phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 12:07:34 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix agentic calling inference

Browse source
This commit is contained in:
Xi Yan 2024-09-11 18:30:09 -07:00
parent 2501b3d7de
commit f55ffa8b53
4 changed files with 8 additions and 22 deletions
Download patch file Download diff file Expand all files Collapse all files

16
llama_toolchain/agentic_system/meta_reference/agent_instance.py
View file

@ -388,19 +388,17 @@ class ChatAgent(ShieldRunnerMixin):
)
)
req = ChatCompletionRequest(
model=self.agent_config.model,
messages=input_messages,
tool_calls = []
content = ""
stop_reason = None
async for chunk in self.inference_api.chat_completion(
self.agent_config.model,
input_messages,
tools=self._get_tools(),
tool_prompt_format=self.agent_config.tool_prompt_format,
stream=True,
sampling_params=sampling_params,
)
tool_calls = []
content = ""
stop_reason = None
async for chunk in self.inference_api.chat_completion_impl(req):
):
event = chunk.event
if event.event_type == ChatCompletionResponseEventType.start:
continue