Conversation
|
apologies for the last-minute PR. It passed pycheck strict locally, but there are issues with the checks now. I'm currently in-flight to New Zealand for a week-long conference and will try to fix these issues as soon as possible. Let me know if any other updates are needed. |
|
Also you need to signoff your commits. See the DCO section for help. edit: You need to add the frontend/requirements-test.txt file for |
| @@ -0,0 +1,277 @@ | |||
| import streamlit as st | |||
There was a problem hiding this comment.
can you rename the dataset files to be separated with _?
instead of Human Eval Dataset.csv -> Human_Eval_Dataset.csv
| @@ -0,0 +1,15 @@ | |||
| # Retriever Metrics Visualization | |||
| ## Dependencies | ||
| - streamlit | ||
| - pandas | ||
| - plotly |
There was a problem hiding this comment.
why are there ._***.py files? what are their purposes
| @@ -0,0 +1,74 @@ | |||
| from chainforge.providers import provider | |||
There was a problem hiding this comment.
Python files should not contain spaces
| @@ -0,0 +1,110 @@ | |||
| import requests | |||
There was a problem hiding this comment.
filename change and put main logic under if __name__ == "__main__":
| @@ -0,0 +1,66 @@ | |||
| # OpenROAD Retriever Benchmark | |||
|
|
|||
| "response_mime_type": "text/plain", | ||
| } | ||
|
|
||
| safety_settings = { |
There was a problem hiding this comment.
What is the default value for this i am wondering. also for production we need to think whether to enable some blocking of harmful outputs.
There was a problem hiding this comment.
What is the default value for this i am wondering. also for production we need to think whether to enable some blocking of harmful outputs.
its default, cause there was issue with the safety settings, sometimes it would block certain questions without having any harmful content which hinders the evaluation script.
There was a problem hiding this comment.
That's fine, but I was curious what is the default safety level. I get that we have to disable it for evaluation, but for production we might need it back since we didn't set it for our backend code.
I guess my question is can we make the evaluation mode as close to production mode as close as possible.
| @@ -0,0 +1,36 @@ | |||
| # See https://help.github.com/articles/ignoring-files/ for more about ignoring files. | |||
There was a problem hiding this comment.
any reason these src folders are nested in another folder orassistant-frontend? if not, prefer it to be under nextjs_frontend directly
| @@ -0,0 +1,47 @@ | |||
| # NextJS Frontend for ORAssistant | |||
| message_placeholder = st.empty() | ||
|
|
||
| response_buffer = '' | ||
| # Option 1: Streaming effect - Send response in chunks |
There was a problem hiding this comment.
There seems to be only one option...
|
@error9098x Please add the nextJS code in a separate PR. Thanks! |
Sure. |
- discussion directly puts latest discussion dataset from hugging face
- previously conducted evaluation visualisation