phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

Remove request wrapper migration (#64)

Browse source 
* [1/n] migrate inference/chat_completion

* migrate inference/completion

* inference/completion

* inference regenerate openapi spec

* safety api

* migrate agentic system

* migrate apis without implementations

* re-generate openapi spec

* remove hack from openapi generator

* fix inference

* fix inference

* openapi generator rerun

* Simplified Telemetry API and tying it to logger (#57)

* Simplified Telemetry API and tying it to logger

* small update which adds a METRIC type

* move span events one level down into structured log events

---------

Co-authored-by: Ashwin Bharambe <ashwin@meta.com>

* fix api to work with openapi generator

* fix agentic calling inference

* together adapter inference

* update inference adapters

---------

Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>
This commit is contained in:
Xi Yan 2024-09-12 15:03:49 -07:00 • committed by GitHub
parent 1d0e91d802
commit 5712566061
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
26 changed files with 1211 additions and 3031 deletions
Download patch file Download diff file Expand all files Collapse all files

14
llama_toolchain/batch_inference/api/api.py
View file

@ -51,11 +51,21 @@ class BatchInference(Protocol):
@webmethod(route="/batch_inference/completion")
async def batch_completion(
self,
request: BatchCompletionRequest,
model: str,
content_batch: List[InterleavedTextMedia],
sampling_params: Optional[SamplingParams] = SamplingParams(),
logprobs: Optional[LogProbConfig] = None,
) -> BatchCompletionResponse: ...
@webmethod(route="/batch_inference/chat_completion")
async def batch_chat_completion(
self,
request: BatchChatCompletionRequest,
model: str,
messages_batch: List[List[Message]],
sampling_params: Optional[SamplingParams] = SamplingParams(),
# zero-shot tool definitions as input to the model
tools: Optional[List[ToolDefinition]] = list,
tool_choice: Optional[ToolChoice] = ToolChoice.auto,
tool_prompt_format: Optional[ToolPromptFormat] = ToolPromptFormat.json,
logprobs: Optional[LogProbConfig] = None,
) -> BatchChatCompletionResponse: ...