https://github.com/blacksmithop/llm-graph-builder

Build Neo4J Knowledge Graphs from Excel files
https://github.com/blacksmithop/llm-graph-builder

knowledge-graph llm neo4j python

Last synced: 2 months ago
JSON representation

Build Neo4J Knowledge Graphs from Excel files

• Host: GitHub
• URL: https://github.com/blacksmithop/llm-graph-builder
• Owner: blacksmithop
• Created: 2024-07-03T09:19:31.000Z (6 months ago)
• Default Branch: main
• Last Pushed: 2024-07-17T06:40:11.000Z (5 months ago)
• Last Synced: 2024-10-10T09:20:13.817Z (2 months ago)
• Topics: knowledge-graph, llm, neo4j, python
• Language: Python
• Homepage:
• Size: 2.66 MB
• Stars: 10
• Watchers: 3
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: Readme.md

Awesome Lists containing this project

README

        
# Knowledge Graph Builder

![Python](https://skillicons.dev/icons?i=python,docker)

## Graph Creation

```mermaid

flowchart TD

    A[File Upload] --> B[Identify File Type]

    B --> C[Create Documents]

    C --> D[Extract Entity from Document]

    D --> E[Get Entity Relationships]

    E --> F[Create Vector Index]

```

### Installation

First, install the dependenices

```bash

pip install -r requirements.txt

```

### Configure Neo4J (Dozerdb)

Next, install Neo4j. I recommend doing this [Dozerb](https://dozerdb.org/) as it offers enterprise features in the community edition. You can use this [script](./install_dozerdb.sh) to get a docker container running.

### Configure LLM, Embeddings

You can use Azure OpenAI, Ollama or your custom provider. You just need to define your LLM and Embeddings model in [llm_core.py](./utils/common/llm_core.py)

### Usage

Once complete you can set your `FILE_PATH` in [knowledge_graph_creator.py](./knowledge_graph_creator.py) and run the python script. It should you populate you Neo4J database.

The Builder supports different modes of operation when creating the nodes. This can be toggled by changing `prompt_version` in [Neo4JKnowledgeGraph](/utils/custom/knowledge_graph.py#L40). Defaults to `2`.

## Question Answering

```mermaid

graph TD

  A[Query] --> B[Construct Cypher from Schema]

  B --> C[Retrieve related Nodes]

  C --> D{Can Answer Question}

  D -->|Yes| E[Response]

  D -->|No| F[Process result]

  F --> E

```

You can perform QA on your knowledge graph using the streamlit application at [graph_qa_chatbot.py](./graph_qa_chatbot.py)

```bash

streamlit run graph_qa_chatbot.py

```