https://github.com/aghoshpro/graphrag
Building knowledge graph (KG) from raw text, creating a community hierarchy, generating summaries, and using these structures for RAG-based tasks.
https://github.com/aghoshpro/graphrag
anthropic-claude embeddings knowledge-graph langchain neo4j ollama openai rag txt
Last synced: 7 months ago
JSON representation
Building knowledge graph (KG) from raw text, creating a community hierarchy, generating summaries, and using these structures for RAG-based tasks.
- Host: GitHub
- URL: https://github.com/aghoshpro/graphrag
- Owner: aghoshpro
- Created: 2020-11-19T09:56:11.000Z (about 5 years ago)
- Default Branch: main
- Last Pushed: 2025-03-13T17:29:09.000Z (10 months ago)
- Last Synced: 2025-06-22T18:06:51.436Z (7 months ago)
- Topics: anthropic-claude, embeddings, knowledge-graph, langchain, neo4j, ollama, openai, rag, txt
- Language: Jupyter Notebook
- Homepage:
- Size: 5.27 MB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# GraphRAG
## Installation
### Clone Repository
- Create a working directory and navigate to it:
```bash
cd ChatDocument
```
- Open `cmd` or `terminal` to clone repository
```bash
git clone https://github.com/aghoshpro/GraphRAG.git
```
### Setup Local Environment
- Create a virtual environment `myvenv` and activate it:
```bash
python -m venv myvenv
```
```bash
.\myvenv\Scripts\activate # On Windows
# ---------------------- OR ---------------------- #
source myvenv/bin/activate # On Linux or Mac
```
- Install dependencies:
```bash
pip install --upgrade -r requirements.txt
```
### Get API Keys
- Anthropic:
- OpenAI
- Put them in `.env` file and add it to `.gitignore` so it will be not shared during git commit
### Start Neo4J Docker
```sh
docker compose up
```
### 🧪 Experiment with code if you want
```sh
jupyter notebook
```
## References
1. [pip](https://pip.pypa.io/en/stable/installation/)
2. [PythonNotes](https://note.nkmk.me/en/)
3. [LangChain ChatModels](https://python.langchain.com/docs/integrations/chat/)
4. [LangChain Neo4J](https://neo4j.com/labs/genai-ecosystem/langchain/)
5. [LangChain Community](https://api.python.langchain.com/en/latest/community_api_reference.html)