mirror of
https://github.com/katanemo/plano.git
synced 2026-06-17 15:25:17 +02:00
Merge branch 'main' of https://github.com/katanemo/arch into cotran/hallucination-fix
This commit is contained in:
cotran
commit
d0496e7d91
116 changed files with 645 additions and 1092 deletions
2
.github/workflows/e2e_archgw.yml
vendored
2
.github/workflows/e2e_archgw.yml
vendored
|
|
@ -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
2
.github/workflows/e2e_model_server.yml
vendored
|
|
@ -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
6
.github/workflows/e2e_test_demos.yml
vendored
|
|
@ -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
2
.github/workflows/e2e_tests.yml
vendored
|
|
@ -7,7 +7,7 @@ on:
|
|||
pull_request:
|
||||
|
||||
jobs:
|
||||
test:
|
||||
e2e_tests:
|
||||
runs-on: ubuntu-latest
|
||||
|
||||
steps:
|
||||
|
|
|
|||
49
README.md
49
README.md
|
|
@ -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-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 fast, hyper-personalized agents with intelligent 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)
|
||||
|
||||
[](https://github.com/katanemo/arch/actions/workflows/pre-commit.yml)
|
||||
[](https://github.com/katanemo/arch/actions/workflows/rust_tests.yml)
|
||||
[](https://github.com/katanemo/arch/actions/workflows/e2e_tests.yml)
|
||||
[](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-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 fast, hyper-personalized agents with intelligent 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**:
|
||||
|
||||
|
|
@ -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==0.2.1
|
||||
```
|
||||
|
||||
### Build AI Agent with Arch Gateway
|
||||
|
|
|
|||
|
|
@ -79,6 +79,8 @@ properties:
|
|||
properties:
|
||||
prompt_target_intent_matching_threshold:
|
||||
type: number
|
||||
optimize_context_window:
|
||||
type: boolean
|
||||
system_prompt:
|
||||
type: string
|
||||
prompt_targets:
|
||||
|
|
|
|||
|
|
@ -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
|
||||
|
|
|
|||
|
|
@ -19,7 +19,7 @@ source venv/bin/activate
|
|||
|
||||
### Step 3: Run the build script
|
||||
```bash
|
||||
pip install archgw==0.2.0
|
||||
pip install archgw==0.2.1
|
||||
```
|
||||
|
||||
## Uninstall Instructions: archgw CLI
|
||||
|
|
|
|||
22
arch/tools/poetry.lock
generated
22
arch/tools/poetry.lock
generated
|
|
@ -2,7 +2,7 @@
|
|||
|
||||
[[package]]
|
||||
name = "archgw_modelserver"
|
||||
version = "0.2.0"
|
||||
version = "0.2.1"
|
||||
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]
|
||||
|
|
@ -34,13 +34,13 @@ tests-mypy = ["mypy (>=1.11.1)", "pytest-mypy-plugins"]
|
|||
|
||||
[[package]]
|
||||
name = "certifi"
|
||||
version = "2024.12.14"
|
||||
version = "2025.1.31"
|
||||
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"},
|
||||
{file = "certifi-2025.1.31-py3-none-any.whl", hash = "sha256:ca78db4565a652026a4db2bcdf68f2fb589ea80d0be70e03929ed730746b84fe"},
|
||||
{file = "certifi-2025.1.31.tar.gz", hash = "sha256:3d5da6925056f6f18f119200434a4780a94263f10d1c21d032a6f6b2baa20651"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
|
|
@ -370,13 +370,13 @@ files = [
|
|||
|
||||
[[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]
|
||||
|
|
@ -568,4 +568,4 @@ zstd = ["zstandard (>=0.18.0)"]
|
|||
[metadata]
|
||||
lock-version = "2.0"
|
||||
python-versions = "^3.10"
|
||||
content-hash = "59543baf4d462d4830e7228ba9eda8ae865416fdabd8ede129492ac45f1926f2"
|
||||
content-hash = "6b29791896ec1680e2c841ac42e835c1bada672b056d8208ab24388f70f9badb"
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
[tool.poetry]
|
||||
name = "archgw"
|
||||
version = "0.2.0"
|
||||
version = "0.2.1"
|
||||
description = "Python-based CLI tool to manage Arch Gateway."
|
||||
authors = ["Katanemo Labs, Inc."]
|
||||
packages = [
|
||||
|
|
@ -10,7 +10,7 @@ readme = "README.md"
|
|||
|
||||
[tool.poetry.dependencies]
|
||||
python = "^3.10"
|
||||
archgw_modelserver = "^0.2.0"
|
||||
archgw_modelserver = "^0.2.1"
|
||||
click = "^8.1.7"
|
||||
jinja2 = "^3.1.4"
|
||||
jsonschema = "^4.23.0"
|
||||
|
|
|
|||
|
|
@ -25,6 +25,7 @@ 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)]
|
||||
|
|
|
|||
|
|
@ -137,9 +137,20 @@ 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(),
|
||||
|
|
|
|||
|
|
@ -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: overrides,
|
||||
request_id: None,
|
||||
traceparent: None,
|
||||
_tracing: tracing,
|
||||
|
|
|
|||
|
|
@ -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"]
|
||||
|
|
@ -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">
|
||||
|
|
@ -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
|
||||
|
|
@ -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
|
||||
|
|
@ -1,4 +0,0 @@
|
|||
fastapi
|
||||
uvicorn
|
||||
pydantic
|
||||
openai
|
||||
|
|
@ -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
|
||||
|
|
@ -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": ""
|
||||
}
|
||||
|
|
@ -1,9 +0,0 @@
|
|||
apiVersion: 1
|
||||
|
||||
datasources:
|
||||
- name: Prometheus
|
||||
type: prometheus
|
||||
url: http://prometheus:9090
|
||||
isDefault: true
|
||||
access: proxy
|
||||
editable: true
|
||||
|
|
@ -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
18
demos/samples_java/weather_forcecast_service/Dockerfile
Normal 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"]
|
||||
|
|
@ -0,0 +1,45 @@
|
|||
version: v0.1
|
||||
listener:
|
||||
address: 127.0.0.1
|
||||
port: 10000 #If you configure port 443, you'll need to update the listener with tls_certificates
|
||||
message_format: huggingface
|
||||
|
||||
# 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
|
||||
|
|
@ -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
40
demos/samples_java/weather_forcecast_service/pom.xml
Normal 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>
|
||||
|
|
@ -0,0 +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);
|
||||
}
|
||||
}
|
||||
|
|
@ -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;
|
||||
}
|
||||
}
|
||||
|
|
@ -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;
|
||||
}
|
||||
}
|
||||
|
|
@ -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;
|
||||
}
|
||||
}
|
||||
|
|
@ -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;
|
||||
}
|
||||
}
|
||||
|
|
@ -0,0 +1 @@
|
|||
server.port=8081
|
||||
|
|
@ -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"
|
||||
|
|
@ -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"
|
||||
|
Before Width: | Height: | Size: 549 KiB After Width: | Height: | Size: 549 KiB |
|
|
@ -12,7 +12,7 @@ services:
|
|||
|
||||
chatbot_ui:
|
||||
build:
|
||||
context: ../shared/chatbot_ui
|
||||
context: ../../shared/chatbot_ui
|
||||
dockerfile: Dockerfile
|
||||
ports:
|
||||
- "18080:8080"
|
||||
|
Before Width: | Height: | Size: 852 KiB After Width: | Height: | Size: 852 KiB |
|
|
@ -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"]
|
||||
|
|
@ -8,7 +8,7 @@ services:
|
|||
|
||||
chatbot_ui:
|
||||
build:
|
||||
context: ../shared/chatbot_ui
|
||||
context: ../../shared/chatbot_ui
|
||||
dockerfile: Dockerfile
|
||||
ports:
|
||||
- "18080:8080"
|
||||
|
Before Width: | Height: | Size: 636 KiB After Width: | Height: | Size: 636 KiB |
|
|
@ -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
|
||||
}
|
||||
|
||||
|
|
@ -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"
|
||||
|
Before Width: | Height: | Size: 673 KiB After Width: | Height: | Size: 673 KiB |
|
|
@ -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"
|
||||
|
|
@ -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"
|
||||
|
|
@ -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"
|
||||
|
|
@ -1,5 +1,5 @@
|
|||
include:
|
||||
- ../shared/signoz/docker-compose-minimal.yaml
|
||||
- ../../shared/signoz/docker-compose-minimal.yaml
|
||||
|
||||
services:
|
||||
weather_forecast_service:
|
||||
|
|
@ -14,7 +14,7 @@ services:
|
|||
|
||||
chatbot_ui:
|
||||
build:
|
||||
context: ../shared/chatbot_ui
|
||||
context: ../../shared/chatbot_ui
|
||||
ports:
|
||||
- "18080:8080"
|
||||
environment:
|
||||
|
|
@ -27,10 +27,10 @@ services:
|
|||
|
||||
prometheus:
|
||||
build:
|
||||
context: ../shared/prometheus
|
||||
context: ../../shared/prometheus
|
||||
|
||||
grafana:
|
||||
build:
|
||||
context: ../shared/grafana
|
||||
context: ../../shared/grafana
|
||||
ports:
|
||||
- "3000:3000"
|
||||
|
|
@ -11,7 +11,7 @@ services:
|
|||
|
||||
chatbot_ui:
|
||||
build:
|
||||
context: ../shared/chatbot_ui
|
||||
context: ../../shared/chatbot_ui
|
||||
ports:
|
||||
- "18080:8080"
|
||||
environment:
|
||||
|
|
@ -19,23 +19,3 @@ services:
|
|||
- 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"
|
||||
|
||||
prometheus:
|
||||
build:
|
||||
context: ../shared/prometheus
|
||||
|
||||
grafana:
|
||||
build:
|
||||
context: ../shared/grafana
|
||||
ports:
|
||||
- "3000:3000"
|
||||
|
|
@ -7,13 +7,13 @@ do
|
|||
echo "******************************************"
|
||||
echo "Running tests for $demo ..."
|
||||
echo "****************************************"
|
||||
cd ../$demo
|
||||
cd ../../samples_python/$demo
|
||||
archgw up arch_config.yaml
|
||||
docker compose up -d
|
||||
cd ../test_runner
|
||||
TEST_DATA=../$demo/test_data.yaml poetry run pytest
|
||||
cd ../$demo
|
||||
cd ../../shared/test_runner
|
||||
TEST_DATA=../../samples_python/$demo/test_data.yaml poetry run pytest
|
||||
cd ../../samples_python/$demo
|
||||
archgw down
|
||||
docker compose down -v
|
||||
cd ../test_runner
|
||||
cd ../../shared/test_runner
|
||||
done
|
||||
|
|
@ -1,5 +1,5 @@
|
|||
# LLM Routing
|
||||
This demo shows how you can arch gateway to manage keys and route to appropriate LLM.
|
||||
This demo shows how you can arch gateway to manage keys and route to upstream LLM.
|
||||
|
||||
# Starting the demo
|
||||
1. Please make sure the [pre-requisites](https://github.com/katanemo/arch/?tab=readme-ov-file#prerequisites) are installed correctly
|
||||
|
|
@ -2,7 +2,7 @@ services:
|
|||
|
||||
chatbot_ui:
|
||||
build:
|
||||
context: ../shared/chatbot_ui
|
||||
context: ../../shared/chatbot_ui
|
||||
dockerfile: Dockerfile
|
||||
ports:
|
||||
- "18080:8080"
|
||||
|
|
@ -15,7 +15,7 @@ services:
|
|||
|
||||
jaeger:
|
||||
build:
|
||||
context: ../shared/jaeger
|
||||
context: ../../shared/jaeger
|
||||
ports:
|
||||
- "16686:16686"
|
||||
- "4317:4317"
|
||||
|
|
@ -23,10 +23,10 @@ services:
|
|||
|
||||
prometheus:
|
||||
build:
|
||||
context: ../shared/prometheus
|
||||
context: ../../shared/prometheus
|
||||
|
||||
grafana:
|
||||
build:
|
||||
context: ../shared/grafana
|
||||
context: ../../shared/grafana
|
||||
ports:
|
||||
- "3000:3000"
|
||||
|
Before Width: | Height: | Size: 273 KiB After Width: | Height: | Size: 273 KiB |
|
Before Width: | Height: | Size: 284 KiB After Width: | Height: | Size: 284 KiB |
|
|
@ -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"
|
||||
|
|
@ -1,7 +1,7 @@
|
|||
services:
|
||||
chatbot_ui:
|
||||
build:
|
||||
context: ../shared/chatbot_ui
|
||||
context: ../../shared/chatbot_ui
|
||||
ports:
|
||||
- "18080:8080"
|
||||
environment:
|
||||
|
|
@ -14,12 +14,12 @@ 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:
|
||||
|
|
@ -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
|
||||
}
|
||||
31
demos/use_cases/spotify_bearer_auth/README.md
Normal file
31
demos/use_cases/spotify_bearer_auth/README.md
Normal file
|
|
@ -0,0 +1,31 @@
|
|||
# Use Case Demo: Bearer Authorization with Spotify APIs
|
||||
|
||||
In this demo, we show how you can use Arch's bearer authorization capability to connect your agentic apps to third-party APIs.
|
||||
More specifically, we demonstrate how you can connect to two Spotify APIs:
|
||||
|
||||
- [`/v1/browse/new-releases`](https://developer.spotify.com/documentation/web-api/reference/get-new-releases)
|
||||
- [`/v1/artists/{artist_id}/top-tracks`](https://developer.spotify.com/documentation/web-api/reference/get-an-artists-top-tracks)
|
||||
|
||||
Where users can engage by asking questions like _"Show me the latest releases in the US"_, followed by queries like _"Show me top tracks from Taylor Swift"_.
|
||||
|
||||
|
||||
|
||||
## Starting the demo
|
||||
|
||||
1. Ensure the [prerequisites](https://github.com/katanemo/arch/?tab=readme-ov-file#prerequisites) are installed correctly.
|
||||
2. Create an `.env` file with API keys for OpenAI and Spotify.
|
||||
- Sign up for an OpenAI API key at [https://platform.openai.com/signup/](https://platform.openai.com/signup/)
|
||||
- Sign up for a Spotify Client Key/Secret by following instructions at [https://developer.spotify.com/dashboard/](https://developer.spotify.com/dashboard/)
|
||||
- Generate a Spotify token using the [https://accounts.spotify.com/api/token API](https://accounts.spotify.com/api/token), using ```curl``` or similar commands.
|
||||
- Create a .env file with the following keys:
|
||||
```
|
||||
OPENAI_API_KEY=your_openai_api_key
|
||||
SPOTIFY_CLIENT_KEY=your_spotify_api_token
|
||||
```
|
||||
|
||||
3. Start Arch
|
||||
```sh
|
||||
sh run_demo.sh
|
||||
```
|
||||
4. Navigate to http://localhost:18080
|
||||
5. Ask "show me new album releases in the US"
|
||||
122
demos/use_cases/spotify_bearer_auth/arch_config.yaml
Normal file
122
demos/use_cases/spotify_bearer_auth/arch_config.yaml
Normal file
|
|
@ -0,0 +1,122 @@
|
|||
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
|
||||
|
||||
overrides:
|
||||
optimize_context_window: true
|
||||
|
||||
endpoints:
|
||||
spotify:
|
||||
endpoint: api.spotify.com
|
||||
protocol: https
|
||||
|
||||
system_prompt: |
|
||||
I have the following JSON data representing a list of albums from Spotify:
|
||||
|
||||
{
|
||||
"items": [
|
||||
{
|
||||
"album_type": "album",
|
||||
"artists": [
|
||||
{
|
||||
"external_urls": {
|
||||
"spotify": "https://open.spotify.com/artist/06HL4z0CvFAxyc27GXpf02"
|
||||
},
|
||||
"href": "https://api.spotify.com/v1/artists/06HL4z0CvFAxyc27GXpf02",
|
||||
"id": "06HL4z0CvFAxyc27GXpf02",
|
||||
"name": "Taylor Swift",
|
||||
"type": "artist",
|
||||
"uri": "spotify:artist:06HL4z0CvFAxyc27GXpf02"
|
||||
}
|
||||
],
|
||||
"available_markets": [ /* ... markets omitted for brevity ... */ ],
|
||||
"external_urls": {
|
||||
"spotify": "https://open.spotify.com/album/1Mo4aZ8pdj6L1jx8zSwJnt"
|
||||
},
|
||||
"href": "https://api.spotify.com/v1/albums/1Mo4aZ8pdj6L1jx8zSwJnt",
|
||||
"id": "1Mo4aZ8pdj6L1jx8zSwJnt",
|
||||
"images": [
|
||||
{
|
||||
"height": 300,
|
||||
"url": "https://i.scdn.co/image/ab67616d00001e025076e4160d018e378f488c33",
|
||||
"width": 300
|
||||
},
|
||||
{
|
||||
"height": 64,
|
||||
"url": "https://i.scdn.co/image/ab67616d000048515076e4160d018e378f488c33",
|
||||
"width": 64
|
||||
},
|
||||
{
|
||||
"height": 640,
|
||||
"url": "https://i.scdn.co/image/ab67616d0000b2735076e4160d018e378f488c33",
|
||||
"width": 640
|
||||
}
|
||||
],
|
||||
"name": "THE TORTURED POETS DEPARTMENT",
|
||||
"release_date": "2024-04-18",
|
||||
"release_date_precision": "day",
|
||||
"total_tracks": 16,
|
||||
"type": "album",
|
||||
"uri": "spotify:album:1Mo4aZ8pdj6L1jx8zSwJnt"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
Please convert this JSON into Markdown with the following layout for each album:
|
||||
|
||||
- Display the album image (using Markdown image syntax) first.
|
||||
- On the next line immediately after the image, display the album title, artist name (use the first artist listed), and the release date, all separated by a hyphen or another clear delimiter.
|
||||
- On the next line, provide the Spotify link (using Markdown link syntax).
|
||||
|
||||
For example, the output should look similar to this (using the data above):
|
||||
|
||||
|
||||
**THE TORTURED POETS DEPARTMENT**
|
||||
Taylor Swift - 2024-04-18
|
||||
[Listen on Spotify](https://open.spotify.com/album/1Mo4aZ8pdj6L1jx8zSwJnt)
|
||||
Arist Id: 06HL4z0CvFAxyc27GXpf02
|
||||
<hr>
|
||||
|
||||
Make sure your output is valid Markdown. And don't say "formatted in Markdown". Thanks!
|
||||
|
||||
llm_providers:
|
||||
- name: openai
|
||||
provider_interface: openai
|
||||
access_key: $OPENAI_API_KEY
|
||||
model: gpt-4o
|
||||
default: true
|
||||
|
||||
prompt_targets:
|
||||
- name: get_new_releases
|
||||
description: Get a list of new album releases featured in Spotify (shown, for example, on a Spotify player’s “Browse” tab).
|
||||
parameters:
|
||||
- name: country
|
||||
description: the country where the album is released
|
||||
required: true
|
||||
type: str
|
||||
in_path: true
|
||||
- name: limit
|
||||
type: integer
|
||||
description: The maximum number of results to return
|
||||
default: "5"
|
||||
endpoint:
|
||||
name: spotify
|
||||
path: /v1/browse/new-releases
|
||||
http_headers:
|
||||
Authorization: "Bearer $SPOTIFY_CLIENT_KEY"
|
||||
|
||||
- name: get_artist_top_tracks
|
||||
description: Get information about an artist's top tracks
|
||||
parameters:
|
||||
- name: artist_id
|
||||
description: The ID of the artist.
|
||||
required: true
|
||||
type: str
|
||||
in_path: true
|
||||
endpoint:
|
||||
name: spotify
|
||||
path: /v1/artists/{artist_id}/top-tracks
|
||||
http_headers:
|
||||
Authorization: "Bearer $SPOTIFY_CLIENT_KEY"
|
||||
21
demos/use_cases/spotify_bearer_auth/docker-compose.yaml
Normal file
21
demos/use_cases/spotify_bearer_auth/docker-compose.yaml
Normal file
|
|
@ -0,0 +1,21 @@
|
|||
services:
|
||||
chatbot_ui:
|
||||
build:
|
||||
context: ../../shared/chatbot_ui
|
||||
ports:
|
||||
- "18080:8080"
|
||||
environment:
|
||||
# this is only because we are running the sample app in the same docker container environemtn as archgw
|
||||
- CHAT_COMPLETION_ENDPOINT=http://host.docker.internal:10000/v1
|
||||
extra_hosts:
|
||||
- "host.docker.internal:host-gateway"
|
||||
volumes:
|
||||
- ./arch_config.yaml:/app/arch_config.yaml
|
||||
|
||||
jaeger:
|
||||
build:
|
||||
context: ../../shared/jaeger
|
||||
ports:
|
||||
- "16686:16686"
|
||||
- "4317:4317"
|
||||
- "4318:4318"
|
||||
Some files were not shown because too many files have changed in this diff Show more
Loading…
Add table
Add a link
Reference in a new issue