cverse-inference-core v0.1.0
subsystem
capsule://quake0day/[email protected]
The core Python inference service that provides a unified gRPC interface for various AI capabilities. It dynamically registers and dispatches requests to different AI model plugins (ASR, LLM, TTS, Avatar, VoiceLLM, RAG).
Owns
- gRPC server implementation for AI services
- Plugin registration and discovery mechanism
- Core inference service definitions and types
Does not own
- Specific AI model implementations (delegates to plugins)
- Go orchestration logic
- Frontend UI
AI orientation
An AI agent working on this capsule would focus on improving the plugin architecture, enhancing gRPC service stability, or optimizing the dispatching mechanism. It requires strong Python skills and understanding of gRPC and plugin-based architectures.
Avoid
- Implementing specific AI models directly within the core service.
- Modifying Go backend logic.
Provides
http_api:asr-grpc— gRPC API for Automatic Speech Recognition.http_api:avatar-grpc— gRPC API for avatar generation.http_api:llm-grpc— gRPC API for Large Language Models.http_api:rag-grpc— gRPC API for Retrieval Augmented Generation.http_api:tts-grpc— gRPC API for Text-to-Speech.http_api:voice-llm-grpc— gRPC API for Voice-enabled Large Language Models.
Requires
library:asr-pluginfromcverse-asr-inference-adapter— Interface for ASR model plugins.library:avatar-pluginfromcverse-avatar-inference-adapter— Interface for avatar model plugins.library:llm-pluginfromcverse-llm-inference-adapter— Interface for LLM plugins.library:rag-pluginfromcverse-rag-inference-adapter— Interface for RAG plugins.library:tts-pluginfromcverse-tts-inference-adapter— Interface for TTS model plugins.library:voice-llm-pluginfromcverse-voice-llm-inference-adapter— Interface for VoiceLLM plugins.
Dependencies
Capsules
cverse-protobuf>=0.1.0
Invariants (must always hold)
- gRPC endpoints must be available and respond to requests.
- Plugins must be discoverable and loadable at runtime.
- The core service must provide a consistent interface for all AI capabilities.
Source files (15)
Click any file to view its content; the path on the right shows where the file lands when this capsule is installed.
src/inference/__init__.py→__init__.pysrc/inference/core/__init__.py→core/__init__.pysrc/inference/core/config.py→core/config.pysrc/inference/core/registry.py→core/registry.pysrc/inference/core/types.py→core/types.pysrc/inference/server.py→server.pysrc/inference/services/__init__.py→services/__init__.pysrc/inference/services/asr_service.py→services/asr_service.pysrc/inference/services/avatar_service.py→services/avatar_service.pysrc/inference/services/llm_service.py→services/llm_service.pysrc/inference/services/rag_service.py→services/rag_service.pysrc/inference/services/tts_service.py→services/tts_service.pysrc/inference/services/voice_llm_service.py→services/voice_llm_service.pysrc/inference/plugins/__init__.py→plugins/__init__.pysrc/inference/plugins/base.py→plugins/base.py
Plus capsule.yaml and
install.json.