diff --git a/lyrics_transcriber_temp/lyrics_transcriber/correction/agentic/router.py b/lyrics_transcriber_temp/lyrics_transcriber/correction/agentic/router.py index 60344dc4..4eca4e13 100644 --- a/lyrics_transcriber_temp/lyrics_transcriber/correction/agentic/router.py +++ b/lyrics_transcriber_temp/lyrics_transcriber/correction/agentic/router.py @@ -5,8 +5,10 @@ from typing import Dict, Any from .providers.config import ProviderConfig -# Default model for cloud deployments - Gemini 3 Flash via Vertex AI -DEFAULT_CLOUD_MODEL = "vertexai/gemini-3-flash-preview" +# Default model for cloud deployments - Gemini 2.0 Flash via Vertex AI +# Note: gemini-3-flash-preview requires 'global' location, not us-central1 +# Using gemini-2.0-flash for broader regional availability +DEFAULT_CLOUD_MODEL = "vertexai/gemini-2.0-flash" class ModelRouter: @@ -19,7 +21,7 @@ class ModelRouter: """Choose appropriate model based on gap characteristics. Returns model identifier in format "provider/model" for LangChain: - - "vertexai/gemini-3-flash-preview" for Gemini via Vertex AI (default) + - "vertexai/gemini-2.0-flash" for Gemini via Vertex AI (default) - "ollama/llama3.2:latest" for local Ollama models - "openai/gpt-4" for OpenAI models - "anthropic/claude-3-sonnet-20240229" for Anthropic models @@ -33,7 +35,7 @@ class ModelRouter: if self._config.privacy_mode: return "ollama/llama3.2:latest" - # Default to Gemini 3 Flash for all cases (fast, cost-effective) + # Default to Gemini 2.0 Flash for all cases (fast, cost-effective) return DEFAULT_CLOUD_MODEL diff --git a/pyproject.toml b/pyproject.toml index f8f4d417..fb5e27c3 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "karaoke-gen" -version = "0.81.3" +version = "0.81.4" description = "Generate karaoke videos with synchronized lyrics. Handles the entire process from downloading audio and lyrics to creating the final video with title screens." authors = ["Andrew Beveridge "] license = "MIT"