apunkt/plano
1
0
Fork 0
mirror of https://github.com/katanemo/plano.git synced 2026-06-17 15:25:17 +02:00
Code Issues Projects Releases Packages Wiki Activity

Merge branch 'main' into shuguang/error_handling

Browse source
This commit is contained in:
Adil Hafeez 2025-03-03 13:12:31 -08:00
commit 6be6cc6346
No known key found for this signature in database
GPG key ID: 9B18EF7691369645
150 changed files with 2416 additions and 6445 deletions
Download patch file Download diff file Expand all files Collapse all files

95
.github/workflows/docker-push.yml vendored
View file

@ -1,40 +1,97 @@
name: Publish Docker image
env:
DOCKER_IMAGE: katanemo/archgw
on:
release:
types: [published]
push:
branches:
- main
jobs:
push_to_registry:
name: Push Docker image to Docker Hub
runs-on: ubuntu-latest
permissions:
packages: write
contents: read
attestations: write
id-token: write
# Build ARM64 image on native ARM64 runner
build-arm64:
runs-on: [linux-arm64]
steps:
- name: Check out the repo
- name: Checkout Repository
uses: actions/checkout@v4
- name: Log in to Docker Hub
uses: docker/login-action@f4ef78c080cd8ba55a85445d5b36e214a81df20a
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Extract metadata (tags, labels) for Docker
id: meta
uses: docker/metadata-action@9ec57ed1fcdbf14dcef7dfbe97b2010124a938b7
uses: docker/metadata-action@v5
with:
images: katanemo/archgw
images: ${{ env.DOCKER_IMAGE }}
tags: |
type=raw,value=latest # Force the tag to be "latest"
- name: Build and push Docker image
id: push
uses: docker/build-push-action@3b5e8027fcad23fda98b2e3ac259d8d67585f671
- name: Build and Push ARM64 Image
uses: docker/build-push-action@v5
with:
context: .
file: ./arch/Dockerfile
platforms: linux/arm64
push: true
tags: ${{ steps.meta.outputs.tags }}
labels: ${{ steps.meta.outputs.labels }}
tags: ${{ steps.meta.outputs.tags }}-arm64
# Build AMD64 image on GitHub's AMD64 runner
build-amd64:
runs-on: ubuntu-latest
steps:
- name: Checkout Repository
uses: actions/checkout@v4
- name: Log in to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Extract metadata (tags, labels) for Docker
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.DOCKER_IMAGE }}
tags: |
type=raw,value=latest # Force the tag to be "latest"
- name: Build and Push AMD64 Image
uses: docker/build-push-action@v5
with:
context: .
file: ./arch/Dockerfile
platforms: linux/amd64
push: true
tags: ${{ steps.meta.outputs.tags }}-amd64
# Combine ARM64 and AMD64 images into a multi-arch manifest
create-manifest:
runs-on: ubuntu-latest
needs: [build-arm64, build-amd64] # Wait for both builds
steps:
- name: Log in to Docker Hub
uses: docker/login-action@v3
with:
username: ${{ secrets.DOCKER_USERNAME }}
password: ${{ secrets.DOCKER_PASSWORD }}
- name: Extract metadata (tags, labels) for Docker
id: meta
uses: docker/metadata-action@v5
with:
images: ${{ env.DOCKER_IMAGE }}
tags: |
type=raw,value=latest # Force the tag to be "latest"
- name: Create Multi-Arch Manifest
run: |
# Combine the architecture-specific images into a "latest" manifest
docker buildx imagetools create -t ${{ steps.meta.outputs.tags }} \
${{ env.DOCKER_IMAGE }}:latest-arm64 \
${{ env.DOCKER_IMAGE }}:latest-amd64

2
.github/workflows/e2e_archgw.yml vendored
View file

@ -7,7 +7,7 @@ on:
pull_request:
jobs:
test:
e2e_archgw_tests:
runs-on: ubuntu-latest-m
defaults:
run:

2
.github/workflows/e2e_model_server.yml vendored
View file

@ -7,7 +7,7 @@ on:
pull_request:
jobs:
test:
e2e_model_server_tests:
runs-on: ubuntu-latest-m
defaults:
run:

6
.github/workflows/e2e_test_demos.yml vendored
View file

@ -7,7 +7,7 @@ on:
pull_request:
jobs:
test:
e2e_demo_tests:
runs-on: ubuntu-latest-m
steps:
@ -37,7 +37,7 @@ jobs:
source venv/bin/activate
cd model_server/ && echo "installing model server" && poetry install
cd ../arch/tools && echo "installing archgw cli" && poetry install
cd ../../demos/test_runner && echo "installing test dependencies" && poetry install
cd ../../demos/shared/test_runner && echo "installing test dependencies" && poetry install
- name: run demo tests
env:
@ -45,4 +45,4 @@ jobs:
MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
run: |
source venv/bin/activate
cd demos/test_runner && sh run_demo_tests.sh
cd demos/shared/test_runner && sh run_demo_tests.sh

2
.github/workflows/e2e_tests.yml vendored
View file

@ -7,7 +7,7 @@ on:
pull_request:
jobs:
test:
e2e_tests:
runs-on: ubuntu-latest
steps:

31
.github/workflows/validate_arch_config.yml vendored Normal file
View file

@ -0,0 +1,31 @@
name: arch config tests
on:
push:
branches:
- main
pull_request:
jobs:
validate_arch_config:
runs-on: ubuntu-latest
defaults:
run:
working-directory: .
steps:
- name: Checkout code
uses: actions/checkout@v3
- name: Set up Python
uses: actions/setup-python@v4
with:
python-version: "3.12"
- name: build arch docker image
run: |
docker build -f arch/Dockerfile . -t katanemo/archgw
- name: validate arch config
run: |
bash arch/validate_arch_config.sh

4
.pre-commit-config.yaml
View file

@ -25,9 +25,7 @@ repos:
name: cargo-test
language: system
types: [file, rust]
# --lib is to only test the library, since when integration tests are made,
# they will be in a seperate tests directory
entry: bash -c "cd crates/llm_gateway && cargo test --lib"
entry: bash -c "cd crates && cargo test --lib"
- repo: https://github.com/psf/black
rev: 23.1.0

49
README.md
View file

@ -1,30 +1,41 @@
<p align="center">
<div align="center">
<img src="docs/source/_static/img/arch-logo.png" alt="Arch Logo" width="75%" heigh=auto>
</p>
<p align="center">
<a href="https://www.producthunt.com/posts/arch-3?embed=true&utm_source=badge-top-post-badge&utm_medium=badge&utm_souce=badge-arch&#0045;3" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/top-post-badge.svg?post_id=565761&theme=light&period=daily" alt="Arch - Build&#0032;fast&#0044;&#0032;hyper&#0045;personalized&#0032;agents&#0032;with&#0032;intelligent&#0032;infra | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
</p>
</div>
<div align="center">
Arch is an **intelligent (edge and LLM) proxy designed for agentic applications** - to help you protect, observe, and build agentic tasks by simply connecting (existing) APIs.
_Arch is an intelligent (edge and LLM) proxy designed for agentic applications - to help you protect, observe, and build agentic tasks by simply connecting (existing) APIs._
Built by the contributors of [Envoy Proxy](https://www.envoyproxy.io/) with the belief that:
>Prompts are nuanced and opaque user requests, which require the same capabilities as traditional HTTP requests including secure handling, intelligent routing, robust observability, and integration with backend (API) systems for personalization – outside core business logic.*
[Quickstart](#Quickstart) •
[Demos](#Demos) •
[Build agentic apps with Arch](#Build-AI-Agent-with-Arch-Gateway) •
[Use Arch as an LLM router](#Use-Arch-Gateway-as-LLM-Router) •
[Documentation](https://docs.archgw.com) •
[Contact](#Contact)
[![pre-commit](https://github.com/katanemo/arch/actions/workflows/pre-commit.yml/badge.svg)](https://github.com/katanemo/arch/actions/workflows/pre-commit.yml)
[![rust tests (prompt and llm gateway)](https://github.com/katanemo/arch/actions/workflows/rust_tests.yml/badge.svg)](https://github.com/katanemo/arch/actions/workflows/rust_tests.yml)
[![e2e tests](https://github.com/katanemo/arch/actions/workflows/e2e_tests.yml/badge.svg)](https://github.com/katanemo/arch/actions/workflows/e2e_tests.yml)
[![Build and Deploy Documentation](https://github.com/katanemo/arch/actions/workflows/static.yml/badge.svg)](https://github.com/katanemo/arch/actions/workflows/static.yml)
</div>
Arch is engineered with purpose-built LLMs to handle critical but undifferentiated tasks related to the handling and processing of prompts. This includes detecting and rejecting [jailbreak](https://github.com/verazuo/jailbreak_llms) attempts, intelligent task routing for improved accuracy, mapping user request into "backend" functions, and managing the observability of prompts and LLM API calls in a centralized way.
# Overview
<a href="https://www.producthunt.com/posts/arch-3?embed=true&utm_source=badge-top-post-badge&utm_medium=badge&utm_souce=badge-arch&#0045;3" target="_blank"><img src="https://api.producthunt.com/widgets/embed-image/v1/top-post-badge.svg?post_id=565761&theme=light&period=daily" alt="Arch - Build&#0032;fast&#0044;&#0032;hyper&#0045;personalized&#0032;agents&#0032;with&#0032;intelligent&#0032;infra | Product Hunt" style="width: 250px; height: 54px;" width="250" height="54" /></a>
Arch Gateway was built by the contributors of [Envoy Proxy](https://www.envoyproxy.io/) with the belief that:
>Prompts are nuanced and opaque user requests, which require the same capabilities as traditional HTTP requests including secure handling, intelligent routing, robust observability, and integration with backend (API) systems for personalization – outside core business logic.*
Arch is engineered with purpose-built LLMs to handle critical but pesky tasks related to the handling and processing of prompts. This includes detecting and rejecting [jailbreak](https://github.com/verazuo/jailbreak_llms) attempts, intent-based routing for improved task accuracy, mapping user request into "backend" functions, and managing the observability of prompts and LLM API calls in a centralized way.
**Core Features**:
- Built on [Envoy](https://envoyproxy.io): Arch runs alongside application servers as a separate containerized process, and builds on top of Envoy's proven HTTP management and scalability features to handle ingress and egress traffic related to prompts and LLMs.
- Task Routing & Fast Function Calling. Engineered with purpose-built [LLMs](https://huggingface.co/collections/katanemo/arch-function-66f209a693ea8df14317ad68) to handle fast, cost-effective, and accurate prompt-based tasks like function/API calling, and parameter extraction from prompts to build more task-accurate agentic applications.
- Prompt [Guard](https://huggingface.co/collections/katanemo/arch-guard-6702bdc08b889e4bce8f446d): Arch centralizes guardrails to prevent jailbreak attempts and ensure safe user interactions without writing a single line of code.
- Routing & Traffic Management: Arch centralizes calls to LLMs used by your applications, offering smart retries, automatic cutover, and resilient upstream connections for continuous availability.
- Observability: Arch uses the W3C Trace Context standard to enable complete request tracing across applications, ensuring compatibility with observability tools, and provides metrics to monitor latency, token usage, and error rates, helping optimize AI application performance.
- **Intent-based prompt routing & fast ⚡ function-calling via APIs**. Engineered with purpose-built [LLMs](https://huggingface.co/collections/katanemo/arch-function-66f209a693ea8df14317ad68) to handle fast, cost-effective, and accurate prompt-based tasks like function/API calling, and parameter extraction from prompts to build more task-accurate agentic applications.
- **Prompt [Guard](https://huggingface.co/collections/katanemo/arch-guard-6702bdc08b889e4bce8f446d)**: Arch centralizes guardrails to prevent jailbreak attempts and ensure safe user interactions without writing a single line of code.
- **LLM Routing & Traffic Management**: Arch centralizes calls to LLMs used by your applications, offering smart retries, automatic cutover, and resilient upstream connections for continuous availability.
- **Observability**: Arch uses the W3C Trace Context standard to enable complete request tracing across applications, ensuring compatibility with observability tools, and provides metrics to monitor latency, token usage, and error rates, helping optimize AI application performance.
- **Built on [Envoy](https://envoyproxy.io)**: Arch runs alongside application servers as a separate containerized process, and builds on top of Envoy's proven HTTP management and scalability features to handle ingress and egress traffic related to prompts and LLMs.
**High-Level Sequence Diagram**:
![alt text](docs/source/_static/img/arch_network_diagram_high_level.png)
@ -38,9 +49,9 @@ Arch is engineered with purpose-built LLMs to handle critical but undifferentiat
To get in touch with us, please join our [discord server](https://discord.gg/pGZf2gcwEc). We will be monitoring that actively and offering support there.
## Demos
* [Weather Forecast](demos/weather_forecast/README.md) - Walk through of the core function calling capabilities of arch gateway using weather forecasting service
* [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
* [Sample App: Weather Forecast Agent](demos/samples_python/weather_forecast/README.md) - A sample agentic weather forecasting app that highlights core function calling capabilities of Arch.
* [Sample App: Network Operator Agent](demos/samples_python/network_switch_operator_agent/README.md) - A simple network device switch operator agent that can retrive device statistics and reboot them.
* [User Case: Connecting to SaaS APIs](demos/use_cases/spotify_bearer_auth) - Connect 3rd party SaaS APIs to your agentic chat experience.
## Quickstart
@ -62,7 +73,7 @@ Arch's CLI allows you to manage and interact with the Arch gateway efficiently.
```console
$ python -m venv venv
$ source venv/bin/activate # On Windows, use: venv\Scripts\activate
$ pip install archgw==0.2.0
$ pip install archgw==0.2.2
```
### Build AI Agent with Arch Gateway

2
arch/Dockerfile
View file

@ -8,7 +8,7 @@ RUN cd prompt_gateway && cargo build --release --target wasm32-wasip1
RUN cd llm_gateway && cargo build --release --target wasm32-wasip1
# copy built filter into envoy image
FROM envoyproxy/envoy:v1.32-latest as envoy
FROM docker.io/envoyproxy/envoy:v1.32-latest as envoy
#Build config generator, so that we have a single build image for both Rust and Python
FROM python:3.12-slim as arch

60
arch/arch_config_schema.yaml
View file

@ -3,21 +3,38 @@ type: object
properties:
version:
type: string
listener:
listeners:
type: object
properties:
address:
type: string
port:
type: integer
message_format:
type: string
connect_timeout:
type: string
additionalProperties: false
required:
- address
- port
properties:
ingress_traffic:
type: object
properties:
address:
type: string
port:
type: integer
message_format:
type: string
enum:
- openai
timeout:
type: string
additionalProperties: false
egress_traffic:
type: object
properties:
address:
type: string
port:
type: integer
message_format:
type: string
enum:
- openai
timeout:
type: string
additionalProperties: false
endpoints:
type: object
patternProperties:
@ -79,6 +96,8 @@ properties:
properties:
prompt_target_intent_matching_threshold:
type: number
optimize_context_window:
type: boolean
system_prompt:
type: string
prompt_targets:
@ -105,7 +124,10 @@ properties:
required:
type: boolean
default:
type: string
anyOf:
- type: string
- type: integer
- type: boolean
description:
type: string
type:
@ -113,7 +135,10 @@ properties:
enum:
type: array
items:
type: string
anyOf:
- type: string
- type: integer
- type: boolean
in_path:
type: boolean
format:
@ -135,6 +160,10 @@ properties:
enum:
- GET
- POST
http_headers:
type: object
additionalProperties:
type: string
additionalProperties: false
required:
- name
@ -218,5 +247,4 @@ properties:
additionalProperties: false
required:
- version
- listener
- llm_providers

2
arch/docker-compose.dev.yaml
View file

@ -8,7 +8,7 @@ services:
- "12000:12000"
- "19901:9901"
volumes:
- ${ARCH_CONFIG_FILE:-../demos/weather_forecast/arch_config.yaml}:/app/arch_config.yaml
- ${ARCH_CONFIG_FILE:-../demos/samples_python/weather_forecast/arch_config.yaml}:/app/arch_config.yaml
- /etc/ssl/cert.pem:/etc/ssl/cert.pem
- ./envoy.template.yaml:/app/envoy.template.yaml
- ./arch_config_schema.yaml:/app/arch_config_schema.yaml

68
arch/envoy.template.yaml
View file

@ -29,11 +29,11 @@ stats_config:
- 180000
static_resources:
listeners:
- name: arch_listener_http
- name: ingress_traffic
address:
socket_address:
address: 0.0.0.0
port_value: 10000
address: {{ prompt_gateway_listener.address }}
port_value: {{ prompt_gateway_listener.port }}
traffic_direction: INBOUND
filter_chains:
- filters:
@ -55,7 +55,7 @@ static_resources:
random_sampling:
value: {{ arch_tracing.random_sampling }}
{% endif %}
stat_prefix: arch_listener_http
stat_prefix: ingress_traffic
codec_type: AUTO
scheme_header_transformation:
scheme_to_overwrite: https
@ -76,13 +76,13 @@ static_resources:
route:
auto_host_rewrite: true
cluster: arch_prompt_gateway_listener
timeout: 60s
timeout: {{ prompt_gateway_listener.timeout }}
http_filters:
- name: envoy.filters.http.router
typed_config:
"@type": type.googleapis.com/envoy.extensions.filters.http.router.v3.Router
- name: arch_prompt_gateway_listener
- name: ingress_traffic_prompt
address:
socket_address:
address: 0.0.0.0
@ -104,11 +104,11 @@ static_resources:
envoy_grpc:
cluster_name: opentelemetry_collector
timeout: 0.250s
service_name: prompt_processor
service_name: ingress_traffic
random_sampling:
value: {{ arch_tracing.random_sampling }}
{% endif %}
stat_prefix: arch_prompt_gateway_listener
stat_prefix: ingress_traffic
codec_type: AUTO
scheme_header_transformation:
scheme_to_overwrite: https
@ -201,7 +201,7 @@ static_resources:
typed_config:
"@type": type.googleapis.com/envoy.extensions.filters.http.router.v3.Router
- name: arch_internal
- name: egress_api_traffic
address:
socket_address:
address: 0.0.0.0
@ -223,11 +223,11 @@ static_resources:
envoy_grpc:
cluster_name: opentelemetry_collector
timeout: 0.250s
service_name: prompt_processor
service_name: egress_api_traffic
random_sampling:
value: {{ arch_tracing.random_sampling }}
{% endif %}
stat_prefix: arch_internal
stat_prefix: egress_api_traffic
codec_type: AUTO
scheme_header_transformation:
scheme_to_overwrite: https
@ -273,13 +273,12 @@ static_resources:
typed_config:
"@type": type.googleapis.com/envoy.extensions.filters.http.router.v3.Router
- name: arch_listener_http_llm
- name: egress_traffic
address:
socket_address:
address: 0.0.0.0
port_value: 12000
traffic_direction: INBOUND
address: {{ llm_gateway_listener.address }}
port_value: {{ llm_gateway_listener.port }}
traffic_direction: OUTBOUND
filter_chains:
- filters:
- name: envoy.filters.network.http_connection_manager
@ -300,7 +299,7 @@ static_resources:
random_sampling:
value: {{ arch_tracing.random_sampling }}
{% endif %}
stat_prefix: arch_listener_http
stat_prefix: egress_traffic
codec_type: AUTO
scheme_header_transformation:
scheme_to_overwrite: https
@ -321,14 +320,13 @@ static_resources:
route:
auto_host_rewrite: true
cluster: arch_listener_llm
timeout: 60s
timeout: {{ llm_gateway_listener.timeout }}
http_filters:
- name: envoy.filters.http.router
typed_config:
"@type": type.googleapis.com/envoy.extensions.filters.http.router.v3.Router
- name: arch_listener_llm
- name: egress_traffic_llm
address:
socket_address:
address: 0.0.0.0
@ -349,11 +347,11 @@ static_resources:
envoy_grpc:
cluster_name: opentelemetry_collector
timeout: 0.250s
service_name: llm_gateway
service_name: egress_traffic_llm
random_sampling:
value: {{ arch_tracing.random_sampling }}
{% endif %}
stat_prefix: arch_listener_http
stat_prefix: egress_traffic
codec_type: AUTO
scheme_header_transformation:
scheme_to_overwrite: https
@ -443,7 +441,7 @@ static_resources:
clusters:
- name: openai
connect_timeout: 5s
connect_timeout: 0.5s
type: LOGICAL_DNS
dns_lookup_family: V4_ONLY
lb_policy: ROUND_ROBIN
@ -467,7 +465,7 @@ static_resources:
tls_minimum_protocol_version: TLSv1_2
tls_maximum_protocol_version: TLSv1_3
- name: mistral
connect_timeout: 5s
connect_timeout: 0.5s
type: LOGICAL_DNS
dns_lookup_family: V4_ONLY
lb_policy: ROUND_ROBIN
@ -486,14 +484,14 @@ static_resources:
typed_config:
"@type": type.googleapis.com/envoy.extensions.transport_sockets.tls.v3.UpstreamTlsContext
sni: api.mistral.ai
{% for internal_clustrer in ["arch_fc", "model_server"] %}
- name: {{ internal_clustrer }}
connect_timeout: 5s
{% for internal_cluster in ["arch_fc", "model_server"] %}
- name: {{ internal_cluster }}
connect_timeout: 0.5s
type: STRICT_DNS
dns_lookup_family: V4_ONLY
lb_policy: ROUND_ROBIN
load_assignment:
cluster_name: {{ internal_clustrer }}
cluster_name: {{ internal_cluster }}
endpoints:
- lb_endpoints:
- endpoint:
@ -501,10 +499,10 @@ static_resources:
socket_address:
address: host.docker.internal
port_value: $MODEL_SERVER_PORT
hostname: {{ internal_clustrer }}
hostname: {{ internal_cluster }}
{% endfor %}
- name: mistral_7b_instruct
connect_timeout: 5s
connect_timeout: 0.5s
type: STRICT_DNS
dns_lookup_family: V4_ONLY
lb_policy: ROUND_ROBIN
@ -523,7 +521,7 @@ static_resources:
{% if cluster.connect_timeout -%}
connect_timeout: {{ cluster.connect_timeout }}
{% else -%}
connect_timeout: 5s
connect_timeout: 0.5s
{% endif -%}
type: LOGICAL_DNS
dns_lookup_family: V4_ONLY
@ -557,7 +555,7 @@ static_resources:
{% for local_llm_provider in local_llms %}
- name: {{ local_llm_provider.name }}
connect_timeout: 5s
connect_timeout: 0.5s
type: LOGICAL_DNS
dns_lookup_family: V4_ONLY
lb_policy: ROUND_ROBIN
@ -589,7 +587,7 @@ static_resources:
{% endfor %}
- name: arch_internal
connect_timeout: 5s
connect_timeout: 0.5s
type: LOGICAL_DNS
dns_lookup_family: V4_ONLY
lb_policy: ROUND_ROBIN
@ -605,7 +603,7 @@ static_resources:
hostname: arch_internal
- name: arch_prompt_gateway_listener
connect_timeout: 5s
connect_timeout: 0.5s
type: LOGICAL_DNS
dns_lookup_family: V4_ONLY
lb_policy: ROUND_ROBIN
@ -621,7 +619,7 @@ static_resources:
hostname: arch_prompt_gateway_listener
- name: arch_listener_llm
connect_timeout: 5s
connect_timeout: 0.5s
type: LOGICAL_DNS
dns_lookup_family: V4_ONLY
lb_policy: ROUND_ROBIN

2
arch/tools/README.md
View file

@ -19,7 +19,7 @@ source venv/bin/activate
### Step 3: Run the build script
```bash
pip install archgw==0.2.0
pip install archgw==0.2.2
```
## Uninstall Instructions: archgw CLI

20
arch/tools/cli/config_generator.py
View file

@ -104,7 +104,27 @@ def validate_and_render_schema():
arch_config_string = yaml.dump(config_yaml)
arch_llm_config_string = yaml.dump(config_yaml)
prompt_gateway_listener = config_yaml.get("listeners", {}).get(
"ingress_traffic", {}
)
if prompt_gateway_listener.get("port") == None:
prompt_gateway_listener["port"] = 10000 # default port for prompt gateway
if prompt_gateway_listener.get("address") == None:
prompt_gateway_listener["address"] = "127.0.0.1"
if prompt_gateway_listener.get("timeout") == None:
prompt_gateway_listener["timeout"] = "10s"
llm_gateway_listener = config_yaml.get("listeners", {}).get("egress_traffic", {})
if llm_gateway_listener.get("port") == None:
llm_gateway_listener["port"] = 12000 # default port for llm gateway
if llm_gateway_listener.get("address") == None:
llm_gateway_listener["address"] = "127.0.0.1"
if llm_gateway_listener.get("timeout") == None:
llm_gateway_listener["timeout"] = "10s"
data = {
"prompt_gateway_listener": prompt_gateway_listener,
"llm_gateway_listener": llm_gateway_listener,
"arch_config": arch_config_string,
"arch_llm_config": arch_llm_config_string,
"arch_clusters": inferred_clusters,

176
arch/tools/cli/core.py
View file

@ -2,102 +2,49 @@ import subprocess
import os
import time
import sys
import glob
import docker
from docker.errors import DockerException
from cli.utils import getLogger, update_docker_host_env
import yaml
from cli.utils import getLogger
from cli.consts import (
ARCHGW_DOCKER_IMAGE,
ARCHGW_DOCKER_NAME,
KATANEMO_LOCAL_MODEL_LIST,
MODEL_SERVER_LOG_FILE,
ACCESS_LOG_FILES,
)
from huggingface_hub import snapshot_download
from dotenv import dotenv_values
import subprocess
from cli.docker_cli import (
docker_container_status,
docker_remove_container,
docker_start_archgw_detached,
docker_stop_container,
health_check_endpoint,
stream_gateway_logs,
)
log = getLogger(__name__)
def start_archgw_docker(client, arch_config_file, env):
logs_path = "~/archgw_logs"
logs_path_abs = os.path.expanduser(logs_path)
def _get_gateway_ports(arch_config_file: str) -> tuple:
PROMPT_GATEWAY_DEFAULT_PORT = 10000
LLM_GATEWAY_DEFAULT_PORT = 12000
return client.containers.run(
name=ARCHGW_DOCKER_NAME,
image=ARCHGW_DOCKER_IMAGE,
detach=True, # Run in detached mode
ports={
"10000/tcp": 10000,
"10001/tcp": 10001,
"11000/tcp": 11000,
"12000/tcp": 12000,
"9901/tcp": 19901,
},
volumes={
f"{arch_config_file}": {
"bind": "/app/arch_config.yaml",
"mode": "ro",
},
"/etc/ssl/cert.pem": {"bind": "/etc/ssl/cert.pem", "mode": "ro"},
logs_path_abs: {"bind": "/var/log"},
},
environment={
"OTEL_TRACING_HTTP_ENDPOINT": "http://host.docker.internal:4318/v1/traces",
"MODEL_SERVER_PORT": os.getenv("MODEL_SERVER_PORT", "51000"),
**env,
},
extra_hosts={"host.docker.internal": "host-gateway"},
healthcheck={
"test": ["CMD", "curl", "-f", "http://localhost:10000/healthz"],
"interval": 5000000000, # 5 seconds
"timeout": 1000000000, # 1 seconds
"retries": 3,
},
# parse arch_config_file yaml file and get prompt_gateway_port
arch_config_dict = {}
with open(arch_config_file) as f:
arch_config_dict = yaml.safe_load(f)
prompt_gateway_port = (
arch_config_dict.get("listeners", {})
.get("ingress_traffic", {})
.get("port", PROMPT_GATEWAY_DEFAULT_PORT)
)
llm_gateway_port = (
arch_config_dict.get("listeners", {})
.get("egress_traffic", {})
.get("port", LLM_GATEWAY_DEFAULT_PORT)
)
def stream_gateway_logs(follow):
"""
Stream logs from the arch gateway service.
"""
log.info("Logs from arch gateway service.")
options = ["docker", "logs", "archgw"]
if follow:
options.append("-f")
try:
# Run `docker-compose logs` to stream logs from the gateway service
subprocess.run(
options,
check=True,
stdout=sys.stdout,
stderr=sys.stderr,
)
except subprocess.CalledProcessError as e:
log.info(f"Failed to stream logs: {str(e)}")
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,
)
return prompt_gateway_port, llm_gateway_port
def start_arch(arch_config_file, env, log_timeout=120, foreground=False):
@ -111,55 +58,58 @@ def start_arch(arch_config_file, env, log_timeout=120, foreground=False):
log.info("Starting arch gateway")
try:
try:
client = docker.from_env()
except DockerException as e:
# try setting up the docker host environment variable and retry
update_docker_host_env()
client = docker.from_env()
archgw_container_status = docker_container_status(ARCHGW_DOCKER_NAME)
if archgw_container_status != "not found":
log.info("archgw found in docker, stopping and removing it")
docker_stop_container(ARCHGW_DOCKER_NAME)
docker_remove_container(ARCHGW_DOCKER_NAME)
try:
container = client.containers.get("archgw")
log.info("archgw container found in docker, stopping and removing it")
# ensure that previous docker container is stopped and removed
container.stop()
container.remove()
log.info("Stopped and removed archgw container")
except docker.errors.NotFound as e:
pass
prompt_gateway_port, llm_gateway_port = _get_gateway_ports(arch_config_file)
container = start_archgw_docker(client, arch_config_file, env)
return_code, _, archgw_stderr = docker_start_archgw_detached(
arch_config_file,
os.path.expanduser("~/archgw_logs"),
env,
prompt_gateway_port,
llm_gateway_port,
)
if return_code != 0:
log.info("Failed to start arch gateway: " + str(return_code))
log.info("stderr: " + archgw_stderr)
sys.exit(1)
start_time = time.time()
while True:
container = client.containers.get(container.id)
prompt_gateway_health_check_status = health_check_endpoint(
f"http://localhost:{prompt_gateway_port}/healthz"
)
llm_gateway_health_check_status = health_check_endpoint(
f"http://localhost:{llm_gateway_port}/healthz"
)
archgw_status = docker_container_status(ARCHGW_DOCKER_NAME)
current_time = time.time()
elapsed_time = current_time - start_time
# Check if timeout is reached
if elapsed_time > log_timeout:
log.info(f"Stopping log monitoring after {log_timeout} seconds.")
log.info(f"stopping log monitoring after {log_timeout} seconds.")
break
container_status = container.attrs["State"]["Health"]["Status"]
if container_status == "healthy":
log.info("Container is healthy!")
if prompt_gateway_health_check_status or llm_gateway_health_check_status:
log.info("archgw is running and is healthy!")
break
else:
log.info(f"Container health status: {container_status}")
log.info(f"archgw status: {archgw_status}, health status: starting")
time.sleep(1)
if foreground:
for line in container.logs(stream=True):
print(line.decode("utf-8").strip("\n"))
stream_gateway_logs(follow=True)
except KeyboardInterrupt:
log.info("Keyboard interrupt received, stopping arch gateway service.")
stop_arch()
except docker.errors.APIError as e:
log.info(f"Failed to start Arch: {str(e)}")
def stop_arch():
@ -173,10 +123,10 @@ def stop_arch():
try:
subprocess.run(
["docker", "stop", "archgw"],
["docker", "stop", ARCHGW_DOCKER_NAME],
)
subprocess.run(
["docker", "remove", "archgw"],
["docker", "rm", ARCHGW_DOCKER_NAME],
)
log.info("Successfully shut down arch gateway service.")

132
arch/tools/cli/docker_cli.py Normal file
View file

@ -0,0 +1,132 @@
import subprocess
import json
import sys
import requests
from cli.consts import ARCHGW_DOCKER_IMAGE, ARCHGW_DOCKER_NAME
from cli.utils import getLogger
log = getLogger(__name__)
def docker_container_status(container: str) -> str:
result = subprocess.run(
["docker", "inspect", "--type=container", container],
capture_output=True,
text=True,
check=False,
)
if result.returncode != 0:
return "not found"
container_status = json.loads(result.stdout)[0]
return container_status.get("State", {}).get("Status", "")
def docker_stop_container(container: str) -> str:
result = subprocess.run(
["docker", "stop", container], capture_output=True, text=True, check=False
)
return result.returncode
def docker_remove_container(container: str) -> str:
result = subprocess.run(
["docker", "rm", container], capture_output=True, text=True, check=False
)
return result.returncode
def docker_start_archgw_detached(
arch_config_file: str,
logs_path_abs: str,
env: dict,
prompt_gateway_port,
llm_gateway_port,
) -> str:
env_args = [item for key, value in env.items() for item in ["-e", f"{key}={value}"]]
port_mappings = [
f"{prompt_gateway_port}:{prompt_gateway_port}",
f"{llm_gateway_port}:{llm_gateway_port}",
"9901:19901",
]
port_mappings_args = [item for port in port_mappings for item in ("-p", port)]
volume_mappings = [
f"{logs_path_abs}:/var/log:rw",
f"{arch_config_file}:/app/arch_config.yaml:ro",
]
volume_mappings_args = [
item for volume in volume_mappings for item in ("-v", volume)
]
options = [
"docker",
"run",
"-d",
"--name",
ARCHGW_DOCKER_NAME,
*port_mappings_args,
*volume_mappings_args,
*env_args,
"--add-host",
"host.docker.internal:host-gateway",
ARCHGW_DOCKER_IMAGE,
]
result = subprocess.run(options, capture_output=True, text=True, check=False)
return result.returncode, result.stdout, result.stderr
def health_check_endpoint(endpoint: str) -> bool:
try:
response = requests.get(endpoint)
if response.status_code == 200:
return True
except requests.RequestException as e:
pass
return False
def stream_gateway_logs(follow):
"""
Stream logs from the arch gateway service.
"""
log.info("Logs from arch gateway service.")
options = ["docker", "logs"]
if follow:
options.append("-f")
options.append(ARCHGW_DOCKER_NAME)
try:
# Run `docker-compose logs` to stream logs from the gateway service
subprocess.run(
options,
check=True,
stdout=sys.stdout,
stderr=sys.stderr,
)
except subprocess.CalledProcessError as e:
log.info(f"Failed to stream logs: {str(e)}")
def docker_validate_archgw_schema(arch_config_file):
result = subprocess.run(
[
"docker",
"run",
"--rm",
"-v",
f"{arch_config_file}:/app/arch_config.yaml:ro",
"--entrypoint",
"python",
ARCHGW_DOCKER_IMAGE,
"config_generator.py",
],
capture_output=True,
text=True,
check=False,
)
return result.returncode, result.stdout, result.stderr

25
arch/tools/cli/main.py
View file

@ -5,11 +5,12 @@ import subprocess
import multiprocessing
import importlib.metadata
from cli import targets
from cli.docker_cli import docker_validate_archgw_schema, stream_gateway_logs
from cli.utils import (
getLogger,
get_llm_provider_access_keys,
load_env_file_to_dict,
validate_schema,
stream_access_logs,
)
from cli.core import (
start_arch_modelserver,
@ -17,12 +18,9 @@ from cli.core import (
start_arch,
stop_arch,
download_models_from_hf,
stream_access_logs,
stream_gateway_logs,
)
from cli.consts import (
KATANEMO_DOCKERHUB_REPO,
KATANEMO_LOCAL_MODEL_LIST,
SERVICE_NAME_ARCHGW,
SERVICE_NAME_MODEL_SERVER,
SERVICE_ALL,
@ -174,17 +172,24 @@ def up(file, path, service, foreground):
log.info(f"Validating {arch_config_file}")
try:
validate_schema(arch_config_file)
except Exception as e:
log.info(f"Exiting archgw up: validation failed")
log.info(f"Error: {str(e)}")
(
validation_return_code,
validation_stdout,
validation_stderr,
) = docker_validate_archgw_schema(arch_config_file)
if validation_return_code != 0:
log.info(f"Error: Validation failed. Exiting")
log.info(f"Validation stdout: {validation_stdout}")
log.info(f"Validation stderr: {validation_stderr}")
sys.exit(1)
log.info("Starting arch model server and arch gateway")
# Set the ARCH_CONFIG_FILE environment variable
env_stage = {}
env_stage = {
"OTEL_TRACING_HTTP_ENDPOINT": "http://host.docker.internal:4318/v1/traces",
"MODEL_SERVER_PORT": os.getenv("MODEL_SERVER_PORT", "51000"),
}
env = os.environ.copy()
# check if access_keys are preesnt in the config file
access_keys = get_llm_provider_access_keys(arch_config_file=arch_config_file)

1
arch/tools/cli/targets.py
View file

@ -2,7 +2,6 @@ import ast
import sys
import yaml
from typing import Any
from pydantic import BaseModel
FLASK_ROUTE_DECORATORS = ["route", "get", "post", "put", "delete", "patch"]
FASTAPI_ROUTE_DECORATORS = ["get", "post", "put", "delete", "patch"]

96
arch/tools/cli/utils.py
View file

@ -1,10 +1,11 @@
import glob
import os
import subprocess
import sys
import yaml
import logging
import docker
from docker.errors import DockerException
from cli.consts import ARCHGW_DOCKER_IMAGE, ARCHGW_DOCKER_NAME
from cli.consts import ACCESS_LOG_FILES
logging.basicConfig(
level=logging.INFO,
@ -21,63 +22,6 @@ def getLogger(name="cli"):
log = getLogger(__name__)
def update_docker_host_env():
"""
Update DOCKER_HOST environment variable to use the local Docker socket
"""
if os.getenv("DOCKER_HOST"):
return
default_docker_socket = os.getenv("DEFAULT_DOCKER_SOCKET", "/var/run/docker.sock")
if not os.path.exists(default_docker_socket):
home_dir = os.getenv("HOME")
docker_host = f"unix://{home_dir}/.docker/run/docker.sock"
log.info(
f"Default docker socket {default_docker_socket} not found, using {docker_host}"
)
os.environ["DOCKER_HOST"] = docker_host
def validate_schema(arch_config_file: str) -> None:
try:
try:
client = docker.from_env()
except DockerException as e:
# try setting up the docker host environment variable and retry
update_docker_host_env()
client = docker.from_env()
container = client.containers.run(
image=ARCHGW_DOCKER_IMAGE,
volumes={
f"{arch_config_file}": {
"bind": "/app/arch_config.yaml",
"mode": "ro",
},
},
entrypoint=["python", "config_generator.py"],
detach=True,
)
# Wait for the container to finish and get the exit code
exit_code = container.wait()
# Check exit code for validation success
if exit_code["StatusCode"] != 0:
# Validation failed (non-zero exit code)
logs = container.logs().decode() # Get container logs for debugging
raise ValueError(
f"Validation failed. Container exited with code {exit_code}.\nLogs:\n{logs}"
)
# Successful validation (exit code 0)
log.info("Schema validation successful!")
except docker.errors.APIError as e:
# Handle container creation error
raise ValueError(f"Failed to create container: {e}")
def get_llm_provider_access_keys(arch_config_file):
with open(arch_config_file, "r") as file:
arch_config = file.read()
@ -89,6 +33,18 @@ def get_llm_provider_access_keys(arch_config_file):
if acess_key is not None:
access_key_list.append(acess_key)
for prompt_target in arch_config_yaml.get("prompt_targets", []):
for k, v in prompt_target.get("endpoint", {}).get("http_headers", {}).items():
if k.lower() == "authorization":
print(
f"found auth header: {k} for prompt_target: {prompt_target.get('name')}/{prompt_target.get('endpoint').get('name')}"
)
auth_tokens = v.split(" ")
if len(auth_tokens) > 1:
access_key_list.append(auth_tokens[1])
else:
access_key_list.append(v)
return access_key_list
@ -115,3 +71,23 @@ def load_env_file_to_dict(file_path):
env_dict[key] = value
return env_dict
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,
)

293
arch/tools/poetry.lock generated
View file

@ -2,7 +2,7 @@
[[package]]
name = "archgw_modelserver"
version = "0.2.0"
version = "0.2.2"
description = "A model server for serving models"
optional = false
python-versions = "*"
@ -15,13 +15,13 @@ url = "../../model_server"
[[package]]
name = "attrs"
version = "24.3.0"
version = "25.1.0"
description = "Classes Without Boilerplate"
optional = false
python-versions = ">=3.8"
files = [
{file = "attrs-24.3.0-py3-none-any.whl", hash = "sha256:ac96cd038792094f438ad1f6ff80837353805ac950cd2aa0e0625ef19850c308"},
{file = "attrs-24.3.0.tar.gz", hash = "sha256:8f5c07333d543103541ba7be0e2ce16eeee8130cb0b3f9238ab904ce1e85baff"},
{file = "attrs-25.1.0-py3-none-any.whl", hash = "sha256:c75a69e28a550a7e93789579c22aa26b0f5b83b75dc4e08fe092980051e1090a"},
{file = "attrs-25.1.0.tar.gz", hash = "sha256:1c97078a80c814273a76b2a298a932eb681c87415c11dee0a6921de7f1b02c3e"},
]
[package.extras]
@ -32,118 +32,6 @@ docs = ["cogapp", "furo", "myst-parser", "sphinx", "sphinx-notfound-page", "sphi
tests = ["cloudpickle", "hypothesis", "mypy (>=1.11.1)", "pympler", "pytest (>=4.3.0)", "pytest-mypy-plugins", "pytest-xdist[psutil]"]
tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"]
[[package]]
name = "certifi"
version = "2024.12.14"
description = "Python package for providing Mozilla's CA Bundle."
optional = false
python-versions = ">=3.6"
files = [
{file = "certifi-2024.12.14-py3-none-any.whl", hash = "sha256:1275f7a45be9464efc1173084eaa30f866fe2e47d389406136d332ed4967ec56"},
{file = "certifi-2024.12.14.tar.gz", hash = "sha256:b650d30f370c2b724812bee08008be0c4163b163ddaec3f2546c1caf65f191db"},
]
[[package]]
name = "charset-normalizer"
version = "3.4.1"
description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet."
optional = false
python-versions = ">=3.7"
files = [
{file = "charset_normalizer-3.4.1-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:91b36a978b5ae0ee86c394f5a54d6ef44db1de0815eb43de826d41d21e4af3de"},
{file = "charset_normalizer-3.4.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:7461baadb4dc00fd9e0acbe254e3d7d2112e7f92ced2adc96e54ef6501c5f176"},
{file = "charset_normalizer-3.4.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e218488cd232553829be0664c2292d3af2eeeb94b32bea483cf79ac6a694e037"},
{file = "charset_normalizer-3.4.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:80ed5e856eb7f30115aaf94e4a08114ccc8813e6ed1b5efa74f9f82e8509858f"},
{file = "charset_normalizer-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b010a7a4fd316c3c484d482922d13044979e78d1861f0e0650423144c616a46a"},
{file = "charset_normalizer-3.4.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4532bff1b8421fd0a320463030c7520f56a79c9024a4e88f01c537316019005a"},
{file = "charset_normalizer-3.4.1-cp310-cp310-musllinux_1_2_aarch64.whl", hash = "sha256:d973f03c0cb71c5ed99037b870f2be986c3c05e63622c017ea9816881d2dd247"},
{file = "charset_normalizer-3.4.1-cp310-cp310-musllinux_1_2_i686.whl", hash = "sha256:3a3bd0dcd373514dcec91c411ddb9632c0d7d92aed7093b8c3bbb6d69ca74408"},
{file = "charset_normalizer-3.4.1-cp310-cp310-musllinux_1_2_ppc64le.whl", hash = "sha256:d9c3cdf5390dcd29aa8056d13e8e99526cda0305acc038b96b30352aff5ff2bb"},
{file = "charset_normalizer-3.4.1-cp310-cp310-musllinux_1_2_s390x.whl", hash = "sha256:2bdfe3ac2e1bbe5b59a1a63721eb3b95fc9b6817ae4a46debbb4e11f6232428d"},
{file = "charset_normalizer-3.4.1-cp310-cp310-musllinux_1_2_x86_64.whl", hash = "sha256:eab677309cdb30d047996b36d34caeda1dc91149e4fdca0b1a039b3f79d9a807"},
{file = "charset_normalizer-3.4.1-cp310-cp310-win32.whl", hash = "sha256:c0429126cf75e16c4f0ad00ee0eae4242dc652290f940152ca8c75c3a4b6ee8f"},
{file = "charset_normalizer-3.4.1-cp310-cp310-win_amd64.whl", hash = "sha256:9f0b8b1c6d84c8034a44893aba5e767bf9c7a211e313a9605d9c617d7083829f"},
{file = "charset_normalizer-3.4.1-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:8bfa33f4f2672964266e940dd22a195989ba31669bd84629f05fab3ef4e2d125"},
{file = "charset_normalizer-3.4.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:28bf57629c75e810b6ae989f03c0828d64d6b26a5e205535585f96093e405ed1"},
{file = "charset_normalizer-3.4.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f08ff5e948271dc7e18a35641d2f11a4cd8dfd5634f55228b691e62b37125eb3"},
{file = "charset_normalizer-3.4.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:234ac59ea147c59ee4da87a0c0f098e9c8d169f4dc2a159ef720f1a61bbe27cd"},
{file = "charset_normalizer-3.4.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fd4ec41f914fa74ad1b8304bbc634b3de73d2a0889bd32076342a573e0779e00"},
{file = "charset_normalizer-3.4.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:eea6ee1db730b3483adf394ea72f808b6e18cf3cb6454b4d86e04fa8c4327a12"},
{file = "charset_normalizer-3.4.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:c96836c97b1238e9c9e3fe90844c947d5afbf4f4c92762679acfe19927d81d77"},
{file = "charset_normalizer-3.4.1-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:4d86f7aff21ee58f26dcf5ae81a9addbd914115cdebcbb2217e4f0ed8982e146"},
{file = "charset_normalizer-3.4.1-cp311-cp311-musllinux_1_2_ppc64le.whl", hash = "sha256:09b5e6733cbd160dcc09589227187e242a30a49ca5cefa5a7edd3f9d19ed53fd"},
{file = "charset_normalizer-3.4.1-cp311-cp311-musllinux_1_2_s390x.whl", hash = "sha256:5777ee0881f9499ed0f71cc82cf873d9a0ca8af166dfa0af8ec4e675b7df48e6"},
{file = "charset_normalizer-3.4.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:237bdbe6159cff53b4f24f397d43c6336c6b0b42affbe857970cefbb620911c8"},
{file = "charset_normalizer-3.4.1-cp311-cp311-win32.whl", hash = "sha256:8417cb1f36cc0bc7eaba8ccb0e04d55f0ee52df06df3ad55259b9a323555fc8b"},
{file = "charset_normalizer-3.4.1-cp311-cp311-win_amd64.whl", hash = "sha256:d7f50a1f8c450f3925cb367d011448c39239bb3eb4117c36a6d354794de4ce76"},
{file = "charset_normalizer-3.4.1-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:73d94b58ec7fecbc7366247d3b0b10a21681004153238750bb67bd9012414545"},
{file = "charset_normalizer-3.4.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:dad3e487649f498dd991eeb901125411559b22e8d7ab25d3aeb1af367df5efd7"},
{file = "charset_normalizer-3.4.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:c30197aa96e8eed02200a83fba2657b4c3acd0f0aa4bdc9f6c1af8e8962e0757"},
{file = "charset_normalizer-3.4.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2369eea1ee4a7610a860d88f268eb39b95cb588acd7235e02fd5a5601773d4fa"},
{file = "charset_normalizer-3.4.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:bc2722592d8998c870fa4e290c2eec2c1569b87fe58618e67d38b4665dfa680d"},
{file = "charset_normalizer-3.4.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:ffc9202a29ab3920fa812879e95a9e78b2465fd10be7fcbd042899695d75e616"},
{file = "charset_normalizer-3.4.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:804a4d582ba6e5b747c625bf1255e6b1507465494a40a2130978bda7b932c90b"},
{file = "charset_normalizer-3.4.1-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:0f55e69f030f7163dffe9fd0752b32f070566451afe180f99dbeeb81f511ad8d"},
{file = "charset_normalizer-3.4.1-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:c4c3e6da02df6fa1410a7680bd3f63d4f710232d3139089536310d027950696a"},
{file = "charset_normalizer-3.4.1-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:5df196eb874dae23dcfb968c83d4f8fdccb333330fe1fc278ac5ceeb101003a9"},
{file = "charset_normalizer-3.4.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:e358e64305fe12299a08e08978f51fc21fac060dcfcddd95453eabe5b93ed0e1"},
{file = "charset_normalizer-3.4.1-cp312-cp312-win32.whl", hash = "sha256:9b23ca7ef998bc739bf6ffc077c2116917eabcc901f88da1b9856b210ef63f35"},
{file = "charset_normalizer-3.4.1-cp312-cp312-win_amd64.whl", hash = "sha256:6ff8a4a60c227ad87030d76e99cd1698345d4491638dfa6673027c48b3cd395f"},
{file = "charset_normalizer-3.4.1-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:aabfa34badd18f1da5ec1bc2715cadc8dca465868a4e73a0173466b688f29dda"},
{file = "charset_normalizer-3.4.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22e14b5d70560b8dd51ec22863f370d1e595ac3d024cb8ad7d308b4cd95f8313"},
{file = "charset_normalizer-3.4.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:8436c508b408b82d87dc5f62496973a1805cd46727c34440b0d29d8a2f50a6c9"},
{file = "charset_normalizer-3.4.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2d074908e1aecee37a7635990b2c6d504cd4766c7bc9fc86d63f9c09af3fa11b"},
{file = "charset_normalizer-3.4.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:955f8851919303c92343d2f66165294848d57e9bba6cf6e3625485a70a038d11"},
{file = "charset_normalizer-3.4.1-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:44ecbf16649486d4aebafeaa7ec4c9fed8b88101f4dd612dcaf65d5e815f837f"},
{file = "charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:0924e81d3d5e70f8126529951dac65c1010cdf117bb75eb02dd12339b57749dd"},
{file = "charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:2967f74ad52c3b98de4c3b32e1a44e32975e008a9cd2a8cc8966d6a5218c5cb2"},
{file = "charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:c75cb2a3e389853835e84a2d8fb2b81a10645b503eca9bcb98df6b5a43eb8886"},
{file = "charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:09b26ae6b1abf0d27570633b2b078a2a20419c99d66fb2823173d73f188ce601"},
{file = "charset_normalizer-3.4.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:fa88b843d6e211393a37219e6a1c1df99d35e8fd90446f1118f4216e307e48cd"},
{file = "charset_normalizer-3.4.1-cp313-cp313-win32.whl", hash = "sha256:eb8178fe3dba6450a3e024e95ac49ed3400e506fd4e9e5c32d30adda88cbd407"},
{file = "charset_normalizer-3.4.1-cp313-cp313-win_amd64.whl", hash = "sha256:b1ac5992a838106edb89654e0aebfc24f5848ae2547d22c2c3f66454daa11971"},
{file = "charset_normalizer-3.4.1-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f30bf9fd9be89ecb2360c7d94a711f00c09b976258846efe40db3d05828e8089"},
{file = "charset_normalizer-3.4.1-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:97f68b8d6831127e4787ad15e6757232e14e12060bec17091b85eb1486b91d8d"},
{file = "charset_normalizer-3.4.1-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7974a0b5ecd505609e3b19742b60cee7aa2aa2fb3151bc917e6e2646d7667dcf"},
{file = "charset_normalizer-3.4.1-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:fc54db6c8593ef7d4b2a331b58653356cf04f67c960f584edb7c3d8c97e8f39e"},
{file = "charset_normalizer-3.4.1-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:311f30128d7d333eebd7896965bfcfbd0065f1716ec92bd5638d7748eb6f936a"},
{file = "charset_normalizer-3.4.1-cp37-cp37m-musllinux_1_2_aarch64.whl", hash = "sha256:7d053096f67cd1241601111b698f5cad775f97ab25d81567d3f59219b5f1adbd"},
{file = "charset_normalizer-3.4.1-cp37-cp37m-musllinux_1_2_i686.whl", hash = "sha256:807f52c1f798eef6cf26beb819eeb8819b1622ddfeef9d0977a8502d4db6d534"},
{file = "charset_normalizer-3.4.1-cp37-cp37m-musllinux_1_2_ppc64le.whl", hash = "sha256:dccbe65bd2f7f7ec22c4ff99ed56faa1e9f785482b9bbd7c717e26fd723a1d1e"},
{file = "charset_normalizer-3.4.1-cp37-cp37m-musllinux_1_2_s390x.whl", hash = "sha256:2fb9bd477fdea8684f78791a6de97a953c51831ee2981f8e4f583ff3b9d9687e"},
{file = "charset_normalizer-3.4.1-cp37-cp37m-musllinux_1_2_x86_64.whl", hash = "sha256:01732659ba9b5b873fc117534143e4feefecf3b2078b0a6a2e925271bb6f4cfa"},
{file = "charset_normalizer-3.4.1-cp37-cp37m-win32.whl", hash = "sha256:7a4f97a081603d2050bfaffdefa5b02a9ec823f8348a572e39032caa8404a487"},
{file = "charset_normalizer-3.4.1-cp37-cp37m-win_amd64.whl", hash = "sha256:7b1bef6280950ee6c177b326508f86cad7ad4dff12454483b51d8b7d673a2c5d"},
{file = "charset_normalizer-3.4.1-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:ecddf25bee22fe4fe3737a399d0d177d72bc22be6913acfab364b40bce1ba83c"},
{file = "charset_normalizer-3.4.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8c60ca7339acd497a55b0ea5d506b2a2612afb2826560416f6894e8b5770d4a9"},
{file = "charset_normalizer-3.4.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:b7b2d86dd06bfc2ade3312a83a5c364c7ec2e3498f8734282c6c3d4b07b346b8"},
{file = "charset_normalizer-3.4.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:dd78cfcda14a1ef52584dbb008f7ac81c1328c0f58184bf9a84c49c605002da6"},
{file = "charset_normalizer-3.4.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6e27f48bcd0957c6d4cb9d6fa6b61d192d0b13d5ef563e5f2ae35feafc0d179c"},
{file = "charset_normalizer-3.4.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:01ad647cdd609225c5350561d084b42ddf732f4eeefe6e678765636791e78b9a"},
{file = "charset_normalizer-3.4.1-cp38-cp38-musllinux_1_2_aarch64.whl", hash = "sha256:619a609aa74ae43d90ed2e89bdd784765de0a25ca761b93e196d938b8fd1dbbd"},
{file = "charset_normalizer-3.4.1-cp38-cp38-musllinux_1_2_i686.whl", hash = "sha256:89149166622f4db9b4b6a449256291dc87a99ee53151c74cbd82a53c8c2f6ccd"},
{file = "charset_normalizer-3.4.1-cp38-cp38-musllinux_1_2_ppc64le.whl", hash = "sha256:7709f51f5f7c853f0fb938bcd3bc59cdfdc5203635ffd18bf354f6967ea0f824"},
{file = "charset_normalizer-3.4.1-cp38-cp38-musllinux_1_2_s390x.whl", hash = "sha256:345b0426edd4e18138d6528aed636de7a9ed169b4aaf9d61a8c19e39d26838ca"},
{file = "charset_normalizer-3.4.1-cp38-cp38-musllinux_1_2_x86_64.whl", hash = "sha256:0907f11d019260cdc3f94fbdb23ff9125f6b5d1039b76003b5b0ac9d6a6c9d5b"},
{file = "charset_normalizer-3.4.1-cp38-cp38-win32.whl", hash = "sha256:ea0d8d539afa5eb2728aa1932a988a9a7af94f18582ffae4bc10b3fbdad0626e"},
{file = "charset_normalizer-3.4.1-cp38-cp38-win_amd64.whl", hash = "sha256:329ce159e82018d646c7ac45b01a430369d526569ec08516081727a20e9e4af4"},
{file = "charset_normalizer-3.4.1-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:b97e690a2118911e39b4042088092771b4ae3fc3aa86518f84b8cf6888dbdb41"},
{file = "charset_normalizer-3.4.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:78baa6d91634dfb69ec52a463534bc0df05dbd546209b79a3880a34487f4b84f"},
{file = "charset_normalizer-3.4.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1a2bc9f351a75ef49d664206d51f8e5ede9da246602dc2d2726837620ea034b2"},
{file = "charset_normalizer-3.4.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:75832c08354f595c760a804588b9357d34ec00ba1c940c15e31e96d902093770"},
{file = "charset_normalizer-3.4.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:0af291f4fe114be0280cdd29d533696a77b5b49cfde5467176ecab32353395c4"},
{file = "charset_normalizer-3.4.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0167ddc8ab6508fe81860a57dd472b2ef4060e8d378f0cc555707126830f2537"},
{file = "charset_normalizer-3.4.1-cp39-cp39-musllinux_1_2_aarch64.whl", hash = "sha256:2a75d49014d118e4198bcee5ee0a6f25856b29b12dbf7cd012791f8a6cc5c496"},
{file = "charset_normalizer-3.4.1-cp39-cp39-musllinux_1_2_i686.whl", hash = "sha256:363e2f92b0f0174b2f8238240a1a30142e3db7b957a5dd5689b0e75fb717cc78"},
{file = "charset_normalizer-3.4.1-cp39-cp39-musllinux_1_2_ppc64le.whl", hash = "sha256:ab36c8eb7e454e34e60eb55ca5d241a5d18b2c6244f6827a30e451c42410b5f7"},
{file = "charset_normalizer-3.4.1-cp39-cp39-musllinux_1_2_s390x.whl", hash = "sha256:4c0907b1928a36d5a998d72d64d8eaa7244989f7aaaf947500d3a800c83a3fd6"},
{file = "charset_normalizer-3.4.1-cp39-cp39-musllinux_1_2_x86_64.whl", hash = "sha256:04432ad9479fa40ec0f387795ddad4437a2b50417c69fa275e212933519ff294"},
{file = "charset_normalizer-3.4.1-cp39-cp39-win32.whl", hash = "sha256:3bed14e9c89dcb10e8f3a29f9ccac4955aebe93c71ae803af79265c9ca5644c5"},
{file = "charset_normalizer-3.4.1-cp39-cp39-win_amd64.whl", hash = "sha256:49402233c892a461407c512a19435d1ce275543138294f7ef013f0b63d5d3765"},
{file = "charset_normalizer-3.4.1-py3-none-any.whl", hash = "sha256:d98b1668f06378c6dbefec3b92299716b931cd4e6061f3c875a71ced1780ab85"},
{file = "charset_normalizer-3.4.1.tar.gz", hash = "sha256:44251f18cd68a75b56585dd00dae26183e102cd5e0f9f1466e6df5da2ed64ea3"},
]
[[package]]
name = "click"
version = "8.1.8"
@ -169,42 +57,6 @@ files = [
{file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
]
[[package]]
name = "docker"
version = "7.1.0"
description = "A Python library for the Docker Engine API."
optional = false
python-versions = ">=3.8"
files = [
{file = "docker-7.1.0-py3-none-any.whl", hash = "sha256:c96b93b7f0a746f9e77d325bcfb87422a3d8bd4f03136ae8a85b37f1898d5fc0"},
{file = "docker-7.1.0.tar.gz", hash = "sha256:ad8c70e6e3f8926cb8a92619b832b4ea5299e2831c14284663184e200546fa6c"},
]
[package.dependencies]
pywin32 = {version = ">=304", markers = "sys_platform == \"win32\""}
requests = ">=2.26.0"
urllib3 = ">=1.26.0"
[package.extras]
dev = ["coverage (==7.2.7)", "pytest (==7.4.2)", "pytest-cov (==4.1.0)", "pytest-timeout (==2.1.0)", "ruff (==0.1.8)"]
docs = ["myst-parser (==0.18.0)", "sphinx (==5.1.1)"]
ssh = ["paramiko (>=2.4.3)"]
websockets = ["websocket-client (>=1.3.0)"]
[[package]]
name = "idna"
version = "3.10"
description = "Internationalized Domain Names in Applications (IDNA)"
optional = false
python-versions = ">=3.6"
files = [
{file = "idna-3.10-py3-none-any.whl", hash = "sha256:946d195a0d259cbba61165e88e65941f16e9b36ea6ddb97f00452bae8b1287d3"},
{file = "idna-3.10.tar.gz", hash = "sha256:12f65c9b470abda6dc35cf8e63cc574b1c52b11df2c86030af0ac09b01b13ea9"},
]
[package.extras]
all = ["flake8 (>=7.1.1)", "mypy (>=1.11.2)", "pytest (>=8.3.2)", "ruff (>=0.6.2)"]
[[package]]
name = "jinja2"
version = "3.1.5"
@ -328,55 +180,76 @@ files = [
]
[[package]]
name = "python-dotenv"
version = "1.0.1"
description = "Read key-value pairs from a .env file and set them as environment variables"
name = "pyyaml"
version = "6.0.2"
description = "YAML parser and emitter for Python"
optional = false
python-versions = ">=3.8"
files = [
{file = "python-dotenv-1.0.1.tar.gz", hash = "sha256:e324ee90a023d808f1959c46bcbc04446a10ced277783dc6ee09987c37ec10ca"},
{file = "python_dotenv-1.0.1-py3-none-any.whl", hash = "sha256:f7b63ef50f1b690dddf550d03497b66d609393b40b564ed0d674909a68ebf16a"},
]
[package.extras]
cli = ["click (>=5.0)"]
[[package]]
name = "pywin32"
version = "308"
description = "Python for Window Extensions"
optional = false
python-versions = "*"
files = [
{file = "pywin32-308-cp310-cp310-win32.whl", hash = "sha256:796ff4426437896550d2981b9c2ac0ffd75238ad9ea2d3bfa67a1abd546d262e"},
{file = "pywin32-308-cp310-cp310-win_amd64.whl", hash = "sha256:4fc888c59b3c0bef905ce7eb7e2106a07712015ea1c8234b703a088d46110e8e"},
{file = "pywin32-308-cp310-cp310-win_arm64.whl", hash = "sha256:a5ab5381813b40f264fa3495b98af850098f814a25a63589a8e9eb12560f450c"},
{file = "pywin32-308-cp311-cp311-win32.whl", hash = "sha256:5d8c8015b24a7d6855b1550d8e660d8daa09983c80e5daf89a273e5c6fb5095a"},
{file = "pywin32-308-cp311-cp311-win_amd64.whl", hash = "sha256:575621b90f0dc2695fec346b2d6302faebd4f0f45c05ea29404cefe35d89442b"},
{file = "pywin32-308-cp311-cp311-win_arm64.whl", hash = "sha256:100a5442b7332070983c4cd03f2e906a5648a5104b8a7f50175f7906efd16bb6"},
{file = "pywin32-308-cp312-cp312-win32.whl", hash = "sha256:587f3e19696f4bf96fde9d8a57cec74a57021ad5f204c9e627e15c33ff568897"},
{file = "pywin32-308-cp312-cp312-win_amd64.whl", hash = "sha256:00b3e11ef09ede56c6a43c71f2d31857cf7c54b0ab6e78ac659497abd2834f47"},
{file = "pywin32-308-cp312-cp312-win_arm64.whl", hash = "sha256:9b4de86c8d909aed15b7011182c8cab38c8850de36e6afb1f0db22b8959e3091"},
{file = "pywin32-308-cp313-cp313-win32.whl", hash = "sha256:1c44539a37a5b7b21d02ab34e6a4d314e0788f1690d65b48e9b0b89f31abbbed"},
{file = "pywin32-308-cp313-cp313-win_amd64.whl", hash = "sha256:fd380990e792eaf6827fcb7e187b2b4b1cede0585e3d0c9e84201ec27b9905e4"},
{file = "pywin32-308-cp313-cp313-win_arm64.whl", hash = "sha256:ef313c46d4c18dfb82a2431e3051ac8f112ccee1a34f29c263c583c568db63cd"},
{file = "pywin32-308-cp37-cp37m-win32.whl", hash = "sha256:1f696ab352a2ddd63bd07430080dd598e6369152ea13a25ebcdd2f503a38f1ff"},
{file = "pywin32-308-cp37-cp37m-win_amd64.whl", hash = "sha256:13dcb914ed4347019fbec6697a01a0aec61019c1046c2b905410d197856326a6"},
{file = "pywin32-308-cp38-cp38-win32.whl", hash = "sha256:5794e764ebcabf4ff08c555b31bd348c9025929371763b2183172ff4708152f0"},
{file = "pywin32-308-cp38-cp38-win_amd64.whl", hash = "sha256:3b92622e29d651c6b783e368ba7d6722b1634b8e70bd376fd7610fe1992e19de"},
{file = "pywin32-308-cp39-cp39-win32.whl", hash = "sha256:7873ca4dc60ab3287919881a7d4f88baee4a6e639aa6962de25a98ba6b193341"},
{file = "pywin32-308-cp39-cp39-win_amd64.whl", hash = "sha256:71b3322d949b4cc20776436a9c9ba0eeedcbc9c650daa536df63f0ff111bb920"},
{file = "PyYAML-6.0.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:0a9a2848a5b7feac301353437eb7d5957887edbf81d56e903999a75a3d743086"},
{file = "PyYAML-6.0.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:29717114e51c84ddfba879543fb232a6ed60086602313ca38cce623c1d62cfbf"},
{file = "PyYAML-6.0.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8824b5a04a04a047e72eea5cec3bc266db09e35de6bdfe34c9436ac5ee27d237"},
{file = "PyYAML-6.0.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:7c36280e6fb8385e520936c3cb3b8042851904eba0e58d277dca80a5cfed590b"},
{file = "PyYAML-6.0.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ec031d5d2feb36d1d1a24380e4db6d43695f3748343d99434e6f5f9156aaa2ed"},
{file = "PyYAML-6.0.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:936d68689298c36b53b29f23c6dbb74de12b4ac12ca6cfe0e047bedceea56180"},
{file = "PyYAML-6.0.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:23502f431948090f597378482b4812b0caae32c22213aecf3b55325e049a6c68"},
{file = "PyYAML-6.0.2-cp310-cp310-win32.whl", hash = "sha256:2e99c6826ffa974fe6e27cdb5ed0021786b03fc98e5ee3c5bfe1fd5015f42b99"},
{file = "PyYAML-6.0.2-cp310-cp310-win_amd64.whl", hash = "sha256:a4d3091415f010369ae4ed1fc6b79def9416358877534caf6a0fdd2146c87a3e"},
{file = "PyYAML-6.0.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:cc1c1159b3d456576af7a3e4d1ba7e6924cb39de8f67111c735f6fc832082774"},
{file = "PyYAML-6.0.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:1e2120ef853f59c7419231f3bf4e7021f1b936f6ebd222406c3b60212205d2ee"},
{file = "PyYAML-6.0.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5d225db5a45f21e78dd9358e58a98702a0302f2659a3c6cd320564b75b86f47c"},
{file = "PyYAML-6.0.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5ac9328ec4831237bec75defaf839f7d4564be1e6b25ac710bd1a96321cc8317"},
{file = "PyYAML-6.0.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3ad2a3decf9aaba3d29c8f537ac4b243e36bef957511b4766cb0057d32b0be85"},
{file = "PyYAML-6.0.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:ff3824dc5261f50c9b0dfb3be22b4567a6f938ccce4587b38952d85fd9e9afe4"},
{file = "PyYAML-6.0.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:797b4f722ffa07cc8d62053e4cff1486fa6dc094105d13fea7b1de7d8bf71c9e"},
{file = "PyYAML-6.0.2-cp311-cp311-win32.whl", hash = "sha256:11d8f3dd2b9c1207dcaf2ee0bbbfd5991f571186ec9cc78427ba5bd32afae4b5"},
{file = "PyYAML-6.0.2-cp311-cp311-win_amd64.whl", hash = "sha256:e10ce637b18caea04431ce14fabcf5c64a1c61ec9c56b071a4b7ca131ca52d44"},
{file = "PyYAML-6.0.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:c70c95198c015b85feafc136515252a261a84561b7b1d51e3384e0655ddf25ab"},
{file = "PyYAML-6.0.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:ce826d6ef20b1bc864f0a68340c8b3287705cae2f8b4b1d932177dcc76721725"},
{file = "PyYAML-6.0.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:1f71ea527786de97d1a0cc0eacd1defc0985dcf6b3f17bb77dcfc8c34bec4dc5"},
{file = "PyYAML-6.0.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9b22676e8097e9e22e36d6b7bda33190d0d400f345f23d4065d48f4ca7ae0425"},
{file = "PyYAML-6.0.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:80bab7bfc629882493af4aa31a4cfa43a4c57c83813253626916b8c7ada83476"},
{file = "PyYAML-6.0.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:0833f8694549e586547b576dcfaba4a6b55b9e96098b36cdc7ebefe667dfed48"},
{file = "PyYAML-6.0.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:8b9c7197f7cb2738065c481a0461e50ad02f18c78cd75775628afb4d7137fb3b"},
{file = "PyYAML-6.0.2-cp312-cp312-win32.whl", hash = "sha256:ef6107725bd54b262d6dedcc2af448a266975032bc85ef0172c5f059da6325b4"},
{file = "PyYAML-6.0.2-cp312-cp312-win_amd64.whl", hash = "sha256:7e7401d0de89a9a855c839bc697c079a4af81cf878373abd7dc625847d25cbd8"},
{file = "PyYAML-6.0.2-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:efdca5630322a10774e8e98e1af481aad470dd62c3170801852d752aa7a783ba"},
{file = "PyYAML-6.0.2-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:50187695423ffe49e2deacb8cd10510bc361faac997de9efef88badc3bb9e2d1"},
{file = "PyYAML-6.0.2-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0ffe8360bab4910ef1b9e87fb812d8bc0a308b0d0eef8c8f44e0254ab3b07133"},
{file = "PyYAML-6.0.2-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:17e311b6c678207928d649faa7cb0d7b4c26a0ba73d41e99c4fff6b6c3276484"},
{file = "PyYAML-6.0.2-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:70b189594dbe54f75ab3a1acec5f1e3faa7e8cf2f1e08d9b561cb41b845f69d5"},
{file = "PyYAML-6.0.2-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:41e4e3953a79407c794916fa277a82531dd93aad34e29c2a514c2c0c5fe971cc"},
{file = "PyYAML-6.0.2-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:68ccc6023a3400877818152ad9a1033e3db8625d899c72eacb5a668902e4d652"},
{file = "PyYAML-6.0.2-cp313-cp313-win32.whl", hash = "sha256:bc2fa7c6b47d6bc618dd7fb02ef6fdedb1090ec036abab80d4681424b84c1183"},
{file = "PyYAML-6.0.2-cp313-cp313-win_amd64.whl", hash = "sha256:8388ee1976c416731879ac16da0aff3f63b286ffdd57cdeb95f3f2e085687563"},
{file = "PyYAML-6.0.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:24471b829b3bf607e04e88d79542a9d48bb037c2267d7927a874e6c205ca7e9a"},
{file = "PyYAML-6.0.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d7fded462629cfa4b685c5416b949ebad6cec74af5e2d42905d41e257e0869f5"},
{file = "PyYAML-6.0.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d84a1718ee396f54f3a086ea0a66d8e552b2ab2017ef8b420e92edbc841c352d"},
{file = "PyYAML-6.0.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9056c1ecd25795207ad294bcf39f2db3d845767be0ea6e6a34d856f006006083"},
{file = "PyYAML-6.0.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:82d09873e40955485746739bcb8b4586983670466c23382c19cffecbf1fd8706"},
{file = "PyYAML-6.0.2-cp38-cp38-win32.whl", hash = "sha256:43fa96a3ca0d6b1812e01ced1044a003533c47f6ee8aca31724f78e93ccc089a"},
{file = "PyYAML-6.0.2-cp38-cp38-win_amd64.whl", hash = "sha256:01179a4a8559ab5de078078f37e5c1a30d76bb88519906844fd7bdea1b7729ff"},
{file = "PyYAML-6.0.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:688ba32a1cffef67fd2e9398a2efebaea461578b0923624778664cc1c914db5d"},
{file = "PyYAML-6.0.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:a8786accb172bd8afb8be14490a16625cbc387036876ab6ba70912730faf8e1f"},
{file = "PyYAML-6.0.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d8e03406cac8513435335dbab54c0d385e4a49e4945d2909a581c83647ca0290"},
{file = "PyYAML-6.0.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f753120cb8181e736c57ef7636e83f31b9c0d1722c516f7e86cf15b7aa57ff12"},
{file = "PyYAML-6.0.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3b1fdb9dc17f5a7677423d508ab4f243a726dea51fa5e70992e59a7411c89d19"},
{file = "PyYAML-6.0.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:0b69e4ce7a131fe56b7e4d770c67429700908fc0752af059838b1cfb41960e4e"},
{file = "PyYAML-6.0.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:a9f8c2e67970f13b16084e04f134610fd1d374bf477b17ec1599185cf611d725"},
{file = "PyYAML-6.0.2-cp39-cp39-win32.whl", hash = "sha256:6395c297d42274772abc367baaa79683958044e5d3835486c16da75d2a694631"},
{file = "PyYAML-6.0.2-cp39-cp39-win_amd64.whl", hash = "sha256:39693e1f8320ae4f43943590b49779ffb98acb81f788220ea932a6b6c51004d8"},
{file = "pyyaml-6.0.2.tar.gz", hash = "sha256:d584d9ec91ad65861cc08d42e834324ef890a082e591037abe114850ff7bbc3e"},
]
[[package]]
name = "referencing"
version = "0.36.1"
version = "0.36.2"
description = "JSON Referencing + Python"
optional = false
python-versions = ">=3.9"
files = [
{file = "referencing-0.36.1-py3-none-any.whl", hash = "sha256:363d9c65f080d0d70bc41c721dce3c7f3e77fc09f269cd5c8813da18069a6794"},
{file = "referencing-0.36.1.tar.gz", hash = "sha256:ca2e6492769e3602957e9b831b94211599d2aade9477f5d44110d2530cf9aade"},
{file = "referencing-0.36.2-py3-none-any.whl", hash = "sha256:e8699adbbf8b5c7de96d8ffa0eb5c158b3beafce084968e2ea8bb08c6794dcd0"},
{file = "referencing-0.36.2.tar.gz", hash = "sha256:df2e89862cd09deabbdba16944cc3f10feb6b3e6f18e902f7cc25609a34775aa"},
]
[package.dependencies]
@ -384,27 +257,6 @@ attrs = ">=22.2.0"
rpds-py = ">=0.7.0"
typing-extensions = {version = ">=4.4.0", markers = "python_version < \"3.13\""}
[[package]]
name = "requests"
version = "2.32.3"
description = "Python HTTP for Humans."
optional = false
python-versions = ">=3.8"
files = [
{file = "requests-2.32.3-py3-none-any.whl", hash = "sha256:70761cfe03c773ceb22aa2f671b4757976145175cdfca038c02654d061d6dcc6"},
{file = "requests-2.32.3.tar.gz", hash = "sha256:55365417734eb18255590a9ff9eb97e9e1da868d4ccd6402399eaf68af20a760"},
]
[package.dependencies]
certifi = ">=2017.4.17"
charset-normalizer = ">=2,<4"
idna = ">=2.5,<4"
urllib3 = ">=1.21.1,<3"
[package.extras]
socks = ["PySocks (>=1.5.6,!=1.5.7)"]
use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"]
[[package]]
name = "rpds-py"
version = "0.22.3"
@ -548,24 +400,7 @@ files = [
{file = "typing_extensions-4.12.2.tar.gz", hash = "sha256:1a7ead55c7e559dd4dee8856e3a88b41225abfe1ce8df57b7c13915fe121ffb8"},
]
[[package]]
name = "urllib3"
version = "2.3.0"
description = "HTTP library with thread-safe connection pooling, file post, and more."
optional = false
python-versions = ">=3.9"
files = [
{file = "urllib3-2.3.0-py3-none-any.whl", hash = "sha256:1cee9ad369867bfdbbb48b7dd50374c0967a0bb7710050facf0dd6911440e3df"},
{file = "urllib3-2.3.0.tar.gz", hash = "sha256:f8c5449b3cf0861679ce7e0503c7b44b5ec981bec0d1d3795a07f1ba96f0204d"},
]
[package.extras]
brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"]
h2 = ["h2 (>=4,<5)"]
socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"]
zstd = ["zstandard (>=0.18.0)"]
[metadata]
lock-version = "2.0"
python-versions = "^3.10"
content-hash = "59543baf4d462d4830e7228ba9eda8ae865416fdabd8ede129492ac45f1926f2"
content-hash = "42553cae81e184f512ab48272a7d5f22efc9711b293c476fc736c1263d42f6dc"

7
arch/tools/pyproject.toml
View file

@ -1,6 +1,6 @@
[tool.poetry]
name = "archgw"
version = "0.2.0"
version = "0.2.2"
description = "Python-based CLI tool to manage Arch Gateway."
authors = ["Katanemo Labs, Inc."]
packages = [
@ -10,13 +10,12 @@ readme = "README.md"
[tool.poetry.dependencies]
python = "^3.10"
archgw_modelserver = "^0.2.0"
archgw_modelserver = "^0.2.2"
click = "^8.1.7"
jinja2 = "^3.1.4"
jsonschema = "^4.23.0"
setuptools = "75.5.0"
docker = "^7.1.0"
python-dotenv = "^1.0.1"
pyyaml = "^6.0.2"
[tool.poetry.scripts]
archgw = "cli.main:main"

20
arch/validate_arch_config.sh Normal file
View file

@ -0,0 +1,20 @@
#!/bin/bash
failed_files=()
for file in $(find . -name arch_config.yaml -o -name arch_config_full_reference.yaml); do
echo "Validating $file..."
if ! docker run --rm -v "$(pwd)/$file:/app/arch_config.yaml:ro" --entrypoint /bin/sh katanemo/archgw:latest -c "python config_generator.py" 2>&1 > /dev/null ; then
echo "Validation failed for $file"
failed_files+=("$file")
fi
done
# Print summary of failed files
if [ ${#failed_files[@]} -ne 0 ]; then
echo -e "\nValidation failed for the following files:"
printf '%s\n' "${failed_files[@]}"
exit 1
else
echo -e "\nAll files validated successfully!"
fi

302
crates/Cargo.lock generated
View file

@ -234,6 +234,8 @@ dependencies = [
"serde_yaml",
"thiserror",
"tiktoken-rs",
"url",
"urlencoding",
]
[[package]]
@ -477,6 +479,17 @@ dependencies = [
"winapi",
]
[[package]]
name = "displaydoc"
version = "0.2.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "97369cbbc041bc366949bc74d34658d6cda5621039731c6310521892a3a20ae0"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.79",
]
[[package]]
name = "duration-string"
version = "0.3.0"
@ -557,6 +570,15 @@ version = "0.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f81ec6369c545a7d40e4589b5597581fa1c441fe1cce96dd1de43159910a36a2"
[[package]]
name = "form_urlencoded"
version = "1.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e13624c2627564efccf4934284bdd98cbaa14e79b0b5a141218e507b3a823456"
dependencies = [
"percent-encoding",
]
[[package]]
name = "futures"
version = "0.3.31"
@ -782,12 +804,151 @@ dependencies = [
"itoa",
]
[[package]]
name = "icu_collections"
version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "db2fa452206ebee18c4b5c2274dbf1de17008e874b4dc4f0aea9d01ca79e4526"
dependencies = [
"displaydoc",
"yoke",
"zerofrom",
"zerovec",
]
[[package]]
name = "icu_locid"
version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "13acbb8371917fc971be86fc8057c41a64b521c184808a698c02acc242dbf637"
dependencies = [
"displaydoc",
"litemap",
"tinystr",
"writeable",
"zerovec",
]
[[package]]
name = "icu_locid_transform"
version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "01d11ac35de8e40fdeda00d9e1e9d92525f3f9d887cdd7aa81d727596788b54e"
dependencies = [
"displaydoc",
"icu_locid",
"icu_locid_transform_data",
"icu_provider",
"tinystr",
"zerovec",
]
[[package]]
name = "icu_locid_transform_data"
version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "fdc8ff3388f852bede6b579ad4e978ab004f139284d7b28715f773507b946f6e"
[[package]]
name = "icu_normalizer"
version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "19ce3e0da2ec68599d193c93d088142efd7f9c5d6fc9b803774855747dc6a84f"
dependencies = [
"displaydoc",
"icu_collections",
"icu_normalizer_data",
"icu_properties",
"icu_provider",
"smallvec",
"utf16_iter",
"utf8_iter",
"write16",
"zerovec",
]
[[package]]
name = "icu_normalizer_data"
version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "f8cafbf7aa791e9b22bec55a167906f9e1215fd475cd22adfcf660e03e989516"
[[package]]
name = "icu_properties"
version = "1.5.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "93d6020766cfc6302c15dbbc9c8778c37e62c14427cb7f6e601d849e092aeef5"
dependencies = [
"displaydoc",
"icu_collections",
"icu_locid_transform",
"icu_properties_data",
"icu_provider",
"tinystr",
"zerovec",
]
[[package]]
name = "icu_properties_data"
version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "67a8effbc3dd3e4ba1afa8ad918d5684b8868b3b26500753effea8d2eed19569"
[[package]]
name = "icu_provider"
version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6ed421c8a8ef78d3e2dbc98a973be2f3770cb42b606e3ab18d6237c4dfde68d9"
dependencies = [
"displaydoc",
"icu_locid",
"icu_provider_macros",
"stable_deref_trait",
"tinystr",
"writeable",
"yoke",
"zerofrom",
"zerovec",
]
[[package]]
name = "icu_provider_macros"
version = "1.5.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1ec89e9337638ecdc08744df490b221a7399bf8d164eb52a665454e60e075ad6"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.79",
]
[[package]]
name = "id-arena"
version = "2.2.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "25a2bc672d1148e28034f176e01fffebb08b35768468cc954630da77a1449005"
[[package]]
name = "idna"
version = "1.0.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "686f825264d630750a544639377bae737628043f20d38bbc029e8f29ea968a7e"
dependencies = [
"idna_adapter",
"smallvec",
"utf8_iter",
]
[[package]]
name = "idna_adapter"
version = "1.2.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "daca1df1c957320b2cf139ac61e7bd64fed304c5040df000a745aa1de3b4ef71"
dependencies = [
"icu_normalizer",
"icu_properties",
]
[[package]]
name = "indexmap"
version = "2.6.0"
@ -883,6 +1044,12 @@ version = "0.4.14"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "78b3ae25bc7c8c38cec158d1f2757ee79e9b3740fbc7ccf0e59e4b08d793fa89"
[[package]]
name = "litemap"
version = "0.7.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "4ee93343901ab17bd981295f2cf0026d4ad018c7c31ba84549a4ddbb47a45104"
[[package]]
name = "llm_gateway"
version = "0.1.0"
@ -1028,6 +1195,12 @@ version = "1.0.15"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "57c0d7b74b563b49d38dae00a0c37d4d6de9b432382b2892f0574ddcae73fd0a"
[[package]]
name = "percent-encoding"
version = "2.3.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "e3148f5046208a5d56bcfc03053e3ca6334e51da8dfb19b6cdc8b306fae3283e"
[[package]]
name = "pin-project-lite"
version = "0.2.14"
@ -1547,6 +1720,17 @@ dependencies = [
"unicode-ident",
]
[[package]]
name = "synstructure"
version = "0.13.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c8af7666ab7b6390ab78131fb5b0fce11d6b7a6951602017c35fa82800708971"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.79",
]
[[package]]
name = "target-lexicon"
version = "0.12.16"
@ -1606,6 +1790,16 @@ dependencies = [
"rustc-hash",
]
[[package]]
name = "tinystr"
version = "0.7.6"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "9117f5d4db391c1cf6927e7bea3db74b9a1c1add8f7eda9ffd5364f40f57b82f"
dependencies = [
"displaydoc",
"zerovec",
]
[[package]]
name = "toml"
version = "0.8.19"
@ -1676,6 +1870,35 @@ version = "0.2.11"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "673aac59facbab8a9007c7f6108d11f63b603f7cabff99fabf650fea5c32b861"
[[package]]
name = "url"
version = "2.5.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "32f8b686cadd1473f4bd0117a5d28d36b1ade384ea9b5069a1c40aefed7fda60"
dependencies = [
"form_urlencoded",
"idna",
"percent-encoding",
]
[[package]]
name = "urlencoding"
version = "2.1.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "daf8dba3b7eb870caf1ddeed7bc9d2a049f3cfdfae7cb521b087cc33ae4c49da"
[[package]]
name = "utf16_iter"
version = "1.0.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "c8232dd3cdaed5356e0f716d285e4b40b932ac434100fe9b7e0e8e935b9e6246"
[[package]]
name = "utf8_iter"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"
[[package]]
name = "uuid"
version = "1.11.0"
@ -2189,12 +2412,48 @@ dependencies = [
"wasmparser 0.212.0",
]
[[package]]
name = "write16"
version = "1.0.0"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "d1890f4022759daae28ed4fe62859b1236caebfc61ede2f63ed4e695f3f6d936"
[[package]]
name = "writeable"
version = "0.5.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "1e9df38ee2d2c3c5948ea468a8406ff0db0b29ae1ffde1bcf20ef305bcc95c51"
[[package]]
name = "yansi"
version = "1.0.1"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cfe53a6657fd280eaa890a3bc59152892ffa3e30101319d168b781ed6529b049"
[[package]]
name = "yoke"
version = "0.7.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "120e6aef9aa629e3d4f52dc8cc43a015c7724194c97dfaf45180d2daf2b77f40"
dependencies = [
"serde",
"stable_deref_trait",
"yoke-derive",
"zerofrom",
]
[[package]]
name = "yoke-derive"
version = "0.7.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "2380878cad4ac9aac1e2435f3eb4020e8374b5f13c296cb75b4620ff8e229154"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.79",
"synstructure",
]
[[package]]
name = "zerocopy"
version = "0.7.35"
@ -2216,6 +2475,49 @@ dependencies = [
"syn 2.0.79",
]
[[package]]
name = "zerofrom"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "cff3ee08c995dee1859d998dea82f7374f2826091dd9cd47def953cae446cd2e"
dependencies = [
"zerofrom-derive",
]
[[package]]
name = "zerofrom-derive"
version = "0.1.5"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "595eed982f7d355beb85837f651fa22e90b3c044842dc7f2c2842c086f295808"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.79",
"synstructure",
]
[[package]]
name = "zerovec"
version = "0.10.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "aa2b893d79df23bfb12d5461018d408ea19dfafe76c2c7ef6d4eba614f8ff079"
dependencies = [
"yoke",
"zerofrom",
"zerovec-derive",
]
[[package]]
name = "zerovec-derive"
version = "0.10.3"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "6eafa6dfb17584ea3e2bd6e76e0cc15ad7af12b09abdd1ca55961bed9b1063c6"
dependencies = [
"proc-macro2",
"quote",
"syn 2.0.79",
]
[[package]]
name = "zstd"
version = "0.13.2"

2
crates/common/Cargo.toml
View file

@ -16,6 +16,8 @@ tiktoken-rs = "0.5.9"
rand = "0.8.5"
serde_json = "1.0"
hex = "0.4.3"
urlencoding = "2.1.3"
url = "2.5.4"
[dev-dependencies]
pretty_assertions = "1.4.1"

5
crates/common/src/api/open_ai.rs
View file

@ -135,7 +135,10 @@ impl From<String> for ParameterType {
"array" => ParameterType::List,
"dict" => ParameterType::Dict,
"dictionary" => ParameterType::Dict,
_ => ParameterType::String,
_ => {
log::warn!("Unknown parameter type: {}, assuming type str", s);
ParameterType::String
},
}
}
}

39
crates/common/src/configuration.rs
View file

@ -9,7 +9,6 @@ use crate::api::open_ai::{
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Configuration {
pub version: String,
pub listener: Listener,
pub endpoints: Option<HashMap<String, Endpoint>>,
pub llm_providers: Vec<LlmProvider>,
pub overrides: Option<Overrides>,
@ -25,6 +24,7 @@ pub struct Configuration {
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct Overrides {
pub prompt_target_intent_matching_threshold: Option<f64>,
pub optimize_context_window: Option<bool>,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
@ -47,32 +47,6 @@ pub struct ErrorTargetDetail {
pub endpoint: Option<EndpointDetails>,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
pub struct Listener {
pub address: String,
pub port: u16,
pub message_format: MessageFormat,
// pub connect_timeout: Option<DurationString>,
}
impl Default for Listener {
fn default() -> Self {
Listener {
address: "".to_string(),
port: 0,
message_format: MessageFormat::default(),
// connect_timeout: None,
}
}
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub enum MessageFormat {
#[serde(rename = "huggingface")]
#[default]
Huggingface,
}
#[derive(Debug, Clone, Serialize, Deserialize, Default)]
pub struct PromptGuards {
pub input_guards: HashMap<GuardType, GuardOptions>,
@ -242,6 +216,7 @@ pub struct EndpointDetails {
pub path: Option<String>,
#[serde(rename = "http_method")]
pub method: Option<HttpMethod>,
pub http_headers: Option<HashMap<String, String>>,
}
#[derive(Debug, Clone, Serialize, Deserialize)]
@ -351,16 +326,6 @@ mod test {
Some("/agent/summary".to_string())
);
let error_target = config.error_target.as_ref().unwrap();
assert_eq!(
error_target.endpoint.as_ref().unwrap().name,
"error_target_1".to_string()
);
assert_eq!(
error_target.endpoint.as_ref().unwrap().path,
Some("/error".to_string())
);
let tracing = config.tracing.as_ref().unwrap();
assert_eq!(tracing.sampling_rate.unwrap(), 0.1);

5
crates/common/src/consts.rs
View file

@ -3,7 +3,10 @@ pub const SYSTEM_ROLE: &str = "system";
pub const USER_ROLE: &str = "user";
pub const TOOL_ROLE: &str = "tool";
pub const ASSISTANT_ROLE: &str = "assistant";
pub const ARCH_FC_REQUEST_TIMEOUT_MS: u64 = 120000; // 2 minutes
pub const ARCH_FC_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
pub const DEFAULT_TARGET_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
pub const API_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
pub const MODEL_SERVER_REQUEST_TIMEOUT_MS: u64 = 30000; // 30 seconds
pub const MODEL_SERVER_NAME: &str = "model_server";
pub const ARCH_ROUTING_HEADER: &str = "x-arch-llm-provider";
pub const MESSAGES_KEY: &str = "messages";

163
crates/common/src/path.rs
View file

@ -1,21 +1,30 @@
use std::collections::HashMap;
use std::collections::{HashMap, HashSet};
use url::Url;
use urlencoding;
use crate::configuration::Parameter;
pub fn replace_params_in_path(
path: &str,
params: &HashMap<String, String>,
) -> Result<String, String> {
let mut result = String::new();
let mut in_param = false;
tool_params: &HashMap<String, String>,
prompt_target_params: &[Parameter],
) -> Result<(String, String, HashMap<String, String>), String> {
let mut query_string_replaced = String::new();
let mut current_param = String::new();
let mut vars_replaced = HashSet::new();
let mut params: HashMap<String, String> = HashMap::new();
let mut in_param = false;
for c in path.chars() {
if c == '{' {
in_param = true;
} else if c == '}' {
in_param = false;
let param_name = current_param.clone();
if let Some(value) = params.get(&param_name) {
result.push_str(value);
if let Some(value) = tool_params.get(&param_name) {
let value = urlencoding::encode(value);
query_string_replaced.push_str(value.into_owned().as_str());
vars_replaced.insert(param_name.clone());
} else {
return Err(format!("Missing value for parameter `{}`", param_name));
}
@ -23,31 +32,106 @@ pub fn replace_params_in_path(
} else if in_param {
current_param.push(c);
} else {
result.push(c);
query_string_replaced.push(c);
}
}
Ok(result)
// add the remaining params in path
for (param_name, value) in tool_params.iter() {
let value = urlencoding::encode(value).into_owned();
if !vars_replaced.contains(param_name) {
vars_replaced.insert(param_name.clone());
params.insert(param_name.clone(), value.clone());
if query_string_replaced.contains("?") {
query_string_replaced.push_str(&format!("&{}={}", param_name, value));
} else {
query_string_replaced.push_str(&format!("?{}={}", param_name, value));
}
}
}
// add default values
for param in prompt_target_params.iter() {
if !vars_replaced.contains(&param.name) && param.default.is_some() {
params.insert(param.name.clone(), param.default.clone().unwrap());
if query_string_replaced.contains("?") {
query_string_replaced.push_str(&format!(
"&{}={}",
param.name,
param.default.as_ref().unwrap()
));
} else {
query_string_replaced.push_str(&format!(
"?{}={}",
param.name,
param.default.as_ref().unwrap()
));
}
}
}
let parsed_uri = Url::parse("http://dummy.com").unwrap();
let parsed_uri = parsed_uri
.join(&query_string_replaced)
.map_err(|e| e.to_string())?;
let query_string = parsed_uri.query().unwrap_or("");
let path_uri = parsed_uri.path();
Ok((path_uri.to_string(), query_string.to_string(), params))
}
#[cfg(test)]
mod test {
use std::collections::HashMap;
use crate::configuration::Parameter;
#[test]
fn test_replace_path() {
let path = "/cluster.open-cluster-management.io/v1/managedclusters/{cluster_name}";
let params = vec![("cluster_name".to_string(), "test1".to_string())]
.into_iter()
.collect();
let params = vec![
("cluster_name".to_string(), "test1".to_string()),
("hello".to_string(), "hello world".to_string()),
]
.into_iter()
.collect();
let prompt_target_params = vec![Parameter {
name: "country".to_string(),
parameter_type: None,
description: "test target".to_string(),
required: None,
enum_values: None,
default: Some("US".to_string()),
in_path: None,
format: None,
}];
let out_params: HashMap<String, String> = vec![
("country".to_string(), "US".to_string()),
("hello".to_string(), "hello%20world".to_string()),
]
.into_iter()
.collect();
assert_eq!(
super::replace_params_in_path(path, &params),
Ok("/cluster.open-cluster-management.io/v1/managedclusters/test1".to_string())
super::replace_params_in_path(path, &params, &prompt_target_params),
Ok((
"/cluster.open-cluster-management.io/v1/managedclusters/test1".to_string(),
"hello=hello%20world&country=US".to_string(),
out_params.clone()
))
);
let out_params = HashMap::new();
let prompt_target_params = vec![];
let path = "/cluster.open-cluster-management.io/v1/managedclusters";
let params = vec![].into_iter().collect();
assert_eq!(
super::replace_params_in_path(path, &params),
Ok("/cluster.open-cluster-management.io/v1/managedclusters".to_string())
super::replace_params_in_path(path, &params, &prompt_target_params),
Ok((
"/cluster.open-cluster-management.io/v1/managedclusters".to_string(),
"".to_string(),
out_params
))
);
let path = "/foo/{bar}/baz";
@ -55,8 +139,8 @@ mod test {
.into_iter()
.collect();
assert_eq!(
super::replace_params_in_path(path, &params),
Ok("/foo/qux/baz".to_string())
super::replace_params_in_path(path, &params, &prompt_target_params),
Ok(("/foo/qux/baz".to_string(), "".to_string(), HashMap::new()))
);
let path = "/foo/{bar}/baz/{qux}";
@ -67,8 +151,45 @@ mod test {
.into_iter()
.collect();
assert_eq!(
super::replace_params_in_path(path, &params),
Ok("/foo/qux/baz/quux".to_string())
super::replace_params_in_path(path, &params, &prompt_target_params),
Ok((
"/foo/qux/baz/quux".to_string(),
"".to_string(),
HashMap::new()
))
);
let path = "/foo/{bar}/baz/{qux}?hello=world";
let params = vec![
("bar".to_string(), "qux".to_string()),
("qux".to_string(), "quux".to_string()),
]
.into_iter()
.collect();
assert_eq!(
super::replace_params_in_path(path, &params, &prompt_target_params),
Ok((
"/foo/qux/baz/quux".to_string(),
"hello=world".to_string(),
HashMap::new()
))
);
let path = "/foo/{bar}/baz/{qux}?hello={hello}";
let params = vec![
("bar".to_string(), "qux".to_string()),
("qux".to_string(), "quux".to_string()),
("hello".to_string(), "hello world".to_string()),
]
.into_iter()
.collect();
assert_eq!(
super::replace_params_in_path(path, &params, &prompt_target_params),
Ok((
"/foo/qux/baz/quux".to_string(),
"hello=hello%20world".to_string(),
HashMap::new()
))
);
let path = "/foo/{bar}/baz/{qux}";
@ -76,7 +197,7 @@ mod test {
.into_iter()
.collect();
assert_eq!(
super::replace_params_in_path(path, &params),
super::replace_params_in_path(path, &params, &prompt_target_params),
Err("Missing value for parameter `qux`".to_string())
);
}

2
crates/common/src/tracing.rs
View file

@ -166,7 +166,7 @@ impl TraceData {
attributes: vec![Attribute {
key: "service.name".to_string(),
value: AttributeValue {
string_value: Some("upstream-llm".to_string()),
string_value: Some("egress_llm_traffic".to_string()),
},
}],
};

2166
crates/llm_gateway/Cargo.lock generated
View file

File diff suppressed because it is too large Load diff

10
crates/llm_gateway/src/stream_context.rs
View file

@ -5,7 +5,7 @@ use common::api::open_ai::{
};
use common::configuration::LlmProvider;
use common::consts::{
ARCH_PROVIDER_HINT_HEADER, ARCH_ROUTING_HEADER, CHAT_COMPLETIONS_PATH,
ARCH_PROVIDER_HINT_HEADER, ARCH_ROUTING_HEADER, CHAT_COMPLETIONS_PATH, HEALTHZ_PATH,
RATELIMIT_SELECTOR_HEADER_KEY, REQUEST_ID_HEADER, TRACE_PARENT_HEADER,
};
use common::errors::ServerError;
@ -176,6 +176,12 @@ impl HttpContext for StreamContext {
// Envoy's HTTP model is event driven. The WASM ABI has given implementors events to hook onto
// the lifecycle of the http request and response.
fn on_http_request_headers(&mut self, _num_headers: usize, _end_of_stream: bool) -> Action {
let request_path = self.get_http_request_header(":path").unwrap_or_default();
if request_path == HEALTHZ_PATH {
self.send_http_response(200, vec![], None);
return Action::Continue;
}
self.select_llm_provider();
// if endpoint is not set then use provider name as routing header so envoy can resolve the cluster name
@ -381,7 +387,7 @@ impl HttpContext for StreamContext {
Ok(traceparent) => {
let mut trace_data = common::tracing::TraceData::new();
let mut llm_span = Span::new(
"upstream_llm_time".to_string(),
"egress_traffic".to_string(),
Some(traceparent.trace_id),
Some(traceparent.parent_id),
self.request_body_sent_time.unwrap(),

2
crates/llm_gateway/tests/integration.rs
View file

@ -18,6 +18,8 @@ fn wasm_module() -> String {
fn request_headers_expectations(module: &mut Tester, http_context: i32) {
module
.call_proxy_on_request_headers(http_context, 0, false)
.expect_get_header_map_value(Some(MapType::HttpRequestHeaders), Some(":path"))
.returning(Some("/v1/chat/completions"))
.expect_get_header_map_value(
Some(MapType::HttpRequestHeaders),
Some("x-arch-llm-provider-hint"),

2166
crates/prompt_gateway/Cargo.lock generated
View file

File diff suppressed because it is too large Load diff

22
crates/prompt_gateway/src/http_context.rs
View file

@ -6,7 +6,8 @@ use common::{
consts::{
ARCH_FC_MODEL_NAME, ARCH_INTERNAL_CLUSTER_NAME, ARCH_STATE_HEADER,
ARCH_UPSTREAM_HOST_HEADER, ASSISTANT_ROLE, CHAT_COMPLETIONS_PATH, HEALTHZ_PATH,
MODEL_SERVER_NAME, REQUEST_ID_HEADER, TOOL_ROLE, TRACE_PARENT_HEADER, USER_ROLE,
MODEL_SERVER_NAME, MODEL_SERVER_REQUEST_TIMEOUT_MS, REQUEST_ID_HEADER, TOOL_ROLE,
TRACE_PARENT_HEADER, USER_ROLE,
},
errors::ServerError,
http::{CallArgs, Client},
@ -137,9 +138,23 @@ impl HttpContext for StreamContext {
.map(|(_, pt)| pt.into())
.collect();
let mut metadata = deserialized_body.metadata.clone();
if let Some(overrides) = self.overrides.as_ref() {
if overrides.optimize_context_window.unwrap_or_default() {
if metadata.is_none() {
metadata = Some(HashMap::new());
}
metadata
.as_mut()
.unwrap()
.insert("optimize_context_window".to_string(), "true".to_string());
}
}
let arch_fc_chat_completion_request = ChatCompletionsRequest {
messages: deserialized_body.messages.clone(),
metadata: deserialized_body.metadata.clone(),
metadata,
stream: deserialized_body.stream,
model: "--".to_string(),
stream_options: deserialized_body.stream_options.clone(),
@ -159,12 +174,15 @@ impl HttpContext for StreamContext {
debug!("sending request to model server");
trace!("request body: {}", json_data);
let timeout_str = MODEL_SERVER_REQUEST_TIMEOUT_MS.to_string();
let mut headers = vec![
(ARCH_UPSTREAM_HOST_HEADER, MODEL_SERVER_NAME),
(":method", "POST"),
(":path", "/function_calling"),
("content-type", "application/json"),
(":authority", MODEL_SERVER_NAME),
("x-envoy-upstream-rq-timeout-ms", timeout_str.as_str()),
];
if self.request_id.is_some() {

1
crates/prompt_gateway/src/lib.rs
View file

@ -7,6 +7,7 @@ mod filter_context;
mod http_context;
mod metrics;
mod stream_context;
mod tools;
proxy_wasm::main! {{
proxy_wasm::set_log_level(LogLevel::Trace);

103
crates/prompt_gateway/src/stream_context.rs
View file

@ -1,13 +1,14 @@
use crate::metrics::Metrics;
use crate::tools::compute_request_path_body;
use common::api::open_ai::{
to_server_events, ArchState, ChatCompletionStreamResponse, ChatCompletionsRequest,
ChatCompletionsResponse, Message, ModelServerResponse, ToolCall,
};
use common::configuration::{Overrides, PromptTarget, Tracing};
use common::consts::{
ARCH_FC_MODEL_NAME, ARCH_FC_REQUEST_TIMEOUT_MS, ARCH_INTERNAL_CLUSTER_NAME,
ARCH_UPSTREAM_HOST_HEADER, ASSISTANT_ROLE, MESSAGES_KEY, REQUEST_ID_HEADER, SYSTEM_ROLE,
TOOL_ROLE, TRACE_PARENT_HEADER, USER_ROLE,
API_REQUEST_TIMEOUT_MS, ARCH_FC_MODEL_NAME, ARCH_INTERNAL_CLUSTER_NAME,
ARCH_UPSTREAM_HOST_HEADER, ASSISTANT_ROLE, DEFAULT_TARGET_REQUEST_TIMEOUT_MS, MESSAGES_KEY,
REQUEST_ID_HEADER, SYSTEM_ROLE, TOOL_ROLE, TRACE_PARENT_HEADER, USER_ROLE,
};
use common::errors::ServerError;
use common::http::{CallArgs, Client};
@ -16,7 +17,6 @@ use derivative::Derivative;
use http::StatusCode;
use log::{debug, trace, warn};
use proxy_wasm::traits::*;
use serde_yaml::Value;
use std::cell::RefCell;
use std::collections::HashMap;
use std::rc::Rc;
@ -46,7 +46,7 @@ pub struct StreamCallContext {
pub struct StreamContext {
system_prompt: Rc<Option<String>>,
pub prompt_targets: Rc<HashMap<String, PromptTarget>>,
_overrides: Rc<Option<Overrides>>,
pub overrides: Rc<Option<Overrides>>,
pub metrics: Rc<Metrics>,
pub callouts: RefCell<HashMap<u32, StreamCallContext>>,
pub context_id: u32,
@ -89,7 +89,7 @@ impl StreamContext {
streaming_response: false,
user_prompt: None,
is_chat_completions_request: false,
_overrides: overrides,
overrides,
request_id: None,
traceparent: None,
_tracing: tracing,
@ -160,7 +160,7 @@ impl StreamContext {
callout_context.request_body.messages.clone(),
);
let arch_messages_json = serde_json::to_string(&params).unwrap();
let timeout_str = ARCH_FC_REQUEST_TIMEOUT_MS.to_string();
let timeout_str = DEFAULT_TARGET_REQUEST_TIMEOUT_MS.to_string();
let mut headers = vec![
(":method", "POST"),
@ -273,84 +273,79 @@ impl StreamContext {
fn schedule_api_call_request(&mut self, mut callout_context: StreamCallContext) {
let tools_call_name = self.tool_calls.as_ref().unwrap()[0].function.name.clone();
let prompt_target = self.prompt_targets.get(&tools_call_name).unwrap();
let tool_params = &self.tool_calls.as_ref().unwrap()[0].function.arguments;
let endpoint_details = prompt_target.endpoint.as_ref().unwrap();
let endpoint_path: String = endpoint_details
.path
.as_ref()
.unwrap_or(&String::from("/"))
.to_string();
let prompt_target = self.prompt_targets.get(&tools_call_name).unwrap().clone();
let http_method = endpoint_details.method.clone().unwrap_or_default();
let prompt_target_params = prompt_target.parameters.clone().unwrap_or_default();
let mut tool_params = self.tool_calls.as_ref().unwrap()[0]
.function
.arguments
.clone();
tool_params.insert(
String::from(MESSAGES_KEY),
serde_yaml::to_value(&callout_context.request_body.messages).unwrap(),
);
let tool_params_json_str = serde_json::to_string(&tool_params).unwrap();
let endpoint = prompt_target.endpoint.unwrap();
let path: String = endpoint.path.unwrap_or(String::from("/"));
// only add params that are of string, number and bool type
let url_params = tool_params
.iter()
.filter(|(_, value)| value.is_number() || value.is_string() || value.is_bool())
.map(|(key, value)| match value {
Value::Number(n) => (key.clone(), n.to_string()),
Value::String(s) => (key.clone(), s.clone()),
Value::Bool(b) => (key.clone(), b.to_string()),
Value::Null => todo!(),
Value::Sequence(_) => todo!(),
Value::Mapping(_) => todo!(),
Value::Tagged(_) => todo!(),
})
.collect::<HashMap<String, String>>();
let path = match common::path::replace_params_in_path(&path, &url_params) {
Ok(path) => path,
let (path, body) = match compute_request_path_body(
&endpoint_path,
tool_params,
&prompt_target_params,
&http_method,
) {
Ok((path, body)) => (path, body),
Err(e) => {
return self.send_server_error(
ServerError::BadRequest {
why: format!("error replacing params in path: {}", e),
why: format!("error computing api request path or body: {}", e),
},
Some(StatusCode::BAD_REQUEST),
);
}
};
let http_method = endpoint.method.unwrap_or_default().to_string();
let mut headers = vec![
(ARCH_UPSTREAM_HOST_HEADER, endpoint.name.as_str()),
(":method", &http_method),
let timeout_str = API_REQUEST_TIMEOUT_MS.to_string();
let http_method_str = http_method.to_string();
let mut headers: HashMap<_, _> = [
(ARCH_UPSTREAM_HOST_HEADER, endpoint_details.name.as_str()),
(":method", &http_method_str),
(":path", &path),
(":authority", endpoint.name.as_str()),
(":authority", endpoint_details.name.as_str()),
("content-type", "application/json"),
("x-envoy-max-retries", "3"),
];
("x-envoy-upstream-rq-timeout-ms", timeout_str.as_str()),
]
.into_iter()
.collect();
if self.request_id.is_some() {
headers.push((REQUEST_ID_HEADER, self.request_id.as_ref().unwrap()));
headers.insert(REQUEST_ID_HEADER, self.request_id.as_ref().unwrap());
}
if self.traceparent.is_some() {
headers.push((TRACE_PARENT_HEADER, self.traceparent.as_ref().unwrap()));
headers.insert(TRACE_PARENT_HEADER, self.traceparent.as_ref().unwrap());
}
// override http headers that are set in the prompt target
let http_headers = endpoint_details.http_headers.clone().unwrap_or_default();
for (key, value) in http_headers.iter() {
headers.insert(key.as_str(), value.as_str());
}
let call_args = CallArgs::new(
ARCH_INTERNAL_CLUSTER_NAME,
&path,
headers,
Some(tool_params_json_str.as_bytes()),
headers.into_iter().collect(),
body.as_deref().map(|s| s.as_bytes()),
vec![],
Duration::from_secs(5),
);
debug!(
"dispatching api call to developer endpoint: {}, path: {}",
endpoint.name, path
"dispatching api call to developer endpoint: {}, path: {}, method: {}",
endpoint_details.name, path, http_method_str
);
trace!("request body: {}", tool_params_json_str);
callout_context.upstream_cluster = Some(endpoint.name.to_owned());
callout_context.upstream_cluster = Some(endpoint_details.name.to_owned());
callout_context.upstream_cluster_path = Some(path.to_owned());
callout_context.response_handler_type = ResponseHandlerType::FunctionCall;

157
crates/prompt_gateway/src/tools.rs Normal file
View file

@ -0,0 +1,157 @@
use common::configuration::{HttpMethod, Parameter};
use std::collections::HashMap;
use serde_yaml::Value;
// only add params that are of string, number and bool type
pub fn filter_tool_params(tool_params: &HashMap<String, Value>) -> HashMap<String, String> {
tool_params
.iter()
.filter(|(_, value)| value.is_number() || value.is_string() || value.is_bool())
.map(|(key, value)| match value {
Value::Number(n) => (key.clone(), n.to_string()),
Value::String(s) => (key.clone(), s.clone()),
Value::Bool(b) => (key.clone(), b.to_string()),
Value::Null => todo!(),
Value::Sequence(_) => todo!(),
Value::Mapping(_) => todo!(),
Value::Tagged(_) => todo!(),
})
.collect::<HashMap<String, String>>()
}
pub fn compute_request_path_body(
endpoint_path: &str,
tool_params: &HashMap<String, Value>,
prompt_target_params: &[Parameter],
http_method: &HttpMethod,
) -> Result<(String, Option<String>), String> {
let tool_url_params = filter_tool_params(tool_params);
let (path_with_params, query_string, additional_params) = common::path::replace_params_in_path(
endpoint_path,
&tool_url_params,
prompt_target_params,
)?;
let (path, body) = match http_method {
HttpMethod::Get => (format!("{}?{}", path_with_params, query_string), None),
HttpMethod::Post => {
let mut additional_params = additional_params;
if !query_string.is_empty() {
query_string.split("&").for_each(|param| {
let mut parts = param.split("=");
let key = parts.next().unwrap();
let value = parts.next().unwrap();
additional_params.insert(key.to_string(), value.to_string());
});
}
let body = serde_json::to_string(&additional_params).unwrap();
(path_with_params, Some(body))
}
};
Ok((path, body))
}
#[cfg(test)]
mod test {
use common::configuration::{HttpMethod, Parameter};
#[test]
fn test_compute_request_path_body() {
let endpoint_path = "/cluster.open-cluster-management.io/v1/managedclusters/{cluster_name}";
let tool_params = serde_yaml::from_str(
r#"
cluster_name: test1
hello: hello world
"#,
)
.unwrap();
let prompt_target_params = vec![Parameter {
name: "country".to_string(),
parameter_type: None,
description: "test target".to_string(),
required: None,
enum_values: None,
default: Some("US".to_string()),
in_path: None,
format: None,
}];
let http_method = HttpMethod::Get;
let (path, body) = super::compute_request_path_body(
endpoint_path,
&tool_params,
&prompt_target_params,
&http_method,
)
.unwrap();
assert_eq!(
path,
"/cluster.open-cluster-management.io/v1/managedclusters/test1?hello=hello%20world&country=US"
);
assert_eq!(body, None);
}
#[test]
fn test_compute_request_path_body_empty_params() {
let endpoint_path = "/cluster.open-cluster-management.io/v1/managedclusters/";
let tool_params = serde_yaml::from_str(r#"{}"#).unwrap();
let prompt_target_params = vec![Parameter {
name: "country".to_string(),
parameter_type: None,
description: "test target".to_string(),
required: None,
enum_values: None,
default: Some("US".to_string()),
in_path: None,
format: None,
}];
let http_method = HttpMethod::Get;
let (path, body) = super::compute_request_path_body(
endpoint_path,
&tool_params,
&prompt_target_params,
&http_method,
)
.unwrap();
assert_eq!(
path,
"/cluster.open-cluster-management.io/v1/managedclusters/?country=US"
);
assert_eq!(body, None);
}
#[test]
fn test_compute_request_path_body_override_default_val() {
let endpoint_path = "/cluster.open-cluster-management.io/v1/managedclusters/";
let tool_params = serde_yaml::from_str(
r#"
country: UK
"#,
)
.unwrap();
let prompt_target_params = vec![Parameter {
name: "country".to_string(),
parameter_type: None,
description: "test target".to_string(),
required: None,
enum_values: None,
default: Some("US".to_string()),
in_path: None,
format: None,
}];
let http_method = HttpMethod::Get;
let (path, body) = super::compute_request_path_body(
endpoint_path,
&tool_params,
&prompt_target_params,
&http_method,
)
.unwrap();
assert_eq!(
path,
"/cluster.open-cluster-management.io/v1/managedclusters/?country=UK"
);
assert_eq!(body, None);
}
}

16
crates/prompt_gateway/tests/integration.rs
View file

@ -81,10 +81,11 @@ fn normal_flow(module: &mut Tester, filter_context: i32, http_context: i32) {
(":path", "/function_calling"),
("content-type", "application/json"),
(":authority", "model_server"),
("x-envoy-upstream-rq-timeout-ms", "30000"),
]),
None,
None,
None,
Some(5000),
)
.returning(Some(1))
.expect_log(Some(LogLevel::Trace), None)
@ -365,6 +366,7 @@ fn prompt_gateway_request_to_llm_gateway() {
metadata: None,
};
let expected_body = "{\"city\":\"seattle\"}";
let arch_fc_resp_str = serde_json::to_string(&arch_fc_resp).unwrap();
module
.call_proxy_on_http_call_response(http_context, 1, 0, arch_fc_resp_str.len() as i32, 0)
@ -377,20 +379,20 @@ fn prompt_gateway_request_to_llm_gateway() {
.expect_log(Some(LogLevel::Debug), None)
.expect_log(Some(LogLevel::Trace), None)
.expect_log(Some(LogLevel::Trace), None)
.expect_log(Some(LogLevel::Trace), None)
.expect_http_call(
Some("arch_internal"),
Some(vec![
("x-arch-upstream", "api_server"),
(":method", "POST"),
(":path", "/weather"),
(":authority", "api_server"),
("content-type", "application/json"),
("x-arch-upstream", "api_server"),
(":authority", "api_server"),
("x-envoy-max-retries", "3"),
(":path", "/weather"),
("x-envoy-upstream-rq-timeout-ms", "30000"),
]),
Some(expected_body),
None,
None,
None,
Some(5000),
)
.returning(Some(2))
.expect_metric_increment("active_http_calls", 1)

19
demos/insurance_agent/Dockerfile
View file

@ -1,19 +0,0 @@
FROM python:3 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-slim AS output
COPY --from=builder /runtime /usr/local
COPY . /app
WORKDIR /app
CMD ["uvicorn", "insurance_agent_main:app", "--host", "0.0.0.0", "--port", "80", "--log-level", "info"]

58
demos/insurance_agent/README.md
View file

@ -1,58 +0,0 @@
# Insurance Agent Demo
This demo showcases how the **Arch** can be used to manage insurance-related tasks such as policy inquiries, initiating policies, and updating claims or deductibles. In this demo, the assistant provides factual information related to insurance policies (e.g., car, boat, house, motorcycle).
The system can perform a variety of tasks, such as answering insurance-related questions, retrieving policy coverage details, initiating policies, and updating claims or deductibles.
## Available Functions:
- **Policy Q/A**: Handles general Q&A related to insurance policies.
- **Endpoint**: `/policy/qa`
- This function answers general inquiries related to insurance, such as coverage details or policy types. It is the default target for insurance-related queries.
- **Get Policy Coverage**: Retrieves the coverage details for a given policy type (car, boat, house, motorcycle).
- **Endpoint**: `/policy/coverage`
- Parameters:
- `policy_type` (required): The type of policy. Available options: `car`, `boat`, `house`, `motorcycle`. Defaults to `car`.
- **Initiate Policy**: Starts a policy coverage for car, boat, motorcycle, or house.
- **Endpoint**: `/policy/initiate`
- Parameters:
- `policy_type` (required): The type of policy. Available options: `car`, `boat`, `house`, `motorcycle`. Defaults to `car`.
- `deductible` (required): The deductible amount set for the policy.
- **Update Claim**: Updates the notes on a specific insurance claim.
- **Endpoint**: `/policy/claim`
- Parameters:
- `claim_id` (required): The claim number.
- `notes` (optional): Notes about the claim number for the adjustor to see.
- **Update Deductible**: Updates the deductible amount for a specific policy coverage.
- **Endpoint**: `/policy/deductible`
- Parameters:
- `policy_id` (required): The ID of the policy.
- `deductible` (required): The deductible amount to be set for the policy.
**Arch** is designed to intelligently routes prompts to the appropriate functions based on the target, allowing for seamless interaction with various insurance-related services.
# 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/
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 visalize 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,
<img width="575" alt="image" src="https://github.com/user-attachments/assets/25d40f46-616e-41ea-be8e-1623055c84ec">

105
demos/insurance_agent/arch_config.yaml
View file

@ -1,105 +0,0 @@
version: v0.1
listener:
address: 127.0.0.1
port: 8080 #If you configure port 443, you'll need to update the listener with tls_certificates
message_format: huggingface
system_prompt: |
You are an insurance assistant that just offers guidance related to car, boat, rental and home insurnace only. Please be pricese and summarize based on the context provided.
llm_providers:
- name: OpenAI
provider_interface: openai
access_key: $OPENAI_API_KEY
model: gpt-4o
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: 0.05s
prompt_targets:
- name: policy_qa
endpoint:
name: app_server
path: /policy/qa
http_method: POST
description: Handle general Q/A related to insurance.
default: true
- name: get_policy_coverage
description: Retrieve the coverage details for an insurance policy.
endpoint:
name: app_server
path: /policy/coverage
http_method: POST
parameters:
- name: policy_type
type: str
description: The type of policy
default: car
required: true
- name: initiate_policy
endpoint:
name: app_server
path: /policy/initiate
http_method: POST
description: Start a policy coverage for an insurance policy
parameters:
- name: policy_type
type: str
description: The type of policy
default: car
required: true
- name: deductible
type: float
description: the deductible amount set of the policy
required: true
- name: update_claim
endpoint:
name: app_server
path: /policy/claim
http_method: POST
description: Update the notes on the claim
parameters:
- name: claim_id
type: str
description: the claim number
required: true
- name: notes
type: str
description: notes about the cliam number for your adjustor to see
required: false
- name: update_deductible
endpoint:
name: app_server
path: /policy/deductible
http_method: POST
description: Update the deductible amount for a specific insurance policy coverage.
parameters:
- name: policy_id
type: str
description: The id of the insurance policy
required: true
- name: deductible
type: float
description: the deductible amount set of the policy
required: true
ratelimits:
- model: gpt-4
selector:
key: selector-key
value: selector-value
limit:
tokens: 1
unit: minute

140
demos/insurance_agent/insurance_agent_main.py
View file

@ -1,140 +0,0 @@
from fastapi import FastAPI, HTTPException
from pydantic import BaseModel, Field
app = FastAPI()
class Conversation(BaseModel):
arch_messages: list
class PolicyCoverageRequest(BaseModel):
policy_type: str = Field(
...,
description="The type of a policy held by the customer For, e.g. car, boat, house, motorcycle)",
)
class PolicyInitiateRequest(PolicyCoverageRequest):
deductible: float = Field(
..., description="The deductible amount set of the policy"
)
class ClaimUpdate(BaseModel):
claim_id: str
notes: str # Status or details of the claim
class DeductibleUpdate(BaseModel):
policy_id: str
deductible: float
class CoverageResponse(BaseModel):
policy_type: str
coverage: str # Description of coverage
premium: float # The premium cost
# Get information about policy coverage
@app.post("/policy/coverage", response_model=CoverageResponse)
async def get_policy_coverage(req: PolicyCoverageRequest):
"""
Retrieve the coverage details for a given policy type (car, boat, house, motorcycle).
"""
policy_coverage = {
"car": {
"coverage": "Full car coverage with collision, liability",
"premium": 500.0,
},
"boat": {
"coverage": "Full boat coverage including theft and storm damage",
"premium": 700.0,
},
"house": {
"coverage": "Full house coverage including fire, theft, flood",
"premium": 1000.0,
},
"motorcycle": {
"coverage": "Full motorcycle coverage with liability",
"premium": 400.0,
},
}
if req.policy_type not in policy_coverage:
raise HTTPException(status_code=404, detail="Policy type not found")
return CoverageResponse(
policy_type=req.policy_type,
coverage=policy_coverage[req.policy_type]["coverage"],
premium=policy_coverage[req.policy_type]["premium"],
)
# Initiate policy coverage
@app.post("/policy/initiate")
async def initiate_policy(policy_request: PolicyInitiateRequest):
"""
Initiate policy coverage for a car, boat, house, or motorcycle.
"""
if policy_request.policy_type not in ["car", "boat", "house", "motorcycle"]:
raise HTTPException(status_code=400, detail="Invalid policy type")
return {
"message": f"Policy initiated for {policy_request.policy_type}",
"deductible": policy_request.deductible,
}
# Update claim details
@app.post("/policy/claim")
async def update_claim(req: ClaimUpdate):
"""
Update the status or details of a claim.
"""
# For simplicity, this is a mock update response
return {
"message": f"Claim {claim_update.claim_id} for policy {claim_update.claim_id} has been updated",
"update": claim_update.notes,
}
# Update deductible amount
@app.post("/policy/deductible")
async def update_deductible(deductible_update: DeductibleUpdate):
"""
Update the deductible amount for a specific policy.
"""
# For simplicity, this is a mock update response
return {
"message": f"Deductible for policy {deductible_update.policy_id} has been updated",
"new_deductible": deductible_update.deductible,
}
# Post method for policy Q/A
@app.post("/policy/qa")
async def policy_qa(conversation: Conversation):
"""
This method handles Q/A related to general issues in insurance.
It forwards the conversation to the OpenAI client via a local proxy and returns the response.
"""
return {
"choices": [
{
"message": {
"role": "assistant",
"content": "I am a helpful insurance agent, and can only help with insurance things",
},
"finish_reason": "completed",
"index": 0,
}
],
"model": "insurance_agent",
"usage": {"completion_tokens": 0},
}
# Run the app using:
# uvicorn main:app --reload

4
demos/insurance_agent/requirements.txt
View file

@ -1,4 +0,0 @@
fastapi
uvicorn
pydantic
openai

12
demos/network_agent/grafana/dashboard.yaml
View file

@ -1,12 +0,0 @@
apiVersion: 1
providers:
- name: "Dashboard provider"
orgId: 1
type: file
disableDeletion: false
updateIntervalSeconds: 10
allowUiUpdates: false
options:
path: /var/lib/grafana/dashboards
foldersFromFilesStructure: true

355
demos/network_agent/grafana/dashboards/envoy_overview.json
View file

@ -1,355 +0,0 @@
{
"annotations": {
"list": [
{
"builtIn": 1,
"datasource": {
"type": "grafana",
"uid": "-- Grafana --"
},
"enable": true,
"hide": true,
"iconColor": "rgba(0, 211, 255, 1)",
"name": "Annotations & Alerts",
"type": "dashboard"
}
]
},
"editable": true,
"fiscalYearStartMonth": 0,
"graphTooltip": 1,
"links": [],
"panels": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 0
},
"id": 2,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "avg(rate(envoy_cluster_internal_upstream_rq_time_sum[1m]) / rate(envoy_cluster_internal_upstream_rq_time_count[1m])) by (envoy_cluster_name)",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "request latency - internal (ms)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 12,
"y": 0
},
"id": 1,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "avg(rate(envoy_cluster_external_upstream_rq_time_sum[1m]) / rate(envoy_cluster_external_upstream_rq_time_count[1m])) by (envoy_cluster_name)",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
}
],
"title": "request latency - external (ms)",
"type": "timeseries"
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"fieldConfig": {
"defaults": {
"color": {
"mode": "palette-classic"
},
"custom": {
"axisBorderShow": false,
"axisCenteredZero": false,
"axisColorMode": "text",
"axisLabel": "",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "line",
"fillOpacity": 0,
"gradientMode": "none",
"hideFrom": {
"legend": false,
"tooltip": false,
"viz": false
},
"insertNulls": false,
"lineInterpolation": "linear",
"lineWidth": 1,
"pointSize": 5,
"scaleDistribution": {
"type": "linear"
},
"showPoints": "auto",
"spanNulls": false,
"stacking": {
"group": "A",
"mode": "none"
},
"thresholdsStyle": {
"mode": "off"
}
},
"mappings": [],
"thresholds": {
"mode": "absolute",
"steps": [
{
"color": "green",
"value": null
},
{
"color": "red",
"value": 80
}
]
}
},
"overrides": []
},
"gridPos": {
"h": 8,
"w": 12,
"x": 0,
"y": 8
},
"id": 3,
"options": {
"legend": {
"calcs": [],
"displayMode": "list",
"placement": "bottom",
"showLegend": true
},
"tooltip": {
"mode": "single",
"sort": "none"
}
},
"targets": [
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "avg(rate(envoy_cluster_internal_upstream_rq_completed[1m])) by (envoy_cluster_name)",
"fullMetaSearch": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "A",
"useBackend": false
},
{
"datasource": {
"type": "prometheus",
"uid": "PBFA97CFB590B2093"
},
"disableTextWrap": false,
"editorMode": "code",
"expr": "avg(rate(envoy_cluster_external_upstream_rq_completed[1m])) by (envoy_cluster_name)",
"fullMetaSearch": false,
"hide": false,
"includeNullMetadata": true,
"instant": false,
"legendFormat": "__auto",
"range": true,
"refId": "B",
"useBackend": false
}
],
"title": "Upstream request count",
"type": "timeseries"
}
],
"schemaVersion": 39,
"tags": [],
"templating": {
"list": []
},
"time": {
"from": "now-15m",
"to": "now"
},
"timepicker": {},
"timezone": "browser",
"title": "Intelligent Gateway Overview",
"uid": "adt6uhx5lk8aob",
"version": 3,
"weekStart": ""
}

9
demos/network_agent/grafana/datasource.yaml
View file

@ -1,9 +0,0 @@
apiVersion: 1
datasources:
- name: Prometheus
type: prometheus
url: http://prometheus:9090
isDefault: true
access: proxy
editable: true

253
demos/network_agent/utils.py
View file

@ -1,253 +0,0 @@
import logging
import random
import re
import sqlite3
from datetime import datetime, timedelta, timezone
import pandas as pd
from dateparser import parse
logging.basicConfig(
level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s"
)
logger = logging.getLogger(__name__)
def loadsql():
# Example Usage
conn = sqlite3.connect(":memory:")
# create and load the devices table
device_data = generate_device_data(conn)
# create and load the interface_stats table
generate_interface_stats_data(conn, device_data)
# create and load the flow table
generate_flow_data(conn, device_data)
return conn
# Function to convert natural language time expressions to "X {time} ago" format
def convert_to_ago_format(expression):
# Define patterns for different time units
time_units = {
r"seconds": "seconds",
r"minutes": "minutes",
r"mins": "mins",
r"hrs": "hrs",
r"hours": "hours",
r"hour": "hour",
r"hr": "hour",
r"days": "days",
r"day": "day",
r"weeks": "weeks",
r"week": "week",
r"months": "months",
r"month": "month",
r"years": "years",
r"yrs": "years",
r"year": "year",
r"yr": "year",
}
# Iterate over each time unit and create regex for each phrase format
for pattern, unit in time_units.items():
# Handle "for the past X {unit}"
match = re.search(rf"(\d+) {pattern}", expression)
if match:
quantity = match.group(1)
return f"{quantity} {unit} ago"
# If the format is not recognized, return None or raise an error
return None
# Function to generate random MAC addresses
def random_mac():
return "AA:BB:CC:DD:EE:" + ":".join(
[f"{random.randint(0, 255):02X}" for _ in range(2)]
)
# Function to generate random IP addresses
def random_ip():
return f"""{random.randint(1, 255)}
.{random.randint(1, 255)}
.{random.randint(1, 255)}
.{random.randint(1, 255)}"""
# Generate synthetic data for the device table
def generate_device_data(
conn,
n=1000,
):
device_data = {
"switchip": [random_ip() for _ in range(n)],
"hwsku": [f"HW{i+1}" for i in range(n)],
"hostname": [f"switch{i+1}" for i in range(n)],
"osversion": [f"v{i+1}" for i in range(n)],
"layer": ["L2" if i % 2 == 0 else "L3" for i in range(n)],
"region": [random.choice(["US", "EU", "ASIA"]) for _ in range(n)],
"uptime": [
f"""{random.randint(0, 10)} days {random.randint(0, 23)}
:{random.randint(0, 59)}:{random.randint(0, 59)}"""
for _ in range(n)
],
"device_mac_address": [random_mac() for _ in range(n)],
}
df = pd.DataFrame(device_data)
df.to_sql("device", conn, index=False)
return df
# Generate synthetic data for the interfacestats table
def generate_interface_stats_data(conn, device_df, n=1000):
interface_stats_data = []
for _ in range(n):
device_mac = random.choice(device_df["device_mac_address"])
ifname = random.choice(["eth0", "eth1", "eth2", "eth3"])
time = datetime.now(timezone.utc) - timedelta(
minutes=random.randint(0, 1440 * 5)
) # random timestamps in the past 5 day
in_discards = random.randint(0, 1000)
in_errors = random.randint(0, 500)
out_discards = random.randint(0, 800)
out_errors = random.randint(0, 400)
in_octets = random.randint(1000, 100000)
out_octets = random.randint(1000, 100000)
interface_stats_data.append(
{
"device_mac_address": device_mac,
"ifname": ifname,
"time": time,
"in_discards": in_discards,
"in_errors": in_errors,
"out_discards": out_discards,
"out_errors": out_errors,
"in_octets": in_octets,
"out_octets": out_octets,
}
)
df = pd.DataFrame(interface_stats_data)
df.to_sql("interfacestats", conn, index=False)
# Generate synthetic data for the ts_flow table
def generate_flow_data(conn, device_df, n=1000):
flow_data = []
for _ in range(n):
sampler_address = random.choice(device_df["switchip"])
proto = random.choice(["TCP", "UDP"])
src_addr = random_ip()
dst_addr = random_ip()
src_port = random.randint(1024, 65535)
dst_port = random.randint(1024, 65535)
in_if = random.randint(1, 10)
out_if = random.randint(1, 10)
flow_start = int(
(datetime.now() - timedelta(days=random.randint(1, 30))).timestamp()
)
flow_end = int(
(datetime.now() - timedelta(days=random.randint(1, 30))).timestamp()
)
bytes_transferred = random.randint(1000, 100000)
packets = random.randint(1, 1000)
flow_time = datetime.now(timezone.utc) - timedelta(
minutes=random.randint(0, 1440 * 5)
) # random flow time
flow_data.append(
{
"sampler_address": sampler_address,
"proto": proto,
"src_addr": src_addr,
"dst_addr": dst_addr,
"src_port": src_port,
"dst_port": dst_port,
"in_if": in_if,
"out_if": out_if,
"flow_start": flow_start,
"flow_end": flow_end,
"bytes": bytes_transferred,
"packets": packets,
"time": flow_time,
}
)
df = pd.DataFrame(flow_data)
df.to_sql("ts_flow", conn, index=False)
def load_params(req):
# Step 1: Convert the from_time natural language string to a timestamp if provided
if req.from_time:
# Use `dateparser` to parse natural language timeframes
logger.info("%s\n\nCaptured from time: %s\n\n", "* " * 50, req.from_time)
parsed_time = parse(req.from_time, settings={"RELATIVE_BASE": datetime.now()})
if not parsed_time:
conv_time = convert_to_ago_format(req.from_time)
if conv_time:
parsed_time = parse(
conv_time, settings={"RELATIVE_BASE": datetime.now()}
)
else:
return {
"error": """Invalid from_time format. Please provide a valid time description
such as 'past 7 days' or 'since last month'."""
}
logger.info("\n\nConverted from time: %s\n\n%s\n\n", parsed_time, "* " * 50)
from_time = parsed_time
logger.info("Using parsed from_time: %f", from_time)
else:
# If no from_time is provided, use a default value (e.g., the past 7 days)
from_time = datetime.now() - timedelta(days=7)
logger.info("Using default from_time: %f", from_time)
# Step 2: Build the dynamic SQL query based on the optional filters
filters = []
params = {"from_time": from_time}
if req.ifname:
filters.append("i.ifname = :ifname")
params["ifname"] = req.ifname
if req.region:
filters.append("d.region = :region")
params["region"] = req.region
if req.min_in_errors is not None:
filters.append("i.in_errors >= :min_in_errors")
params["min_in_errors"] = req.min_in_errors
if req.max_in_errors is not None:
filters.append("i.in_errors <= :max_in_errors")
params["max_in_errors"] = req.max_in_errors
if req.min_out_errors is not None:
filters.append("i.out_errors >= :min_out_errors")
params["min_out_errors"] = req.min_out_errors
if req.max_out_errors is not None:
filters.append("i.out_errors <= :max_out_errors")
params["max_out_errors"] = req.max_out_errors
if req.min_in_discards is not None:
filters.append("i.in_discards >= :min_in_discards")
params["min_in_discards"] = req.min_in_discards
if req.max_in_discards is not None:
filters.append("i.in_discards <= :max_in_discards")
params["max_in_discards"] = req.max_in_discards
if req.min_out_discards is not None:
filters.append("i.out_discards >= :min_out_discards")
params["min_out_discards"] = req.min_out_discards
if req.max_out_discards is not None:
filters.append("i.out_discards <= :max_out_discards")
params["max_out_discards"] = req.max_out_discards
return params, filters

18
demos/samples_java/weather_forcecast_service/Dockerfile Normal file
View file

@ -0,0 +1,18 @@
# Stage 1: Build the application using Maven
FROM maven:3.8.7-openjdk-18-slim AS build
WORKDIR /app
# Copy pom.xml and download dependencies first (caching)
COPY pom.xml .
RUN mvn dependency:go-offline
# Copy the source code and build the application
COPY src ./src
RUN mvn clean package -DskipTests
# Stage 2: Run the application using a slim JDK image
FROM openjdk:17-jdk-slim
WORKDIR /app
# Copy the built jar from the previous stage
COPY --from=build /app/target/weather-forecast-service-0.0.1-SNAPSHOT.jar app.jar
# Expose the port on which the app runs (default Spring Boot is 8080)
EXPOSE 8081
ENTRYPOINT ["java", "-jar", "app.jar"]

47
demos/samples_java/weather_forcecast_service/arch_config.yaml Normal file
View file

@ -0,0 +1,47 @@
version: v0.1
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:
- name: OpenAI
provider_interface: openai
access_key: $OPENAI_API_KEY
model: gpt-4o-mini
default: true
# Arch creates a round-robin load balancing between different endpoints, managed via the cluster subsystem.
endpoints:
weather_forecast_service:
# 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:18081
# 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 helpful weather assistant.
prompt_targets:
- name: weather_forecast
description: get the weather forecast
parameters:
- name: location
description: the location for which to get the weather forecast
required: true
type: string
format: City, State
- name: days
description: the number of days for the forecast
required: true
type: int
endpoint:
name: weather_forecast_service
path: /weather
http_method: POST

10
demos/insurance_agent/docker-compose.yaml → demos/samples_java/weather_forcecast_service/docker-compose.yaml
View file

@ -1,18 +1,14 @@
services:
api_server:
weather_forecast_service:
build:
context: .
dockerfile: Dockerfile
ports:
- "18083:80"
healthcheck:
test: ["CMD", "curl" ,"http://localhost:80/healthz"]
interval: 5s
retries: 20
- "18081:8081"
chatbot_ui:
build:
context: ../shared/chatbot_ui
context: ../../shared/chatbot_ui
dockerfile: Dockerfile
ports:
- "18080:8080"

40
demos/samples_java/weather_forcecast_service/pom.xml Normal file
View file

@ -0,0 +1,40 @@
<project xmlns="http://maven.apache.org/POM/4.0.0"
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0
https://maven.apache.org/xsd/maven-4.0.0.xsd">
<modelVersion>4.0.0</modelVersion>
<groupId>weather</groupId>
<artifactId>weather-forecast-service</artifactId>
<version>0.0.1-SNAPSHOT</version>
<packaging>jar</packaging>
<parent>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-parent</artifactId>
<version>2.7.10</version>
<relativePath/>
</parent>
<dependencies>
<!-- Spring Boot Starter Web -->
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter-web</artifactId>
</dependency>
<dependency>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-starter</artifactId>
</dependency>
</dependencies>
<build>
<plugins>
<!-- Spring Boot Maven Plugin -->
<plugin>
<groupId>org.springframework.boot</groupId>
<artifactId>spring-boot-maven-plugin</artifactId>
</plugin>
</plugins>
</build>
</project>

0
demos/currency_exchange/run_demo.sh → demos/samples_java/weather_forcecast_service/run_demo.sh
View file

12
demos/samples_java/weather_forcecast_service/src/main/java/weather/WeatherForecastApplication.java Normal file
View file

@ -0,0 +1,12 @@
// File: src/main/java/com/example/weather/WeatherForecastApplication.java
package weather;
import org.springframework.boot.SpringApplication;
import org.springframework.boot.autoconfigure.SpringBootApplication;
@SpringBootApplication
public class WeatherForecastApplication {
public static void main(String[] args) {
SpringApplication.run(WeatherForecastApplication.class, args);
}
}

54
demos/samples_java/weather_forcecast_service/src/main/java/weather/controller/WeatherController.java Normal file
View file

@ -0,0 +1,54 @@
package weather.controller;
import weather.model.DayForecast;
import weather.model.WeatherForecastResponse;
import weather.model.WeatherRequest;
import org.springframework.web.bind.annotation.PostMapping;
import org.springframework.web.bind.annotation.RequestBody;
import org.springframework.web.bind.annotation.RestController;
import java.time.Instant;
import java.time.LocalDate;
import java.util.ArrayList;
import java.util.List;
import java.util.Random;
@RestController
public class WeatherController {
private Random random = new Random();
@PostMapping("/weather")
public WeatherForecastResponse getRandomWeatherForecast(@RequestBody WeatherRequest req) {
WeatherForecastResponse response = new WeatherForecastResponse();
response.setLocation(req.getLocation());
response.setUnits(req.getUnits());
List<DayForecast> forecasts = new ArrayList<>();
for (int i = 0; i < req.getDays(); i++) {
// Generate a random min temperature between 50 and 89 (inclusive)
int minTemp = random.nextInt(90 - 50) + 50;
// Generate a max temperature between (minTemp + 5) and (minTemp + 19)
int maxTemp = random.nextInt(15) + (minTemp + 5);
double finalMinTemp = minTemp;
double finalMaxTemp = maxTemp;
// Convert to Celsius if necessary
if (req.getUnits().equalsIgnoreCase("celsius") || req.getUnits().equalsIgnoreCase("c")) {
finalMinTemp = (minTemp - 32) * 5.0 / 9.0;
finalMaxTemp = (maxTemp - 32) * 5.0 / 9.0;
}
DayForecast dayForecast = new DayForecast();
dayForecast.setDate(LocalDate.now().plusDays(i).toString());
dayForecast.setMin(finalMinTemp);
dayForecast.setMax(finalMaxTemp);
dayForecast.setUnits(req.getUnits());
forecasts.add(dayForecast);
}
response.setDailyForecast(forecasts);
return response;
}
}

40
demos/samples_java/weather_forcecast_service/src/main/java/weather/model/DayForecast.java Normal file
View file

@ -0,0 +1,40 @@
package weather.model;
public class DayForecast {
private String date;
private String units;
private double min;
private double max;
public DayForecast() {}
// Getters and setters
public String getDate() {
return date;
}
public void setDate(String date) {
this.date = date;
}
public String getUnits() {
return units;
}
public void setUnits(String units) {
this.units = units;
}
public double getMin() {
return min;
}
public void setMin(double min) {
this.min = min;
}
public double getMax() {
return max;
}
public void setMax(double max) {
this.max = max;
}
}

37
demos/samples_java/weather_forcecast_service/src/main/java/weather/model/WeatherForecastResponse.java Normal file
View file

@ -0,0 +1,37 @@
package weather.model;
import java.util.List;
public class WeatherForecastResponse {
private String location;
private String units;
private List<DayForecast> forecast;
// Default Constructor
public WeatherForecastResponse() {}
// Getters and Setters
public String getLocation() {
return location;
}
public void setLocation(String location) {
this.location = location;
}
public String getUnits() {
return units;
}
public void setUnits(String units) {
this.units = units;
}
public List<DayForecast> getDailyForecast() {
return forecast;
}
public void setDailyForecast(List<DayForecast> forecast) {
this.forecast = forecast;
}
}

29
demos/samples_java/weather_forcecast_service/src/main/java/weather/model/WeatherRequest.java Normal file
View file

@ -0,0 +1,29 @@
package weather.model;
public class WeatherRequest {
private String location;
private int days = 7;
private String units = "Farenheit";
public WeatherRequest() {}
// Getters and setters
public String getLocation() {
return location;
}
public void setLocation(String location) {
this.location = location;
}
public int getDays() {
return days;
}
public void setDays(int days) {
this.days = days;
}
public String getUnits() {
return units;
}
public void setUnits(String units) {
this.units = units;
}
}

1
demos/samples_java/weather_forcecast_service/src/main/resources/application.properties Normal file
View file

@ -0,0 +1 @@
server.port=8081

0
demos/currency_exchange/README.md → demos/samples_python/currency_exchange/README.md
View file

23
demos/currency_exchange/arch_config.yaml → demos/samples_python/currency_exchange/arch_config.yaml
View file

@ -1,10 +1,11 @@
version: v0.1
listener:
address: 0.0.0.0
port: 10000
message_format: huggingface
connect_timeout: 0.005s
listeners:
ingress_traffic:
address: 0.0.0.0
port: 10000
message_format: openai
timeout: 30s
llm_providers:
- name: gpt-4o
@ -12,6 +13,11 @@ llm_providers:
provider_interface: openai
model: gpt-4o
endpoints:
frankfurther_api:
endpoint: api.frankfurter.dev
protocol: https
system_prompt: |
You are a helpful assistant.
@ -26,7 +32,7 @@ prompt_targets:
description: Get currency exchange rate from USD to other currencies
parameters:
- name: currency_symbol
description: the currency that needs conversion
description: currency symbol to convert from USD
required: true
type: str
in_path: true
@ -42,11 +48,6 @@ prompt_targets:
name: frankfurther_api
path: /v1/currencies
endpoints:
frankfurther_api:
endpoint: api.frankfurter.dev
protocol: https
tracing:
random_sampling: 100
trace_arch_internal: true

4
demos/currency_exchange_ollama/docker-compose.yaml → demos/samples_python/currency_exchange/docker-compose.yaml
View file

@ -1,7 +1,7 @@
services:
chatbot_ui:
build:
context: ../shared/chatbot_ui
context: ../../shared/chatbot_ui
ports:
- "18080:8080"
environment:
@ -14,7 +14,7 @@ services:
jaeger:
build:
context: ../shared/jaeger
context: ../../shared/jaeger
ports:
- "16686:16686"
- "4317:4317"

0
demos/currency_exchange_ollama/run_demo.sh → demos/samples_python/currency_exchange/run_demo.sh
View file

0
demos/currency_exchange/test_data.yaml → demos/samples_python/currency_exchange/test_data.yaml
View file

0
demos/hr_agent/Dockerfile → demos/samples_python/human_resources_agent/Dockerfile
View file

0
demos/hr_agent/README.md → demos/samples_python/human_resources_agent/README.md
View file

10
demos/hr_agent/arch_config.yaml → demos/samples_python/human_resources_agent/arch_config.yaml
View file

@ -1,8 +1,10 @@
version: v0.1
listener:
address: 127.0.0.1
port: 8080 #If you configure port 443, you'll need to update the listener with tls_certificates
message_format: huggingface
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:

3
demos/hr_agent/docker-compose.yaml → demos/samples_python/human_resources_agent/docker-compose.yaml
View file

@ -8,7 +8,6 @@ services:
- CHAT_COMPLETION_ENDPOINT=http://host.docker.internal:10000/v1
volumes:
- ./arch_config.yaml:/app/arch_config.yaml
- ../shared/chatbot_ui/common.py:/app/common.py
ports:
- "18080:80"
healthcheck:
@ -18,7 +17,7 @@ services:
chatbot_ui:
build:
context: ../shared/chatbot_ui
context: ../../shared/chatbot_ui
dockerfile: Dockerfile
ports:
- "18080:8080"

0
demos/hr_agent/image.png → demos/samples_python/human_resources_agent/image.png
View file

Side by side Swipe Overlay

Before

Width:  |  Height:  |  Size: 549 KiB

After

Width:  |  Height:  |  Size: 549 KiB

Before After
Before After

0
demos/hr_agent/main.py → demos/samples_python/human_resources_agent/main.py
View file

0
demos/hr_agent/requirements.txt → demos/samples_python/human_resources_agent/requirements.txt
View file

0
demos/hr_agent/run_demo.sh → demos/samples_python/human_resources_agent/run_demo.sh
View file

0
demos/hr_agent/test_data.yaml → demos/samples_python/human_resources_agent/test_data.yaml
View file

0
demos/hr_agent/workforce_data.json → demos/samples_python/human_resources_agent/workforce_data.json
View file

0
demos/multi_turn_rag_agent/Dockerfile → demos/samples_python/multi_turn_rag_agent/Dockerfile
View file

0
demos/multi_turn_rag_agent/README.md → demos/samples_python/multi_turn_rag_agent/README.md
View file

11
demos/multi_turn_rag_agent/arch_config.yaml → demos/samples_python/multi_turn_rag_agent/arch_config.yaml
View file

@ -1,10 +1,11 @@
version: v0.1
listener:
address: 127.0.0.1
port: 10000
message_format: huggingface
connect_timeout: 0.005s
listeners:
ingress_traffic:
address: 0.0.0.0
port: 10000
message_format: openai
timeout: 30s
endpoints:
rag_energy_source_agent:

2
demos/multi_turn_rag_agent/docker-compose.yaml → demos/samples_python/multi_turn_rag_agent/docker-compose.yaml
View file

@ -12,7 +12,7 @@ services:
chatbot_ui:
build:
context: ../shared/chatbot_ui
context: ../../shared/chatbot_ui
dockerfile: Dockerfile
ports:
- "18080:8080"

0
demos/multi_turn_rag_agent/main.py → demos/samples_python/multi_turn_rag_agent/main.py
View file

0
demos/multi_turn_rag_agent/mutli-turn-example.png → demos/samples_python/multi_turn_rag_agent/mutli-turn-example.png
View file

Side by side Swipe Overlay

Before

Width:  |  Height:  |  Size: 852 KiB

After

Width:  |  Height:  |  Size: 852 KiB

Before After
Before After

0
demos/multi_turn_rag_agent/requirements.txt → demos/samples_python/multi_turn_rag_agent/requirements.txt
View file

0
demos/multi_turn_rag_agent/run_demo.sh → demos/samples_python/multi_turn_rag_agent/run_demo.sh
View file

4
demos/network_agent/Dockerfile → demos/samples_python/network_switch_operator_agent/Dockerfile
View file

@ -7,13 +7,13 @@ WORKDIR /src
COPY requirements.txt /src/
RUN pip install --prefix=/runtime --force-reinstall -r requirements.txt
COPY . /src
COPY ../. /src
FROM python:3.12-slim AS output
COPY --from=builder /runtime /usr/local
COPY . /app
COPY ../. /app
WORKDIR /app
CMD ["uvicorn", "main:app", "--host", "0.0.0.0", "--port", "80", "--log-level", "info"]

0
demos/network_agent/README.md → demos/samples_python/network_switch_operator_agent/README.md
View file

10
demos/network_agent/arch_config.yaml → demos/samples_python/network_switch_operator_agent/arch_config.yaml
View file

@ -1,8 +1,10 @@
version: v0.1
listener:
address: 127.0.0.1
port: 8080 #If you configure port 443, you'll need to update the listener with tls_certificates
message_format: huggingface
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:

2
demos/network_agent/docker-compose.yaml → demos/samples_python/network_switch_operator_agent/docker-compose.yaml
View file

@ -8,7 +8,7 @@ services:
chatbot_ui:
build:
context: ../shared/chatbot_ui
context: ../../shared/chatbot_ui
dockerfile: Dockerfile
ports:
- "18080:8080"

0
demos/network_agent/image.png → demos/samples_python/network_switch_operator_agent/image.png
View file

Side by side Swipe Overlay

Before

Width:  |  Height:  |  Size: 636 KiB

After

Width:  |  Height:  |  Size: 636 KiB

Before After
Before After

0
demos/network_agent/main.py → demos/samples_python/network_switch_operator_agent/main.py
View file

0
demos/network_agent/requirements.txt → demos/samples_python/network_switch_operator_agent/requirements.txt
View file

1
demos/network_agent/run_demo.sh → demos/samples_python/network_switch_operator_agent/run_demo.sh
View file

@ -24,6 +24,7 @@ start_demo() {
# Step 4: Start Network Agent
echo "Starting Network Agent using Docker Compose..."
cd build
docker compose up -d # Run in detached mode
}

9
demos/samples_python/stock_quote/README.md Normal file
View file

@ -0,0 +1,9 @@
This demo shows how you can use a publicly hosted rest api that is protected by an access key.
Before you start the demo make sure you set `OPENAI_API_KEY` and `TWELVEDATA_API_KEY`.
To get `TWELVEDATA_API_KEY` please head over to https://twelvedata.com/.
Following screenshot shows interaction with stock quote demo,
![alt text](stock_quote_demo.png)

70
demos/samples_python/stock_quote/arch_config.yaml Normal file
View file

@ -0,0 +1,70 @@
version: v0.1
listeners:
ingress_traffic:
address: 0.0.0.0
port: 10000
message_format: openai
timeout: 30s
llm_providers:
- name: gpt-4o
access_key: $OPENAI_API_KEY
provider_interface: openai
model: gpt-4o
endpoints:
twelvedata_api:
endpoint: api.twelvedata.com
protocol: https
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
parameters:
- name: symbol
description: Stock symbol
required: true
type: str
endpoint:
name: twelvedata_api
path: /quote
http_headers:
Authorization: "apikey $TWELVEDATA_API_KEY"
system_prompt: |
You are a helpful stock exchange assistant. You are given stock symbol along with its exchange rate in json format. Your task is to parse the data and present it in a human-readable format. Keep the details to highlevel and be concise.
- name: stock_quote_time_series
description: get historical stock exchange rate for a given symbol
parameters:
- name: symbol
description: Stock symbol
required: true
type: str
- name: interval
description: Time interval
default: 1day
enum:
- 1h
- 1day
type: str
endpoint:
name: twelvedata_api
path: /time_series
http_headers:
Authorization: "apikey $TWELVEDATA_API_KEY"
system_prompt: |
You are a helpful stock exchange assistant. You are given stock symbol along with its historical data in json format. Your task is to parse the data and present it in a human-readable format. Keep the details to highlevel only and be concise.
tracing:
random_sampling: 100
trace_arch_internal: true

21
demos/samples_python/stock_quote/docker-compose.yaml Normal file
View 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 environment 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"

2
demos/insurance_agent/run_demo.sh → demos/samples_python/stock_quote/run_demo.sh
View file

@ -22,7 +22,7 @@ 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..."
docker compose up -d # Run in detached mode
}

BIN
demos/samples_python/stock_quote/stock_quote_demo.png Normal file
View file

Binary file not shown.
Side by side

After

Width:  |  Height:  |  Size: 673 KiB

0
demos/weather_forecast/Dockerfile → demos/samples_python/weather_forecast/Dockerfile
View file

0
demos/weather_forecast/README.md → demos/samples_python/weather_forecast/README.md
View file

11
demos/weather_forecast/arch_config.yaml → demos/samples_python/weather_forecast/arch_config.yaml
View file

@ -1,10 +1,11 @@
version: "0.1-beta"
listener:
address: 0.0.0.0
port: 10000
message_format: huggingface
connect_timeout: 0.005s
listeners:
ingress_traffic:
address: 0.0.0.0
port: 10000
message_format: openai
timeout: 30s
endpoints:
weather_forecast_service:

10
demos/weather_forecast/docker-compose-honeycomb.yaml → demos/samples_python/weather_forecast/docker-compose-honeycomb.yaml
View file

@ -11,7 +11,7 @@ services:
chatbot_ui:
build:
context: ../shared/chatbot_ui
context: ../../shared/chatbot_ui
ports:
- "18080:8080"
environment:
@ -24,12 +24,12 @@ services:
otel-collector:
build:
context: ../shared/honeycomb/
context: ../../shared/honeycomb/
ports:
- "4317:4317"
- "4318:4318"
volumes:
- ../shared/honeycomb/otel-collector-config.yaml:/etc/otel-collector-config.yaml
- ../../shared/honeycomb/otel-collector-config.yaml:/etc/otel-collector-config.yaml
env_file:
- .env
environment:
@ -37,10 +37,10 @@ services:
prometheus:
build:
context: ../shared/prometheus
context: ../../shared/prometheus
grafana:
build:
context: ../shared/grafana
context: ../../shared/grafana
ports:
- "3000:3000"

8
demos/weather_forecast/docker-compose-jaeger.yaml → demos/samples_python/weather_forecast/docker-compose-jaeger.yaml
View file

@ -11,7 +11,7 @@ services:
chatbot_ui:
build:
context: ../shared/chatbot_ui
context: ../../shared/chatbot_ui
ports:
- "18080:8080"
environment:
@ -24,7 +24,7 @@ services:
jaeger:
build:
context: ../shared/jaeger
context: ../../shared/jaeger
ports:
- "16686:16686"
- "4317:4317"
@ -32,10 +32,10 @@ services:
prometheus:
build:
context: ../shared/prometheus
context: ../../shared/prometheus
grafana:
build:
context: ../shared/grafana
context: ../../shared/grafana
ports:
- "3000:3000"

10
demos/weather_forecast/docker-compose-logfire.yaml → demos/samples_python/weather_forecast/docker-compose-logfire.yaml
View file

@ -11,7 +11,7 @@ services:
chatbot_ui:
build:
context: ../shared/chatbot_ui
context: ../../shared/chatbot_ui
ports:
- "18080:8080"
environment:
@ -24,12 +24,12 @@ services:
otel-collector:
build:
context: ../shared/logfire/
context: ../../shared/logfire/
ports:
- "4317:4317"
- "4318:4318"
volumes:
- ../shared/logfire/otel-collector-config.yaml:/etc/otel-collector-config.yaml
- ../../shared/logfire/otel-collector-config.yaml:/etc/otel-collector-config.yaml
env_file:
- .env
environment:
@ -37,10 +37,10 @@ services:
prometheus:
build:
context: ../shared/prometheus
context: ../../shared/prometheus
grafana:
build:
context: ../shared/grafana
context: ../../shared/grafana
ports:
- "3000:3000"

Some files were not shown because too many files have changed in this diff Show more