Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/tomasonjo-labs/text2cypher_llama_agent
A collection of LlamaIndex Workflows-powered agents that convert natural language to Cypher queries designed to retrieve information from a Neo4j database to answer the question with included benchmark data.
https://github.com/tomasonjo-labs/text2cypher_llama_agent
graph graphrag llamaindex llm neo4j workflows
Last synced: about 19 hours ago
JSON representation
A collection of LlamaIndex Workflows-powered agents that convert natural language to Cypher queries designed to retrieve information from a Neo4j database to answer the question with included benchmark data.
- Host: GitHub
- URL: https://github.com/tomasonjo-labs/text2cypher_llama_agent
- Owner: tomasonjo-labs
- License: mit
- Created: 2024-12-12T11:28:32.000Z (27 days ago)
- Default Branch: main
- Last Pushed: 2025-01-07T23:30:03.000Z (about 22 hours ago)
- Last Synced: 2025-01-07T23:32:31.573Z (about 22 hours ago)
- Topics: graph, graphrag, llamaindex, llm, neo4j, workflows
- Language: Jupyter Notebook
- Homepage:
- Size: 338 KB
- Stars: 3
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Text2Cypher LLama Agents
A collection of LlamaIndex Workflows-powered agents that convert natural language to Cypher queries designed to retrieve information from a Neo4j database to answer the question.
## 🎯 Features
- Multiple text2Cypher agents
- Built-in benchmarking suite
- Interactive web UI for testing
- Powered by LlamaIndex Workflows
## 🚀 Getting Started with web UI
### Prerequisites
1. Create a `.env` file based on `.env.example`
2. Install `uv` package manager:
```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```
### Installation
Install dependencies:
```bash
uv sync
```
### Run Development Server
Start the FastAPI server:
```bash
uv run fastapi dev
```
Open the `localhost:8000`
## 📊 Benchmarking
The `benchmark` directory contains:
- Test datasets
- Evaluation notebooks using Ragas
The benchmark can be evaluated against the `recommendations` database.
```
URI: neo4j+s://demo.neo4jlabs.com
username: recommendations
password: recommendations
database: recommendations
```
## 🤝 Contributing
Contributions are welcome! Please feel free to submit a Pull Request.