phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 19:04:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

add /inference/chat_completion to SSE special case

Browse source
This commit is contained in:
Dalton Flanagan 2024-09-10 01:14:11 -04:00
parent 4f021de10f
commit 2b63074676
3 changed files with 31 additions and 28 deletions
Download patch file Download diff file Expand all files Collapse all files

5
rfcs/openapi_generator/generate.py
View file

@ -35,7 +35,10 @@ from llama_toolchain.stack import LlamaStack
# TODO: this should be fixed in the generator itself so it reads appropriate annotations
STREAMING_ENDPOINTS = ["/agentic_system/turn/create"]
STREAMING_ENDPOINTS = [
"/agentic_system/turn/create",
"/inference/chat_completion",
]
def patch_sse_stream_responses(spec: Specification):