Skip to content
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.

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

LLM micro service input data does not have input model name #447

Merged
merged 1 commit into from
Aug 12, 2024

Conversation

xiguiw
Copy link
Collaborator

@xiguiw xiguiw commented Aug 9, 2024

vLLM and oLLAMa get the model name from the envrionment

@xiguiw xiguiw changed the title LLM micro service does not input model LLM micro service input data does not have input model name Aug 12, 2024
@Spycsh
Copy link
Member

Spycsh commented Aug 12, 2024

@xiguiw why OLLAMA needs this? https://github.com/xiguiw/GenAIComps/blob/main/comps/cores/proto/docarray.py#L81 here has the input model name instead of using another env variable

No input model from UI.
vLLM and OLLAMA get the model name from the envrionment
TGI mode model form ModelID

Signed-off-by: Wang, Xigui <[email protected]>
@xiguiw xiguiw removed the request for review from XuhuiRen August 12, 2024 07:59
@xiguiw xiguiw merged commit 761f7e0 into opea-project:main Aug 12, 2024
8 checks passed
@xiguiw xiguiw deleted the ollama branch August 12, 2024 12:54
BaoHuiling pushed a commit to siddhivelankar23/GenAIComps that referenced this pull request Aug 15, 2024
No input model from UI.
vLLM and OLLAMA get the model name from the envrionment
TGI mode model form ModelID

Signed-off-by: Wang, Xigui <[email protected]>
BaoHuiling pushed a commit to siddhivelankar23/GenAIComps that referenced this pull request Aug 15, 2024
No input model from UI.
vLLM and OLLAMA get the model name from the envrionment
TGI mode model form ModelID

Signed-off-by: Wang, Xigui <[email protected]>
Signed-off-by: BaoHuiling <[email protected]>
sharanshirodkar7 pushed a commit to predictionguard/pg-GenAIComps that referenced this pull request Sep 3, 2024
No input model from UI.
vLLM and OLLAMA get the model name from the envrionment
TGI mode model form ModelID

Signed-off-by: Wang, Xigui <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants