Files
Enterprise-Knowledge-Base/internal/models/rerank/remote_api.go
T
wizardchen fd3e2992b1 feat(models): support custom HTTP headers across all remote model calls
Introduce per-model `custom_headers` config (similar to OpenAI Python SDK's
`extra_headers`) so users can inject gateway auth tokens, trace IDs, etc.
into every outbound API request for chat / embedding / rerank / VLLM / ASR
models. Reserved headers like Authorization / Content-Type are always
preserved to avoid breaking auth or signing flows.

Along the way, unify production and "test connection" paths onto a single
`ConfigFromModel(*types.Model, appID, appSecret)` constructor in each
model package. Both `service.modelService.GetXxxModel` and the four
`handler.initialization.Check*Model` / `TestEmbeddingModel` endpoints now
go through the same field mapping, so new parameters only need to be
added in one place.

Backend:
- Add `CustomHeaders map[string]string` to `types.ModelParameters` with
  JSON/YAML `omitempty` tags for forward compatibility.
- New `internal/utils/extraheaders.go` providing `ApplyCustomHeaders`
  (for hand-rolled HTTP paths) and `WrapHTTPClientWithHeaders` /
  `CustomHeadersRoundTripper` (for SDK paths like go-openai). Reserved
  headers (Authorization, api-key, Content-Type, Accept, Host,
  Content-Length, User-Agent) are filtered out.
- Inject headers in every remote model path: chat (SDK + raw HTTP),
  embedding (openai/aliyun/jina/volcengine/nvidia/azure_openai), rerank
  (remote_api/aliyun/jina/nvidia/zhipu — via shared `customHeaderSetter`
  interface), VLM and ASR (via http.Client wrapping).
- Add `ConfigFromModel` to each of chat/embedding/rerank/vlm/asr,
  consolidating field mapping (ExtraConfig, CustomHeaders, InterfaceType
  defaulting, WeKnoraCloud credentials, etc.) and cover it with
  dedicated unit tests per package.
- Refactor `service/model.go`: replace ~100 lines of hand-written Config
  literals with one-line `ConfigFromModel` calls; drop the now-unused
  `stringMapToAnyMap` helper.
- Refactor `handler/initialization.go` test-connection endpoints: merge
  four ad-hoc request structs into one `ModelTestRequest`, extract
  `buildTestModel` and `resolveTenantWeKnoraCloudCreds` helpers, and
  route all four endpoints through `ConfigFromModel` + `NewXxx` so the
  test path is now behaviorally identical to production.

Frontend:
- Add `custom_headers` to the `ModelConfig` API type.
- `ModelEditorDialog.vue`: new Key-Value header editor (add/remove rows),
  auto-converts map <-> array when loading/saving, and passes the
  current header set to the `Test Connection` button so the preview
  reflects exactly what production will send.
- `ModelSettings.vue`: serialize the header array back into a map for
  the backend (drops empty rows).
- i18n: add custom-header labels / descriptions / placeholders to
  zh-CN, en-US, ru-RU, ko-KR.

Tests:
- `internal/utils/extraheaders_test.go` covers reserved-header filtering
  and round-tripper wrapping (including nil-client fallback).
- New `config_from_model_test.go` in chat / embedding / rerank / vlm /
  asr verifies all fields (CustomHeaders, ExtraConfig, InterfaceType
  defaulting, AppID/AppSecret) are propagated end-to-end.
2026-04-23 23:36:40 +08:00

127 lines
4.2 KiB
Go

package rerank
import (
"bytes"
"context"
"encoding/json"
"fmt"
"io"
"net/http"
"github.com/Tencent/WeKnora/internal/logger"
secutils "github.com/Tencent/WeKnora/internal/utils"
)
// OpenAIReranker implements a reranking system based on OpenAI models
type OpenAIReranker struct {
modelName string // Name of the model used for reranking
modelID string // Unique identifier of the model
apiKey string // API key for authentication
baseURL string // Base URL for API requests
client *http.Client // HTTP client for making API requests
customHeaders map[string]string
}
// SetCustomHeaders 设置用户自定义 HTTP 请求头(类似 OpenAI Python SDK 的 extra_headers)。
func (r *OpenAIReranker) SetCustomHeaders(headers map[string]string) {
r.customHeaders = headers
}
// RerankRequest represents a request to rerank documents based on relevance to a query
type RerankRequest struct {
Model string `json:"model"` // Model to use for reranking
Query string `json:"query"` // Query text to compare documents against
Documents []string `json:"documents"` // List of document texts to rerank
AdditionalData map[string]interface{} `json:"additional_data"` // Optional additional data for the model
TruncatePromptTokens int `json:"truncate_prompt_tokens"` // Maximum prompt tokens to use
}
// RerankResponse represents the response from a reranking request
type RerankResponse struct {
ID string `json:"id"` // Request ID
Model string `json:"model"` // Model used for reranking
Usage UsageInfo `json:"usage"` // Token usage information
Results []RankResult `json:"results"` // Ranked results with relevance scores
}
// UsageInfo contains information about token usage in the API request
type UsageInfo struct {
TotalTokens int `json:"total_tokens"` // Total tokens consumed
}
// NewOpenAIReranker creates a new instance of OpenAI reranker with the provided configuration
func NewOpenAIReranker(config *RerankerConfig) (*OpenAIReranker, error) {
apiKey := config.APIKey
baseURL := "https://api.openai.com/v1"
if url := config.BaseURL; url != "" {
baseURL = url
}
return &OpenAIReranker{
modelName: config.ModelName,
modelID: config.ModelID,
apiKey: apiKey,
baseURL: baseURL,
client: &http.Client{},
}, nil
}
// Rerank performs document reranking based on relevance to the query
func (r *OpenAIReranker) Rerank(ctx context.Context, query string, documents []string) ([]RankResult, error) {
// Build the request body
requestBody := &RerankRequest{
Model: r.modelName,
Query: query,
Documents: documents,
TruncatePromptTokens: 511,
}
jsonData, err := json.Marshal(requestBody)
if err != nil {
return nil, fmt.Errorf("marshal request body: %w", err)
}
// Send the request
req, err := http.NewRequestWithContext(ctx, "POST", fmt.Sprintf("%s/rerank", r.baseURL), bytes.NewBuffer(jsonData))
if err != nil {
return nil, fmt.Errorf("create request: %w", err)
}
req.Header.Set("Content-Type", "application/json")
req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", r.apiKey))
secutils.ApplyCustomHeaders(req, r.customHeaders)
logger.Debugf(ctx, "%s", buildRerankRequestDebug(r.modelName, fmt.Sprintf("%s/rerank", r.baseURL), query, documents))
resp, err := r.client.Do(req)
if err != nil {
return nil, fmt.Errorf("do request: %w", err)
}
defer resp.Body.Close()
// Read the response
body, err := io.ReadAll(resp.Body)
if err != nil {
return nil, fmt.Errorf("read response body: %w", err)
}
if resp.StatusCode != http.StatusOK {
return nil, fmt.Errorf("Rerank API error: Http Status: %s", resp.Status)
}
var response RerankResponse
if err := json.Unmarshal(body, &response); err != nil {
return nil, fmt.Errorf("unmarshal response: %w", err)
}
return response.Results, nil
}
// GetModelName returns the name of the reranking model
func (r *OpenAIReranker) GetModelName() string {
return r.modelName
}
// GetModelID returns the unique identifier of the reranking model
func (r *OpenAIReranker) GetModelID() string {
return r.modelID
}