phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-15 16:22:46 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add response format to signature

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-21 19:14:52 -07:00 • committed by Ashwin Bharambe
parent 6d26bbdce3
commit 40ba22f4c8
15 changed files with 93 additions and 32 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/providers/adapters/inference/bedrock/bedrock.py
View file

@ -52,6 +52,7 @@ class BedrockInferenceAdapter(ModelRegistryHelper, Inference):
model: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> Union[CompletionResponse, CompletionResponseStreamChunk]:
@ -288,6 +289,7 @@ class BedrockInferenceAdapter(ModelRegistryHelper, Inference):
model: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
# zero-shot tool definitions as input to the model
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,

2
llama_stack/providers/adapters/inference/databricks/databricks.py
View file

@ -53,6 +53,7 @@ class DatabricksInferenceAdapter(ModelRegistryHelper, Inference):
model: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
@ -63,6 +64,7 @@ class DatabricksInferenceAdapter(ModelRegistryHelper, Inference):
model: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,

2
llama_stack/providers/adapters/inference/fireworks/fireworks.py
View file

@ -56,6 +56,7 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference):
model: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
@ -66,6 +67,7 @@ class FireworksInferenceAdapter(ModelRegistryHelper, Inference):
model: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,

2
llama_stack/providers/adapters/inference/ollama/ollama.py
View file

@ -93,6 +93,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
model: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
@ -160,6 +161,7 @@ class OllamaInferenceAdapter(Inference, ModelsProtocolPrivate):
model: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,

2
llama_stack/providers/adapters/inference/tgi/tgi.py
View file

@ -71,6 +71,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
model: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
@ -81,6 +82,7 @@ class _HfAdapter(Inference, ModelsProtocolPrivate):
model: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,

2
llama_stack/providers/adapters/inference/together/together.py
View file

@ -59,6 +59,7 @@ class TogetherInferenceAdapter(
model: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> AsyncGenerator:
@ -69,6 +70,7 @@ class TogetherInferenceAdapter(
model: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,

2
llama_stack/providers/adapters/inference/vllm/vllm.py
View file

@ -80,6 +80,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
model: str,
content: InterleavedTextMedia,
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
stream: Optional[bool] = False,
logprobs: Optional[LogProbConfig] = None,
) -> Union[CompletionResponse, CompletionResponseStreamChunk]:
@ -90,6 +91,7 @@ class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
model: str,
messages: List[Message],
sampling_params: Optional[SamplingParams] = SamplingParams(),
response_format: Optional[ResponseFormat] = None,
tools: Optional[List[ToolDefinition]] = None,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,