mirror of
https://github.com/katanemo/plano.git
synced 2026-07-14 16:22:12 +02:00
better model names (#517)
This commit is contained in:
Adil Hafeez
GitHub
parent
4e2355965b
commit
a7fddf30f9
55 changed files with 979 additions and 483 deletions
|
|
@ -66,11 +66,16 @@ properties:
|
|||
properties:
|
||||
name:
|
||||
type: string
|
||||
# provider field is deprecated, use provider_interface instead
|
||||
provider:
|
||||
access_key:
|
||||
type: string
|
||||
model:
|
||||
type: string
|
||||
default:
|
||||
type: boolean
|
||||
base_url:
|
||||
type: string
|
||||
http_host:
|
||||
type: string
|
||||
enum:
|
||||
- openai
|
||||
provider_interface:
|
||||
type: string
|
||||
enum:
|
||||
|
|
@ -81,29 +86,22 @@ properties:
|
|||
- mistral
|
||||
- openai
|
||||
- gemini
|
||||
access_key:
|
||||
type: string
|
||||
model:
|
||||
type: string
|
||||
default:
|
||||
type: boolean
|
||||
# endpoint field is deprecated, use base_url instead
|
||||
endpoint:
|
||||
type: string
|
||||
base_url:
|
||||
type: string
|
||||
protocol:
|
||||
type: string
|
||||
enum:
|
||||
- http
|
||||
- https
|
||||
http_host:
|
||||
type: string
|
||||
usage:
|
||||
type: string
|
||||
routing_preferences:
|
||||
type: array
|
||||
items:
|
||||
type: object
|
||||
properties:
|
||||
name:
|
||||
type: string
|
||||
description:
|
||||
type: string
|
||||
additionalProperties: false
|
||||
required:
|
||||
- name
|
||||
- description
|
||||
additionalProperties: false
|
||||
required:
|
||||
- name
|
||||
- model
|
||||
overrides:
|
||||
type: object
|
||||
properties:
|
||||
|
|
|
|||
|
|
@ -5,16 +5,16 @@ import yaml
|
|||
from jsonschema import validate
|
||||
from urllib.parse import urlparse
|
||||
|
||||
ENVOY_CONFIG_TEMPLATE_FILE = os.getenv(
|
||||
"ENVOY_CONFIG_TEMPLATE_FILE", "envoy.template.yaml"
|
||||
)
|
||||
ARCH_CONFIG_FILE = os.getenv("ARCH_CONFIG_FILE", "/app/arch_config.yaml")
|
||||
ENVOY_CONFIG_FILE_RENDERED = os.getenv(
|
||||
"ENVOY_CONFIG_FILE_RENDERED", "/etc/envoy/envoy.yaml"
|
||||
)
|
||||
ARCH_CONFIG_SCHEMA_FILE = os.getenv(
|
||||
"ARCH_CONFIG_SCHEMA_FILE", "arch_config_schema.yaml"
|
||||
)
|
||||
|
||||
SUPPORTED_PROVIDERS = [
|
||||
"arch",
|
||||
"claude",
|
||||
"deepseek",
|
||||
"groq",
|
||||
"mistral",
|
||||
"openai",
|
||||
"gemini",
|
||||
]
|
||||
|
||||
|
||||
def get_endpoint_and_port(endpoint, protocol):
|
||||
|
|
@ -32,8 +32,22 @@ def get_endpoint_and_port(endpoint, protocol):
|
|||
|
||||
|
||||
def validate_and_render_schema():
|
||||
env = Environment(loader=FileSystemLoader("./"))
|
||||
template = env.get_template("envoy.template.yaml")
|
||||
ENVOY_CONFIG_TEMPLATE_FILE = os.getenv(
|
||||
"ENVOY_CONFIG_TEMPLATE_FILE", "envoy.template.yaml"
|
||||
)
|
||||
ARCH_CONFIG_FILE = os.getenv("ARCH_CONFIG_FILE", "/app/arch_config.yaml")
|
||||
ARCH_CONFIG_FILE_RENDERED = os.getenv(
|
||||
"ARCH_CONFIG_FILE_RENDERED", "/app/arch_config_rendered.yaml"
|
||||
)
|
||||
ENVOY_CONFIG_FILE_RENDERED = os.getenv(
|
||||
"ENVOY_CONFIG_FILE_RENDERED", "/etc/envoy/envoy.yaml"
|
||||
)
|
||||
ARCH_CONFIG_SCHEMA_FILE = os.getenv(
|
||||
"ARCH_CONFIG_SCHEMA_FILE", "arch_config_schema.yaml"
|
||||
)
|
||||
|
||||
env = Environment(loader=FileSystemLoader(os.getenv("TEMPLATE_ROOT", "./")))
|
||||
template = env.get_template(ENVOY_CONFIG_TEMPLATE_FILE)
|
||||
|
||||
try:
|
||||
validate_prompt_config(ARCH_CONFIG_FILE, ARCH_CONFIG_SCHEMA_FILE)
|
||||
|
|
@ -82,6 +96,8 @@ def validate_and_render_schema():
|
|||
updated_llm_providers = []
|
||||
llm_provider_name_set = set()
|
||||
llms_with_usage = []
|
||||
model_name_keys = set()
|
||||
model_usage_name_keys = set()
|
||||
for llm_provider in config_yaml["llm_providers"]:
|
||||
if llm_provider.get("usage", None):
|
||||
llms_with_usage.append(llm_provider["name"])
|
||||
|
|
@ -89,10 +105,52 @@ def validate_and_render_schema():
|
|||
raise Exception(
|
||||
f"Duplicate llm_provider name {llm_provider.get('name')}, please provide unique name for each llm_provider"
|
||||
)
|
||||
if llm_provider.get("name") is None:
|
||||
|
||||
model_name = llm_provider.get("model")
|
||||
if model_name in model_name_keys:
|
||||
raise Exception(
|
||||
f"llm_provider name is required, please provide name for llm_provider"
|
||||
f"Duplicate model name {model_name}, please provide unique model name for each llm_provider"
|
||||
)
|
||||
model_name_keys.add(model_name)
|
||||
if llm_provider.get("name") is None:
|
||||
llm_provider["name"] = model_name
|
||||
|
||||
model_name_tokens = model_name.split("/")
|
||||
if len(model_name_tokens) < 2:
|
||||
raise Exception(
|
||||
f"Invalid model name {model_name}. Please provide model name in the format <provider>/<model_id>."
|
||||
)
|
||||
provider = model_name_tokens[0]
|
||||
model_id = "/".join(model_name_tokens[1:])
|
||||
if provider not in SUPPORTED_PROVIDERS:
|
||||
if (
|
||||
llm_provider.get("base_url", None) is None
|
||||
or llm_provider.get("provider_interface", None) is None
|
||||
):
|
||||
raise Exception(
|
||||
f"Must provide base_url and provider_interface for unsupported provider {provider} for model {model_name}. Supported providers are: {', '.join(SUPPORTED_PROVIDERS)}"
|
||||
)
|
||||
provider = llm_provider.get("provider_interface", None)
|
||||
elif llm_provider.get("provider_interface", None) is not None:
|
||||
raise Exception(
|
||||
f"Please provide provider interface as part of model name {model_name} using the format <provider>/<model_id>. For example, use 'openai/gpt-3.5-turbo' instead of 'gpt-3.5-turbo' "
|
||||
)
|
||||
|
||||
if model_id in model_name_keys:
|
||||
raise Exception(
|
||||
f"Duplicate model_id {model_id}, please provide unique model_id for each llm_provider"
|
||||
)
|
||||
model_name_keys.add(model_id)
|
||||
|
||||
for routing_preference in llm_provider.get("routing_preferences", []):
|
||||
if routing_preference.get("name") in model_usage_name_keys:
|
||||
raise Exception(
|
||||
f"Duplicate routing preference name \"{routing_preference.get('name')}\", please provide unique name for each routing preference"
|
||||
)
|
||||
model_usage_name_keys.add(routing_preference.get("name"))
|
||||
|
||||
llm_provider["model"] = model_id
|
||||
llm_provider["provider_interface"] = provider
|
||||
llm_provider_name_set.add(llm_provider.get("name"))
|
||||
provider = None
|
||||
if llm_provider.get("provider") and llm_provider.get("provider_interface"):
|
||||
|
|
@ -105,21 +163,14 @@ def validate_and_render_schema():
|
|||
del llm_provider["provider"]
|
||||
updated_llm_providers.append(llm_provider)
|
||||
|
||||
if llm_provider.get("endpoint") and llm_provider.get("base_url"):
|
||||
raise Exception("Please provide either endpoint or base_url, not both")
|
||||
|
||||
if llm_provider.get("endpoint", None):
|
||||
endpoint = llm_provider["endpoint"]
|
||||
protocol = llm_provider.get("protocol", "http")
|
||||
llm_provider["endpoint"], llm_provider["port"] = get_endpoint_and_port(
|
||||
endpoint, protocol
|
||||
)
|
||||
llms_with_endpoint.append(llm_provider)
|
||||
elif llm_provider.get("base_url", None):
|
||||
if llm_provider.get("base_url", None):
|
||||
base_url = llm_provider["base_url"]
|
||||
urlparse_result = urlparse(base_url)
|
||||
if llm_provider.get("port"):
|
||||
raise Exception("Please provider port in base_url")
|
||||
url_path = urlparse_result.path
|
||||
if url_path and url_path != "/":
|
||||
raise Exception(
|
||||
f"Please provide base_url without path, got {base_url}. Use base_url like 'http://example.com' instead of 'http://example.com/path'."
|
||||
)
|
||||
if urlparse_result.scheme == "" or urlparse_result.scheme not in [
|
||||
"http",
|
||||
"https",
|
||||
|
|
@ -140,7 +191,7 @@ def validate_and_render_schema():
|
|||
llm_provider["protocol"] = protocol
|
||||
llms_with_endpoint.append(llm_provider)
|
||||
|
||||
if len(llms_with_usage) > 0:
|
||||
if len(model_usage_name_keys) > 0:
|
||||
routing_llm_provider = config_yaml.get("routing", {}).get("llm_provider", None)
|
||||
if routing_llm_provider and routing_llm_provider not in llm_provider_name_set:
|
||||
raise Exception(
|
||||
|
|
@ -198,6 +249,7 @@ def validate_and_render_schema():
|
|||
agent_orchestrator = list(endpoints.keys())[0]
|
||||
|
||||
print("agent_orchestrator: ", agent_orchestrator)
|
||||
|
||||
data = {
|
||||
"prompt_gateway_listener": prompt_gateway_listener,
|
||||
"llm_gateway_listener": llm_gateway_listener,
|
||||
|
|
@ -216,6 +268,9 @@ def validate_and_render_schema():
|
|||
with open(ENVOY_CONFIG_FILE_RENDERED, "w") as file:
|
||||
file.write(rendered)
|
||||
|
||||
with open(ARCH_CONFIG_FILE_RENDERED, "w") as file:
|
||||
file.write(arch_config_string)
|
||||
|
||||
|
||||
def validate_prompt_config(arch_config_file, arch_config_schema_file):
|
||||
with open(arch_config_file, "r") as file:
|
||||
|
|
@ -231,7 +286,7 @@ def validate_prompt_config(arch_config_file, arch_config_schema_file):
|
|||
validate(config_yaml, config_schema_yaml)
|
||||
except Exception as e:
|
||||
print(
|
||||
f"Error validating arch_config file: {arch_config_file}, schema file: {arch_config_schema_file}, error: {e.message}"
|
||||
f"Error validating arch_config file: {arch_config_file}, schema file: {arch_config_schema_file}, error: {e}"
|
||||
)
|
||||
raise e
|
||||
|
||||
|
|
|
|||
134
arch/tools/poetry.lock
generated
134
arch/tools/poetry.lock
generated
|
|
@ -57,6 +57,34 @@ files = [
|
|||
{file = "colorama-0.4.6.tar.gz", hash = "sha256:08695f5cb7ed6e0531a20572697297273c47b8cae5a63ffc6d6ed5c201be6e44"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "exceptiongroup"
|
||||
version = "1.3.0"
|
||||
description = "Backport of PEP 654 (exception groups)"
|
||||
optional = false
|
||||
python-versions = ">=3.7"
|
||||
files = [
|
||||
{file = "exceptiongroup-1.3.0-py3-none-any.whl", hash = "sha256:4d111e6e0c13d0644cad6ddaa7ed0261a0b36971f6d23e7ec9b4b9097da78a10"},
|
||||
{file = "exceptiongroup-1.3.0.tar.gz", hash = "sha256:b241f5885f560bc56a59ee63ca4c6a8bfa46ae4ad651af316d4e81817bb9fd88"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
typing-extensions = {version = ">=4.6.0", markers = "python_version < \"3.13\""}
|
||||
|
||||
[package.extras]
|
||||
test = ["pytest (>=6)"]
|
||||
|
||||
[[package]]
|
||||
name = "iniconfig"
|
||||
version = "2.1.0"
|
||||
description = "brain-dead simple config-ini parsing"
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
files = [
|
||||
{file = "iniconfig-2.1.0-py3-none-any.whl", hash = "sha256:9deba5723312380e77435581c6bf4935c94cbfab9b1ed33ef8d238ea168eb760"},
|
||||
{file = "iniconfig-2.1.0.tar.gz", hash = "sha256:3abbd2e30b36733fee78f9c7f7308f2d0050e88f0087fd25c2645f63c773e1c7"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "jinja2"
|
||||
version = "3.1.6"
|
||||
|
|
@ -179,6 +207,69 @@ files = [
|
|||
{file = "markupsafe-3.0.2.tar.gz", hash = "sha256:ee55d3edf80167e48ea11a923c7386f4669df67d7994554387f84e7d8b0a2bf0"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "packaging"
|
||||
version = "25.0"
|
||||
description = "Core utilities for Python packages"
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
files = [
|
||||
{file = "packaging-25.0-py3-none-any.whl", hash = "sha256:29572ef2b1f17581046b3a2227d5c611fb25ec70ca1ba8554b24b0e69331a484"},
|
||||
{file = "packaging-25.0.tar.gz", hash = "sha256:d443872c98d677bf60f6a1f2f8c1cb748e8fe762d2bf9d3148b5599295b0fc4f"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "pluggy"
|
||||
version = "1.6.0"
|
||||
description = "plugin and hook calling mechanisms for python"
|
||||
optional = false
|
||||
python-versions = ">=3.9"
|
||||
files = [
|
||||
{file = "pluggy-1.6.0-py3-none-any.whl", hash = "sha256:e920276dd6813095e9377c0bc5566d94c932c33b27a3e3945d8389c374dd4746"},
|
||||
{file = "pluggy-1.6.0.tar.gz", hash = "sha256:7dcc130b76258d33b90f61b658791dede3486c3e6bfb003ee5c9bfb396dd22f3"},
|
||||
]
|
||||
|
||||
[package.extras]
|
||||
dev = ["pre-commit", "tox"]
|
||||
testing = ["coverage", "pytest", "pytest-benchmark"]
|
||||
|
||||
[[package]]
|
||||
name = "pygments"
|
||||
version = "2.19.2"
|
||||
description = "Pygments is a syntax highlighting package written in Python."
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
files = [
|
||||
{file = "pygments-2.19.2-py3-none-any.whl", hash = "sha256:86540386c03d588bb81d44bc3928634ff26449851e99741617ecb9037ee5ec0b"},
|
||||
{file = "pygments-2.19.2.tar.gz", hash = "sha256:636cb2477cec7f8952536970bc533bc43743542f70392ae026374600add5b887"},
|
||||
]
|
||||
|
||||
[package.extras]
|
||||
windows-terminal = ["colorama (>=0.4.6)"]
|
||||
|
||||
[[package]]
|
||||
name = "pytest"
|
||||
version = "8.4.1"
|
||||
description = "pytest: simple powerful testing with Python"
|
||||
optional = false
|
||||
python-versions = ">=3.9"
|
||||
files = [
|
||||
{file = "pytest-8.4.1-py3-none-any.whl", hash = "sha256:539c70ba6fcead8e78eebbf1115e8b589e7565830d7d006a8723f19ac8a0afb7"},
|
||||
{file = "pytest-8.4.1.tar.gz", hash = "sha256:7c67fd69174877359ed9371ec3af8a3d2b04741818c51e5e99cc1742251fa93c"},
|
||||
]
|
||||
|
||||
[package.dependencies]
|
||||
colorama = {version = ">=0.4", markers = "sys_platform == \"win32\""}
|
||||
exceptiongroup = {version = ">=1", markers = "python_version < \"3.11\""}
|
||||
iniconfig = ">=1"
|
||||
packaging = ">=20"
|
||||
pluggy = ">=1.5,<2"
|
||||
pygments = ">=2.7.2"
|
||||
tomli = {version = ">=1", markers = "python_version < \"3.11\""}
|
||||
|
||||
[package.extras]
|
||||
dev = ["argcomplete", "attrs (>=19.2)", "hypothesis (>=3.56)", "mock", "requests", "setuptools", "xmlschema"]
|
||||
|
||||
[[package]]
|
||||
name = "pyyaml"
|
||||
version = "6.0.2"
|
||||
|
|
@ -430,6 +521,47 @@ enabler = ["pytest-enabler (>=2.2)"]
|
|||
test = ["build[virtualenv] (>=1.0.3)", "filelock (>=3.4.0)", "ini2toml[lite] (>=0.14)", "jaraco.develop (>=7.21)", "jaraco.envs (>=2.2)", "jaraco.path (>=3.2.0)", "jaraco.test (>=5.5)", "packaging (>=24.2)", "pip (>=19.1)", "pyproject-hooks (!=1.1)", "pytest (>=6,!=8.1.*)", "pytest-home (>=0.5)", "pytest-perf", "pytest-subprocess", "pytest-timeout", "pytest-xdist (>=3)", "tomli-w (>=1.0.0)", "virtualenv (>=13.0.0)", "wheel (>=0.44.0)"]
|
||||
type = ["importlib-metadata (>=7.0.2)", "jaraco.develop (>=7.21)", "mypy (>=1.12,<1.14)", "pytest-mypy"]
|
||||
|
||||
[[package]]
|
||||
name = "tomli"
|
||||
version = "2.2.1"
|
||||
description = "A lil' TOML parser"
|
||||
optional = false
|
||||
python-versions = ">=3.8"
|
||||
files = [
|
||||
{file = "tomli-2.2.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:678e4fa69e4575eb77d103de3df8a895e1591b48e740211bd1067378c69e8249"},
|
||||
{file = "tomli-2.2.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:023aa114dd824ade0100497eb2318602af309e5a55595f76b626d6d9f3b7b0a6"},
|
||||
{file = "tomli-2.2.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:ece47d672db52ac607a3d9599a9d48dcb2f2f735c6c2d1f34130085bb12b112a"},
|
||||
{file = "tomli-2.2.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:6972ca9c9cc9f0acaa56a8ca1ff51e7af152a9f87fb64623e31d5c83700080ee"},
|
||||
{file = "tomli-2.2.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c954d2250168d28797dd4e3ac5cf812a406cd5a92674ee4c8f123c889786aa8e"},
|
||||
{file = "tomli-2.2.1-cp311-cp311-musllinux_1_2_aarch64.whl", hash = "sha256:8dd28b3e155b80f4d54beb40a441d366adcfe740969820caf156c019fb5c7ec4"},
|
||||
{file = "tomli-2.2.1-cp311-cp311-musllinux_1_2_i686.whl", hash = "sha256:e59e304978767a54663af13c07b3d1af22ddee3bb2fb0618ca1593e4f593a106"},
|
||||
{file = "tomli-2.2.1-cp311-cp311-musllinux_1_2_x86_64.whl", hash = "sha256:33580bccab0338d00994d7f16f4c4ec25b776af3ffaac1ed74e0b3fc95e885a8"},
|
||||
{file = "tomli-2.2.1-cp311-cp311-win32.whl", hash = "sha256:465af0e0875402f1d226519c9904f37254b3045fc5084697cefb9bdde1ff99ff"},
|
||||
{file = "tomli-2.2.1-cp311-cp311-win_amd64.whl", hash = "sha256:2d0f2fdd22b02c6d81637a3c95f8cd77f995846af7414c5c4b8d0545afa1bc4b"},
|
||||
{file = "tomli-2.2.1-cp312-cp312-macosx_10_13_x86_64.whl", hash = "sha256:4a8f6e44de52d5e6c657c9fe83b562f5f4256d8ebbfe4ff922c495620a7f6cea"},
|
||||
{file = "tomli-2.2.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:8d57ca8095a641b8237d5b079147646153d22552f1c637fd3ba7f4b0b29167a8"},
|
||||
{file = "tomli-2.2.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4e340144ad7ae1533cb897d406382b4b6fede8890a03738ff1683af800d54192"},
|
||||
{file = "tomli-2.2.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:db2b95f9de79181805df90bedc5a5ab4c165e6ec3fe99f970d0e302f384ad222"},
|
||||
{file = "tomli-2.2.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:40741994320b232529c802f8bc86da4e1aa9f413db394617b9a256ae0f9a7f77"},
|
||||
{file = "tomli-2.2.1-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:400e720fe168c0f8521520190686ef8ef033fb19fc493da09779e592861b78c6"},
|
||||
{file = "tomli-2.2.1-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:02abe224de6ae62c19f090f68da4e27b10af2b93213d36cf44e6e1c5abd19fdd"},
|
||||
{file = "tomli-2.2.1-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:b82ebccc8c8a36f2094e969560a1b836758481f3dc360ce9a3277c65f374285e"},
|
||||
{file = "tomli-2.2.1-cp312-cp312-win32.whl", hash = "sha256:889f80ef92701b9dbb224e49ec87c645ce5df3fa2cc548664eb8a25e03127a98"},
|
||||
{file = "tomli-2.2.1-cp312-cp312-win_amd64.whl", hash = "sha256:7fc04e92e1d624a4a63c76474610238576942d6b8950a2d7f908a340494e67e4"},
|
||||
{file = "tomli-2.2.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:f4039b9cbc3048b2416cc57ab3bda989a6fcf9b36cf8937f01a6e731b64f80d7"},
|
||||
{file = "tomli-2.2.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:286f0ca2ffeeb5b9bd4fcc8d6c330534323ec51b2f52da063b11c502da16f30c"},
|
||||
{file = "tomli-2.2.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a92ef1a44547e894e2a17d24e7557a5e85a9e1d0048b0b5e7541f76c5032cb13"},
|
||||
{file = "tomli-2.2.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:9316dc65bed1684c9a98ee68759ceaed29d229e985297003e494aa825ebb0281"},
|
||||
{file = "tomli-2.2.1-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:e85e99945e688e32d5a35c1ff38ed0b3f41f43fad8df0bdf79f72b2ba7bc5272"},
|
||||
{file = "tomli-2.2.1-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:ac065718db92ca818f8d6141b5f66369833d4a80a9d74435a268c52bdfa73140"},
|
||||
{file = "tomli-2.2.1-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:d920f33822747519673ee656a4b6ac33e382eca9d331c87770faa3eef562aeb2"},
|
||||
{file = "tomli-2.2.1-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:a198f10c4d1b1375d7687bc25294306e551bf1abfa4eace6650070a5c1ae2744"},
|
||||
{file = "tomli-2.2.1-cp313-cp313-win32.whl", hash = "sha256:d3f5614314d758649ab2ab3a62d4f2004c825922f9e370b29416484086b264ec"},
|
||||
{file = "tomli-2.2.1-cp313-cp313-win_amd64.whl", hash = "sha256:a38aa0308e754b0e3c67e344754dff64999ff9b513e691d0e786265c93583c69"},
|
||||
{file = "tomli-2.2.1-py3-none-any.whl", hash = "sha256:cb55c73c5f4408779d0cf3eef9f762b9c9f147a77de7b258bef0a5628adc85cc"},
|
||||
{file = "tomli-2.2.1.tar.gz", hash = "sha256:cd45e1dc79c835ce60f7404ec8119f2eb06d38b1deba146f07ced3bbc44505ff"},
|
||||
]
|
||||
|
||||
[[package]]
|
||||
name = "typing-extensions"
|
||||
version = "4.14.1"
|
||||
|
|
@ -444,4 +576,4 @@ files = [
|
|||
[metadata]
|
||||
lock-version = "2.0"
|
||||
python-versions = "^3.10"
|
||||
content-hash = "7d17c2f24f8ad4503a5248c3f7e1a74f458a5ea55a2fb63db382cb6abe6d52df"
|
||||
content-hash = "83d32fa807f6c7058ecbfc43b777c4d4c637695025cf774ff10532bff8f6712b"
|
||||
|
|
|
|||
|
|
@ -20,6 +20,13 @@ pyyaml = "^6.0.2"
|
|||
[tool.poetry.scripts]
|
||||
archgw = "cli.main:main"
|
||||
|
||||
[tool.poetry.group.dev.dependencies]
|
||||
pytest = "^8.4.1"
|
||||
|
||||
[build-system]
|
||||
requires = ["poetry-core>=1.0.0"]
|
||||
build-backend = "poetry.core.masonry.api"
|
||||
|
||||
|
||||
[tool.pytest.ini_options]
|
||||
addopts = ["-v"]
|
||||
|
|
|
|||
|
|
@ -1,45 +0,0 @@
|
|||
from fastapi import FastAPI
|
||||
from pydantic import BaseModel
|
||||
from typing import List, Dict, Set
|
||||
|
||||
app = FastAPI()
|
||||
|
||||
|
||||
class User(BaseModel):
|
||||
name: str = Field(
|
||||
"John Doe", description="The name of the user."
|
||||
) # Default value and description for name
|
||||
location: int = None
|
||||
age: int = Field(
|
||||
30, description="The age of the user."
|
||||
) # Default value and description for age
|
||||
tags: Set[str] = Field(
|
||||
default_factory=set, description="A set of tags associated with the user."
|
||||
) # Default empty set and description for tags
|
||||
metadata: Dict[str, int] = Field(
|
||||
default_factory=dict,
|
||||
description="A dictionary storing metadata about the user, with string keys and integer values.",
|
||||
) # Default empty dict and description for metadata
|
||||
|
||||
|
||||
@app.get("/agent/default")
|
||||
async def default(request: User):
|
||||
"""
|
||||
This endpoint handles information extraction queries.
|
||||
It can summarize, extract details, and perform various other information-related tasks.
|
||||
"""
|
||||
return {"info": f"Query: {request.name}, Count: {request.age}"}
|
||||
|
||||
|
||||
@app.post("/agent/action")
|
||||
async def reboot_network_device(device_id: str, confirmation: str):
|
||||
"""
|
||||
This endpoint reboots a network device based on the device ID.
|
||||
Confirmation is required to proceed with the reboot.
|
||||
|
||||
Args:
|
||||
device_id: The device_id that you want to reboot.
|
||||
confirmation: The confirmation that the user wants to reboot.
|
||||
metadata: Ignore this parameter
|
||||
"""
|
||||
return {"status": "Device rebooted", "device_id": device_id}
|
||||
|
|
@ -1,33 +0,0 @@
|
|||
prompt_targets:
|
||||
- name: default
|
||||
path: /agent/default
|
||||
description: "This endpoint handles information extraction queries.\n It can\
|
||||
\ summarize, extract details, and perform various other information-related tasks."
|
||||
parameters:
|
||||
- name: query
|
||||
type: str
|
||||
description: Field from Pydantic model DefaultRequest
|
||||
default_value: null
|
||||
required: false
|
||||
- name: count
|
||||
type: int
|
||||
description: Field from Pydantic model DefaultRequest
|
||||
default_value: null
|
||||
required: false
|
||||
type: default
|
||||
auto-llm-dispatch-on-response: true
|
||||
- name: reboot_network_device
|
||||
path: /agent/action
|
||||
description: "This endpoint reboots a network device based on the device ID.\n \
|
||||
\ Confirmation is required to proceed with the reboot."
|
||||
parameters:
|
||||
- name: device_id
|
||||
type: str
|
||||
description: Description for device_id
|
||||
default_value: ''
|
||||
required: true
|
||||
- name: confirmation
|
||||
type: int
|
||||
description: Description for confirmation
|
||||
default_value: ''
|
||||
required: true
|
||||
|
|
@ -1,42 +0,0 @@
|
|||
import pytest
|
||||
from click.testing import CliRunner
|
||||
from tools.cli.main import main # Import your CLI's entry point
|
||||
import importlib.metadata
|
||||
|
||||
|
||||
def get_version():
|
||||
"""Helper function to fetch the version."""
|
||||
try:
|
||||
version = importlib.metadata.version("archgw")
|
||||
return version
|
||||
except importlib.metadata.PackageNotFoundError:
|
||||
return None
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def runner():
|
||||
"""Fixture to create a Click test runner."""
|
||||
return CliRunner()
|
||||
|
||||
|
||||
def test_version_option(runner):
|
||||
"""Test the --version option."""
|
||||
result = runner.invoke(main, ["--version"])
|
||||
assert result.exit_code == 0
|
||||
expected_version = get_version()
|
||||
assert f"archgw cli version: {expected_version}" in result.output
|
||||
|
||||
|
||||
def test_default_behavior(runner):
|
||||
"""Test the default behavior when no command is provided."""
|
||||
result = runner.invoke(main)
|
||||
assert result.exit_code == 0
|
||||
assert "Arch (The Intelligent Prompt Gateway) CLI" in result.output
|
||||
assert "Usage:" in result.output # Ensure help text is shown
|
||||
|
||||
|
||||
def test_invalid_command(runner):
|
||||
"""Test that an invalid command returns an appropriate error message."""
|
||||
result = runner.invoke(main, ["invalid_command"])
|
||||
assert result.exit_code != 0 # Non-zero exit code for invalid command
|
||||
assert "Error: No such command 'invalid_command'" in result.output
|
||||
272
arch/tools/test/test_config_generator.py
Normal file
272
arch/tools/test/test_config_generator.py
Normal file
|
|
@ -0,0 +1,272 @@
|
|||
import pytest
|
||||
from unittest import mock
|
||||
import sys
|
||||
from cli.config_generator import validate_and_render_schema
|
||||
|
||||
# Patch sys.path to allow import from cli/
|
||||
import os
|
||||
|
||||
sys.path.insert(
|
||||
0, os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "cli"))
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def cleanup_env(monkeypatch):
|
||||
# Clean up environment variables and mocks after each test
|
||||
yield
|
||||
monkeypatch.undo()
|
||||
|
||||
|
||||
def test_validate_and_render_happy_path(monkeypatch):
|
||||
monkeypatch.setenv("ARCH_CONFIG_FILE", "fake_arch_config.yaml")
|
||||
monkeypatch.setenv("ARCH_CONFIG_SCHEMA_FILE", "fake_arch_config_schema.yaml")
|
||||
monkeypatch.setenv("ENVOY_CONFIG_TEMPLATE_FILE", "./envoy.template.yaml")
|
||||
monkeypatch.setenv("ARCH_CONFIG_FILE_RENDERED", "fake_arch_config_rendered.yaml")
|
||||
monkeypatch.setenv("ENVOY_CONFIG_FILE_RENDERED", "fake_envoy.yaml")
|
||||
monkeypatch.setenv("TEMPLATE_ROOT", "../")
|
||||
|
||||
arch_config = """
|
||||
version: v0.1.0
|
||||
|
||||
listeners:
|
||||
egress_traffic:
|
||||
address: 0.0.0.0
|
||||
port: 12000
|
||||
message_format: openai
|
||||
timeout: 30s
|
||||
|
||||
llm_providers:
|
||||
|
||||
- model: openai/gpt-4o-mini
|
||||
access_key: $OPENAI_API_KEY
|
||||
default: true
|
||||
|
||||
- model: openai/gpt-4o
|
||||
access_key: $OPENAI_API_KEY
|
||||
routing_preferences:
|
||||
- name: code understanding
|
||||
description: understand and explain existing code snippets, functions, or libraries
|
||||
|
||||
- model: openai/gpt-4.1
|
||||
access_key: $OPENAI_API_KEY
|
||||
routing_preferences:
|
||||
- name: code generation
|
||||
description: generating new code snippets, functions, or boilerplate based on user prompts or requirements
|
||||
|
||||
tracing:
|
||||
random_sampling: 100
|
||||
"""
|
||||
arch_config_schema = ""
|
||||
with open("../arch_config_schema.yaml", "r") as file:
|
||||
arch_config_schema = file.read()
|
||||
|
||||
m_open = mock.mock_open()
|
||||
# Provide enough file handles for all open() calls in validate_and_render_schema
|
||||
m_open.side_effect = [
|
||||
mock.mock_open(read_data="").return_value,
|
||||
mock.mock_open(read_data=arch_config).return_value, # ARCH_CONFIG_FILE
|
||||
mock.mock_open(
|
||||
read_data=arch_config_schema
|
||||
).return_value, # ARCH_CONFIG_SCHEMA_FILE
|
||||
mock.mock_open(read_data=arch_config).return_value, # ARCH_CONFIG_FILE
|
||||
mock.mock_open(
|
||||
read_data=arch_config_schema
|
||||
).return_value, # ARCH_CONFIG_SCHEMA_FILE
|
||||
mock.mock_open().return_value, # ENVOY_CONFIG_FILE_RENDERED (write)
|
||||
mock.mock_open().return_value, # ARCH_CONFIG_FILE_RENDERED (write)
|
||||
]
|
||||
with mock.patch("builtins.open", m_open):
|
||||
with mock.patch("config_generator.Environment"):
|
||||
validate_and_render_schema()
|
||||
|
||||
|
||||
arch_config_test_cases = [
|
||||
{
|
||||
"id": "duplicate_provider_name",
|
||||
"expected_error": "Duplicate llm_provider name",
|
||||
"arch_config": """
|
||||
version: v0.1.0
|
||||
|
||||
listeners:
|
||||
egress_traffic:
|
||||
address: 0.0.0.0
|
||||
port: 12000
|
||||
message_format: openai
|
||||
timeout: 30s
|
||||
|
||||
llm_providers:
|
||||
|
||||
- name: test1
|
||||
model: openai/gpt-4o
|
||||
access_key: $OPENAI_API_KEY
|
||||
|
||||
- name: test1
|
||||
model: openai/gpt-4o
|
||||
access_key: $OPENAI_API_KEY
|
||||
|
||||
""",
|
||||
},
|
||||
{
|
||||
"id": "provider_interface_with_model_id",
|
||||
"expected_error": "Please provide provider interface as part of model name",
|
||||
"arch_config": """
|
||||
version: v0.1.0
|
||||
|
||||
listeners:
|
||||
egress_traffic:
|
||||
address: 0.0.0.0
|
||||
port: 12000
|
||||
message_format: openai
|
||||
timeout: 30s
|
||||
|
||||
llm_providers:
|
||||
|
||||
- model: openai/gpt-4o
|
||||
access_key: $OPENAI_API_KEY
|
||||
provider_interface: openai
|
||||
|
||||
""",
|
||||
},
|
||||
{
|
||||
"id": "duplicate_model_id",
|
||||
"expected_error": "Duplicate model_id",
|
||||
"arch_config": """
|
||||
version: v0.1.0
|
||||
|
||||
listeners:
|
||||
egress_traffic:
|
||||
address: 0.0.0.0
|
||||
port: 12000
|
||||
message_format: openai
|
||||
timeout: 30s
|
||||
|
||||
llm_providers:
|
||||
|
||||
- model: openai/gpt-4o
|
||||
access_key: $OPENAI_API_KEY
|
||||
|
||||
- model: mistral/gpt-4o
|
||||
|
||||
""",
|
||||
},
|
||||
{
|
||||
"id": "custom_provider_base_url",
|
||||
"expected_error": "Must provide base_url and provider_interface",
|
||||
"arch_config": """
|
||||
version: v0.1.0
|
||||
|
||||
listeners:
|
||||
egress_traffic:
|
||||
address: 0.0.0.0
|
||||
port: 12000
|
||||
message_format: openai
|
||||
timeout: 30s
|
||||
|
||||
llm_providers:
|
||||
|
||||
- model: custom/gpt-4o
|
||||
|
||||
""",
|
||||
},
|
||||
{
|
||||
"id": "base_url_no_prefix",
|
||||
"expected_error": "Please provide base_url without path",
|
||||
"arch_config": """
|
||||
version: v0.1.0
|
||||
|
||||
listeners:
|
||||
egress_traffic:
|
||||
address: 0.0.0.0
|
||||
port: 12000
|
||||
message_format: openai
|
||||
timeout: 30s
|
||||
|
||||
llm_providers:
|
||||
|
||||
- model: custom/gpt-4o
|
||||
base_url: "http://custom.com/test"
|
||||
provider_interface: openai
|
||||
|
||||
""",
|
||||
},
|
||||
{
|
||||
"id": "duplicate_routeing_preference_name",
|
||||
"expected_error": "Duplicate routing preference name",
|
||||
"arch_config": """
|
||||
version: v0.1.0
|
||||
|
||||
listeners:
|
||||
egress_traffic:
|
||||
address: 0.0.0.0
|
||||
port: 12000
|
||||
message_format: openai
|
||||
timeout: 30s
|
||||
|
||||
llm_providers:
|
||||
|
||||
- model: openai/gpt-4o-mini
|
||||
access_key: $OPENAI_API_KEY
|
||||
default: true
|
||||
|
||||
- model: openai/gpt-4o
|
||||
access_key: $OPENAI_API_KEY
|
||||
routing_preferences:
|
||||
- name: code understanding
|
||||
description: understand and explain existing code snippets, functions, or libraries
|
||||
|
||||
- model: openai/gpt-4.1
|
||||
access_key: $OPENAI_API_KEY
|
||||
routing_preferences:
|
||||
- name: code understanding
|
||||
description: generating new code snippets, functions, or boilerplate based on user prompts or requirements
|
||||
|
||||
tracing:
|
||||
random_sampling: 100
|
||||
|
||||
""",
|
||||
},
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"arch_config_test_case",
|
||||
arch_config_test_cases,
|
||||
ids=[case["id"] for case in arch_config_test_cases],
|
||||
)
|
||||
def test_validate_and_render_schema_tests(monkeypatch, arch_config_test_case):
|
||||
monkeypatch.setenv("ARCH_CONFIG_FILE", "fake_arch_config.yaml")
|
||||
monkeypatch.setenv("ARCH_CONFIG_SCHEMA_FILE", "fake_arch_config_schema.yaml")
|
||||
monkeypatch.setenv("ENVOY_CONFIG_TEMPLATE_FILE", "./envoy.template.yaml")
|
||||
monkeypatch.setenv("ARCH_CONFIG_FILE_RENDERED", "fake_arch_config_rendered.yaml")
|
||||
monkeypatch.setenv("ENVOY_CONFIG_FILE_RENDERED", "fake_envoy.yaml")
|
||||
monkeypatch.setenv("TEMPLATE_ROOT", "../")
|
||||
|
||||
arch_config = arch_config_test_case["arch_config"]
|
||||
expected_error = arch_config_test_case["expected_error"]
|
||||
test_id = arch_config_test_case["id"]
|
||||
|
||||
arch_config_schema = ""
|
||||
with open("../arch_config_schema.yaml", "r") as file:
|
||||
arch_config_schema = file.read()
|
||||
|
||||
m_open = mock.mock_open()
|
||||
# Provide enough file handles for all open() calls in validate_and_render_schema
|
||||
m_open.side_effect = [
|
||||
mock.mock_open(read_data="").return_value,
|
||||
mock.mock_open(read_data=arch_config).return_value, # ARCH_CONFIG_FILE
|
||||
mock.mock_open(
|
||||
read_data=arch_config_schema
|
||||
).return_value, # ARCH_CONFIG_SCHEMA_FILE
|
||||
mock.mock_open(read_data=arch_config).return_value, # ARCH_CONFIG_FILE
|
||||
mock.mock_open(
|
||||
read_data=arch_config_schema
|
||||
).return_value, # ARCH_CONFIG_SCHEMA_FILE
|
||||
mock.mock_open().return_value, # ENVOY_CONFIG_FILE_RENDERED (write)
|
||||
mock.mock_open().return_value, # ARCH_CONFIG_FILE_RENDERED (write)
|
||||
]
|
||||
with mock.patch("builtins.open", m_open):
|
||||
with mock.patch("config_generator.Environment"):
|
||||
with pytest.raises(Exception) as excinfo:
|
||||
validate_and_render_schema()
|
||||
assert expected_error in str(excinfo.value)
|
||||
|
|
@ -3,11 +3,22 @@
|
|||
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 "Validating ${file}..."
|
||||
touch $(pwd)/${file}_rendered
|
||||
if ! docker run --rm -v "$(pwd)/${file}:/app/arch_config.yaml:ro" -v "$(pwd)/${file}_rendered:/app/arch_config_rendered.yaml:rw" --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
|
||||
RENDERED_CHECKED_IN_FILE=$(echo $file | sed 's/\.yaml$/_rendered.yaml/')
|
||||
if [ -f "$RENDERED_CHECKED_IN_FILE" ]; then
|
||||
echo "Checking rendered file against checked-in version..."
|
||||
if ! diff -q "${file}_rendered" "$RENDERED_CHECKED_IN_FILE" > /dev/null; then
|
||||
echo "Rendered file ${file}_rendered does not match checked-in version ${RENDERED_CHECKED_IN_FILE}"
|
||||
failed_files+=("${file}_rendered")
|
||||
else
|
||||
echo "Rendered file matches checked-in version."
|
||||
fi
|
||||
fi
|
||||
done
|
||||
|
||||
# Print summary of failed files
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue