当前位置：首页 > news >正文

开源模型应用落地-工具使用篇-从零开始搭建Qdrant Web UI-可视化管理工具-Windows（十）

news 来源：原创 2025/6/14 11:43:09

一、前言

Qdrant 是一个高性能的向量搜索引擎，广泛应用于相似性搜索、推荐系统和大规模数据检索等场景。虽然其原生 API 提供了强大的功能，但对于开发者和运维人员来说，缺乏直观的可视化界面常常增加了使用门槛。为了解决这一问题，Qdrant Web UI 应运而生——它提供了一个简洁友好的前端操作界面，帮助用户更高效地管理集合、查看数据、执行查询和监控服务状态。

本文将手把手带你搭建 Qdrant Web UI，从环境准备到部署运行，一步步实现对 Qdrant 服务的可视化管理，让向量数据库的操作变得更加简单直观。

二、术语

2.1、向量数据库

向量数据库是一种专门用于存储和处理高维向量数据的数据库系统。与传统的关系型数据库或文档数据库不同，向量数据库的设计目标是高效地支持向量数据的索引和相似性搜索。

在传统数据库中，数据通常是以结构化的表格形式存储，每个记录都有预定义的字段。但是，对于包含大量高维向量的数据，如图像、音频、文本等，传统的数据库模型往往无法有效地处理。向量数据库通过引入特定的数据结构和索引算法，允许高效地存储和查询向量数据。

向量数据库的核心概念是向量索引。它使用一种称为向量空间模型的方法，将向量映射到多维空间中的点，并利用这种映射关系构建索引结构。这样，当需要搜索相似向量时，可以通过计算向量之间的距离或相似度来快速定位相似的向量。

2.2、向量数据库的使用场景

向量数据库在许多领域中都有广泛的应用场景，特别是涉及到高维向量数据存储和相似性搜索的任务。以下是一些常见的使用场景：

目标识别和图像搜索：向量数据库可用于存储图像特征向量，以支持快速的相似图像搜索和目标识别。它在图像搜索引擎、人脸识别和视频监控等领域具有重要作用。
推荐系统：向量数据库可以存储用户和物品的特征向量，用于个性化推荐。基于相似性搜索，可以找到与用户兴趣相似的物品，提供个性化的推荐结果。
自然语言处理：在文本处理任务中，可以使用向量数据库存储文本向量，如词向量、句向量等。基于相似性搜索，可以进行文本匹配、语义相似度计算等操作。
数据聚类和分类：向量数据库可用于高维向量数据的聚类和分类分析。它可以帮助发现数据集中的聚类模式和类别，用于数据挖掘和机器学习任务。
检索与推荐系统：在电子商务和商品搜索中，向量数据库可以存储商品特征向量，以支持相似商品的搜索和推荐。它可以提供更准确和个性化的搜索结果。
医疗和生物信息学：向量数据库可用于存储基因表达向量、蛋白质特征向量等生物信息学数据。它可以在基因组学、药物研发等领域中帮助进行数据分析和研究。
视频内容分析：向量数据库可用于存储视频特征向量，如视频帧特征、视频片段特征等。它可以用于视频内容搜索、视频剪辑和视频推荐等应用。

2.3、Qdrant

Qdrant 是一个高性能、易用、功能丰富的开源向量搜索引擎，适用于需要处理大量向量数据并执行相似性搜索的各种 AI 应用。它结合了现代索引技术、灵活的数据模型以及强大的 API 接口，非常适合构建智能推荐、图像检索、语义搜索等系统。

三、前置条件

3.1、下载Qdrant

https://github.com/qdrant/qdrant/releases/tag/v1.14.1https://github.com/qdrant/qdrant/releases/tag/v1.14.1 此次以Windows系统为例，下载文件：qdrant-x86_64-pc-windows-msvc.zip

解压qdrant-x86_64-pc-windows-msvc.zip得到一个qdrant.exe文件

3.2、新建config配置文件

在qdrant.exe文件的同级目录创建一个config文件夹，并在config文件夹里面创建一个config.yaml，并写入以下内容

log_level: INFO# Logging configuration
# Qdrant logs to stdout. You may configure to also write logs to a file on disk.
# Be aware that this file may grow indefinitely.
# logger:
#   # Logging format, supports `text` and `json`
#   format: text
#   on_disk:
#     enabled: true
#     log_file: path/to/log/file.log
#     log_level: INFO
#     # Logging format, supports `text` and `json`
#     format: textstorage:# Where to store all the datastorage_path: E:/qdrant/storage# Where to store snapshotssnapshots_path: E:/qdrant/snapshotssnapshots_config:# "local" or "s3" - where to store snapshotssnapshots_storage: local# s3_config:#   bucket: ""#   region: ""#   access_key: ""#   secret_key: ""# Where to store temporary files# If null, temporary snapshots are stored in: storage/snapshots_temp/temp_path: null# If true - point payloads will not be stored in memory.# It will be read from the disk every time it is requested.# This setting saves RAM by (slightly) increasing the response time.# Note: those payload values that are involved in filtering and are indexed - remain in RAM.# # Default: trueon_disk_payload: true# Maximum number of concurrent updates to shard replicas# If `null` - maximum concurrency is used.update_concurrency: null# Write-ahead-log related configurationwal:# Size of a single WAL segmentwal_capacity_mb: 32# Number of WAL segments to create ahead of actual data requirementwal_segments_ahead: 0# Normal node - receives all updates and answers all queriesnode_type: "Normal"# Listener node - receives all updates, but does not answer search/read queries# Useful for setting up a dedicated backup node# node_type: "Listener"performance:# Number of parallel threads used for search operations. If 0 - auto selection.max_search_threads: 0# Max number of threads (jobs) for running optimizations across all collections, each thread runs one job.# If 0 - have no limit and choose dynamically to saturate CPU.# Note: each optimization job will also use `max_indexing_threads` threads by itself for index building.max_optimization_threads: 0# CPU budget, how many CPUs (threads) to allocate for an optimization job.# If 0 - auto selection, keep 1 or more CPUs unallocated depending on CPU size# If negative - subtract this number of CPUs from the available CPUs.# If positive - use this exact number of CPUs.optimizer_cpu_budget: 0# Prevent DDoS of too many concurrent updates in distributed mode.# One external update usually triggers multiple internal updates, which breaks internal# timings. For example, the health check timing and consensus timing.# If null - auto selection.update_rate_limit: null# Limit for number of incoming automatic shard transfers per collection on this node, does not affect user-requested transfers.# The same value should be used on all nodes in a cluster.# Default is to allow 1 transfer.# If null - allow unlimited transfers.#incoming_shard_transfers_limit: 1# Limit for number of outgoing automatic shard transfers per collection on this node, does not affect user-requested transfers.# The same value should be used on all nodes in a cluster.# Default is to allow 1 transfer.# If null - allow unlimited transfers.#outgoing_shard_transfers_limit: 1# Enable async scorer which uses io_uring when rescoring.# Only supported on Linux, must be enabled in your kernel.# See: <https://qdrant.tech/articles/io_uring/#and-what-about-qdrant>#async_scorer: falseoptimizers:# The minimal fraction of deleted vectors in a segment, required to perform segment optimizationdeleted_threshold: 0.2# The minimal number of vectors in a segment, required to perform segment optimizationvacuum_min_vector_number: 1000# Target amount of segments optimizer will try to keep.# Real amount of segments may vary depending on multiple parameters:#  - Amount of stored points#  - Current write RPS## It is recommended to select default number of segments as a factor of the number of search threads,# so that each segment would be handled evenly by one of the threads.# If `default_segment_number = 0`, will be automatically selected by the number of available CPUsdefault_segment_number: 0# Do not create segments larger this size (in KiloBytes).# Large segments might require disproportionately long indexation times,# therefore it makes sense to limit the size of segments.## If indexation speed have more priority for your - make this parameter lower.# If search speed is more important - make this parameter higher.# Note: 1Kb = 1 vector of size 256# If not set, will be automatically selected considering the number of available CPUs.max_segment_size_kb: null# Maximum size (in KiloBytes) of vectors to store in-memory per segment.# Segments larger than this threshold will be stored as read-only memmapped file.# To enable memmap storage, lower the threshold# Note: 1Kb = 1 vector of size 256# To explicitly disable mmap optimization, set to `0`.# If not set, will be disabled by default.memmap_threshold_kb: null# Maximum size (in KiloBytes) of vectors allowed for plain index.# Default value based on https://github.com/google-research/google-research/blob/master/scann/docs/algorithms.md# Note: 1Kb = 1 vector of size 256# To explicitly disable vector indexing, set to `0`.# If not set, the default value will be used.indexing_threshold_kb: 20000# Interval between forced flushes.flush_interval_sec: 5# Max number of threads (jobs) for running optimizations per shard.# Note: each optimization job will also use `max_indexing_threads` threads by itself for index building.# If null - have no limit and choose dynamically to saturate CPU.# If 0 - no optimization threads, optimizations will be disabled.max_optimization_threads: null# This section has the same options as 'optimizers' above. All values specified here will overwrite the collections# optimizers configs regardless of the config above and the options specified at collection creation.#optimizers_overwrite:#  deleted_threshold: 0.2#  vacuum_min_vector_number: 1000#  default_segment_number: 0#  max_segment_size_kb: null#  memmap_threshold_kb: null#  indexing_threshold_kb: 20000#  flush_interval_sec: 5#  max_optimization_threads: null# Default parameters of HNSW Index. Could be overridden for each collection or named vector individuallyhnsw_index:# Number of edges per node in the index graph. Larger the value - more accurate the search, more space required.m: 16# Number of neighbours to consider during the index building. Larger the value - more accurate the search, more time required to build index.ef_construct: 100# Minimal size (in KiloBytes) of vectors for additional payload-based indexing.# If payload chunk is smaller than `full_scan_threshold_kb` additional indexing won't be used -# in this case full-scan search should be preferred by query planner and additional indexing is not required.# Note: 1Kb = 1 vector of size 256full_scan_threshold_kb: 10000# Number of parallel threads used for background index building.# If 0 - automatically select.# Best to keep between 8 and 16 to prevent likelihood of building broken/inefficient HNSW graphs.# On small CPUs, less threads are used.max_indexing_threads: 0# Store HNSW index on disk. If set to false, index will be stored in RAM. Default: falseon_disk: false# Custom M param for hnsw graph built for payload index. If not set, default M will be used.payload_m: null# Default shard transfer method to use if none is defined.# If null - don't have a shard transfer preference, choose automatically.# If stream_records, snapshot or wal_delta - prefer this specific method.# More info: https://qdrant.tech/documentation/guides/distributed_deployment/#shard-transfer-methodshard_transfer_method: null# Default parameters for collectionscollection:# Number of replicas of each shard that network tries to maintainreplication_factor: 1# How many replicas should apply the operation for us to consider it successfulwrite_consistency_factor: 1# Default parameters for vectors.vectors:# Whether vectors should be stored in memory or on disk.on_disk: null# shard_number_per_node: 1# Default quantization configuration.# More info: https://qdrant.tech/documentation/guides/quantizationquantization: null# Default strict mode parameters for newly created collections.strict_mode:# Whether strict mode is enabled for a collection or not.enabled: false# Max allowed `limit` parameter for all APIs that don't have their own max limit.max_query_limit: null# Max allowed `timeout` parameter.max_timeout: null# Allow usage of unindexed fields in retrieval based (eg. search) filters.unindexed_filtering_retrieve: null# Allow usage of unindexed fields in filtered updates (eg. delete by payload).unindexed_filtering_update: null# Max HNSW value allowed in search parameters.search_max_hnsw_ef: null# Whether exact search is allowed or not.search_allow_exact: null# Max oversampling value allowed in search.search_max_oversampling: nullservice:# Maximum size of POST data in a single request in megabytesmax_request_size_mb: 32# Number of parallel workers used for serving the api. If 0 - equal to the number of available cores.# If missing - Same as storage.max_search_threadsmax_workers: 0# Host to bind the service onhost: 0.0.0.0# HTTP(S) port to bind the service onhttp_port: 6333# gRPC port to bind the service on.# If `null` - gRPC is disabled. Default: null# Comment to disable gRPC:grpc_port: 6334# Enable CORS headers in REST API.# If enabled, browsers would be allowed to query REST endpoints regardless of query origin.# More info: https://developer.mozilla.org/en-US/docs/Web/HTTP/CORS# Default: trueenable_cors: true# Enable HTTPS for the REST and gRPC APIenable_tls: false# Check user HTTPS client certificate against CA file specified in tls configverify_https_client_certificate: false# Set an api-key.# If set, all requests must include a header with the api-key.# example header: `api-key: <API-KEY>`## If you enable this you should also enable TLS.# (Either above or via an external service like nginx.)# Sending an api-key over an unencrypted channel is insecure.## Uncomment to enable.# api_key: your_secret_api_key_here# Set an api-key for read-only operations.# If set, all requests must include a header with the api-key.# example header: `api-key: <API-KEY>`## If you enable this you should also enable TLS.# (Either above or via an external service like nginx.)# Sending an api-key over an unencrypted channel is insecure.## Uncomment to enable.# read_only_api_key: your_secret_read_only_api_key_here# Uncomment to enable JWT Role Based Access Control (RBAC).# If enabled, you can generate JWT tokens with fine-grained rules for access control.# Use generated token instead of API key.## jwt_rbac: true# Hardware reporting adds information to the API responses with a# hint on how many resources were used to execute the request.## Uncomment to enable.# hardware_reporting: truecluster:# Use `enabled: true` to run Qdrant in distributed deployment modeenabled: false# Configuration of the inter-cluster communicationp2p:# Port for internal communication between peersport: 6335# Use TLS for communication between peersenable_tls: false# Configuration related to distributed consensus algorithmconsensus:# How frequently peers should ping each other.# Setting this parameter to lower value will allow consensus# to detect disconnected nodes earlier, but too frequent# tick period may create significant network and CPU overhead.# We encourage you NOT to change this parameter unless you know what you are doing.tick_period_ms: 100# Set to true to prevent service from sending usage statistics to the developers.
# Read more: https://qdrant.tech/documentation/guides/telemetry
telemetry_disabled: false# TLS configuration.
# Required if either service.enable_tls or cluster.p2p.enable_tls is true.
tls:# Server certificate chain filecert: ./tls/cert.pem# Server private key filekey: ./tls/key.pem# Certificate authority certificate file.# This certificate will be used to validate the certificates# presented by other nodes during inter-cluster communication.## If verify_https_client_certificate is true, it will verify# HTTPS client certificate## Required if cluster.p2p.enable_tls is true.ca_cert: ./tls/cacert.pem# TTL in seconds to reload certificate from disk, useful for certificate rotations.# Only works for HTTPS endpoints. Does not support gRPC (and intra-cluster communication).# If `null` - TTL is disabled.cert_ttl: 3600

主要修改以下参数：

storage_path: E:/qdrant/storage
snapshots_path: E:/qdrant/snapshots
host: 0.0.0.0
http_port: 6333

3.3、生成WebUI资源文件

执行以下sh文件，生成static目录

#!/usr/bin/env bashset -euo pipefailSTATIC_DIR=${STATIC_DIR:-"./static"}
OPENAPI_FILE=${OPENAPI_DIR:-"./docs/redoc/master/openapi.json"}# Download `dist.zip` from the latest release of https://github.com/qdrant/qdrant-web-ui and unzip given folder# Get latest dist.zip, assume jq is installed
DOWNLOAD_LINK=$(curl --silent "https://api.github.com/repos/qdrant/qdrant-web-ui/releases/latest" | jq -r '.assets[] | select(.name=="dist-qdrant.zip") | .browser_download_url')if command -v wget &> /dev/null
thenwget -O dist-qdrant.zip $DOWNLOAD_LINK
elsecurl -L -o dist-qdrant.zip $DOWNLOAD_LINK
firm -rf "${STATIC_DIR}/"*
unzip -o dist-qdrant.zip -d "${STATIC_DIR}"
rm dist-qdrant.zip
cp -r "${STATIC_DIR}/dist/"* "${STATIC_DIR}"
rm -rf "${STATIC_DIR}/dist"cp "${OPENAPI_FILE}" "${STATIC_DIR}/openapi.json"

资源文件明细：

注意：把生成的static文件夹，复制到qdrant.exe文件的同级目录

四、运行Qdrant Web UI

4.1、启动Qdrant

在命令行执行以下命令

qdrant.exe --config-path E:/qdrant/config/config.yaml

4.2、访问WebUI

http://localhost:6333/dashboard

五、附带说明

5.1、直接使用qdrant-web-ui

以上web-ui是集成到qdrant的使用方式，也可以直接使用qdrant-web-ui的方式

https://github.com/qdrant/qdrant-web-uihttps://github.com/qdrant/qdrant-web-ui 1. 下载qdrant-web-ui源码

2. 安装依赖

npm install

3. 启动开发服务器

npm start

4. 访问qdrant-web-ui（端口为5173）

打开浏览器访问 http://localhost:5173/

5. 修改默认端口为3000

修改vite.config.js文件

import { defineConfig } from 'vite';
import reactRefresh from '@vitejs/plugin-react';
import svgrPlugin from 'vite-plugin-svgr';
import eslintPlugin from 'vite-plugin-eslint';
import {rehypeMetaAsAttributes} from "./src/lib/rehype-meta-as-attributes";// https://vitejs.dev/config/
export default defineConfig(async () => {const mdx = await import('@mdx-js/rollup');return {base: './',// This changes the output dir from dist to build// comment this out if that isn't relevant for your projectbuild: {outDir: 'dist',},server: {port: 3000 // 修改为你希望使用的端口号},plugins: [reactRefresh(),svgrPlugin({svgrOptions: {icon: true,// ...svgr options (https://react-svgr.com/docs/options/)},}),eslintPlugin({include: ['src/**/*.jsx', 'src/**/*.js', 'src/**/*.ts', 'src/**/*.tsx'],exclude: ['node_modules/**','dist/**, build/**','**/*.mdx','**/*.md'],}),mdx.default({rehypePlugins: [rehypeMetaAsAttributes,],}),],test: {globals: true,environment: 'jsdom',setupFiles: ['./src/setupTests.js'],},}
});