fix: changed stream parameter to streaming in curl command

[jjmaturino]

Description

Incorrect json key set for curl command.

Issues

N/A

Type of change

List the type of change like below. Please delete options that are not relevant.

• Bug fix (non-breaking change which fixes an issue)

Dependencies

N/A

Tests

Integration tests under tests/llms

[jjmaturino]

@lvliang-intel RFR 🛸

[xiguiw]

@jjmaturino

https://github.com/huggingface/text-generation-inference/blob/main/README.md#get-started
it's stream, not streaming.

Would you please let us in which format or protocol, streaming is used?

[jjmaturino]

@xiguiw .

On the Pydantic Model LLMParamsDoc , the attribute for stream is defined as streaming.

From my understanding and testing, Pydantic Model JSON Marshaling and Unmarshalling is based on the attribute variable name as the key in the json objects.

GenAIComps/comps/cores/proto/docarray.py

Line 187 in 8d6b4b0

streaming: bool = True

This is why I changed stream to streaming to make the curl command work.

So if this is the desired case, we will need to change the pydantic model's key... that seems like a breaking change imo.

[jjmaturino]

@xiguiw Let me know if you want me to open up an issue and related pr for the topic discussed above!

[jjmaturino]

Created issue ticket

[xiguiw]

@xiguiw .

On the Pydantic Model LLMParamsDoc , the attribute for stream is defined as streaming.

From my understanding and testing, Pydantic Model JSON Marshaling and Unmarshalling is based on the attribute variable name as the key in the json objects.

GenAIComps/comps/cores/proto/docarray.py

Line 187 in 8d6b4b0

streaming: bool = True

This is why I changed stream to streaming to make the curl command work.

So if this is the desired case, we will need to change the pydantic model's key... that seems like a breaking change imo.

@jjmaturino
Good catching!

Thanks！ Let me check it.

[jjmaturino]

@xiguiw No problem! Let me know if I can help.

Also, any tips on getting PR's reviewed more quickly in the future?

I want to contribute as much as I can to this project and would like a tight feedback loop 🚀

Hope you have a great week and happy new year!

[xiguiw]

@xiguiw No problem! Let me know if I can help.

Also, any tips on getting PR's reviewed more quickly in the future?

I want to contribute as much as I can to this project and would like a tight feedback loop 🚀

Hope you have a great week and happy new year!

@jjmaturino
Thank you for your contribution!
Sorry for the late response for the PR review.
We noted this. Now we are trying to improve this process.

My suggestion for the PR's review feedback is to describe what the problems, feature that the PR for clearly, so we get to know the priority of the PR.

Happy new year!

[xiguiw]

@jjmaturino
Could this PR be closed?

[jjmaturino]

@xiguiw yes! I was talking about other prs

[jjmaturino]

Closed!