feat: support dify upload image file

This commit is contained in:
1808837298@qq.com
2025-03-15 19:10:12 +08:00
parent 19bfa158cc
commit dd393cd0d9
7 changed files with 239 additions and 72 deletions

View File

@@ -414,7 +414,7 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *dto.ClaudeResponse) *dto
// 加密的不管, 只输出明文的推理过程
thinkingContent = message.Thinking
case "text":
responseText = *message.Text
responseText = message.GetText()
}
}
}

View File

@@ -74,7 +74,7 @@ func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayIn
if request == nil {
return nil, errors.New("request is nil")
}
return requestOpenAI2Dify(*request), nil
return requestOpenAI2Dify(c, info, *request), nil
}
func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {

View File

@@ -8,6 +8,14 @@ type DifyChatRequest struct {
ResponseMode string `json:"response_mode"`
User string `json:"user"`
AutoGenerateName bool `json:"auto_generate_name"`
Files []DifyFile `json:"files"`
}
type DifyFile struct {
Type string `json:"type"`
TransferMode string `json:"transfer_mode"`
URL string `json:"url,omitempty"`
UploadFileId string `json:"upload_file_id,omitempty"`
}
type DifyMetaData struct {
@@ -17,6 +25,8 @@ type DifyMetaData struct {
type DifyData struct {
WorkflowId string `json:"workflow_id"`
NodeId string `json:"node_id"`
NodeType string `json:"node_type"`
Status string `json:"status"`
}
type DifyChatCompletionResponse struct {

View File

@@ -2,9 +2,12 @@ package dify
import (
"bufio"
"bytes"
"encoding/base64"
"encoding/json"
"github.com/gin-gonic/gin"
"fmt"
"io"
"mime/multipart"
"net/http"
"one-api/common"
"one-api/constant"
@@ -12,35 +15,163 @@ import (
relaycommon "one-api/relay/common"
"one-api/relay/helper"
"one-api/service"
"os"
"strings"
"github.com/gin-gonic/gin"
)
func requestOpenAI2Dify(request dto.GeneralOpenAIRequest) *DifyChatRequest {
content := ""
for _, message := range request.Messages {
if message.Role == "system" {
content += "SYSTEM: \n" + message.StringContent() + "\n"
} else if message.Role == "assistant" {
content += "ASSISTANT: \n" + message.StringContent() + "\n"
} else {
content += "USER: \n" + message.StringContent() + "\n"
func uploadDifyFile(c *gin.Context, info *relaycommon.RelayInfo, user string, media dto.MediaContent) *DifyFile {
uploadUrl := fmt.Sprintf("%s/v1/files/upload", info.BaseUrl)
switch media.Type {
case dto.ContentTypeImageURL:
// Decode base64 data
imageMedia := media.GetImageMedia()
base64Data := imageMedia.Url
// Remove base64 prefix if exists (e.g., "data:image/jpeg;base64,")
if idx := strings.Index(base64Data, ","); idx != -1 {
base64Data = base64Data[idx+1:]
}
// Decode base64 string
decodedData, err := base64.StdEncoding.DecodeString(base64Data)
if err != nil {
common.SysError("failed to decode base64: " + err.Error())
return nil
}
// Create temporary file
tempFile, err := os.CreateTemp("", "dify-upload-*")
if err != nil {
common.SysError("failed to create temp file: " + err.Error())
return nil
}
defer tempFile.Close()
defer os.Remove(tempFile.Name())
// Write decoded data to temp file
if _, err := tempFile.Write(decodedData); err != nil {
common.SysError("failed to write to temp file: " + err.Error())
return nil
}
// Create multipart form
body := &bytes.Buffer{}
writer := multipart.NewWriter(body)
// Add user field
if err := writer.WriteField("user", user); err != nil {
common.SysError("failed to add user field: " + err.Error())
return nil
}
// Create form file with proper mime type
mimeType := imageMedia.MimeType
if mimeType == "" {
mimeType = "image/jpeg" // default mime type
}
// Create form file
part, err := writer.CreateFormFile("file", fmt.Sprintf("image.%s", strings.TrimPrefix(mimeType, "image/")))
if err != nil {
common.SysError("failed to create form file: " + err.Error())
return nil
}
// Copy file content to form
if _, err = io.Copy(part, bytes.NewReader(decodedData)); err != nil {
common.SysError("failed to copy file content: " + err.Error())
return nil
}
writer.Close()
// Create HTTP request
req, err := http.NewRequest("POST", uploadUrl, body)
if err != nil {
common.SysError("failed to create request: " + err.Error())
return nil
}
req.Header.Set("Content-Type", writer.FormDataContentType())
req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
// Send request
client := service.GetImpatientHttpClient()
resp, err := client.Do(req)
if err != nil {
common.SysError("failed to send request: " + err.Error())
return nil
}
defer resp.Body.Close()
// Parse response
var result struct {
Id string `json:"id"`
}
if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {
common.SysError("failed to decode response: " + err.Error())
return nil
}
return &DifyFile{
UploadFileId: result.Id,
Type: "image",
TransferMode: "local_file",
}
}
return nil
}
func requestOpenAI2Dify(c *gin.Context, info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) *DifyChatRequest {
difyReq := DifyChatRequest{
Inputs: make(map[string]interface{}),
AutoGenerateName: false,
}
user := request.User
if user == "" {
user = helper.GetResponseID(c)
}
difyReq.User = user
files := make([]DifyFile, 0)
var content strings.Builder
for _, message := range request.Messages {
if message.Role == "system" {
content.WriteString("SYSTEM: \n" + message.StringContent() + "\n")
} else if message.Role == "assistant" {
content.WriteString("ASSISTANT: \n" + message.StringContent() + "\n")
} else {
parseContent := message.ParseContent()
for _, mediaContent := range parseContent {
switch mediaContent.Type {
case dto.ContentTypeText:
content.WriteString("USER: \n" + mediaContent.Text + "\n")
case dto.ContentTypeImageURL:
media := mediaContent.GetImageMedia()
var file *DifyFile
if media.IsRemoteImage() {
file.Type = media.MimeType
file.TransferMode = "remote_url"
file.URL = media.Url
} else {
file = uploadDifyFile(c, info, difyReq.User, mediaContent)
}
if file != nil {
files = append(files, *file)
}
}
}
}
}
difyReq.Query = content.String()
difyReq.Files = files
mode := "blocking"
if request.Stream {
mode = "streaming"
}
user := request.User
if user == "" {
user = "api-user"
}
return &DifyChatRequest{
Inputs: make(map[string]interface{}),
Query: content,
ResponseMode: mode,
User: user,
AutoGenerateName: false,
}
difyReq.ResponseMode = mode
return &difyReq
}
func streamResponseDify2OpenAI(difyResponse DifyChunkChatCompletionResponse) *dto.ChatCompletionsStreamResponse {
@@ -50,10 +181,22 @@ func streamResponseDify2OpenAI(difyResponse DifyChunkChatCompletionResponse) *dt
Model: "dify",
}
var choice dto.ChatCompletionsStreamResponseChoice
if constant.DifyDebug && difyResponse.Event == "workflow_started" {
choice.Delta.SetContentString("Workflow: " + difyResponse.Data.WorkflowId + "\n")
} else if constant.DifyDebug && difyResponse.Event == "node_started" {
choice.Delta.SetContentString("Node: " + difyResponse.Data.NodeId + "\n")
if strings.HasPrefix(difyResponse.Event, "workflow_") {
if constant.DifyDebug {
text := "Workflow: " + difyResponse.Data.WorkflowId
if difyResponse.Event == "workflow_finished" {
text += " " + difyResponse.Data.Status
}
choice.Delta.SetReasoningContent(text + "\n")
}
} else if strings.HasPrefix(difyResponse.Event, "node_") {
if constant.DifyDebug {
text := "Node: " + difyResponse.Data.NodeType
if difyResponse.Event == "node_finished" {
text += " " + difyResponse.Data.Status
}
choice.Delta.SetReasoningContent(text + "\n")
}
} else if difyResponse.Event == "message" || difyResponse.Event == "agent_message" {
choice.Delta.SetContentString(difyResponse.Answer)
}
@@ -66,38 +209,38 @@ func difyStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Re
usage := &dto.Usage{}
scanner := bufio.NewScanner(resp.Body)
scanner.Split(bufio.ScanLines)
var nodeToken int
helper.SetEventStreamHeaders(c)
for scanner.Scan() {
data := scanner.Text()
if len(data) < 5 || !strings.HasPrefix(data, "data:") {
continue
}
data = strings.TrimPrefix(data, "data:")
helper.StreamScannerHandler(c, resp, info, func(data string) bool {
var difyResponse DifyChunkChatCompletionResponse
err := json.Unmarshal([]byte(data), &difyResponse)
if err != nil {
common.SysError("error unmarshalling stream response: " + err.Error())
continue
return true
}
var openaiResponse dto.ChatCompletionsStreamResponse
if difyResponse.Event == "message_end" {
usage = &difyResponse.MetaData.Usage
break
return false
} else if difyResponse.Event == "error" {
break
return false
} else {
openaiResponse = *streamResponseDify2OpenAI(difyResponse)
if len(openaiResponse.Choices) != 0 {
responseText += openaiResponse.Choices[0].Delta.GetContentString()
if openaiResponse.Choices[0].Delta.ReasoningContent != nil {
nodeToken += 1
}
}
}
err = helper.ObjectData(c, openaiResponse)
if err != nil {
common.SysError(err.Error())
}
}
return true
})
if err := scanner.Err(); err != nil {
common.SysError("error reading stream: " + err.Error())
}
@@ -112,6 +255,7 @@ func difyStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.Re
usage.CompletionTokens, _ = service.CountTextToken("gpt-3.5-turbo", responseText)
usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
}
usage.CompletionTokens += nodeToken
return nil, usage
}