phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 20:14:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add tools to chat completion request

Browse source
This commit is contained in:
Hardik Shah 2024-08-21 17:48:48 -07:00
parent 9777639a1c
commit 68855ed218
26 changed files with 558 additions and 226 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_toolchain/inference/ollama/ollama.py
View file

@ -32,7 +32,7 @@ from llama_toolchain.inference.api import (
ToolCallDelta,
ToolCallParseStatus,
)
from llama_toolchain.inference.prepare_messages import prepare_messages_for_tools
from .config import OllamaImplConfig
# TODO: Eventually this will move to the llama cli model list command
@ -111,6 +111,7 @@ class OllamaInference(Inference):
return options
async def chat_completion(self, request: ChatCompletionRequest) -> AsyncGenerator:
request = prepare_messages_for_tools(request)
# accumulate sampling params and other options to pass to ollama
options = self.get_ollama_chat_options(request)
ollama_model = self.resolve_ollama_model(request.model)