feat: implement /v1/embeddings endpoint for OpenAI-compatible embeddings support

[dittops]

This pr implements comprehensive embeddings support across all AIBrix components:

Core Implementation:

• Add EmbeddingRequest, EmbeddingResponse, EmbeddingData, and EmbeddingUsage protocol models
• Implement create_embeddings abstract method in InferenceEngine base class
• Add VLLM engine implementation for embeddings with proper error handling
• Create /v1/embeddings FastAPI endpoint following existing patterns

Gateway Integration:

• Update request validation in gateway util.go to handle embeddings requests
• Support multiple input formats (string, string array, token arrays)
• Extract model and message fields for routing decisions

Testing:

• Comprehensive unit tests for all protocol models
• Integration tests for VLLM engine and API endpoint
• Test coverage for error scenarios and edge cases
• Validation tests for different input formats

Documentation:

• Complete embeddings API guide with usage examples
• RAG integration examples and best practices
• Configuration instructions and troubleshooting guide
• Performance optimization recommendations

Features:

• OpenAI-compatible API specification
• Support for float and base64 encoding formats
• Batch processing capabilities
• Proper error handling with meaningful messages
• Authentication support via API keys