Skip to content

fix(eval): bump Gemini model from gemini-2.5-pro to gemini-3.1-pro-preview #276

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.

Sign up for GitHub

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

Merged
luarss merged 1 commit into from
May 17, 2026
Merged

fix(eval): bump Gemini model from gemini-2.5-pro to gemini-3.1-pro-preview #276

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
7 changes: 2 additions & 5 deletions evaluation/auto_evaluation/eval_main.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,8 +11,8 @@
from dotenv import load_dotenv
from deepeval.test_case import LLMTestCase
from deepeval import evaluate
from deepeval.models import GeminiModel

from auto_evaluation.src.models.gemini import GoogleGeminiLangChain
from auto_evaluation.src.metrics.retrieval import (
make_contextual_precision_metric,
make_contextual_recall_metric,
Expand Down Expand Up @@ -41,10 +41,7 @@ def __init__(self, base_url: str, dataset: str, reranker_base_url: str = ""):
self.dataset = dataset
self.reranker_base_url = reranker_base_url
self.qns = preprocess.read_data(self.dataset)
self.eval_model = GeminiModel(
model_name="gemini-2.5-pro",
api_key=os.getenv("GOOGLE_API_KEY"),
)
self.eval_model = GoogleGeminiLangChain(model_name="gemini-3.1-pro-preview")
self.log_dir = "logs"
os.makedirs(self.log_dir, exist_ok=True)
self.sanity_check()
Expand Down
4 changes: 2 additions & 2 deletions evaluation/auto_evaluation/src/models/gemini.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,15 +68,15 @@ def get_model_name(self):


def main():
model = GoogleGeminiLangChain(model_name="gemini-2.5-pro")
model = GoogleGeminiLangChain(model_name="gemini-3.1-pro-preview")
prompt = "Write me a joke"
print(f"Prompt: {prompt}")
response = model.generate(prompt, schema=Response)
print(f"Response: {response}")


async def main_async():
model = GoogleGeminiLangChain(model_name="gemini-2.5-pro")
model = GoogleGeminiLangChain(model_name="gemini-3.1-pro-preview")
prompt = "Write me a joke"
print(f"Prompt: {prompt}")
response = await model.a_generate(prompt, schema=Response)
Expand Down
2 changes: 1 addition & 1 deletion evaluation/script_based_evaluation/models/gemini_model.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -58,7 +58,7 @@ def base_gemini_pro(query: str) -> tuple[str, float]:
try:
start_time = time.time()
response = _client.models.generate_content(
model="gemini-2.5-pro",
model="gemini-3.1-pro-preview",
contents=" " + query,
config=types.GenerateContentConfig(
safety_settings=_safety_config,
Expand Down
Loading