xinyin025/new-api
1
0
Fork 0
mirror of https://github.com/linux-do/new-api.git synced 2025-11-09 23:53:41 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

feat: support ollama embedding

Browse Source
This commit is contained in:
CaIon
2024-03-26 19:53:53 +08:00
parent 319e97d677
commit 8eedad9470
3 changed files with 120 additions and 23 deletions
Download Patch File Download Diff File Expand all files Collapse all files

21
relay/channel/ollama/adaptor.go
View File

@@ -9,6 +9,7 @@ import (
"one-api/relay/channel"
"one-api/relay/channel/openai"
relaycommon "one-api/relay/common"
relayconstant "one-api/relay/constant"
"one-api/service"
)
@@ -19,7 +20,12 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo, request dto.GeneralOpenAIReq
}
func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
switch info.RelayMode {
case relayconstant.RelayModeEmbeddings:
return info.BaseUrl + "/api/embeddings", nil
default:
return relaycommon.GetFullRequestURL(info.BaseUrl, info.RequestURLPath, info.ChannelType), nil
}
}
func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error {
@@ -31,7 +37,12 @@ func (a *Adaptor) ConvertRequest(c *gin.Context, relayMode int, request *dto.Gen
if request == nil {
return nil, errors.New("request is nil")
}
return requestOpenAI2Ollama(*request), nil
switch relayMode {
case relayconstant.RelayModeEmbeddings:
return requestOpenAI2Embeddings(*request), nil
default:
return requestOpenAI2Ollama(*request), nil
}
}
func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error) {
@@ -44,7 +55,11 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
err, responseText = openai.OpenaiStreamHandler(c, resp, info.RelayMode)
usage, _ = service.ResponseText2Usage(responseText, info.UpstreamModelName, info.PromptTokens)
} else {
err, usage, sensitiveResp = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName, info.RelayMode)
if info.RelayMode == relayconstant.RelayModeEmbeddings {
err, usage, sensitiveResp = ollamaEmbeddingHandler(c, resp, info.PromptTokens, info.UpstreamModelName, info.RelayMode)
} else {
err, usage, sensitiveResp = openai.OpenaiHandler(c, resp, info.PromptTokens, info.UpstreamModelName, info.RelayMode)
}
}
return
}