forked from songquanpeng/one-api
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathrelay.go
218 lines (194 loc) · 5.94 KB
/
relay.go
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
package controller
import (
"fmt"
"net/http"
"one-api/common"
"strconv"
"strings"
"github.com/gin-gonic/gin"
)
type Message struct {
Role string `json:"role"`
Content string `json:"content"`
Name *string `json:"name,omitempty"`
}
const (
RelayModeUnknown = iota
RelayModeChatCompletions
RelayModeCompletions
RelayModeEmbeddings
RelayModeModerations
RelayModeImagesGenerations
RelayModeEdits
)
// https://platform.openai.com/docs/api-reference/chat
type GeneralOpenAIRequest struct {
Model string `json:"model,omitempty"`
Messages []Message `json:"messages,omitempty"`
Prompt any `json:"prompt,omitempty"`
Stream bool `json:"stream,omitempty"`
MaxTokens int `json:"max_tokens,omitempty"`
Temperature float64 `json:"temperature,omitempty"`
TopP float64 `json:"top_p,omitempty"`
N int `json:"n,omitempty"`
Input any `json:"input,omitempty"`
Instruction string `json:"instruction,omitempty"`
Size string `json:"size,omitempty"`
}
type ChatRequest struct {
Model string `json:"model"`
Messages []Message `json:"messages"`
MaxTokens int `json:"max_tokens"`
}
type TextRequest struct {
Model string `json:"model"`
Messages []Message `json:"messages"`
Prompt string `json:"prompt"`
MaxTokens int `json:"max_tokens"`
//Stream bool `json:"stream"`
}
type ImageRequest struct {
Prompt string `json:"prompt"`
N int `json:"n"`
Size string `json:"size"`
}
type Usage struct {
PromptTokens int `json:"prompt_tokens"`
CompletionTokens int `json:"completion_tokens"`
TotalTokens int `json:"total_tokens"`
}
type OpenAIError struct {
Message string `json:"message"`
Type string `json:"type"`
Param string `json:"param"`
Code any `json:"code"`
}
type OpenAIErrorWithStatusCode struct {
OpenAIError
StatusCode int `json:"status_code"`
}
type TextResponse struct {
Choices []OpenAITextResponseChoice `json:"choices"`
Usage `json:"usage"`
Error OpenAIError `json:"error"`
}
type OpenAITextResponseChoice struct {
Index int `json:"index"`
Message `json:"message"`
FinishReason string `json:"finish_reason"`
}
type OpenAITextResponse struct {
Id string `json:"id"`
Object string `json:"object"`
Created int64 `json:"created"`
Choices []OpenAITextResponseChoice `json:"choices"`
Usage `json:"usage"`
}
type OpenAIEmbeddingResponseItem struct {
Object string `json:"object"`
Index int `json:"index"`
Embedding []float64 `json:"embedding"`
}
type OpenAIEmbeddingResponse struct {
Object string `json:"object"`
Data []OpenAIEmbeddingResponseItem `json:"data"`
Model string `json:"model"`
Usage `json:"usage"`
}
type ImageResponse struct {
Created int `json:"created"`
Data []struct {
Url string `json:"url"`
}
}
type ChatCompletionsStreamResponseChoice struct {
Delta struct {
Content string `json:"content"`
} `json:"delta"`
FinishReason *string `json:"finish_reason"`
}
type ChatCompletionsStreamResponse struct {
Id string `json:"id"`
Object string `json:"object"`
Created int64 `json:"created"`
Model string `json:"model"`
Choices []ChatCompletionsStreamResponseChoice `json:"choices"`
}
type CompletionsStreamResponse struct {
Choices []struct {
Text string `json:"text"`
FinishReason string `json:"finish_reason"`
} `json:"choices"`
}
func Relay(c *gin.Context) {
relayMode := RelayModeUnknown
if strings.HasPrefix(c.Request.URL.Path, "/v1/chat/completions") {
relayMode = RelayModeChatCompletions
} else if strings.HasPrefix(c.Request.URL.Path, "/v1/completions") {
relayMode = RelayModeCompletions
} else if strings.HasPrefix(c.Request.URL.Path, "/v1/embeddings") {
relayMode = RelayModeEmbeddings
} else if strings.HasSuffix(c.Request.URL.Path, "embeddings") {
relayMode = RelayModeEmbeddings
} else if strings.HasPrefix(c.Request.URL.Path, "/v1/moderations") {
relayMode = RelayModeModerations
} else if strings.HasPrefix(c.Request.URL.Path, "/v1/images/generations") {
relayMode = RelayModeImagesGenerations
} else if strings.HasPrefix(c.Request.URL.Path, "/v1/edits") {
relayMode = RelayModeEdits
}
var err *OpenAIErrorWithStatusCode
switch relayMode {
case RelayModeImagesGenerations:
err = relayImageHelper(c, relayMode)
default:
err = relayTextHelper(c, relayMode)
}
if err != nil {
retryTimesStr := c.Query("retry")
retryTimes, _ := strconv.Atoi(retryTimesStr)
if retryTimesStr == "" {
retryTimes = common.RetryTimes
}
if retryTimes > 0 {
c.Redirect(http.StatusTemporaryRedirect, fmt.Sprintf("%s?retry=%d", c.Request.URL.Path, retryTimes-1))
} else {
if err.StatusCode == http.StatusTooManyRequests {
err.OpenAIError.Message = "当前分组上游负载已饱和,请稍后再试"
}
c.JSON(err.StatusCode, gin.H{
"error": err.OpenAIError,
})
}
channelId := c.GetInt("channel_id")
common.SysError(fmt.Sprintf("relay error (channel #%d): %s", channelId, err.Message))
// https://platform.openai.com/docs/guides/error-codes/api-errors
if shouldDisableChannel(&err.OpenAIError) {
channelId := c.GetInt("channel_id")
channelName := c.GetString("channel_name")
disableChannel(channelId, channelName, err.Message)
}
}
}
func RelayNotImplemented(c *gin.Context) {
err := OpenAIError{
Message: "API not implemented",
Type: "one_api_error",
Param: "",
Code: "api_not_implemented",
}
c.JSON(http.StatusNotImplemented, gin.H{
"error": err,
})
}
func RelayNotFound(c *gin.Context) {
err := OpenAIError{
Message: fmt.Sprintf("Invalid URL (%s %s)", c.Request.Method, c.Request.URL.Path),
Type: "invalid_request_error",
Param: "",
Code: "",
}
c.JSON(http.StatusNotFound, gin.H{
"error": err,
})
}