mirror of
https://github.com/katanemo/plano.git
synced 2026-06-17 15:25:17 +02:00
add k8s demo for api server
This commit is contained in:
parent
1bbc5d2233
commit
7a7288314a
4 changed files with 166 additions and 0 deletions
26
demos/samples_python/k8s_pods/README.md
Normal file
26
demos/samples_python/k8s_pods/README.md
Normal file
|
|
@ -0,0 +1,26 @@
|
|||
This demo shows how you can use a publicly hosted rest api and interact it using arch gateway.
|
||||
|
||||
# How to run this demo.
|
||||
|
||||
Before staring make sure you have completed the pre-requisites [here](https://github.com/katanemo/archgw?tab=readme-ov-file#prerequisites)
|
||||
|
||||
In separate window start 1) model server, 2) arch gateway 3) docker container for UI and for debugging 4) tail access logs
|
||||
|
||||
1. start model server
|
||||
```
|
||||
archgw up --service model_server --foreground
|
||||
```
|
||||
|
||||
1. start arch gateway
|
||||
```
|
||||
archgw up --service archgw --foreground
|
||||
```
|
||||
|
||||
1. start docker container for ui
|
||||
```
|
||||
docker compose up
|
||||
```
|
||||
1. tail access logs
|
||||
```
|
||||
tail -F ~/archgw_logs/access_*
|
||||
```
|
||||
72
demos/samples_python/k8s_pods/arch_config.yaml
Normal file
72
demos/samples_python/k8s_pods/arch_config.yaml
Normal file
|
|
@ -0,0 +1,72 @@
|
|||
version: v0.1
|
||||
|
||||
listeners:
|
||||
ingress_traffic:
|
||||
address: 0.0.0.0
|
||||
port: 10000
|
||||
message_format: openai
|
||||
timeout: 30s
|
||||
|
||||
overrides:
|
||||
optimize_context_window: true
|
||||
|
||||
llm_providers:
|
||||
- name: gpt-4o
|
||||
access_key: $OPENAI_API_KEY
|
||||
provider_interface: openai
|
||||
model: gpt-4o
|
||||
|
||||
endpoints:
|
||||
k8s_api_gateway:
|
||||
endpoint: host.docker.internal:8001
|
||||
http_host: localhost
|
||||
|
||||
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: list_namespaces
|
||||
description: List all namespaces in the cluster
|
||||
endpoint:
|
||||
name: k8s_api_gateway
|
||||
path: /api/v1/namespaces
|
||||
system_prompt: |
|
||||
You are a helpful k8s assistant. Show status of each namespace as well in each line.
|
||||
|
||||
- name: show_namespace_details
|
||||
description: Show details of a specific namespace
|
||||
endpoint:
|
||||
name: k8s_api_gateway
|
||||
path: /api/v1/namespaces/{namespace}
|
||||
parameters:
|
||||
- name: namespace
|
||||
description: namespace to show details
|
||||
required: true
|
||||
type: str
|
||||
in_path: true
|
||||
system_prompt: |
|
||||
You are a helpful k8s assistant. Please show high level details of the namespace.
|
||||
|
||||
- name: get_pods_for_namespace
|
||||
description: Get all pods in a specific namespace
|
||||
endpoint:
|
||||
name: k8s_api_gateway
|
||||
path: /api/v1/namespaces/{namespace}/pods
|
||||
parameters:
|
||||
- name: namespace
|
||||
description: namespace to show details
|
||||
required: true
|
||||
type: str
|
||||
in_path: true
|
||||
system_prompt: |
|
||||
You are a helpful k8s assistant. Please only show high level details of each pod.
|
||||
|
||||
tracing:
|
||||
random_sampling: 100
|
||||
trace_arch_internal: true
|
||||
21
demos/samples_python/k8s_pods/docker-compose.yaml
Normal file
21
demos/samples_python/k8s_pods/docker-compose.yaml
Normal file
|
|
@ -0,0 +1,21 @@
|
|||
services:
|
||||
chatbot_ui:
|
||||
build:
|
||||
context: ../../shared/chatbot_ui
|
||||
ports:
|
||||
- "18080:8080"
|
||||
environment:
|
||||
# this is only because we are running the sample app in the same docker container environemtn as archgw
|
||||
- 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"
|
||||
47
demos/samples_python/k8s_pods/run_demo.sh
Normal file
47
demos/samples_python/k8s_pods/run_demo.sh
Normal file
|
|
@ -0,0 +1,47 @@
|
|||
#!/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 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 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
|
||||
Loading…
Add table
Add a link
Reference in a new issue