Files
Enterprise-Knowledge-Base/internal/models/provider/openai.go
T
wizardchen 9e08ab7302 fix(chat): map MaxTokens to MaxCompletionTokens for GPT-5/o-series
OpenAI's GPT-5 series and o-series reasoning models (o1/o3/o4-mini) no
longer accept `max_tokens` and reject non-default sampling params
(`temperature`, `top_p`, `frequency_penalty`, `presence_penalty`).
Azure OpenAI propagates the same constraint, returning HTTP 400 with
"this model is not supported MaxTokens, please use MaxCompletionTokens".

Lower the compatibility shim into `RemoteAPIChat.BuildChatCompletionRequest`
(the single OpenAI-protocol egress) so every internal caller keeps using
`MaxTokens` uniformly:

- Add `provider.IsOpenAIReasoningOrGPT5Model` with precise prefix matching
  (covers `gpt-5*`, `o1`/`o1-*`, `o3`/`o3-*`, `o4`/`o4-*`; rejects
  `olympus-1`, `openai-*`, `o3xtra`, etc.).
- When the provider is `openai`/`azure_openai` and the model matches, map
  `MaxTokens` to `MaxCompletionTokens` (explicit `MaxCompletionTokens`
  wins) and skip the unsupported sampling fields; `omitempty` keeps them
  off the wire.
- Behavior is unchanged for gpt-4o, gpt-4, and all other providers.

Add unit tests for the matcher and for the request-building path
(Azure gpt-5.2, OpenAI gpt-5/o1-mini/o3/o4-mini, plus negative cases).

Fixes #1283
2026-05-13 00:40:35 +08:00

87 lines
2.5 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
package provider
import (
"fmt"
"strings"
"github.com/Tencent/WeKnora/internal/types"
)
const (
OpenAIBaseURL = "https://api.openai.com/v1"
)
// OpenAIProvider 实现 OpenAI 的 Provider 接口
type OpenAIProvider struct{}
func init() {
Register(&OpenAIProvider{})
}
// Info 返回 OpenAI provider 的元数据
func (p *OpenAIProvider) Info() ProviderInfo {
return ProviderInfo{
Name: ProviderOpenAI,
DisplayName: "OpenAI",
Description: "gpt-5.2, gpt-5-mini, etc.",
DefaultURLs: map[types.ModelType]string{
types.ModelTypeKnowledgeQA: OpenAIBaseURL,
types.ModelTypeEmbedding: OpenAIBaseURL,
types.ModelTypeRerank: OpenAIBaseURL,
types.ModelTypeVLLM: OpenAIBaseURL,
types.ModelTypeASR: OpenAIBaseURL,
},
ModelTypes: []types.ModelType{
types.ModelTypeKnowledgeQA,
types.ModelTypeEmbedding,
types.ModelTypeRerank,
types.ModelTypeVLLM,
types.ModelTypeASR,
},
RequiresAuth: true,
}
}
// ValidateConfig 验证 OpenAI provider 配置
func (p *OpenAIProvider) ValidateConfig(config *Config) error {
if config.APIKey == "" {
return fmt.Errorf("API key is required for OpenAI provider")
}
if config.ModelName == "" {
return fmt.Errorf("model name is required")
}
return nil
}
// IsOpenAIReasoningOrGPT5Model 判断模型是否为 OpenAI / Azure OpenAI 的
// 推理类(o-series)或 GPT-5 系列模型。
//
// 这些模型在 OpenAI Chat Completions API 中:
// - 不再支持 `max_tokens`,必须使用 `max_completion_tokens`;
// - 仅支持默认的 `temperature=1`、`top_p=1`,且不支持 `frequency_penalty` /
// `presence_penalty` 等采样参数(传非默认值会被拒绝)。
//
// 参考:
// - https://platform.openai.com/docs/api-reference/chat
// - https://learn.microsoft.com/azure/ai-services/openai/how-to/reasoning
//
// 仅基于模型名做启发式匹配;对于 Azure OpenAI,因为模型名实际上是 deployment 名,
// 用户若用了自定义部署名我们无法识别,此时仍会按普通模型处理(保持原行为)。
func IsOpenAIReasoningOrGPT5Model(modelName string) bool {
name := strings.ToLower(strings.TrimSpace(modelName))
if name == "" {
return false
}
if strings.HasPrefix(name, "gpt-5") {
return true
}
// o1 / o1-mini / o1-preview / o3 / o3-mini / o4-mini ...
// 必须精确匹配,避免误命中 "openai-..." 之类。
for _, prefix := range []string{"o1", "o3", "o4"} {
if name == prefix || strings.HasPrefix(name, prefix+"-") {
return true
}
}
return false
}