Neo4j LLM Graph Builder: Full-Stack Knowledge Graph from Documents
本文为开源社区精选内容,由 neo4j-labs 原创。 文中链接将跳转到原始仓库,部分图片可能加载较慢。
查看原始来源AI 导读
Knowledge Graph Builder Transform unstructured data (PDFs, DOCs, TXTs, YouTube videos, web pages, etc.) into a structured Knowledge Graph stored in Neo4j using the power of Large Language Models...
Knowledge Graph Builder
Transform unstructured data (PDFs, DOCs, TXTs, YouTube videos, web pages, etc.) into a structured Knowledge Graph stored in Neo4j using the power of Large Language Models (LLMs) and the LangChain framework.
This application allows you to upload files from various sources (local machine, GCS, S3 bucket, or web sources), choose your preferred LLM model, and generate a Knowledge Graph.
Key Features
Knowledge Graph Creation
- Seamlessly transform unstructured data into structured Knowledge Graphs using advanced LLMs.
- Extract nodes, relationships, and their properties to create structured graphs.
Schema Support
- Use a custom schema or existing schemas configured in the settings to generate graphs.
Graph Visualization
- View graphs for specific or multiple data sources simultaneously in Neo4j Bloom.
Chat with Data
- Interact with your data in the Neo4j database through conversational queries.
- Retrieve metadata about the source of responses to your queries.
- For a dedicated chat interface, use the standalone chat application with the /chat-only route.
LLMs Supported
- OpenAI
- Gemini
- Diffbot
- Azure OpenAI (dev deployed version)
- Anthropic (dev deployed version)
- Fireworks (dev deployed version)
- Groq (dev deployed version)
- Amazon Bedrock (dev deployed version)
- Ollama (dev deployed version)
- Deepseek (dev deployed version)
- Other OpenAI-compatible base URL models (dev deployed version)
Token Usage Tracking
- Easily monitor and track your LLM token usage for each user and database connection.
- Enable this feature by setting the
TRACK_USER_USAGEenvironment variable totruein your backend configuration. - View your daily and monthly token consumption and limits, helping you manage usage and avoid overages.
- You can check your remaining token limits at any time using the provided API endpoint.
Embedding Model Selection
- Choose from a variety of embedding models to generate vector embeddings for your data. This can be configured from the frontend in Graph Settings > Processing Configuration > Select Embedding Model.
- Supported model providers include OpenAI, Gemini, Amazon Titan, and Sentence Transformers.
- Your selected embedding model is saved to your user profile when
TRACK_USER_USAGEis enabled.
Local Configuration
You have two ways to configure the embedding model locally:
With User Tracking (
TRACK_USER_USAGE=true):- Set
TRACK_USER_USAGEtotruein your backend.envfile.
使用用户跟踪 (TRACK_USER_USAGE=true): 在您的后端 .env 文件中将 TRACK_USER_USAGE 设置为 true。- Set
- Provide your token tracking database credentials (
TOKEN_TRACKER_DB_URI,TOKEN_TRACKER_DB_USERNAME, etc.). - Select your desired embedding model from the frontend. Your selection will be saved and automatically used in subsequent sessions.
Without User Tracking (
TRACK_USER_USAGE=false):- Set
TRACK_USER_USAGEtofalse.
无用户追踪(User Tracking)(TRACK_USER_USAGE=false): 将 TRACK_USER_USAGE 设置为 false。- Set
- Specify the embedding model and provider directly in your backend
.envfile usingEMBEDDING_MODELandEMBEDDING_PROVIDER. - If these variables are not set, the application defaults to a Sentence Transformer model.
- In this mode, the embedding model cannot be changed from the frontend.
Deployment Options
Local Deployment
Using Docker-Compose
Run the application using the default docker-compose configuration.
Supported LLM Models:
By default, only OpenAI and Diffbot are enabled. Gemini requires additional GCP configurations.
Use theVITE_LLM_MODELS_PRODvariable to configure the models you need. Example:VITE_LLM_MODELS_PROD="gemini_2.5_flash,openai_gpt_5_mini,diffbot,anthropic_claude_4.5_haiku"Input Sources:
By default, the following sources are enabled:local,YouTube,Wikipedia,AWS S3, andweb.
To add Google Cloud Storage (GCS) integration, includegcsand your Google client ID:VITE_REACT_APP_SOURCES="local,youtube,wiki,s3,gcs,web" VITE_GOOGLE_CLIENT_ID="your-google-client-id"
Chat Modes
Configure chat modes using the VITE_CHAT_MODES variable:
- By default, all modes are enabled:
vector,graph_vector,graph,fulltext,graph_vector_fulltext,entity_vector, andglobal_vector. - To specify specific modes, update the variable. For example:
VITE_CHAT_MODES="vector,graph"
Running Backend and Frontend Separately
For development, you can run the backend and frontend independently.
Frontend Setup
- Create a
.envfile in thefrontendfolder by copyingfrontend/example.env. - Update environment variables as needed.
- Run:
cd frontend yarn yarn run dev
Backend Setup
- Create a
.envfile in thebackendfolder by copyingbackend/example.env. - Pre-configure user credentials in the
.envfile to bypass the login dialog:NEO4J_URI=<your-neo4j-uri> NEO4J_USERNAME=<your-username> NEO4J_PASSWORD=<your-password> NEO4J_DATABASE=<your-database-name> - Run:
cd backend python -m venv envName source envName/bin/activate pip install -r requirements.txt uvicorn score:app --reload
Cloud Deployment
Deploy the application on Google Cloud Platform using the following commands:
Frontend Deployment
gcloud run deploy dev-frontend \
--source . \
--region us-central1 \
--allow-unauthenticated
Backend Deployment
gcloud run deploy dev-backend \
--set-env-vars "OPENAI_API_KEY=<your-openai-api-key>" \
--set-env-vars "DIFFBOT_API_KEY=<your-diffbot-api-key>" \
--set-env-vars "NEO4J_URI=<your-neo4j-uri>" \
--set-env-vars "NEO4J_USERNAME=<your-username>" \
--set-env-vars "NEO4J_PASSWORD=<your-password>" \
--source . \
--region us-central1 \
--allow-unauthenticated
For local llms (Ollama)
- Pull the docker image of ollama
docker pull ollama/ollama - Run the ollama docker image
docker run -d -v ollama:/root/.ollama -p 11434:11434 --name ollama ollama/ollama - Execute any llm model, e.g., llama3
docker exec -it ollama ollama run llama3 - Configure env variable in docker compose.
LLM_MODEL_CONFIG_ollama_<model_name> # example LLM_MODEL_CONFIG_ollama_llama3=${LLM_MODEL_CONFIG_ollama_llama3-llama3,http://host.docker.internal:11434} - Configure the backend API url
VITE_BACKEND_API_URL=${VITE_BACKEND_API_URL-backendurl} - Open the application in browser and select the ollama model for the extraction.
- Enjoy Graph Building.
Usage
- Connect to a Neo4j Aura Instance, which can be either AURA DS or AURA DB, by passing the URI and password through the backend environment, filling in the login dialog, or dragging and dropping the Neo4j credentials file.
- To differentiate, we have added different icons. For AURA DB, there is a database icon, and for AURA DS, there is a scientific molecule icon right under the Neo4j Connection details label.
- Choose your source from a list of unstructured sources to create a graph.
- Change the LLM (if required) from the dropdown, which will be used to generate the graph.
- Optionally, define the schema (nodes and relationship labels) in the entity graph extraction settings.
- Either select multiple files to 'Generate Graph', or all the files in 'New' status will be processed for graph creation.
- View the graph for individual files using 'View' in the grid, or select one or more files and 'Preview Graph'.
- Ask questions related to the processed/completed sources to the chatbot. Also, get detailed information about your answers generated by the LLM.
ENV
| Env Variable Name | Mandatory/Optional | Default Value | Description |
|---|---|---|---|
| BACKEND ENV | |||
| OPENAI_API_KEY | Optional | An OpenAI Key is required to use OpenAI LLM model to authenticate and track requests | |
| DIFFBOT_API_KEY | Mandatory | API key is required to use Diffbot's NLP service to extract entities and relationships from unstructured data | |
| BUCKET_UPLOAD_FILE | Optional | Bucket name to store uploaded file on GCS | |
| BUCKET_FAILED_FILE | Optional | Bucket name to store failed file on GCS while extraction | |
| NEO4J_USER_AGENT | Optional | llm-graph-builder | Name of the user agent to track Neo4j database activity |
| ENABLE_USER_AGENT | Optional | true | Boolean value to enable/disable Neo4j user agent |
| DUPLICATE_TEXT_DISTANCE | Optional | 5 | This value is used to find distance for all node pairs in the graph and is calculated based on node properties |
| DUPLICATE_SCORE_VALUE | Optional | 0.97 | Node score value to match duplicate nodes |
| EFFECTIVE_SEARCH_RATIO | Optional | 1 | Ratio used for effective search calculations |
| GRAPH_CLEANUP_MODEL | Optional | openai_gpt_5_mini | Model name to clean up graph in post processing |
| MAX_TOKEN_CHUNK_SIZE | Optional | 10000 | Maximum token size to process file content |
| YOUTUBE_TRANSCRIPT_PROXY | Mandatory | Proxy key to process YouTube videos for getting transcripts | |
| IS_EMBEDDING | Optional | true | Flag to enable text embedding |
| KNN_MIN_SCORE | Optional | 0.8 | Minimum score for KNN algorithm |
| GCP_LOG_METRICS_ENABLED | Optional | False | Flag to enable Google Cloud logs |
| NEO4J_URI | Optional | neo4j://database:7687 | URI for Neo4j database |
| NEO4J_USERNAME | Optional | neo4j | Username for Neo4j database |
| NEO4J_PASSWORD | Optional | password | Password for Neo4j database |
| GCS_FILE_CACHE | Optional | False | If set to True, will save files to process into GCS. If False, will save files locally |
| ENTITY_EMBEDDING | Optional | False | If set to True, it will add embeddings for each entity in the database |
| LLM_MODEL_CONFIG_ollama_ |
Optional | Set ollama config as model_name,model_local_url for local deployments | |
| FRONTEND ENV | |||
| VITE_BLOOM_URL | Mandatory | Bloom URL | URL for Bloom visualization |
| VITE_REACT_APP_SOURCES | Mandatory | local,youtube,wiki,s3 | List of input sources that will be available |
| VITE_CHAT_MODES | Mandatory | vector,graph+vector,graph,hybrid | Chat modes available for Q&A |
| VITE_ENV | Mandatory | DEV or PROD | Environment variable for the app |
| VITE_LLM_MODELS | Optional | openai_gpt_5_mini,gemini_2.5_flash,anthropic_claude_4.5_haiku | Supported models for the application |
| VITE_BACKEND_API_URL | Optional | localhost | URL for backend API |
| VITE_TIME_PER_PAGE | Optional | 50 | Time per page for processing |
| VITE_CHUNK_SIZE | Optional | 5242880 | Size of each chunk of file for upload |
| VITE_GOOGLE_CLIENT_ID | Optional | Client ID for Google authentication | |
| VITE_LLM_MODELS_PROD | Optional | openai_gpt_5_mini,gemini_2.5_flash,anthropic_claude_4.5_haiku | To distinguish models based on environment (PROD or DEV) |
| VITE_AUTH0_CLIENT_ID | Mandatory if you are enabling Authentication otherwise it is optional | Okta OAuth Client ID for authentication | |
| VITE_AUTH0_DOMAIN | Mandatory if you are enabling Authentication otherwise it is optional | Okta OAuth Client Domain | |
| VITE_SKIP_AUTH | Optional | true | Flag to skip authentication |
| VITE_CHUNK_OVERLAP | Optional | 20 | Variable to configure chunk overlap |
| VITE_TOKENS_PER_CHUNK | Optional | 100 | Variable to configure tokens count per chunk. This gives flexibility for users who may require different chunk sizes for various tokenization tasks |
| VITE_CHUNK_TO_COMBINE | Optional | 1 | Variable to configure number of chunks to combine for parallel processing |
Example Environment Files
Refer to the example environment files for additional variables and configuration:
- Backend example.env
- Frontend example.env
Cloud Build Deployment
You can deploy the backend and the frontend to Google Cloud Run using Cloud Build, either manually or via automated triggers.
Automated Deployment (Recommended)
Connect your repository to Google Cloud Build:
- In the Google Cloud Console, go to Cloud Build > Triggers.
将您的存储库连接到 Google Cloud Build: 在 Google Cloud Console 中,转到 Cloud Build > Triggers(触发器)。- Create a new trigger and select your repository.
- Set the trigger to run on push to your desired branch (
main,staging, ordev). - Cloud Build will automatically use the
cloudbuild.yamlfile in the root of your repository. Configure Substitutions and Secrets:
- In the trigger settings, add required substitutions (e.g.,
_OPENAI_API_KEY,_DIFFBOT_API_KEY, etc.) as environment variables or use Secret Manager for sensitive data.
配置替换和密钥: 在触发器设置中,添加所需替换(例如,_OPENAI_API_KEY、_DIFFBOT_API_KEY 等)作为环境变量,或者使用 Secret Manager 管理敏感数据。- In the trigger settings, add required substitutions (e.g.,
Push your code:
- When you push to the configured branch, Cloud Build will build and deploy your backend (and optionally frontend) to Cloud Run using the steps defined in
cloudbuild.yaml.
推送您的代码: 当您推送到配置的分支时,Cloud Build 将构建您的后端(以及可选的前端),并使用 cloudbuild.yaml 中定义的步骤将其部署到 Cloud Run。- When you push to the configured branch, Cloud Build will build and deploy your backend (and optionally frontend) to Cloud Run using the steps defined in
Manual Deployment
Set up Google Cloud SDK and authenticate:
gcloud auth login gcloud config set project <YOUR_PROJECT_ID>Run Cloud Build manually:
gcloud builds submit --config cloudbuild.yaml \ --substitutions=_REGION=us-central1,_REPO=cloud-run-repo,_OPENAI_API_KEY=<your-openai-key>,_DIFFBOT_API_KEY=<your-diffbot-key>,_BUCKET_UPLOAD_FILE=<your-bucket>,_BUCKET_FAILED_FILE=<your-bucket>,_PROJECT_ID=<your-project-id>,_GCS_FILE_CACHE=False,_TRACK_USER_USAGE=False,_TOKEN_TRACKER_DB_URI=...,_TOKEN_TRACKER_DB_USERNAME=...,_TOKEN_TRACKER_DB_PASSWORD=...,_TOKEN_TRACKER_DB_DATABASE=...,_DEFAULT_DIFFBOT_CHAT_MODEL=...,_YOUTUBE_TRANSCRIPT_PROXY=...,_EMBEDDING_MODEL=..., _EMBEDDING_PROVIDER=...,_BEDROCK_EMBEDDING_MODEL_KEY=...,_LLM_MODEL_CONFIG_OPENAI_GPT_5_2=...,_LLM_MODEL_CONFIG_OPENAI_GPT_5_MINI=...,_LLM_MODEL_CONFIG_GEMINI_2_5_FLASH=...,_LLM_MODEL_CONFIG_GEMINI_2_5_PRO=...,_LLM_MODEL_CONFIG_DIFFBOT=...,_LLM_MODEL_CONFIG_GROQ_LLAMA3_1_8B=...,_LLM_MODEL_CONFIG_ANTHROPIC_CLAUDE_4_5_SONNET=...,_LLM_MODEL_CONFIG_ANTHROPIC_CLAUDE_4_5_HAIKU=...,_LLM_MODEL_CONFIG_LLAMA4_MAVERICK=...,_LLM_MODEL_CONFIG_FIREWORKS_QWEN3_30B=...,_LLM_MODEL_CONFIG_FIREWORKS_GPT_OSS=...,_LLM_MODEL_CONFIG_FIREWORKS_DEEPSEEK_V3=...,_LLM_MODEL_CONFIG_BEDROCK_NOVA_MICRO_V1=...,_LLM_MODEL_CONFIG_BEDROCK_NOVA_LITE_V1=...,_LLM_MODEL_CONFIG_BEDROCK_NOVA_PRO_V1=...,_LLM_MODEL_CONFIG_OLLAMA_LLAMA3=...- Replace the values in angle brackets with your actual configuration and secrets.
手动运行 Cloud Build: gcloud builds submit --config cloudbuild.yaml \ --substitutions=_REGION=us-central1,_REPO=cloud-run-repo,_OPENAI_API_KEY=<your-openai-key>,_DIFFBOT_API_KEY=<your-diffbot-key>,_BUCKET_UPLOAD_FILE=<your-bucket>,_BUCKET_FAILED_FILE=<your-bucket>,_PROJECT_ID=<your-project-id>,_GCS_FILE_CACHE=False,_TRACK_USER_USAGE=False,_TOKEN_TRACKER_DB_URI=...,_TOKEN_TRACKER_DB_USERNAME=...,_TOKEN_TRACKER_DB_PASSWORD=...,_TOKEN_TRACKER_DB_DATABASE=...,_DEFAULT_DIFFBOT_CHAT_MODEL=...,_YOUTUBE_TRANSCRIPT_PROXY=...,_EMBEDDING_MODEL=..., _EMBEDDING_PROVIDER=...,_BEDROCK_EMBEDDING_MODEL_KEY=...,_LLM_MODEL_CONFIG_OPENAI_GPT_5_2=...,_LLM_MODEL_CONFIG_OPENAI_GPT_5_MINI=...,_LLM_MODEL_CONFIG_GEMINI_2_5_FLASH=...,_LLM_MODEL_CONFIG_GEMINI_2_5_PRO=...,_LLM_MODEL_CONFIG_DIFFBOT=...,_LLM_MODEL_CONFIG_GROQ_LLAMA3_1_8B=...,_LLM_MODEL_CONFIG_ANTHROPIC_CLAUDE_4_5_SONNET=...,_LLM_MODEL_CONFIG_ANTHROPIC_CLAUDE_4_5_HAIKU=...,_LLM_MODEL_CONFIG_LLAMA4_MAVERICK=...,_LLM_MODEL_CONFIG_FIREWORKS_QWEN3_30B=...,_LLM_MODEL_CONFIG_FIREWORKS_GPT_OSS=...,_LLM_MODEL_CONFIG_FIREWORKS_DEEPSEEK_V3=...,_LLM_MODEL_CONFIG_BEDROCK_NOVA_MICRO_V1=...,_LLM_MODEL_CONFIG_BEDROCK_NOVA_LITE_V1=...,_LLM_MODEL_CONFIG_BEDROCK_NOVA_PRO_V1=...,_LLM_MODEL_CONFIG_OLLAMA_LLAMA3=... 将尖括号中的值替换为您实际的配置和密钥。- You can omit or add substitutions as needed for your deployment.
Monitor the build:
- The build and deployment process will be visible in the Cloud Build console.
监控构建: 构建和部署过程将在 Cloud Build 控制台中可见。Access your deployed service:
- After deployment, your backend will be available at the Cloud Run service URL shown in the Cloud Console.
访问您部署的服务: 部署后,您的后端将在 Cloud Console 中显示的 Cloud Run 服务 URL 上可用。
Note:
- The
cloudbuild.yamlfile supports multiple environments (main,staging,dev) based on the branch name. - The frontend build and deployment steps are commented out by default. Uncomment them in
cloudbuild.yamlif you wish to deploy the frontend as well.
For more details, see the comments in cloudbuild.yaml.
Links
LLM Knowledge Graph Builder Application
Reference
Contact
For any inquiries or support, feel free to raise GitHub Issues
Happy Graph Building!
深度加工(NotebookLM 生成)
基于本文内容生成的 PPT 大纲、博客摘要、短视频脚本与 Deep Dive 播客,用于多场景复用
PPT 大纲(5-8 张幻灯片) 点击展开
Neo4j LLM Graph Builder: Full-Stack Knowledge Graph from Documents — ppt
这是一份基于您提供的参考资料生成的 PPT 大纲,共包含 6 张幻灯片,严格按照您的要求使用 Markdown 格式和 3-5 个要点进行整理:
幻灯片 1:Neo4j LLM Graph Builder 简介
- 核心定义:它是一款全栈应用程序,利用大语言模型 (LLM) 和 LangChain 框架,将非结构化数据转化为存储在 Neo4j 中的结构化知识图谱 [1]。
- 多数据源支持:支持从本地机器、YouTube 视频、维基百科、网页以及云存储(AWS S3、Google Cloud Storage)上传并处理 PDF、TXT 等多种文件 [1-3]。
- 自动提取与构建:能够无缝提取数据中的实体节点、关联关系及其属性,支持用户使用自定义 Schema 或配置的现有 Schema 生成图谱 [1]。
- 核心价值(与数据对话):提供专门的聊天交互界面,用户可以通过对话式查询与数据库互动,并能够获取问题回答的来源元数据 [1, 4]。
幻灯片 2:模型支持与资源管理
- 广泛的 LLM 支持:集成了 OpenAI、Gemini、Anthropic、Diffbot、Amazon Bedrock 以及 Deepseek 等多种云端大语言模型 [2, 4]。
- 本地模型兼容:支持通过 Ollama 部署和执行本地模型(如 Llama3),实现离线的实体提取和图谱构建 [5, 6]。
- 多维度的嵌入模型选取:支持 OpenAI、Gemini、Amazon Titan 和 Sentence Transformers,用户可以在前端界面灵活切换 [4, 7]。
- Token 使用监控追踪:开启追踪环境变量后,可轻松监控每位用户的日度和月度 Token 消耗及额度限制,帮助有效管理成本避免超支 [4]。
幻灯片 3:丰富的问答与检索模式
- 多模式对话配置:系统支持通过环境变量自定义聊天模式,包括向量检索 (vector)、图检索 (graph)、全文检索 (fulltext) 及其多种混合模式 (hybrid) [3, 8]。
- 精细化分块策略:系统允许通过环境变量高度自定义处理过程,例如设置 Token 分块大小、分块重叠数以及并发处理的分块数量 [9]。
- 图谱节点清洗去重:内置了节点匹配与去重机制,通过设定距离计算参数和重复匹配分数阈值,并利用指定模型进行后处理来优化图谱质量 [10, 11]。
- 独立聊天应用接口:除了内嵌交互,还可通过
/chat-only路由使用独立的聊天界面,专注问答体验 [4]。
幻灯片 4:可视化呈现与操作体验
- 强大的图谱可视化:深度集成 Neo4j Bloom,允许用户在前端同时查看和分析特定数据源或多个来源联合的图谱结构 [1, 8]。
- 快捷的数据库接入:可通过填入 URI、在环境配置中直接写入,或是直接拖拽配置文件的方式,快速连接到 Neo4j Aura DB 或 DS 实例 [6, 11]。
- 可视化操作状态反馈:内置状态网格,用户不仅可以“生成图谱”,还可以针对个别或多个处于已处理/完成状态的文件进行“预览图谱”操作 [6, 10]。
- 前端个性化记忆功能:在开启用户追踪的模式下,前端所选择的嵌入模型将自动保存到用户档案中,并自动应用于后续会话 [7]。
幻灯片 5:灵活多样的部署方案
- 本地极速部署:提供默认的 Docker-Compose 配置方案,极大简化了整体应用的本地容器化部署流程 [2]。
- 前后端分离开发:开发者可以独立运行前端 (基于 Vite/Yarn) 和后端 (基于 Python 虚拟环境和 Uvicorn),方便进行代码调试 [3, 5]。
- 谷歌云 (GCP) 快速上线:支持利用
gcloud run deploy命令行指令,将前后端快速部署到 Google Cloud 的 Cloud Run 服务中 [5]。 - CI/CD 自动化构建:推荐连接 Google Cloud Build 设置触发器,实现代码推送到指定分支后,基于
cloudbuild.yaml自动构建部署 [9, 12]。
幻灯片 6:系统配置与环境变量控制
- 后端核心认证集成:通过后端
.env文件必须配置如DIFFBOT_API_KEY、Neo4j 数据库连接凭据及相关云服务的 API Key [3, 10, 11]。 - 前端功能开关控制:前端环境变量控制着界面的核心功能,如通过
VITE_REACT_APP_SOURCES决定开启哪些输入源,VITE_CHAT_MODES控制可选的问答模式 [8]。 - 灵活的安全与授权机制:如果需要身份验证,可强制配置 Auth0/Okta 的 OAuth 客户端和域名;开发环境下也可配置跳过验证 [8, 9]。
- 云端机密管理:在自动化云部署流程中,诸如 API 密钥等敏感信息可以通过替换变量 (Substitutions) 或利用 Secret Manager 安全传入系统中 [12]。
博客摘要 + 核心看点 点击展开
Neo4j LLM Graph Builder: Full-Stack Knowledge Graph from Documents — summary
SEO 友好博客摘要
想要将PDF、网页或YouTube视频等非结构化数据转化为强大的知识图谱吗?Neo4j LLM Graph Builder 结合了先进的大语言模型(LLMs)与 LangChain 框架,为您提供高效的全栈解决方案[1]。本文深入解析了该应用的核心功能,包括自定义 Schema、Neo4j Bloom 直观可视化以及与数据库对话的智能问答体验[1]。无论您是选择通过 Docker 进行本地环境搭建,还是在 Google Cloud Platform 上进行云端部署[2, 3],都能轻松配置 OpenAI、Gemini、Ollama 等多种顶级大模型和嵌入模型[3, 4]。了解如何利用此工具打破数据孤岛,轻松构建和管理专属知识图谱,全面提升数据检索与分析效率!
核心看点
- 自动化知识图谱构建:利用大模型将文本、视频等非结构化数据转化为结构化图谱。[1]
- 广泛的模型与部署支持:兼容OpenAI、Gemini等,支持Docker本地与GCP云部署。[2-4]
- 数据可视化与智能问答:对接Neo4j Bloom实现可视化,并支持多种模式的智能对话。[1, 5]
60 秒短视频脚本 点击展开
Neo4j LLM Graph Builder: Full-Stack Knowledge Graph from Documents — video
这是一份基于您上传文章的 60 秒短视频脚本,严格按照您的字数和结构要求编写:
【钩子开场】
一键解锁AI知识图谱!
【核心解说】
画面一: 结合大语言模型,将文档视频等复杂数据,秒变知识图谱 [1]。
画面二: 支持本地与云端数据导入,兼容多款主流大模型及本地部署 [1-3]。
画面三: 提供直观的图谱可视化,更能开启对话模式与专属数据聊天 [1, 4]。
【收束】
快来部署体验,打造你的专属数据大脑吧!
课后巩固
与本文内容匹配的闪卡与测验,帮助巩固所学知识
延伸阅读
根据本文主题,为你推荐相关的学习资料