-
Notifications
You must be signed in to change notification settings - Fork 47
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
automating tool benchmarks #188
Conversation
scripts/tool_benchmarks.py
Outdated
"{instructions} Here are some example conversations of the user interacting with the AI until the correct answer is reached: ", | ||
), | ||
] | ||
+ semantic_similar_few_shots("{question}", retriever, examples) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
this needs to be part of the actual chain, currently its just getting static examples based on the string literal "{question}"
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
should just have an examples placeholder thats filled at runtime
scripts/tool_benchmarks.py
Outdated
) | ||
retriever = vectorstore.as_retriever() | ||
|
||
prompts = [ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
could we upload all these prompts to the prompt hub and pull from it in the script?
…i/langchain-benchmarks into isaac/toolbenchmarks
No description provided.