Method EmbedText

pkg/vector/openai_embedder.go:55–109

EmbedText 调用 OpenAI 兼容的 embeddings 接口。

(ctx context.Context, texts []string)

// EmbedText 调用 OpenAI 兼容的 embeddings 接口。
func (e *OpenAIEmbedder) EmbedText(ctx context.Context, texts []string) ([][]float32, error) {
	if len(texts) == 0 {
		return [][]float32{}, nil
	}
	if e.APIKey == "" {
		return nil, errors.New("API key is required for OpenAIEmbedder")
	}

	reqBody := openAIEmbeddingRequest{
		Input: texts,
		Model: e.Model,
	}
	data, err := json.Marshal(reqBody)
	if err != nil {
		return nil, fmt.Errorf("marshal request: %w", err)
	}

	req, err := http.NewRequestWithContext(ctx, http.MethodPost, e.BaseURL+"/v1/embeddings", bytes.NewReader(data))
	if err != nil {
		return nil, fmt.Errorf("create request: %w", err)
	}

	req.Header.Set("Content-Type", "application/json")
	req.Header.Set("Authorization", "Bearer "+e.APIKey)

	resp, err := e.Client.Do(req)
	if err != nil {
		return nil, fmt.Errorf("send request: %w", err)
	}
	defer func() { _ = resp.Body.Close() }()

	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
		return nil, fmt.Errorf("embeddings API error: %s", resp.Status)
	}

	var apiResp openAIEmbeddingResponse
	if err := json.NewDecoder(resp.Body).Decode(&apiResp); err != nil {
		return nil, fmt.Errorf("decode response: %w", err)
	}

	if len(apiResp.Data) != len(texts) {
		return nil, fmt.Errorf("embedding response mismatch: got %d vectors, want %d", len(apiResp.Data), len(texts))
	}

	out := make([][]float32, len(apiResp.Data))
	for i, d := range apiResp.Data {
		vec := make([]float32, len(d.Embedding))
		for j, v := range d.Embedding {
			vec[j] = float32(v)
		}
		out[i] = vec
	}

	return out, nil
}