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 have been fully validated and included in the product's standard testing process.
• These models have passed comprehensive tests in terms of functionality, performance, and stability, and provide service availability guarantees (SLA).

Experimental Support

• Refers to models that are accessible and can be used in main workflows.
• Only basic functional tests are completed (interface connectivity, main workflow validation), with no guarantee of long-term performance or stability.
• Clearly marked as "Experimental Support" in 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, Tencent 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

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.

Future Plans

• Continuously expand standard support for mainstream models (such as Mistral, Yi, Qwen series).
• Provide model performance benchmarks and compatibility reports.
• Launch a model integration certification mechanism (Model Certification).