karaoke-gen 0.76.28__tar.gz → 0.81.5__tar.gz

{karaoke_gen-0.76.28 → karaoke_gen-0.81.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: karaoke-gen
-Version: 0.76.28
+Version: 0.81.5
 Summary: Generate karaoke videos with synchronized lyrics. Handles the entire process from downloading audio and lyrics to creating the final video with title screens.
 License: MIT
 License-File: LICENSE
@@ -20,6 +20,7 @@ Requires-Dist: audio-separator[cpu] (>=0.34.0)
 Requires-Dist: beautifulsoup4 (>=4)
 Requires-Dist: cattrs (>=24.1.2)
 Requires-Dist: dropbox (>=12)
+Requires-Dist: email-validator (>=2.0.0)
 Requires-Dist: fastapi (>=0.104.0)
 Requires-Dist: fetch-lyrics-from-genius (>=0.1)
 Requires-Dist: ffmpeg-python (>=0.2.0,<0.3.0)
@@ -41,6 +42,7 @@ Requires-Dist: kbputils (>=0.0.16,<0.0.17)
 Requires-Dist: langchain (>=0.3.0)
 Requires-Dist: langchain-anthropic (>=0.2.0)
 Requires-Dist: langchain-core (>=0.3.0)
+Requires-Dist: langchain-google-vertexai (>=3.1.1)
 Requires-Dist: langchain-ollama (>=0.2.0)
 Requires-Dist: langchain-openai (>=0.2.0)
 Requires-Dist: langfuse (>=3.0.0)
@@ -75,10 +77,12 @@ Requires-Dist: python-levenshtein (>=0.26)
 Requires-Dist: python-multipart (>=0.0.20,<0.0.21)
 Requires-Dist: python-slugify (>=8)
 Requires-Dist: requests (>=2)
+Requires-Dist: sendgrid (>=6.10.0)
 Requires-Dist: shortuuid (>=1.0.13)
 Requires-Dist: spacy (>=3.8.7)
 Requires-Dist: spacy-syllables (>=3)
 Requires-Dist: srsly (>=2.5.1)
+Requires-Dist: stripe (>=7.0.0)
 Requires-Dist: syllables (>=1)
 Requires-Dist: syrics (>=0)
 Requires-Dist: thefuzz (>=0.22)

{karaoke_gen-0.76.28 → karaoke_gen-0.81.5}/lyrics_transcriber_temp/lyrics_transcriber/correction/agentic/providers/config.py

@@ -18,6 +18,11 @@ class ProviderConfig:
     privacy_mode: bool
     cache_dir: str
 
+    # GCP/Vertex AI settings
+    # Note: Gemini 3 models require 'global' location (not regional like us-central1)
+    gcp_project_id: Optional[str] = None
+    gcp_location: str = "global"
+
     request_timeout_seconds: float = 30.0
     max_retries: int = 2
     retry_backoff_base_seconds: float = 0.2
@@ -46,6 +51,8 @@ class ProviderConfig:
             openrouter_api_key=os.getenv("OPENROUTER_API_KEY"),
             privacy_mode=os.getenv("PRIVACY_MODE", "false").lower() in {"1", "true", "yes"},
             cache_dir=cache_dir,
+            gcp_project_id=os.getenv("GOOGLE_CLOUD_PROJECT") or os.getenv("GCP_PROJECT_ID"),
+            gcp_location=os.getenv("GCP_LOCATION", "global"),
             request_timeout_seconds=float(os.getenv("AGENTIC_TIMEOUT_SECONDS", "30.0")),
             max_retries=int(os.getenv("AGENTIC_MAX_RETRIES", "2")),
             retry_backoff_base_seconds=float(os.getenv("AGENTIC_BACKOFF_BASE_SECONDS", "0.2")),

{karaoke_gen-0.76.28 → karaoke_gen-0.81.5}/lyrics_transcriber_temp/lyrics_transcriber/correction/agentic/providers/langchain_bridge.py

@@ -187,26 +187,41 @@ class LangChainBridge(BaseAIProvider):
     
     def _invoke_model(self, prompt: str) -> str:
         """Invoke the chat model with a prompt.
-        
+
         This is a simple wrapper that can be passed to the retry executor.
-        
+
         Args:
             prompt: The prompt to send
-            
+
         Returns:
             Response content as string
-            
+
         Raises:
             Exception: Any error from the model invocation
         """
         from langchain_core.messages import HumanMessage
-        
+
         # Prepare config with session_id in metadata (Langfuse format)
         config = {}
         if hasattr(self, '_session_id') and self._session_id:
             config["metadata"] = {"langfuse_session_id": self._session_id}
             logger.debug(f"🤖 [LangChain] Invoking with session_id: {self._session_id}")
-        
+
         response = self._chat_model.invoke([HumanMessage(content=prompt)], config=config)
-        return response.content
+        content = response.content
+
+        # Handle multimodal response format from Gemini 3+ models
+        # Response can be a list of content parts: [{'type': 'text', 'text': '...'}]
+        if isinstance(content, list):
+            # Extract text from the first text content part
+            for part in content:
+                if isinstance(part, dict) and part.get('type') == 'text':
+                    return part.get('text', '')
+            # Fallback: concatenate all text parts
+            return ''.join(
+                part.get('text', '') if isinstance(part, dict) else str(part)
+                for part in content
+            )
+
+        return content
 

{karaoke_gen-0.76.28 → karaoke_gen-0.81.5}/lyrics_transcriber_temp/lyrics_transcriber/correction/agentic/providers/model_factory.py

@@ -155,6 +155,8 @@ class ModelFactory:
                 return self._create_openai_model(model_name, callbacks, config)
             elif provider == "anthropic":
                 return self._create_anthropic_model(model_name, callbacks, config)
+            elif provider in ("vertexai", "google"):
+                return self._create_vertexai_model(model_name, callbacks, config)
             else:
                 raise ValueError(f"Unsupported provider: {provider}")
         except ImportError as e:
@@ -197,7 +199,7 @@ class ModelFactory:
     ) -> Any:
         """Create ChatAnthropic model."""
         from langchain_anthropic import ChatAnthropic
-        
+
         model = ChatAnthropic(
             model=model_name,
             timeout=config.request_timeout_seconds,
@@ -207,3 +209,25 @@ class ModelFactory:
         logger.debug(f"🤖 Created Anthropic model: {model_name}")
         return model
 
+    def _create_vertexai_model(
+        self, model_name: str, callbacks: List[Any], config: ProviderConfig
+    ) -> Any:
+        """Create ChatVertexAI model for Google Gemini via Vertex AI.
+
+        Uses Application Default Credentials (ADC) for authentication.
+        In Cloud Run, this uses the service account automatically.
+        Locally, run: gcloud auth application-default login
+        """
+        from langchain_google_vertexai import ChatVertexAI
+
+        model = ChatVertexAI(
+            model=model_name,
+            project=config.gcp_project_id,
+            location=config.gcp_location,
+            timeout=config.request_timeout_seconds,
+            max_retries=config.max_retries,
+            callbacks=callbacks,
+        )
+        logger.debug(f"🤖 Created Vertex AI model: {model_name} (project={config.gcp_project_id})")
+        return model
+

karaoke_gen-0.81.5/lyrics_transcriber_temp/lyrics_transcriber/correction/agentic/router.py

@@ -0,0 +1,40 @@
+from __future__ import annotations
+
+import os
+from typing import Dict, Any
+
+from .providers.config import ProviderConfig
+
+# Default model for cloud deployments - Gemini 3 Flash via Vertex AI
+# Note: Gemini 3 models require 'global' location (not regional like us-central1)
+DEFAULT_CLOUD_MODEL = "vertexai/gemini-3-flash-preview"
+
+
+class ModelRouter:
+    """Rules-based routing by gap type/length/uncertainty (scaffold)."""
+
+    def __init__(self, config: ProviderConfig | None = None):
+        self._config = config or ProviderConfig.from_env()
+
+    def choose_model(self, gap_type: str, uncertainty: float) -> str:
+        """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)
+        - "ollama/llama3.2:latest" for local Ollama models
+        - "openai/gpt-4" for OpenAI models
+        - "anthropic/claude-3-sonnet-20240229" for Anthropic models
+        """
+        # Check for explicit model override from environment
+        env_model = os.getenv("AGENTIC_AI_MODEL")
+        if env_model:
+            return env_model
+
+        # Privacy mode: use local Ollama
+        if self._config.privacy_mode:
+            return "ollama/llama3.2:latest"
+
+        # Default to Gemini 3 Flash for all cases (fast, cost-effective, latest capabilities)
+        return DEFAULT_CLOUD_MODEL
+
+

{karaoke_gen-0.76.28 → karaoke_gen-0.81.5}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "karaoke-gen"
-version = "0.76.28"
+version = "0.81.5"
 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 <andrew@beveridge.uk>"]
 license = "MIT"
@@ -66,6 +66,7 @@ langchain-core = ">=0.3.0"
 langchain-openai = ">=0.2.0"
 langchain-anthropic = ">=0.2.0"
 langchain-ollama = ">=0.2.0"
+langchain-google-vertexai = ">=3.1.1"
 langfuse = ">=3.0.0"
 jiwer = ">=3.0.0"
 kbputils = "^0.0.16"
@@ -93,6 +94,10 @@ google-cloud-tasks = ">=2.16.0"  # Cloud Tasks for worker coordination (Phase 1
 google-cloud-run = ">=0.10.0"  # Cloud Run Jobs for long-running video encoding (Phase 2 scalability)
 python-dotenv = ">=1.0.0"
 pydub = ">=0.25.1"
+# Payment and email services
+stripe = ">=7.0.0"
+sendgrid = ">=6.10.0"
+email-validator = ">=2.0.0"  # For Pydantic EmailStr validation
 # OpenTelemetry for distributed tracing
 opentelemetry-api = ">=1.20.0"
 opentelemetry-sdk = ">=1.20.0"

karaoke_gen-0.76.28/lyrics_transcriber_temp/lyrics_transcriber/correction/agentic/router.py

@@ -1,35 +0,0 @@
-from __future__ import annotations
-
-import os
-from typing import Dict, Any
-
-from .providers.config import ProviderConfig
-
-
-class ModelRouter:
-    """Rules-based routing by gap type/length/uncertainty (scaffold)."""
-
-    def __init__(self, config: ProviderConfig | None = None):
-        self._config = config or ProviderConfig.from_env()
-
-    def choose_model(self, gap_type: str, uncertainty: float) -> str:
-        """Choose appropriate model based on gap characteristics.
-        
-        Returns model identifier in format "provider/model" for LangChain:
-        - "ollama/gpt-oss:latest" for local Ollama models
-        - "openai/gpt-4" for OpenAI models  
-        - "anthropic/claude-3-sonnet-20240229" for Anthropic models
-        """
-        # Simple baseline per technical guidance
-        if self._config.privacy_mode:
-            # Use the actual model from env, or default to a common Ollama model
-            return os.getenv("AGENTIC_AI_MODEL", "ollama/gpt-oss:latest")
-        
-        # For high-uncertainty gaps, use Claude (best reasoning)
-        if uncertainty > 0.5:
-            return "anthropic/claude-3-sonnet-20240229"
-        
-        # Default to GPT-4 for general cases
-        return "openai/gpt-4"
-
-