Skip to content

Let request params be changed via model config #16

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jan 27, 2025
Merged

Let request params be changed via model config #16

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 15 additions & 3 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,7 +23,11 @@ import asyncio
import any_llm_client


config = any_llm_client.OpenAIConfig(url="http://127.0.0.1:11434/v1/chat/completions", model_name="qwen2.5-coder:1.5b")
config = any_llm_client.OpenAIConfig(
url="http://127.0.0.1:11434/v1/chat/completions",
model_name="qwen2.5-coder:1.5b",
request_extra={"best_of": 3}
)


async def main() -> None:
Expand Down Expand Up @@ -52,7 +56,11 @@ import asyncio
import any_llm_client


config = any_llm_client.OpenAIConfig(url="http://127.0.0.1:11434/v1/chat/completions", model_name="qwen2.5-coder:1.5b")
config = any_llm_client.OpenAIConfig(
url="http://127.0.0.1:11434/v1/chat/completions",
model_name="qwen2.5-coder:1.5b",
request_extra={"best_of": 3}
)


async def main() -> None:
Expand Down Expand Up @@ -127,7 +135,8 @@ class Settings(pydantic_settings.BaseSettings):
os.environ["LLM_MODEL"] = """{
"api_type": "openai",
"url": "http://127.0.0.1:11434/v1/chat/completions",
"model_name": "qwen2.5-coder:1.5b"
"model_name": "qwen2.5-coder:1.5b",
"request_extra": {"best_of": 3}
}"""
settings = Settings()

Expand All @@ -146,6 +155,7 @@ config = any_llm_client.OpenAIConfig(
url=pydantic.HttpUrl("https://api.openai.com/v1/chat/completions"),
auth_token=os.environ["OPENAI_API_KEY"],
model_name="gpt-4o-mini",
request_extra={"best_of": 3}
)

async with any_llm_client.OpenAIClient(config, ...) as client:
Expand Down Expand Up @@ -191,3 +201,5 @@ async with any_llm_client.get_client(..., request_retry=any_llm_client.RequestRe
```python
await client.request_llm_message("Кек, чо как вообще на нарах?", extra={"best_of": 3})
```

The `extra` parameter is united with `request_extra` in OpenAIConfig
5 changes: 3 additions & 2 deletions any_llm_client/clients/openai.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -34,6 +34,7 @@ class OpenAIConfig(LLMConfig):
url: pydantic.HttpUrl
auth_token: str | None = pydantic.Field(default_factory=lambda: os.environ.get(OPENAI_AUTH_TOKEN_ENV_NAME))
model_name: str
request_extra: dict[str, typing.Any] = pydantic.Field(default_factory=dict)
force_user_assistant_message_alternation: bool = False
"Gemma 2 doesn't support {role: system, text: ...} message, and requires alternated messages"
api_type: typing.Literal["openai"] = "openai"
Expand Down Expand Up @@ -149,7 +150,7 @@ async def request_llm_message(
model=self.config.model_name,
messages=self._prepare_messages(messages),
temperature=temperature,
**extra or {},
**self.config.request_extra | (extra or {}),
).model_dump(mode="json")
try:
response: typing.Final = await make_http_request(
Expand Down Expand Up @@ -182,7 +183,7 @@ async def stream_llm_message_chunks(
model=self.config.model_name,
messages=self._prepare_messages(messages),
temperature=temperature,
**extra or {},
**self.config.request_extra | (extra or {}),
).model_dump(mode="json")
try:
async with make_streaming_http_request(
Expand Down
Loading