Scope of Model Support
To ensure the stability and maintainability of the AI Central platform in multi-cloud and multi-model environments, we have established unified support specifications for the integrated Large Language Models (LLM), Embedding Models, Speech and Document Recognition Models.
These specifications aim 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 have passed comprehensive tests in terms of functionality, performance, and stability, and provide service availability guarantees (SLA).
Experimental Support
-
Refers to models that have integration capabilities and can be used in the main workflow.
-
Only basic functionality tests (interface connectivity, main workflow verification) have been completed, with no guarantee of long-term performance or stability.
-
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 |
Remarks |
|---|---|---|---|
|
Large Language Models (LLM) |
GPT-4, GPT-4o, GPT-5 |
Standard Support |
Multi-round testing and integration completed |
|
Large Language Model (LLM) |
Amazon Titan |
Experimental Support |
Performance and stability evaluation not yet completed |
|
Embedding Models |
text-embedding-3-large |
Standard Support |
Suitable for knowledge retrieval and semantic matching |
|
Embedding Model |
Titan Embedding |
Experimental Support |
Performance and stability evaluation not yet completed |
|
Image Recognition / OCR |
Azure Document Intelligent |
Standard Support |
Limited to text recognition scenarios |
|
Image Recognition / OCR |
Amazon Textract |
Experimental Support |
Performance and stability evaluation not yet completed |
|
Speech Recognition (STT) |
Azure Whisper |
Standard Support |
Completed multiple rounds of testing and integration |
|
Speech Recognition (STT) |
Amazon Transcribe |
Experimental Support |
Performance and stability evaluation not yet completed |
|
Search |
Google Search |
Standard Support |
Completed multiple rounds of testing and integration |
|
Text-to-Image |
None |
Standard Support |
Standard image generation models can be adapted |
|
Text-to-Speech (TTS) |
Azure Speech, OpenAI TTS |
Experimental Support |
Functionality available, performance under verification |
Integration and Verification Requirements
-
Unified Interface Specification
-
All models must be called through a unified Model Gateway service.
-
Request and response formats must comply with the AI Central model interface specifications.
-
-
Security and Compliance
-
Calling third-party public APIs without security verification is prohibited.
-
Integrated models must comply with company data compliance requirements (privacy, security, regional restrictions, etc.).
-
-
Performance and Observability
-
Models must support call logging and performance monitoring.
-
Health checks and circuit breaker mechanisms must be established for standard support models.
-