Sakurasan
ef3025dd80
Major rewrite of the Go backend to support:
- Three API format imports: openai, anthropic, compatible
- Three protocol conversions: Chat Completions, Responses, Messages
- Hub-and-spoke architecture with Chat as intermediate format
Deleted:
- opencat.go (old entry)
- store/, team/, pkg/team/, pkg/store/ (old data layer)
- internal/model/, internal/consts/ (old types)
- internal/service/team/, internal/controller/team/ (old handlers)
- llm/ (removed LLM client library, pure proxy mode)
- dist/, assets/ (old build artifacts)
Added:
- internal/store/ — 9 GORM models + multi-DB support
- internal/pkg/ — crypto (AES-GCM), apikey, jwt, ratelimit, resp, tokenizer
- internal/channel/ — channel selection, weighted LB, health checks
- internal/proxy/convert/ — 6 protocol conversion functions + SSE streaming
- internal/proxy/ — gateway with request dispatch and upstream selection
- internal/usage/ — async usage recorder with batch writes
- internal/api/ — management API (auth, users, keys, channels, models)
- Makefile for build/test/deploy
Fixed API to match frontend expectations:
- Login response wraps token in { data: { token } }
- GET /api/profile route added
- Profile response wraps user in { code, data }
- Role returned as number (10=admin, 1=user)
87 lines
2.2 KiB
Go
87 lines
2.2 KiB
Go
package tokenizer
|
|
|
|
import (
|
|
"fmt"
|
|
"strings"
|
|
|
|
"github.com/pkoukk/tiktoken-go"
|
|
)
|
|
|
|
// Count 计算字符串的 token 数量
|
|
func Count(text, model string) int {
|
|
tkm, err := tiktoken.EncodingForModel(model)
|
|
if err != nil {
|
|
tkm, _ = tiktoken.GetEncoding("cl100k_base")
|
|
}
|
|
return len(tkm.Encode(text, nil, nil))
|
|
}
|
|
|
|
// Cost 计算模型调用成本（USD，按每百万 token 定价）
|
|
func Cost(model string, inputTokens, outputTokens int) float64 {
|
|
var inputPrice, outputPrice float64
|
|
|
|
switch {
|
|
case strings.Contains(model, "gpt-4o-mini"):
|
|
inputPrice = 0.15
|
|
outputPrice = 0.60
|
|
case strings.Contains(model, "gpt-4o"):
|
|
inputPrice = 2.50
|
|
outputPrice = 10.00
|
|
case strings.Contains(model, "gpt-4-turbo"):
|
|
inputPrice = 10.00
|
|
outputPrice = 30.00
|
|
case strings.Contains(model, "gpt-4"):
|
|
inputPrice = 30.00
|
|
outputPrice = 60.00
|
|
case strings.Contains(model, "gpt-3.5-turbo"):
|
|
inputPrice = 0.50
|
|
outputPrice = 1.50
|
|
case strings.Contains(model, "claude-3-5-sonnet"):
|
|
inputPrice = 3.00
|
|
outputPrice = 15.00
|
|
case strings.Contains(model, "claude-3-opus"):
|
|
inputPrice = 15.00
|
|
outputPrice = 75.00
|
|
case strings.Contains(model, "claude-3-haiku"):
|
|
inputPrice = 0.25
|
|
outputPrice = 1.25
|
|
case strings.Contains(model, "claude"):
|
|
inputPrice = 8.00
|
|
outputPrice = 24.00
|
|
case strings.Contains(model, "gemini-1.5-pro"):
|
|
inputPrice = 3.50
|
|
outputPrice = 10.50
|
|
case strings.Contains(model, "gemini-1.5-flash"):
|
|
inputPrice = 0.35
|
|
outputPrice = 0.53
|
|
case strings.Contains(model, "gemini"):
|
|
inputPrice = 0.50
|
|
outputPrice = 1.50
|
|
default:
|
|
inputPrice = 0.15
|
|
outputPrice = 0.60
|
|
}
|
|
|
|
cost := float64(inputTokens)/1e6*inputPrice + float64(outputTokens)/1e6*outputPrice
|
|
if cost < 0.000001 {
|
|
cost = 0.000001
|
|
}
|
|
return cost
|
|
}
|
|
|
|
// CostWithModel 从数据库模型记录获取定价
|
|
func CostWithModel(inputTokens, outputTokens, cacheReadTokens, cacheCreationTokens int64, inputPrice, outputPrice, cacheReadPrice float64) float64 {
|
|
cost := float64(inputTokens)/1e6*inputPrice +
|
|
float64(outputTokens)/1e6*outputPrice +
|
|
float64(cacheReadTokens)/1e6*cacheReadPrice +
|
|
float64(cacheCreationTokens)/1e6*inputPrice*1.25
|
|
if cost < 0.000001 {
|
|
cost = 0.000001
|
|
}
|
|
return cost
|
|
}
|
|
|
|
func init() {
|
|
_ = fmt.Sprintf // ensure fmt is used
|
|
}
|