||||
if [ -z "$OPENAI_API_KEY" ]; then
|
||||
echo "Error: OPENAI_API_KEY environment variable is not set for the demo."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "Creating .env file..."
|
||||
echo "OPENAI_API_KEY=$OPENAI_API_KEY" > .env
|
||||
echo ".env file created with OPENAI_API_KEY."
|
||||
fi
|
||||
|
||||
# Step 3: Start Arch
|
||||
echo "Starting Arch with arch_config.yaml..."
|
||||
archgw up arch_config.yaml
|
||||
|
||||
# Step 4: Start Network Agent
|
||||
echo "Starting HR Agent using Docker Compose..."
|
||||
docker compose up -d # Run in detached mode
|
||||
}
|
||||
|
||||
# Function to stop the demo
|
||||
stop_demo() {
|
||||
# Step 1: Stop Docker Compose services
|
||||
echo "Stopping HR Agent using Docker Compose..."
|
||||
docker compose down
|
||||
|
||||
# Step 2: Stop Arch
|
||||
echo "Stopping Arch..."
|
||||
archgw down
|
||||
}
|
||||
|
||||
# Main script logic
|
||||
if [ "$1" == "down" ]; then
|
||||
stop_demo
|
||||
else
|
||||
# Default action is to bring the demo up
|
||||
start_demo
|
||||
fi
|
||||
|
|
@ -1,14 +0,0 @@
|
|||
test_cases:
|
||||
- id: get workforce data
|
||||
input:
|
||||
messages:
|
||||
- role: user
|
||||
content: what is workforce data for asia for fte employees
|
||||
expected_tools:
|
||||
- type: function
|
||||
function:
|
||||
name: workforce
|
||||
arguments:
|
||||
staffing_type: fte
|
||||
region: asia
|
||||
expected_output_contains: asia
|
||||
|
|
@ -1,29 +0,0 @@
|
|||
[
|
||||
{
|
||||
"data_snapshot_days_ago": 0,
|
||||
"regions": [
|
||||
{ "region": "asia", "contract": 100, "fte": 150, "agency": 2000 },
|
||||
{ "region": "europe", "contract": 80, "fte": 120, "agency": 2500 },
|
||||
{ "region": "americas", "contract": 90, "fte": 200, "agency": 3100 }
|
||||
],
|
||||
"satisfaction": 3.5
|
||||
},
|
||||
{
|
||||
"data_snapshot_days_ago": 30,
|
||||
"regions": [
|
||||
{ "region": "asia", "contract": 110, "fte": 155, "agency": 1000 },
|
||||
{ "region": "europe", "contract": 85, "fte": 130, "agency": 1600 },
|
||||
{ "region": "americas", "contract": 95, "fte": 210, "agency": 3100 }
|
||||
],
|
||||
"satisfaction": 4.0
|
||||
},
|
||||
{
|
||||
"data_snapshot_days_ago": 60,
|
||||
"regions": [
|
||||
{ "region": "asia", "contract": 115, "fte": 160, "agency": 500 },
|
||||
{ "region": "europe", "contract": 90, "fte": 140, "agency": 700 },
|
||||
{ "region": "americas", "contract": 100, "fte": 220, "agency": 1200 }
|
||||
],
|
||||
"satisfaction": 4.7
|
||||
}
|
||||
]
|
||||
|
|
@ -1,19 +0,0 @@
|
|||
FROM python:3.12 AS base
|
||||
|
||||
FROM base AS builder
|
||||
|
||||
WORKDIR /src
|
||||
|
||||
COPY requirements.txt /src/
|
||||
RUN pip install --prefix=/runtime --force-reinstall -r requirements.txt
|
||||
|
||||
COPY ../. /src
|
||||
|
||||
FROM python:3.12-slim AS output
|
||||
|
||||
COPY --from=builder /runtime /usr/local
|
||||
|
||||
COPY ../. /app
|
||||
WORKDIR /app
|
||||
|
||||
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "80", "--log-level", "info"]
|
||||
|
|
@ -1,42 +0,0 @@
|
|||
# Network Agent Demo
|
||||
|
||||
This demo illustrates how **Arch** can be used to perform function calling with network-related tasks. In this demo, you act as a **network assistant** that provides factual information, without offering advice on manufacturers or purchasing decisions.
|
||||
|
||||
The assistant can perform several key operations, including rebooting devices, answering general networking questions, and retrieving device statistics. By default, the system prompt ensures that the assistant's responses are factual and neutral.
|
||||
|
||||
## Available Functions:
|
||||
- **Reboot Devices**: Allows rebooting specific devices or device groups, with an optional time range for scheduling the reboot.
|
||||
- Parameters:
|
||||
- `device_ids` (required): A list of device IDs to reboot.
|
||||
- `time_range` (optional): Specifies the time range in days, defaulting to 7 days if not provided.
|
||||
|
||||
- **Network Q/A**: Handles general Q&A related to networking. This function is the default target for general networking queries.
|
||||
|
||||
- **Device Summary**: Retrieves statistics for specific devices within a given time range.
|
||||
- Parameters:
|
||||
- `device_ids` (required): A list of device IDs for which statistics will be retrieved.
|
||||
- `time_range` (optional): Specifies the time range in days for gathering statistics, with a default of 7 days.
|
||||
|
||||
|
||||
# Starting the demo
|
||||
1. Please make sure the [pre-requisites](https://github.com/katanemo/arch/?tab=readme-ov-file#prerequisites) are installed correctly
|
||||
2. Start Arch
|
||||
```sh
|
||||
sh run_demo.sh
|
||||
```
|
||||
3. Navigate to http://localhost:18080/agent/chat
|
||||
4. Tell me what can you do for me?"
|
||||
|
||||
# Observability
|
||||
Arch gateway publishes stats endpoint at http://localhost:19901/stats. In this demo we are using prometheus to pull stats from arch and we are using grafana to visualize the stats in dashboard. To see grafana dashboard follow instructions below,
|
||||
|
||||
1. Start grafana and prometheus using following command
|
||||
```yaml
|
||||
docker compose --profile monitoring up
|
||||
```
|
||||
1. Navigate to http://localhost:3000/ to open grafana UI (use admin/grafana as credentials)
|
||||
1. From grafana left nav click on dashboards and select "Intelligent Gateway Overview" to view arch gateway stats
|
||||
|
||||
Here is sample interaction
|
||||
|
||||
|
||||
|
|
@ -1,61 +0,0 @@
|
|||
version: v0.1.0
|
||||
listeners:
|
||||
ingress_traffic:
|
||||
address: 0.0.0.0
|
||||
port: 10000
|
||||
message_format: openai
|
||||
timeout: 30s
|
||||
|
||||
# Centralized way to manage LLMs, manage keys, retry logic, failover and limits in a central way
|
||||
llm_providers:
|
||||
- access_key: $OPENAI_API_KEY
|
||||
model: openai/gpt-4o
|
||||
default: true
|
||||
|
||||
# default system prompt used by all prompt targets
|
||||
system_prompt: |
|
||||
You are a network assistant that helps operators with a better understanding of network traffic flow and perform actions on networking operations. No advice on manufacturers or purchasing decisions.
|
||||
|
||||
prompt_targets:
|
||||
- name: device_summary
|
||||
description: Retrieve network statistics for specific devices within a time range
|
||||
endpoint:
|
||||
name: app_server
|
||||
path: /agent/device_summary
|
||||
http_method: POST
|
||||
parameters:
|
||||
- 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_device
|
||||
description: Reboot a device
|
||||
endpoint:
|
||||
name: app_server
|
||||
path: /agent/device_reboot
|
||||
http_method: POST
|
||||
parameters:
|
||||
- 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:
|
||||
app_server:
|
||||
# value could be ip address or a hostname with port
|
||||
# this could also be a list of endpoints for load balancing
|
||||
# for example endpoint: [ ip1:port, ip2:port ]
|
||||
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
|
||||
|
|
@ -1,28 +0,0 @@
|
|||
services:
|
||||
api_server:
|
||||
build:
|
||||
context: .
|
||||
dockerfile: Dockerfile
|
||||
ports:
|
||||
- "18083:80"
|
||||
|
||||
chatbot_ui:
|
||||
build:
|
||||
context: ../../shared/chatbot_ui
|
||||
dockerfile: Dockerfile
|
||||
ports:
|
||||
- "18080:8080"
|
||||
environment:
|
||||
- CHAT_COMPLETION_ENDPOINT=http://host.docker.internal:10000/v1
|
||||
extra_hosts:
|
||||
- "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"
|
||||
Binary file not shown.
|
Before Width: | Height: | Size: 636 KiB |
|
|
@ -1,92 +0,0 @@
|
|||
import os
|
||||
from typing import List, Optional
|
||||
|
||||
from fastapi import FastAPI, HTTPException
|
||||
from openai import OpenAI
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
app = FastAPI()
|
||||
DEMO_DESCRIPTION = """This demo illustrates how **Arch** can be used to perform function calling
|
||||
with network-related tasks. In this demo, you act as a **network assistant** that provides factual
|
||||
information, without offering advice on manufacturers or purchasing decisions."""
|
||||
|
||||
|
||||
# Define the request model
|
||||
class DeviceSummaryRequest(BaseModel):
|
||||
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: str
|
||||
time_range: str
|
||||
data: str
|
||||
|
||||
|
||||
class DeviceSummaryResponse(BaseModel):
|
||||
statistics: List[DeviceStatistics]
|
||||
|
||||
# Request model for device reboot
|
||||
|
||||
|
||||
class DeviceRebootRequest(BaseModel):
|
||||
device_id: str
|
||||
|
||||
|
||||
# Response model for the device reboot
|
||||
class CoverageResponse(BaseModel):
|
||||
status: str
|
||||
summary: dict
|
||||
|
||||
|
||||
@app.post("/agent/device_reboot", response_model=CoverageResponse)
|
||||
def reboot_network_device(request_data: DeviceRebootRequest):
|
||||
"""
|
||||
Endpoint to reboot network devices based on device IDs and an optional time range.
|
||||
"""
|
||||
|
||||
# Access data from the Pydantic model
|
||||
device_id = request_data.device_id
|
||||
|
||||
# Validate 'device_id'
|
||||
# (This is already validated by Pydantic, but additional logic can be added if needed)
|
||||
if not device_id:
|
||||
raise HTTPException(status_code=400, detail="'device_id' parameter is required")
|
||||
|
||||
# Simulate reboot operation and return the response
|
||||
statistics = []
|
||||
# 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_id": device_id})
|
||||
|
||||
|
||||
# Post method for device summary
|
||||
@app.post("/agent/device_summary", response_model=DeviceSummaryResponse)
|
||||
def get_device_summary(request: DeviceSummaryRequest):
|
||||
"""
|
||||
Endpoint to retrieve device statistics based on device IDs and an optional time range.
|
||||
"""
|
||||
|
||||
# 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 = 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))
|
||||
|
||||
return DeviceSummaryResponse(statistics=statistics)
|
||||
|
|
@ -1,14 +0,0 @@
|
|||
fastapi
|
||||
uvicorn
|
||||
pydantic
|
||||
typing
|
||||
pandas
|
||||
gradio==5.3.0
|
||||
huggingface_hub<1.0.0
|
||||
async_timeout==4.0.3
|
||||
loguru==0.7.2
|
||||
asyncio==3.4.3
|
||||
httpx==0.27.0
|
||||
python-dotenv==1.0.1
|
||||
pydantic==2.8.2
|
||||
openai==1.51.0
|
||||
|
|
@ -1,47 +0,0 @@
|
|||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
# Function to start the demo
|
||||
start_demo() {
|
||||
# Step 1: Check if .env file exists
|
||||
if [ -f ".env" ]; then
|
||||
echo ".env file already exists. Skipping creation."
|
||||
else
|
||||
# Step 2: Create `.env` file and set OpenAI key
|
||||
if [ -z "$OPENAI_API_KEY" ]; then
|
||||
echo "Error: OPENAI_API_KEY environment variable is not set for the demo."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "Creating .env file..."
|
||||
echo "OPENAI_API_KEY=$OPENAI_API_KEY" > .env
|
||||
echo ".env file created with OPENAI_API_KEY."
|
||||
fi
|
||||
|
||||
# Step 3: Start Arch
|
||||
echo "Starting Arch with arch_config.yaml..."
|
||||
archgw up arch_config.yaml
|
||||
|
||||
# Step 4: Start developer services
|
||||
echo "Starting Network Agent using Docker Compose..."
|
||||
docker compose up -d # Run in detached mode
|
||||
}
|
||||
|
||||
# Function to stop the demo
|
||||
stop_demo() {
|
||||
# Step 1: Stop Docker Compose services
|
||||
echo "Stopping Network Agent using Docker Compose..."
|
||||
docker compose down
|
||||
|
||||
# Step 2: Stop Arch
|
||||
echo "Stopping Arch..."
|
||||
archgw down
|
||||
}
|
||||
|
||||
# Main script logic
|
||||
if [ "$1" == "down" ]; then
|
||||
stop_demo
|
||||
else
|
||||
# Default action is to bring the demo up
|
||||
start_demo
|
||||
fi
|
||||
|
|
@ -19,12 +19,6 @@ endpoints:
|
|||
system_prompt: |
|
||||
You are a helpful assistant.
|
||||
|
||||
prompt_guards:
|
||||
input_guards:
|
||||
jailbreak:
|
||||
on_exception:
|
||||
message: Looks like you're curious about my abilities, but I can only provide assistance for currency exchange.
|
||||
|
||||
prompt_targets:
|
||||
- name: stock_quote
|
||||
description: get current stock exchange rate for a given symbol
|
||||
|
|
|
|||
|
|
@ -39,12 +39,6 @@ llm_providers:
|
|||
system_prompt: |
|
||||
You are a helpful assistant.
|
||||
|
||||
prompt_guards:
|
||||
input_guards:
|
||||
jailbreak:
|
||||
on_exception:
|
||||
message: Looks like you're curious about my abilities, but I can only provide assistance for weather forecasting.
|
||||
|
||||
prompt_targets:
|
||||
- name: get_current_weather
|
||||
description: Get current weather at a location.
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue