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

Companion example for nemo/trulens blog #1131

Open
wants to merge 5 commits into
base: main
Choose a base branch
from
Open

Conversation

joshreini1
Copy link
Contributor

Other details that are good to know but need not be announced:

  • Companion example notebook for blog to show all nemo/trulens combined capabilities

Copy link

Check out this pull request on  ReviewNB

See visual diffs & provide feedback on Jupyter Notebooks.


Powered by ReviewNB

@joshreini1 joshreini1 marked this pull request as ready for review May 10, 2024 20:25
@dosubot dosubot bot added the size:XXL This PR changes 1000+ lines, ignoring generated files. label May 10, 2024
@joshreini1 joshreini1 requested a review from piotrm0 May 10, 2024 20:25
@dosubot dosubot bot added the documentation Improvements or additions to documentation label May 10, 2024
@@ -0,0 +1,1250 @@
{
Copy link
Contributor

@piotrm0 piotrm0 May 13, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Line #24.          "text1":"{question_lens}",\

The nemo persons suggested that using the variables version of the lenses here (for example {context_lens} ) is a bit confusing. Because of this, there is the other notebook that does it a bit simpler by defining python methods for each of these flows.


Reply via ReviewNB

@@ -0,0 +1,1250 @@
{
Copy link
Contributor

@piotrm0 piotrm0 May 13, 2024

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Line #64.      if $groundedness_result < 0.7

Confused here. $groundedness_result, $answerrelevance_result, $contextrelevance_result have not been defined. Also unclear when the prior two flows get executed. Perhaps the code text is oudated?


Reply via ReviewNB

Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Updated to include $groundedness_result, $answerrelevance_result, $contextrelevance_result generation.

Not sure what you mean by "Also unclear when the prior two flows get executed."?

Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This config specification determines what "flows" get executed when the bot wants to output something:

output:
  flows:
    - check language match
    # triad defined seperately so hopefully they can be executed in parallel
    - check rag triad groundedness
    - check rag triad relevance
    - check rag triad qs_relevance
    - bot: explain usage and capabilities

The last flow in the notebook is check rag triad context_relevance which is now not executed as it is not in the list. Even if it were in the list, it is unclear how the values that were set by the other flows are set or whether they are available in that flow (I'm uncertain if colang will make the variables defined in one flow available in another). The other issue is even if variables were available, you would need to make sure the 2 flows that compute $groundedness_result and $answerrelevance_result are executed before they are used in the check rag triad context_relevance flow.

@dosubot dosubot bot added size:XL This PR changes 500-999 lines, ignoring generated files. and removed size:XXL This PR changes 1000+ lines, ignoring generated files. labels May 13, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
documentation Improvements or additions to documentation size:XL This PR changes 500-999 lines, ignoring generated files.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

2 participants