Skip to content

Adding api-key arg to LlamaStackClient #117

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

Closed
vladimirivic wants to merge 1 commit into from
Closed

Adding api-key arg to LlamaStackClient #117

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
16 changes: 16 additions & 0 deletions src/llama_stack_client/_client.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -103,6 +103,7 @@ def __init__(
self,
*,
base_url: str | httpx.URL | None = None,
api_key: str | None = None,
timeout: Union[float, Timeout, None, NotGiven] = NOT_GIVEN,
max_retries: int = DEFAULT_MAX_RETRIES,
default_headers: Mapping[str, str] | None = None,
Expand All @@ -125,17 +126,22 @@ def __init__(
"""Construct a new synchronous llama-stack-client client instance."""
if base_url is None:
base_url = os.environ.get("LLAMA_STACK_CLIENT_BASE_URL")
if api_key is None:
api_key = os.environ.get("LLAMA_STACK_CLIENT_API_KEY")
if base_url is None:
base_url = f"http://any-hosted-llama-stack.com"

custom_headers = default_headers or {}
custom_headers["X-LlamaStack-Client-Version"] = __version__
if api_key is not None:
custom_headers["Authorization"] = f"Bearer {api_key}"
if provider_data is not None:
custom_headers["X-LlamaStack-Provider-Data"] = json.dumps(provider_data)

super().__init__(
version=__version__,
base_url=base_url,
api_key=api_key,
max_retries=max_retries,
timeout=timeout,
http_client=http_client,
Expand Down Expand Up @@ -188,6 +194,7 @@ def copy(
self,
*,
base_url: str | httpx.URL | None = None,
api_key: str | None = None,
timeout: float | Timeout | None | NotGiven = NOT_GIVEN,
http_client: httpx.Client | None = None,
max_retries: int | NotGiven = NOT_GIVEN,
Expand Down Expand Up @@ -221,6 +228,7 @@ def copy(
http_client = http_client or self._client
return self.__class__(
base_url=base_url or self.base_url,
api_key=api_key or self.api_key,
timeout=self.timeout if isinstance(timeout, NotGiven) else timeout,
http_client=http_client,
max_retries=max_retries if is_given(max_retries) else self.max_retries,
Expand Down Expand Up @@ -300,6 +308,7 @@ def __init__(
self,
*,
base_url: str | httpx.URL | None = None,
api_key: str | None = None,
timeout: Union[float, Timeout, None, NotGiven] = NOT_GIVEN,
max_retries: int = DEFAULT_MAX_RETRIES,
default_headers: Mapping[str, str] | None = None,
Expand All @@ -322,17 +331,22 @@ def __init__(
"""Construct a new async llama-stack-client client instance."""
if base_url is None:
base_url = os.environ.get("LLAMA_STACK_CLIENT_BASE_URL")
if api_key is None:
api_key = os.environ.get("LLAMA_STACK_CLIENT_API_KEY")
if base_url is None:
base_url = f"http://any-hosted-llama-stack.com"

custom_headers = default_headers or {}
custom_headers["X-LlamaStack-Client-Version"] = __version__
if api_key is not None:
custom_headers["Authorization"] = f"Bearer {api_key}"
if provider_data is not None:
custom_headers["X-LlamaStack-Provider-Data"] = json.dumps(provider_data)

super().__init__(
version=__version__,
base_url=base_url,
api_key=api_key,
max_retries=max_retries,
timeout=timeout,
http_client=http_client,
Expand Down Expand Up @@ -385,6 +399,7 @@ def copy(
self,
*,
base_url: str | httpx.URL | None = None,
api_key: str | None = None,
timeout: float | Timeout | None | NotGiven = NOT_GIVEN,
http_client: httpx.AsyncClient | None = None,
max_retries: int | NotGiven = NOT_GIVEN,
Expand Down Expand Up @@ -418,6 +433,7 @@ def copy(
http_client = http_client or self._client
return self.__class__(
base_url=base_url or self.base_url,
api_key=api_key or self.api_key,
timeout=self.timeout if isinstance(timeout, NotGiven) else timeout,
http_client=http_client,
max_retries=max_retries if is_given(max_retries) else self.max_retries,
Expand Down
8 changes: 8 additions & 0 deletions src/llama_stack_client/resources/inference.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -272,6 +272,8 @@ def chat_completion(
extra_body: Body | None = None,
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
) -> ChatCompletionResponse | Stream[ChatCompletionResponseStreamChunk]:
if stream:
extra_headers = {"Accept": "text/event-stream", **(extra_headers or {})}
return self._post(
"/v1/inference/chat-completion",
body=maybe_transform(
Expand Down Expand Up @@ -451,6 +453,8 @@ def completion(
extra_body: Body | None = None,
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
) -> CompletionResponse | Stream[CompletionResponse]:
if stream:
extra_headers = {"Accept": "text/event-stream", **(extra_headers or {})}
return self._post(
"/v1/inference/completion",
body=maybe_transform(
Expand Down Expand Up @@ -751,6 +755,8 @@ async def chat_completion(
extra_body: Body | None = None,
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
) -> ChatCompletionResponse | AsyncStream[ChatCompletionResponseStreamChunk]:
if stream:
extra_headers = {"Accept": "text/event-stream", **(extra_headers or {})}
return await self._post(
"/v1/inference/chat-completion",
body=await async_maybe_transform(
Expand Down Expand Up @@ -930,6 +936,8 @@ async def completion(
extra_body: Body | None = None,
timeout: float | httpx.Timeout | None | NotGiven = NOT_GIVEN,
) -> CompletionResponse | AsyncStream[CompletionResponse]:
if stream:
extra_headers = {"Accept": "text/event-stream", **(extra_headers or {})}
return await self._post(
"/v1/inference/completion",
body=await async_maybe_transform(
Expand Down