📝 Update README with detailed instructions and references for local API testing

This commit is contained in:
2026-04-19 11:26:36 +08:00
parent 3c9ce684a9
commit 4de35240f3
3 changed files with 77 additions and 0 deletions

View File

@@ -1,7 +1,29 @@
# local-ai-test
## How to run?
Export environments then run:
```shell
uv run main.py
```
Run with `tiny-encrypt` environments:
```shell
tiny-encrypt -X -k $(cat ~/.config/envs/LCOAL_DEFAULT_TINY_ENCRYPT_KEY_ID) \
~/secrets/alibaba-cloud-ai-cn.env.tinyenc -- go run main.go
```
Use local llm-proxy:
```shell
OPENAI_API_BASE=http://127.0.0.1:8080/ python main.py
OPENAI_API_BASE=http://127.0.0.1:8080/ python main-stream.py
```
## Reference
- https://help.aliyun.com/zh/model-studio/stream - 大模型服务平台百炼 / 文本生成 / 流式输出

View File

@@ -0,0 +1,10 @@
_:
@just --list
alias r:=run
# Run main.py
run:
te -X -k $(cat ~/.config/envs/LCOAL_DEFAULT_TINY_ENCRYPT_KEY_ID) ~/secrets/alibaba-cloud-ai-cn.env.tinyenc -- uv run main.py

View File

@@ -0,0 +1,45 @@
import os
from pprint import pprint
from openai import OpenAI
from openai._types import Timeout
from openai.types.chat import ChatCompletionUserMessageParam, ChatCompletionSystemMessageParam
def main():
client = OpenAI(
api_key=os.environ.get("OPENAI_API_KEY", "sk-dummy"),
base_url=os.environ.get("OPENAI_API_BASE", "http://localhost:11434/v1"),
timeout=Timeout(30, connect=5),
)
response = client.chat.completions.create(
model=os.environ.get("OPENAI_MODEL", "qwen-math-turbo"),
messages=[
ChatCompletionSystemMessageParam(role="system", content="You are a useful assistant."),
# ChatCompletionUserMessageParam(**{"role": "user", "content": "Hello!"}),
ChatCompletionUserMessageParam(role="user", content="Hello!"),
],
stream=True,
# stream_options={"include_usage": True},
)
print()
pprint(vars(response))
print()
# print(response.choices[0].message.content)
for chunk in response:
print('xx')
if chunk.choices:
content = chunk.choices[0].delta.content or ""
print('CHUNK:', content, end="", flush=True)
# content_parts.append(content)
elif chunk.usage:
print("\n--- 请求用量 ---")
print(f"输入 Tokens: {chunk.usage.prompt_tokens}")
print(f"输出 Tokens: {chunk.usage.completion_tokens}")
print(f"总计 Tokens: {chunk.usage.total_tokens}")
if __name__ == "__main__":
main()