phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-15 01:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: small ollama package

Browse source
This commit is contained in:
Raghotham Murthy 2025-05-28 21:13:48 -07:00
commit 2d5d05a2b4
103 changed files with 7262 additions and 7422 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/utils/inference/openai_compat.py
View file

@ -1402,9 +1402,8 @@ class OpenAIChatCompletionToLlamaStackMixin:
outstanding_responses: list[Awaitable[AsyncIterator[ChatCompletionResponseStreamChunk]]],
):
id = f"chatcmpl-{uuid.uuid4()}"
for outstanding_response in outstanding_responses:
for i, outstanding_response in enumerate(outstanding_responses):
response = await outstanding_response
i = 0
async for chunk in response:
event = chunk.event
finish_reason = _convert_stop_reason_to_openai_finish_reason(event.stop_reason)
@ -1459,7 +1458,6 @@ class OpenAIChatCompletionToLlamaStackMixin:
model=model,
object="chat.completion.chunk",
)
i = i + 1
async def _process_non_stream_response(
self, model: str, outstanding_responses: list[Awaitable[ChatCompletionResponse]]

10
llama_stack/providers/utils/tools/mcp.py
View file

@ -51,16 +51,6 @@ async def sse_client_wrapper(endpoint: str, headers: dict[str, str]):
raise
def convert_header_list_to_dict(header_list: list[str]) -> dict[str, str]:
headers = {}
for header in header_list:
parts = header.split(":")
if len(parts) == 2:
k, v = parts
headers[k.strip()] = v.strip()
return headers
async def list_mcp_tools(endpoint: str, headers: dict[str, str]) -> ListToolDefsResponse:
tools = []
async with sse_client_wrapper(endpoint, headers) as session: