Add trace-guided RAG failure mode checklist notebook (WFGY Problem Map No.1–No.16)#2552
Open
onestardao wants to merge 4 commits intolangfuse:mainfrom
Open
Add trace-guided RAG failure mode checklist notebook (WFGY Problem Map No.1–No.16)#2552onestardao wants to merge 4 commits intolangfuse:mainfrom
onestardao wants to merge 4 commits intolangfuse:mainfrom
Conversation
Add a new cookbook notebook that demonstrates how to: - classify RAG / LLM failures using a structured failure map (No.1–No.16) - map symptoms from traces to concrete inspection points - apply minimal structural fixes instead of generic advice The notebook uses an OpenAI-compatible endpoint and is designed as a practical debugging checklist for Langfuse users.
|
@onestardao is attempting to deploy a commit to the langfuse Team on Vercel. A member of the Team first needs to authorize it. |
|
Check out this pull request on See visual diffs & provide feedback on Jupyter Notebooks. Powered by ReviewNB |
dosubot
bot
added
the
size:L
|
|
Author
|
Noticed that the Vercel preview build failed, which I believe requires maintainer permissions to re-run or fix. Just let me know if there’s anything I should adjust on my side — happy to update the PR if needed. Thanks! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Hi Langfuse team,
This PR adds a new cookbook notebook: cookbook/rag_failure_mode_checklist.ipynb.
It demonstrates a simple workflow to:
take a failing RAG/LLM run from Langfuse traces
copy prompt + answer + retrieved context + relevant logs into the notebook
map the failure to a consistent label using a shared failure-mode vocabulary (Problem Map No.1–No.16)
reuse that label inside Langfuse as a tag/metadata field to filter and aggregate recurring failures over time
Notes:
The notebook does not send anything to Langfuse automatically (copy/paste workflow only).
It downloads the WFGY Problem Map and TXTOS prompt directly from GitHub at runtime.
Default configuration is set to the official OpenAI endpoint (https://api.openai.com/v1) with gpt-4o, but users can swap in any OpenAI-compatible base URL/model if desired.
Happy to adjust naming/location/formatting to match the cookbook conventions.
Thanks!