feat: implement tiered billing expression evaluation and related functionality

- Added support for tiered billing expressions in the billing system.
- Introduced new types and functions for handling billing expressions, including caching and execution.
- Updated existing billing logic to accommodate tiered billing scenarios.
- Enhanced request handling to support incoming billing expression requests.
- Added tests for tiered billing functionality to ensure correctness.

relay/embedding_handler.go

@@ -3,6 +3,7 @@ package relay
 import (
 	"bytes"
 	"fmt"
+	"io"
 	"net/http"
 
 	"github.com/QuantumNous/new-api/common"
@@ -58,7 +59,7 @@ func EmbeddingHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *
 	}
 
 	logger.LogDebug(c, fmt.Sprintf("converted embedding request body: %s", string(jsonData)))
-	requestBody := bytes.NewBuffer(jsonData)
+	var requestBody io.Reader = bytes.NewBuffer(jsonData)
 	statusCodeMappingStr := c.GetString("status_code_mapping")
 	resp, err := adaptor.DoRequest(c, info, requestBody)
 	if err != nil {