Neo4j graph construction from unstructured data using LLMs

Creating knowledge graphs from unstructured data

This application is designed to turn Unstructured data (pdfs,docs,txt,youtube video,web pages,etc.) into a knowledge graph stored in Neo4j. It utilizes the power of Large language models (OpenAI,Gemini,etc.) to extract nodes, relationships and their properties from the text and create a structured knowledge graph using Langchain framework.

Upload your files from local machine, GCS or S3 bucket or from web sources, choose your LLM model and generate knowledge graph.

• Knowledge Graph Creation: Transform unstructured data into structured knowledge graphs using LLMs.
• Providing Schema: Provide your own custom schema or use existing schema in settings to generate graph.
• View Graph: View graph for a particular source or multiple sources at a time in Bloom.
• Chat with Data: Interact with your data in a Neo4j database through conversational queries, also retrive metadata about the source of response to your queries.

⚠️ You will need to have a Neo4j Database V5.15 or later with APOC installed to use this Knowledge Graph Builder. You can use any Neo4j Aura database (including the free database) If you are using Neo4j Desktop, you will not be able to use the docker-compose but will have to follow the separate deployment of backend and frontend section. ⚠️

By default only OpenAI and Diffbot are enabled since Gemini requires extra GCP configurations.

In your root folder, create a .env file with your OPENAI and DIFFBOT keys (if you want to use both):

OPENAI_API_KEY="your-openai-key"
DIFFBOT_API_KEY="your-diffbot-key"

if you only want OpenAI:

LLM_MODELS="diffbot,openai-gpt-3.5,openai-gpt-4o"
OPENAI_API_KEY="your-openai-key"

if you only want Diffbot:

LLM_MODELS="diffbot"
DIFFBOT_API_KEY="your-diffbot-key"

You can then run Docker Compose to build and start all components:

docker-compose up --build

By default, the input sources will be: Local files, Youtube, Wikipedia ,AWS S3 and Webpages. As this default config is applied:

REACT_APP_SOURCES="local,youtube,wiki,s3,web"

If however you want the Google GCS integration, add gcs and your Google client ID:

REACT_APP_SOURCES="local,youtube,wiki,s3,gcs,web"
GOOGLE_CLIENT_ID="xxxx"

You can of course combine all (local, youtube, wikipedia, s3 and gcs) or remove any you don't want/need.

By default,all of the chat modes will be available: vector, graph+vector and graph. If none of the mode is mentioned in the chat modes variable all modes will be available:

CHAT_MODES=""

If however you want to specifiy the only vector mode or only graph mode you can do that by specifying the mode in the env:

CHAT_MODES="vector,graph+vector"

Alternatively, you can run the backend and frontend separately:

• For the frontend:

1. Create the frontend/.env file by copy/pasting the frontend/example.env.
2. Change values as needed

3. cd frontend
   yarn
   yarn run dev

• For the backend:

1. Create the backend/.env file by copy/pasting the backend/example.env.
2. Change values as needed

3. cd backend
   python -m venv envName
   source envName/bin/activate 
   pip install -r requirements.txt
   uvicorn score:app --reload

To deploy the app and packages on Google Cloud Platform, run the following command on google cloud run:

# Frontend deploy 
gcloud run deploy 
source location current directory > Frontend
region : 32 [us-central 1]
Allow unauthenticated request : Yes

# Backend deploy 
gcloud run deploy --set-env-vars "OPENAI_API_KEY = " --set-env-vars "DIFFBOT_API_KEY = " --set-env-vars "NEO4J_URI = " --set-env-vars "NEO4J_PASSWORD = " --set-env-vars "NEO4J_USERNAME = "
source location current directory > Backend
region : 32 [us-central 1]
Allow unauthenticated request : Yes

1. Connect to Neo4j Aura Instance by passing URI and password or using Neo4j credentials file.
2. Choose your source from a list of Unstructured sources to create graph.
3. Change the LLM (if required) from drop down, which will be used to generate graph.
4. Optionally, define schema(nodes and relationship labels) in entity graph extraction settings.
5. Either select multiple files to 'Generate Graph' or all the files in 'New' status will be processed for graph creation.
6. Have a look at the graph for individial files using 'View' in grid or select one or more files and 'Preview Graph'
7. Ask questions related to the processed/completed sources to chat-bot, Also get detailed information about your answers generated by LLM.

LLM Knowledge Graph Builder Application

Neo4j Workspace

Demo of application

For any inquiries or support, feel free to raise Github Issue