使用 Dify、Meilisearch、零一万物模型实现最简单的 RAG 应用（三）：AI 电影推荐

name: meli
# https://www.meilisearch.com/docs/learn/configuration/instance_options
services:
  meilisearch:
    image: getmeili/meilisearch:v1.8.0
    container_name: meilisearch
    restart: always
    ports:
      - 7700:7700
    volumes:
      - ./meili_data:/meili_data
    environment:
      MEILI_MASTER_KEY: "soulteary"
      MEILI_NO_ANALYTICS: "true"
      MEILI_LOG_LEVEL: "info"
      MEILI_MAX_INDEXING_MEMORY: "200 MB"
      MEILI_MAX_INDEXING_THREADS: "2"
      MEILI_HTTP_PAYLOAD_SIZE_LIMIT: "500 MB"
      # MEILI_HTTP_ADDR: 0.0.0.0:7700
      # MEILI_DB_PATH: /meili_data

# docker logs meilisearch -f

888b     d888          d8b 888 d8b                                            888
8888b   d8888          Y8P 888 Y8P                                            888
88888b.d88888              888                                                888
888Y88888P888  .d88b.  888 888 888 .d8888b   .d88b.   8888b.  888d888 .d8888b 88888b.
888 Y888P 888 d8P  Y8b 888 888 888 88K      d8P  Y8b     "88b 888P"  d88P"    888 "88b
888  Y8P  888 88888888 888 888 888 "Y8888b. 88888888 .d888888 888    888      888  888
888   "   888 Y8b.     888 888 888      X88 Y8b.     888  888 888    Y88b.    888  888
888       888  "Y8888  888 888 888  88888P'  "Y8888  "Y888888 888     "Y8888P 888  888

Config file path:	"none"
Database path:		"./data.ms"
Server listening on:	"http://0.0.0.0:7700"
Environment:		"development"
Commit SHA:		"c668043c4f4d2616cc5dee1598742c3f87303bfb"
Commit date:		"2024-05-02T14:55:32Z"
Package version:	"1.8.0"
Anonymous telemetry:	"Disabled"

A master key has been set. Requests to Meilisearch won't be authorized unless you provide an authentication key.


 Meilisearch started with a master key considered unsafe for use in a production environment.

 A master key of at least 16 bytes will be required when switching to a production environment.


We generated a new secure master key for you (you can safely use this token):

>> --master-key Pbnpc8A0IBVqDmLghU0Yj3KvZRgjBbZXNJSeDBhmdAk <<

Restart Meilisearch with the argument above to use this new and secure master key.

Check out Meilisearch Cloud!	https://www.meilisearch.com/cloud?utm_campaign=oss&utm_source=engine&utm_medium=cli
Documentation:			https://www.meilisearch.com/docs
Source code:			https://github.com/meilisearch/meilisearch
Discord:			https://discord.meilisearch.com

2024-05-20T06:42:22.290321Z  INFO actix_server::builder: starting 8 workers
2024-05-20T06:42:22.290339Z  INFO actix_server::server: Actix runtime found; starting in Actix runtime
2024-05-20T06:42:31.820935Z  INFO HTTP request{method=POST host="127.0.0.1:7700" route=/indexes/movies/documents query_parameters= user_agent=Meilisearch Go (v0.26.3) status_code=202}: meilisearch: close time.busy=13.3ms time.idle=327ms
2024-05-20T06:42:31.824691Z  INFO milli::update::index_documents::enrich: Primary key was not specified in index. Inferred to 'id'
2024-05-20T06:42:35.533861Z  INFO index_scheduler::batch: document indexing done indexing_result=DocumentAdditionResult { indexed_documents: 15309, number_of_documents: 15309 }
2024-05-20T06:42:35.700474Z  INFO index_scheduler: A batch of tasks was successfully completed with 1 successful tasks and 0 failed tasks.

{
  "id": 10515,
  "title": "Castle in the Sky",
  "overview": "A young boy and a girl with a magic crystal must race against pirates and foreign agents in a search for a legendary floating castle.",
  "genres": ["Adventure", "Fantasy", "Animation", "Action", "Family", "Romance"],
  "poster": "https://image.tmdb.org/t/p/w500/npOnzAbLh6VOIu3naU5QaEcTepo.jpg",
  "release_date": 523324800
}

package main

import (
	"encoding/json"
	"fmt"
	"os"

	"github.com/meilisearch/meilisearch-go"
)

type Movie struct {
	ID          int      `json:"id"`
	Title       string   `json:"title"`
	Overview    string   `json:"overview"`
	Genres      []string `json:"genres"`
	Poster      string   `json:"poster"`
	ReleaseDate int      `json:"release_date"`
}

func main() {
	client := meilisearch.NewClient(meilisearch.ClientConfig{
		Host:   "http://127.0.0.1:7700",
		APIKey: "soulteary",
	})

	// 创建一个名为 'movies' 的索引，用来存储后续的数据
	index := client.Index("movies")

	// 如果索引 'movies' 不存在，Meilisearch 会在第一次添加文档时创建它
	// documents := []map[string]interface{}{
	// 	{"id": 1, "title": "Carol", "genres": []string{"Romance", "Drama"}},
	// 	{"id": 2, "title": "Wonder Woman", "genres": []string{"Action", "Adventure"}},
	// 	{"id": 3, "title": "Life of Pi", "genres": []string{"Adventure", "Drama"}},
	// }

	buf, err := os.ReadFile("data/movies.json")
	if err != nil {
		fmt.Println(err)
		os.Exit(1)
	}
	var documents []Movie
	err = json.Unmarshal(buf, &documents)
	if err != nil {
		fmt.Println(err)
		os.Exit(1)

	}

	task, err := index.AddDocuments(documents)
	if err != nil {
		fmt.Println(err)
		os.Exit(1)
	}

	fmt.Println(task.TaskUID)
}

# go run main.go
0

2024-05-20T06:30:40.771571Z  INFO HTTP request{method=POST host="127.0.0.1:7700" route=/indexes/movies/documents query_parameters= user_agent=Meilisearch Go (v0.26.3) status_code=202}: meilisearch: close time.busy=3.46ms time.idle=4.30ms
2024-05-20T06:30:40.776351Z  INFO milli::update::index_documents::enrich: Primary key was not specified in index. Inferred to 'id'
2024-05-20T06:30:40.807314Z  INFO index_scheduler::batch: document indexing done indexing_result=DocumentAdditionResult { indexed_documents: 1, number_of_documents: 1 }
2024-05-20T06:30:40.809256Z  INFO index_scheduler: A batch of tasks was successfully completed with 1 successful tasks and 0 failed tasks.

<!DOCTYPE html>
<html lang="en">
  <head>
    <meta charset="utf-8" />
    <link rel="stylesheet" href="https://cdn.jsdelivr.net/npm/@meilisearch/instant-meilisearch/templates/basic_search.css" />
    <style>
      .hit-name {
        font-size: 1.2em;
        font-weight: bold;
      }
      .hit-content {
        font-size: 0.8em;
      }
    </style>
  </head>
  <body>
    <div class="wrapper">
      <div id="searchbox" focus></div>
      <div id="hits"></div>
    </div>
  </body>
  <script src="https://cdn.jsdelivr.net/npm/@meilisearch/instant-meilisearch/dist/instant-meilisearch.umd.min.js"></script>
  <script src="https://cdn.jsdelivr.net/npm/instantsearch.js@4"></script>
  <script>
    const search = instantsearch({
      indexName: "movies",
      searchClient: instantMeiliSearch("http://localhost:7700", "soulteary").searchClient,
    });
    search.addWidgets([
      instantsearch.widgets.searchBox({
        container: "#searchbox",
      }),
      instantsearch.widgets.configure({ hitsPerPage: 8 }),
      instantsearch.widgets.hits({
        container: "#hits",
        templates: {
          item: `
            <div>
              <div class="hit-name">
                    {{#helpers.highlight}}{ "attribute": "title" }{{/helpers.highlight}}
              </div>
              <div class="hit-content">
                {{#helpers.highlight}}{ "attribute": "overview" }{{/helpers.highlight}}
              </div>
            </div>
          `,
        },
      }),
    ]);
    search.start();
  </script>
</html>

curl 'http://localhost:7700/multi-search' \
  -H 'Authorization: Bearer soulteary' \
  -H 'Content-Type: application/json' \
  --data-raw '{"queries":[{"indexUid":"movies","q":"sky","limit":3,"offset":0}]}'

{"results":[{"indexUid":"movies","hits":[{"id":101031,"title":"Sky Captain and the World of Tomorrow","overview":"When gigantic robots attack New York City, \"Sky Captain\" uses his private air force to fight them off. His ex-girlfriend, reporter Polly Perkins, has been investigating the recent disappearance of prominent scientists. Suspecting a link between the global robot attacks and missing men, Sky Captain and Polly decide to work together. They fly to the Himalayas in pursuit of the mysterious Dr. Totenkopf, the mastermind behind the robots.","genres":["Mystery","Action","Thriller","Science Fiction","Adventure"],"poster":"https://image.tmdb.org/t/p/w500/ceW9Zi43hEQPdxkPkohVCcG1CuT.jpg","release_date":1095379200},{"id":102112,"title":"Sky Fighters","overview":"Les Chevaliers du ciel (English: Sky Fighters) is a 2005 French film directed by Gérard Pirès about two air force pilots preventing a terrorist attack on the Bastille Day celebrations in Paris. It is based on Tanguy et Laverdure, a comics series by Jean-Michel Charlier and Albert Uderzo – of Astérix fame, which was also made into a hugely successful TV series from 1967 to 1969 making Tanguy and Laverdure, the two main heroes, part of popular Francophone culture.","genres":["Action","Adventure"],"poster":"https://image.tmdb.org/t/p/w500/fXyIF7W059RtNwSZViVUR9bUXWX.jpg","release_date":1129334400},{"id":102368,"title":"Sky High","overview":"Set in a world where superheroes are commonly known and accepted, young Will Stronghold, the son of the Commander and Jetstream, tries to find a balance between being a normal teenager and an extraordinary being.","genres":["Adventure","Comedy","Family"],"poster":"https://image.tmdb.org/t/p/w500/yk51E2OxA9zUdRqK0YvPTx6lfa7.jpg","release_date":1122595200}],"query":"sky","processingTimeMs":4,"limit":3,"offset":0,"estimatedTotalHits":113}]}

// base on: https://github.com/soulteary/dify-simple-rag-with-wp/blob/main/main.go

package main

import (
	"net/http"

	"github.com/gin-gonic/gin"
)

type ExtensionPointRequest struct {
	Point  string `json:"point"`
	Params struct {
		AppID        string                 `json:"app_id"`
		ToolVariable string                 `json:"tool_variable"`
		Inputs       map[string]interface{} `json:"inputs"`
		Query        string                 `json:"query"`
	} `json:"params"`
}

type ExtensionPointResponse struct {
	Result string `json:"result"`
}

func main() {
	router := gin.Default()

	router.POST("/new-api-for-dify", func(c *gin.Context) {
		var req ExtensionPointRequest

		if err := c.BindJSON(&req); err != nil {
			c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
			return
		}

		if req.Point == "ping" {
			c.JSON(http.StatusOK, ExtensionPointResponse{Result: "pong"})
			return
		}

		c.JSON(http.StatusOK, ExtensionPointResponse{Result: "data processed successfully"})
	})

	router.Run(":8084")
}

你是一个资深的电影影评人，擅长根据“参考信息”来生成充满趣味性的回答，始终使用中文输出内容。

## 参考信息

{{movies_data}}

## 最终输出

router.POST("/new-api-for-dify", func(c *gin.Context) {
	var req ExtensionPointRequest

	if err := c.BindJSON(&req); err != nil {
		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
		return
	}

	if req.Point == "ping" {
		c.JSON(http.StatusOK, ExtensionPointResponse{Result: "pong"})
		return
	}

	// 打印请求信息
	dump, _ := json.Marshal(req)
	fmt.Println(string(dump))

	c.JSON(http.StatusOK, ExtensionPointResponse{Result: "data processed successfully"})
})

{"point":"app.external_data_tool.query","params":{"app_id":"55f2f15b-3731-494b-b034-240cd169d0cb","tool_variable":"movies_data","inputs":{"keywords":"sky"},"query":"为什么推荐这几部电影？"}}
[GIN] 2024/05/20 - 21:56:17 | 200 |     1.08275ms |     10.11.12.90 | POST     "/new-api-for-dify"

{"point":"app.external_data_tool.query","params":{"app_id":"55f2f15b-3731-494b-b034-240cd169d0cb","tool_variable":"movies_data","inputs":{"keywords":"sky"},"query":"为什么推荐这几部电影？"}}

// ...
if req.Point == "ping" {
	c.JSON(http.StatusOK, ExtensionPointResponse{Result: "pong"})
	return
}

// 之前的代码

if req.Point != "app.external_data_tool.query" {
	c.JSON(http.StatusBadRequest, gin.H{"error": "invalid point"})
	return
}

keywords, exist := req.Params.Inputs["keywords"]
if !exist {
	c.JSON(http.StatusBadRequest, gin.H{"error": "missing keyword"})
	return
}

s := strings.TrimSpace(fmt.Sprintf("%s", keywords))
if s == "" {
	c.JSON(http.StatusBadRequest, gin.H{"error": "empty keyword"})
	return
}

movies, err := GetSearchResult(s, 3, "movies", 0, "soulteary")
if err != nil {
	c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
	return
}

type QueryPayload struct {
	Queries []QueryBody `json:"queries"`
}

type QueryBody struct {
	IndexUID string `json:"indexUid"`
	Q        string `json:"q"`
	Limit    int    `json:"limit"`
	Offset   int    `json:"offset"`
}

type SearchResults struct {
	Results []SearchResult `json:"results"`
}

type SearchResult struct {
	IndexUID string `json:"indexUid"`
	Hits     []struct {
		ID          int      `json:"id"`
		Title       string   `json:"title"`
		Overview    string   `json:"overview"`
		Genres      []string `json:"genres"`
		Poster      string   `json:"poster"`
		ReleaseDate int      `json:"release_date"`
	} `json:"hits"`
	Query              string `json:"query"`
	ProcessingTimeMs   int    `json:"processingTimeMs"`
	Limit              int    `json:"limit"`
	Offset             int    `json:"offset"`
	EstimatedTotalHits int    `json:"estimatedTotalHits"`
}

func GetSearchResult(search string, count int, indexes string, page int, token string) (result SearchResults, err error) {
	client := &http.Client{}

	var queryBody QueryBody
	queryBody.IndexUID = indexes
	queryBody.Q = search
	queryBody.Limit = count
	queryBody.Offset = page

	var queryPayload QueryPayload
	queryPayload.Queries = append(queryPayload.Queries, queryBody)

	payload, err := json.Marshal(queryPayload)
	if err != nil {
		return result, err
	}

	var data = strings.NewReader(string(payload))
	req, err := http.NewRequest("POST", "http://localhost:7700/multi-search", data)
	if err != nil {
		return result, err
	}

	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", token))
	req.Header.Set("Content-Type", "application/json")
	resp, err := client.Do(req)
	if err != nil {
		return result, err
	}
	defer resp.Body.Close()

	bodyText, err := io.ReadAll(resp.Body)
	if err != nil {
		return result, err
	}

	err = json.Unmarshal(bodyText, &result)
	if err != nil {
		return result, err
	}
	return result, nil
}

movies, err := GetSearchResult(s, 3, "movies", 0, "soulteary")
if err != nil {
	c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
	return
}

// 之前的代码

var result string
for _, movie := range movies.Results {
	for _, hit := range movie.Hits {
		result += fmt.Sprintf("- 标题：%s\n", hit.Title)
		result += fmt.Sprintf("- 简介：%s\n\n", hit.Overview)
	}
}

c.JSON(http.StatusOK, ExtensionPointResponse{Result: result})

// base on: https://github.com/soulteary/dify-simple-rag-with-wp/blob/main/main.go

package main

import (
	"encoding/json"
	"fmt"
	"io"
	"net/http"
	"strings"

	"github.com/gin-gonic/gin"
)

type QueryPayload struct {
	Queries []QueryBody `json:"queries"`
}

type QueryBody struct {
	IndexUID string `json:"indexUid"`
	Q        string `json:"q"`
	Limit    int    `json:"limit"`
	Offset   int    `json:"offset"`
}

type SearchResults struct {
	Results []SearchResult `json:"results"`
}

type SearchResult struct {
	IndexUID string `json:"indexUid"`
	Hits     []struct {
		ID          int      `json:"id"`
		Title       string   `json:"title"`
		Overview    string   `json:"overview"`
		Genres      []string `json:"genres"`
		Poster      string   `json:"poster"`
		ReleaseDate int      `json:"release_date"`
	} `json:"hits"`
	Query              string `json:"query"`
	ProcessingTimeMs   int    `json:"processingTimeMs"`
	Limit              int    `json:"limit"`
	Offset             int    `json:"offset"`
	EstimatedTotalHits int    `json:"estimatedTotalHits"`
}

func GetSearchResult(search string, count int, indexes string, page int, token string) (result SearchResults, err error) {
	client := &http.Client{}

	var queryBody QueryBody
	queryBody.IndexUID = indexes
	queryBody.Q = search
	queryBody.Limit = count
	queryBody.Offset = page

	var queryPayload QueryPayload
	queryPayload.Queries = append(queryPayload.Queries, queryBody)

	payload, err := json.Marshal(queryPayload)
	if err != nil {
		return result, err
	}

	var data = strings.NewReader(string(payload))
	req, err := http.NewRequest("POST", "http://localhost:7700/multi-search", data)
	if err != nil {
		return result, err
	}

	req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", token))
	req.Header.Set("Content-Type", "application/json")
	resp, err := client.Do(req)
	if err != nil {
		return result, err
	}
	defer resp.Body.Close()

	bodyText, err := io.ReadAll(resp.Body)
	if err != nil {
		return result, err
	}

	err = json.Unmarshal(bodyText, &result)
	if err != nil {
		return result, err
	}
	return result, nil
}

type ExtensionPointRequest struct {
	Point  string `json:"point"`
	Params struct {
		AppID        string                 `json:"app_id"`
		ToolVariable string                 `json:"tool_variable"`
		Inputs       map[string]interface{} `json:"inputs"`
		Query        string                 `json:"query"`
	} `json:"params"`
}

type ExtensionPointResponse struct {
	Result string `json:"result"`
}

func main() {
	router := gin.Default()

	router.POST("/new-api-for-dify", func(c *gin.Context) {
		var req ExtensionPointRequest

		if err := c.BindJSON(&req); err != nil {
			c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
			return
		}

		if req.Point == "ping" {
			c.JSON(http.StatusOK, ExtensionPointResponse{Result: "pong"})
			return
		}

		if req.Point != "app.external_data_tool.query" {
			c.JSON(http.StatusBadRequest, gin.H{"error": "invalid point"})
			return
		}

		keywords, exist := req.Params.Inputs["keywords"]
		if !exist {
			c.JSON(http.StatusBadRequest, gin.H{"error": "missing keyword"})
			return
		}

		s := strings.TrimSpace(fmt.Sprintf("%s", keywords))
		if s == "" {
			c.JSON(http.StatusBadRequest, gin.H{"error": "empty keyword"})
			return
		}

		movies, err := GetSearchResult(s, 3, "movies", 0, "soulteary")
		if err != nil {
			c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
			return
		}

		var result string
		for _, movie := range movies.Results {
			for _, hit := range movie.Hits {
				result += fmt.Sprintf("- 标题：%s\n", hit.Title)
				result += fmt.Sprintf("- 简介：%s\n\n", hit.Overview)
			}
		}

		c.JSON(http.StatusOK, ExtensionPointResponse{Result: result})
	})

	router.Run(":8084")
}