Model Support

---

Scope of Model Support

To ensure the stability and maintainability of the SERVICEME platform in multi-cloud and multi-model environments, we have established unified support standards for integrated Large Language Models (LLM), Embedding Models, and Speech & Document Recognition Models.

The purpose of these standards is to:

• Reduce the complexity of multi-model compatibility and operations
• Improve overall performance and controllability
• Ensure stable availability of new features on mainstream models

Model Support Levels

Standard Support

• Refers to models that are fully included within the product support scope.
• Medalsoft has completed comprehensive testing covering functionality, performance, and stability, and the models have passed product-level validation.
• These models are suitable for stable use in production environments and are covered by service availability guarantees (SLA).

Experimental Support

• Refers to models that have been integrated and can be used within the main workflow for functional validation or scenario pilots.
• Only basic functional testing has been completed (such as API connectivity and main workflow verification).
• Medalsoft has not conducted performance or stability validation for these models.
• Performance and stability evaluations must be carried out and validated by users themselves.
• These models will be clearly marked as “Experimental Support” in the product documentation.

Model Categories and Support Status

Model Type	Example Models	Current Support Level	Notes
Large Language Models (LLM)	GPT-4, GPT-4o, GPT-5	Standard Support	Multi-round testing and integration completed
Embedding Models	text-embedding-3-large	Standard Support	Suitable for knowledge retrieval and semantic matching
Image Recognition / OCR	Azure Document Intelligent	Standard Support	Limited to text recognition scenarios
Speech Recognition (STT)	Azure Whisper	Standard Support	Multi-round testing and integration completed
Search	Google Search	Standard Support	Multi-round testing and integration completed
Text-to-Image	None	Standard Support	All standard image generation models are compatible
Text-to-Speech (TTS)	Azure Speech, OpenAI TTS	Experimental Support	Functionality available, performance under validation
Large Language Model (LLM)	Amazon Titan	Experimental Support	Performance and stability evaluations have not been completed
Embedding Model	Titan Embedding	Experimental Support	Performance and stability evaluations have not been completed
Image Recognition / OCR	Amazon Textract	Experimental Support	Performance and stability evaluations have not been completed
Speech-to-Text (STT)	Amazon Transcribe	Experimental Support	Performance and stability evaluations have not been completed

Integration and Verification Requirements

1. Unified Interface Standards

   • All models must be invoked through the unified Model Gateway service.
   • Request and response formats must comply with the SERVICEME model interface specification.

2. Security and Compliance

   • It is prohibited to call third-party public APIs without security verification.
   • Integrated models must comply with company data compliance requirements (privacy, security, regional restrictions, etc.).

3. Performance and Observability

   • Models must support invocation logging and performance monitoring.
   • Health checks and circuit breaker mechanisms must be established for standard support models.