package main

import (
	"encoding/json"
	"fmt"
	"github.com/joho/godotenv"
	uuid "github.com/satori/go.uuid"
	"knowledge/utils"
	"log"
	"os"
)

func main() {
	err := godotenv.Load(".env")
	// 读取环境变量
	OPENAI_API_KEY := os.Getenv("OPENAI_KEY")
	OPENAI_API_BASE := os.Getenv("OPENAI_API_BASE")
	utils.QdrantBase = os.Getenv("QDRANT_BASE")
	utils.QdrantPort = os.Getenv("QDRANT_PORT")
	sqlTool := utils.DBTool{
		Username: os.Getenv("MySQL_Username"),
		Password: os.Getenv("MySQL_Password"),
		Server:   os.Getenv("MySQL_Server"),
		Port:     os.Getenv("MySQL_Port"),
		Database: os.Getenv("MySQL_Database"),
	}

	gpt := utils.NewChatGptTool(OPENAI_API_BASE, OPENAI_API_KEY)

	list, err := sqlTool.QuerySql("select id, content from article where ent_id=5 limit 2,1000")
	if err != nil {
		fmt.Println("Error:", err)
		return
	}
	for _, row := range list {
		if row["content"] == "" {
			continue
		}
		// 打印文件内容
		fileData := row["content"].(string)
		response, err := gpt.GetEmbedding(fileData, "text-embedding-ada-002")
		var embeddingResponse utils.EmbeddingResponse
		json.Unmarshal([]byte(response), &embeddingResponse)

		collectionName := "data_collection"
		id := uuid.NewV4().String()
		points := []map[string]interface{}{
			{
				"id":      id,
				"payload": map[string]interface{}{"text": fileData},
				"vector":  embeddingResponse.Data[0].Embedding,
			},
		}
		res, err := utils.PutPoints(collectionName, points)
		log.Println(fileData, res, err)
	}

}