Skip to content

fix: update default VLM model from gemini-2.0-flash to gemini-2.5-flash #48

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

Open
haruyuki-oda wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix: update default VLM model from gemini-2.0-flash to gemini-2.5-flash #48

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
2 changes: 1 addition & 1 deletion configs/config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,7 +4,7 @@
# Provider settings
vlm:
provider: gemini
model: gemini-2.0-flash
model: gemini-2.5-flash

image:
provider: google_imagen
Expand Down
2 changes: 1 addition & 1 deletion configs/provider/vlm/gemini.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,7 @@ capabilities:
- vision_input
- json_mode
config:
model: gemini-2.0-flash
model: gemini-2.5-flash
api_key: ${GOOGLE_API_KEY}
temperature: 1.0
max_tokens: 4096
2 changes: 1 addition & 1 deletion examples/generate_diagram.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,7 +39,7 @@ async def main():

settings = Settings(
vlm_provider="gemini",
vlm_model="gemini-2.0-flash",
vlm_model="gemini-2.5-flash",
image_provider="google_imagen",
image_model="gemini-3-pro-image-preview",
refinement_iterations=2,
Expand Down
4 changes: 2 additions & 2 deletions paperbanana/core/config.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -16,7 +16,7 @@ class VLMConfig(BaseSettings):
"""VLM provider configuration."""

provider: str = "gemini"
model: str = "gemini-2.0-flash"
model: str = "gemini-2.5-flash"


class ImageConfig(BaseSettings):
Expand Down Expand Up @@ -57,7 +57,7 @@ class Settings(BaseSettings):

# Provider settings
vlm_provider: str = Field(default="gemini", alias="VLM_PROVIDER")
vlm_model: str = Field(default="gemini-2.0-flash", alias="VLM_MODEL")
vlm_model: str = Field(default="gemini-2.5-flash", alias="VLM_MODEL")
image_provider: str = Field(default="google_imagen", alias="IMAGE_PROVIDER")
image_model: str = Field(default="gemini-3-pro-image-preview", alias="IMAGE_MODEL")

Expand Down
2 changes: 1 addition & 1 deletion paperbanana/providers/vlm/gemini.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,7 +20,7 @@ class GeminiVLM(VLMProvider):
Free tier: https://makersuite.google.com/app/apikey
"""

def __init__(self, api_key: Optional[str] = None, model: str = "gemini-2.0-flash"):
def __init__(self, api_key: Optional[str] = None, model: str = "gemini-2.5-flash"):
self._api_key = api_key
self._model = model
self._client = None
Expand Down
4 changes: 2 additions & 2 deletions tests/test_providers/test_registry.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,12 +12,12 @@ def test_create_gemini_vlm():
"""Test creating a Gemini VLM provider."""
settings = Settings(
vlm_provider="gemini",
vlm_model="gemini-2.0-flash",
vlm_model="gemini-2.5-flash",
google_api_key="test-key",
)
vlm = ProviderRegistry.create_vlm(settings)
assert vlm.name == "gemini"
assert vlm.model_name == "gemini-2.0-flash"
assert vlm.model_name == "gemini-2.5-flash"


def test_create_google_imagen_gen():
Expand Down