Skip to content

Enable remote inference non streaming response #1806

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
chensuyue merged 8 commits into from
Jul 2, 2025
Merged

Enable remote inference non streaming response #1806

Show file tree
Hide file tree
Changes from 7 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
9aba5b1
enable header for non streaming
Jun 18, 2025
22c60cb
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Jun 20, 2025
6e3953b
Merge branch 'main' into denvr
srinarayan-srikanthan Jun 20, 2025
c513323
docsum changes
Jun 23, 2025
29b551e
[pre-commit.ci] auto fixes from pre-commit.com hooks
pre-commit-ci[bot] Jun 23, 2025
b771e7f
removed prints
Jun 23, 2025
38e50c2
removed prints
Jun 23, 2025
b9eb541
Merge branch 'main' into denvr
srinarayan-srikanthan Jul 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 1 addition & 2 deletions comps/cores/mega/micro_service.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -159,8 +159,7 @@

def endpoint_path(self, model=None):
if self.api_key:
model_endpoint = model.split("/")[1]
return f"{self.host}/{model_endpoint}{self.endpoint}"
return f"{self.host}{self.endpoint}"

Check warning on line 162 in comps/cores/mega/micro_service.py

View check run for this annotation

Codecov / codecov/patch

comps/cores/mega/micro_service.py#L162 

Added line #L162 was not covered by tests
else:
return f"{self.protocol}://{self.host}:{self.port}{self.endpoint}"

Expand Down
7 changes: 6 additions & 1 deletion comps/cores/mega/orchestrator.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -276,6 +276,7 @@ async def execute(
stream=True,
timeout=2000,
)

else:
response = requests.post(
url=endpoint,
Expand Down Expand Up @@ -367,7 +368,11 @@ def generate():
if ENABLE_OPEA_TELEMETRY
else contextlib.nullcontext()
):
response = await session.post(endpoint, json=input_data)
response = await session.post(
endpoint,
json=input_data,
headers={"Content-type": "application/json", "Authorization": f"Bearer {access_token}"},
)

if response.content_type == "audio/wav":
audio_data = await response.read()
Expand Down
12 changes: 9 additions & 3 deletions comps/llms/src/doc-summarization/integrations/common.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,6 +27,7 @@
TOKEN_URL = os.getenv("TOKEN_URL")
CLIENTID = os.getenv("CLIENTID")
CLIENT_SECRET = os.getenv("CLIENT_SECRET")
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
MAX_INPUT_TOKENS = int(os.getenv("MAX_INPUT_TOKENS", 2048))
MAX_TOTAL_TOKENS = int(os.getenv("MAX_TOTAL_TOKENS", 4096))

Expand Down Expand Up @@ -67,9 +68,14 @@ class OpeaDocSum(OpeaComponent):

def __init__(self, name: str, description: str, config: dict = None):
super().__init__(name, ServiceType.LLM.name.lower(), description, config)
self.access_token = (
get_access_token(TOKEN_URL, CLIENTID, CLIENT_SECRET) if TOKEN_URL and CLIENTID and CLIENT_SECRET else None
)
if OPENAI_API_KEY:
self.access_token = OPENAI_API_KEY
else:
self.access_token = (
get_access_token(TOKEN_URL, CLIENTID, CLIENT_SECRET)
if TOKEN_URL and CLIENTID and CLIENT_SECRET
else None
)
self.llm_endpoint = get_llm_endpoint()
self.tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
health_status = self.check_health()
Expand Down
Loading