AI 网关切换 OpenAI 兼容面并移除 chat 端点,新增模型黑白名单
This commit is contained in:
@@ -0,0 +1,73 @@
|
||||
package oci
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"context"
|
||||
"fmt"
|
||||
"io"
|
||||
"net/http"
|
||||
|
||||
"github.com/oracle/oci-go-sdk/v65/common"
|
||||
)
|
||||
|
||||
// compatResponsesLimit 限制直通响应体大小;web_search 输出含多段引用,给足余量。
|
||||
const compatResponsesLimit = int64(8 << 20)
|
||||
|
||||
// GenAiCompatResponses 实现 Client:把 OpenAI Responses 请求体直通到 OCI
|
||||
// `/20231130/actions/v1/responses`(IAM 签名)。该端点实测可执行 xAI 服务端工具
|
||||
// (web_search / x_search),但不在 Oracle 文档化工具白名单内,行为可能随服务
|
||||
// 版本、模型或区域变化;调用方须自行校验并改写请求体(store/stream)。
|
||||
func (c *RealClient) GenAiCompatResponses(ctx context.Context, cred Credentials, region string, body []byte) ([]byte, error) {
|
||||
ic, err := c.genAiInferenceClient(cred, region)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
client := ic.BaseClient
|
||||
common.UpdateEndpointTemplateForOptions(&client)
|
||||
common.SetMissingTemplateParams(&client)
|
||||
request, err := http.NewRequestWithContext(ctx, http.MethodPost, "/actions/v1/responses", bytes.NewReader(body))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("build compat responses request: %w", err)
|
||||
}
|
||||
request.Header.Set("Content-Type", "application/json")
|
||||
request.Header.Set("CompartmentId", cred.TenancyOCID)
|
||||
request.Header.Set("opc-compartment-id", cred.TenancyOCID)
|
||||
response, err := client.Call(ctx, request)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
defer response.Body.Close()
|
||||
payload, err := io.ReadAll(io.LimitReader(response.Body, compatResponsesLimit))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("read compat responses body: %w", err)
|
||||
}
|
||||
return payload, nil
|
||||
}
|
||||
|
||||
// GenAiCompatResponsesStream 实现 Client:以流式直通 OCI `/actions/v1/responses`,
|
||||
// 建立成功(2xx)返回 SSE body(调用方负责 Close);建立失败返回 SDK ServiceError,
|
||||
// 与既有渠道切换/熔断错误分类兼容。请求体须由调用方置 stream:true。
|
||||
func (c *RealClient) GenAiCompatResponsesStream(ctx context.Context, cred Credentials, region string, body []byte) (io.ReadCloser, error) {
|
||||
ic, err := c.genAiInferenceClient(cred, region)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
client := ic.BaseClient
|
||||
common.UpdateEndpointTemplateForOptions(&client)
|
||||
common.SetMissingTemplateParams(&client)
|
||||
request, err := http.NewRequestWithContext(ctx, http.MethodPost, "/actions/v1/responses", bytes.NewReader(body))
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("build compat responses stream request: %w", err)
|
||||
}
|
||||
request.Header.Set("Content-Type", "application/json")
|
||||
request.Header.Set("CompartmentId", cred.TenancyOCID)
|
||||
request.Header.Set("opc-compartment-id", cred.TenancyOCID)
|
||||
response, err := client.Call(ctx, request)
|
||||
if err != nil {
|
||||
if response != nil && response.Body != nil {
|
||||
response.Body.Close()
|
||||
}
|
||||
return nil, err
|
||||
}
|
||||
return response.Body, nil
|
||||
}
|
||||
Reference in New Issue
Block a user