Files
oci-portal/internal/oci/genai_responses.go
T
wangdefa 0a86b5a291
CI / test (push) Successful in 32s
Release / release (push) Successful in 1m4s
AI网关新增TTS/重排/审核端点,xAI工具扩展,swagger修缺
- 新端点 /ai/v1/audio/speech(xai.grok-tts)、/rerank(cohere.rerank-v4)、/moderations(OCI Guardrails)
- Responses 放行 code_interpreter 与远程 mcp 工具,web_search/x_search 解除仅非流式限制
- 模型能力映射扩展:TEXT_RERANK→RERANK、TEXT_TO_AUDIO→TTS
- AI 网关文档独立 docs/ai-gateway.md,字段兼容矩阵只列支持项;README 精简引用
- swagger 修缺:135 处响应注解具体化,RawMessage/联合类型统一渲染 AnyJSON,overrides 迁至 docs/.swaggo
- CHANGELOG 0.4.0,版本段不再记日期;DASH_VERSION v0.4.0
2026-07-13 20:17:06 +08:00

74 lines
2.7 KiB
Go

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)。xAI 服务端工具(web_search /
// x_search / code_interpreter)与 mcp 已被 Oracle 文档正式支持,工具参数与限制
// 遵循 xAI 规格;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
}