wx44wx/pipecat
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Add service_tier to BaseOpenAILLMService

Browse Source
This commit is contained in:
Mark Backman
2025-10-08 08:32:35 -04:00
parent 233fb25e6c
commit c85a3f0b94
2 changed files with 10 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
CHANGELOG.md
View File

@@ -18,6 +18,10 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
... ...
``` ```
- Added a `service_tier` `InputParam` to the `BaseOpenAILLMService`. This
parameter can influence the latency of the response. For example `"priority"`
will result in faster completions, but in exchange for a higher price.
## [0.0.89] - 2025-10-07 ## [0.0.89] - 2025-10-07
### Fixed ### Fixed
@@ -36,8 +40,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
- Added `HumeTTSService` for text-to-speech synthesis using Hume AI's expressive - Added `HumeTTSService` for text-to-speech synthesis using Hume AI's expressive
voice models. Provides high-quality, emotionally expressive speech synthesis voice models. Provides high-quality, emotionally expressive speech synthesis
with support for various voice models. Includes example in with support for various voice models. Includes example in
`examples/foundational/07ad-interruptible-hume.py`. Use with `uv pip install `examples/foundational/07ad-interruptible-hume.py`. Use with:
pipecat-ai[hume]`. `uv pip install pipecat-ai[hume]`.
### Changed ### Changed

4
src/pipecat/services/openai/base_llm.py
View File

@@ -66,6 +66,7 @@ class BaseOpenAILLMService(LLMService):
top_p: Top-p (nucleus) sampling parameter (0.0 to 1.0). top_p: Top-p (nucleus) sampling parameter (0.0 to 1.0).
max_tokens: Maximum tokens in response (deprecated, use max_completion_tokens). max_tokens: Maximum tokens in response (deprecated, use max_completion_tokens).
max_completion_tokens: Maximum completion tokens to generate. max_completion_tokens: Maximum completion tokens to generate.
service_tier: Service tier to use (e.g., "auto", "flex", "priority").
extra: Additional model-specific parameters. extra: Additional model-specific parameters.
""" """
@@ -83,6 +84,7 @@ class BaseOpenAILLMService(LLMService):
top_p: Optional[float] = Field(default_factory=lambda: NOT_GIVEN, ge=0.0, le=1.0) top_p: Optional[float] = Field(default_factory=lambda: NOT_GIVEN, ge=0.0, le=1.0)
max_tokens: Optional[int] = Field(default_factory=lambda: NOT_GIVEN, ge=1) max_tokens: Optional[int] = Field(default_factory=lambda: NOT_GIVEN, ge=1)
max_completion_tokens: Optional[int] = Field(default_factory=lambda: NOT_GIVEN, ge=1) max_completion_tokens: Optional[int] = Field(default_factory=lambda: NOT_GIVEN, ge=1)
service_tier: Optional[str] = Field(default_factory=lambda: NOT_GIVEN)
extra: Optional[Dict[str, Any]] = Field(default_factory=dict) extra: Optional[Dict[str, Any]] = Field(default_factory=dict)
def __init__( def __init__(
@@ -125,6 +127,7 @@ class BaseOpenAILLMService(LLMService):
"top_p": params.top_p, "top_p": params.top_p,
"max_tokens": params.max_tokens, "max_tokens": params.max_tokens,
"max_completion_tokens": params.max_completion_tokens, "max_completion_tokens": params.max_completion_tokens,
"service_tier": params.service_tier,
"extra": params.extra if isinstance(params.extra, dict) else {}, "extra": params.extra if isinstance(params.extra, dict) else {},
} }
self._retry_timeout_secs = retry_timeout_secs self._retry_timeout_secs = retry_timeout_secs
@@ -236,6 +239,7 @@ class BaseOpenAILLMService(LLMService):
"top_p": self._settings["top_p"], "top_p": self._settings["top_p"],
"max_tokens": self._settings["max_tokens"], "max_tokens": self._settings["max_tokens"],
"max_completion_tokens": self._settings["max_completion_tokens"], "max_completion_tokens": self._settings["max_completion_tokens"],
"service_tier": self._settings["service_tier"],
} }
# Messages, tools, tool_choice # Messages, tools, tool_choice