forked from phoenix-oss/llama-stack-mirror
3a31611486
# What does this PR do? The goal is to have a fairly complete set of provider and e2e tests for /chat-completion and /completion. This is the current list, ``` grep -oE "def test_[a-zA-Z_+]*" llama_stack/providers/tests/inference/test_text_inference.py | cut -d' ' -f2 ``` - test_model_list - test_text_completion_non_streaming - test_text_completion_streaming - test_text_completion_logprobs_non_streaming - test_text_completion_logprobs_streaming - test_text_completion_structured_output - test_text_chat_completion_non_streaming - test_text_chat_completion_structured_output - test_text_chat_completion_streaming - test_text_chat_completion_with_tool_calling - test_text_chat_completion_with_tool_calling_streaming ``` grep -oE "def test_[a-zA-Z_+]*" tests/client-sdk/inference/test_text_inference.py | cut -d' ' -f2 ``` - test_text_completion_non_streaming - test_text_completion_streaming - test_text_completion_log_probs_non_streaming - test_text_completion_log_probs_streaming - test_text_completion_structured_output - test_text_chat_completion_non_streaming - test_text_chat_completion_streaming - test_text_chat_completion_with_tool_calling_and_non_streaming - test_text_chat_completion_with_tool_calling_and_streaming - test_text_chat_completion_with_tool_choice_required - test_text_chat_completion_with_tool_choice_none - test_text_chat_completion_structured_output - test_text_chat_completion_tool_calling_tools_not_in_request ## Test plan == Set up Ollama local server ``` OLLAMA_HOST=127.0.0.1:8321 with-proxy ollama serve OLLAMA_HOST=127.0.0.1:8321 ollama run llama3.2:3b-instruct-fp16 --keepalive 60m ``` == Run a provider test ``` conda activate stack OLLAMA_URL="http://localhost:8321" \ pytest -v -s -k "ollama" --inference-model="llama3.2:3b-instruct-fp16" \ llama_stack/providers/tests/inference/test_text_inference.py::TestInference ``` == Run an e2e test ``` conda activate sherpa with-proxy pip install llama-stack export INFERENCE_MODEL=llama3.2:3b-instruct-fp16 export LLAMA_STACK_PORT=8322 with-proxy llama stack build --template ollama with-proxy llama stack run --env OLLAMA_URL=http://localhost:8321 ollama ``` ``` conda activate stack LLAMA_STACK_PORT=8322 LLAMA_STACK_BASE_URL="http://localhost:8322" \ pytest -v -s --inference-model="llama3.2:3b-instruct-fp16" \ tests/client-sdk/inference/test_text_inference.py ```
39 lines
1.2 KiB
Python
39 lines
1.2 KiB
Python
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
|
# All rights reserved.
|
|
#
|
|
# This source code is licensed under the terms described in the LICENSE file in
|
|
# the root directory of this source tree.
|
|
|
|
import json
|
|
import pathlib
|
|
|
|
|
|
class TestCase:
|
|
_apis = [
|
|
"inference/chat_completion",
|
|
"inference/completion",
|
|
]
|
|
_jsonblob = {}
|
|
|
|
def __init__(self, name):
|
|
# loading all test cases
|
|
if self._jsonblob == {}:
|
|
for api in self._apis:
|
|
with open(pathlib.Path(__file__).parent / f"{api}.json", "r") as f:
|
|
coloned = api.replace("/", ":")
|
|
try:
|
|
loaded = json.load(f)
|
|
except json.JSONDecodeError as e:
|
|
raise ValueError(f"There is a syntax error in {api}.json: {e}") from e
|
|
TestCase._jsonblob.update({f"{coloned}:{k}": v for k, v in loaded.items()})
|
|
|
|
# loading this test case
|
|
tc = self._jsonblob.get(name)
|
|
if tc is None:
|
|
raise ValueError(f"Test case {name} not found")
|
|
|
|
# these are the only fields we need
|
|
self.data = tc.get("data")
|
|
|
|
def __getitem__(self, key):
|
|
return self.data[key]
|