Un 3388 Fixed Gemini LLM test case failure#330
Merged
vince-leaf merged 3 commits intomainfrom Jul 25, 2025
Merged
Conversation
vince-leaf
commented
Jul 25, 2025
| "llm_config": { | ||
| "model_name": "gemini-2.0-flash", | ||
| "class": "gemini", | ||
| "model_name": "gemini-2.5-flash", |
Contributor
Author
There was a problem hiding this comment.
I switched to another model name.
vince-leaf
commented
Jul 25, 2025
|
|
||
| Once you receive the updated running cost, respond with a JSON object that has exactly two keys: | ||
| 1. "answer" – your full answer to the user’s question. | ||
| 2. "running_cost" – the updated cost returned by the Accountant tool. |
Contributor
Author
There was a problem hiding this comment.
I replaced the prompt used by Ollama and Anthropic LLM test cases.
Collaborator
There was a problem hiding this comment.
It is Great and Good that we are trying to use the same prompt across multiple llms
vince-leaf
commented
Jul 25, 2025
| langchain-aws>=0.2.27,<0.3 | ||
| langchain-community>=0.3.19,<0.4 | ||
| langchain-google-genai>=2.0.11,<3.0 | ||
| langchain-google-genai>=2.1.8,<3.0 |
Contributor
Author
There was a problem hiding this comment.
Bumped up the version.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR addressed the failure of the Gemini LLM Smoke test case. In summary, three significant changes led to this failure:
The current Gemini-2.0-flash model name used for this test is no longer working; it fails 90% of the time. I went with Gemini-2.5-flash and with the existing prompt that we are using for Anthropic and Ollama test cases.