Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/vemonet/langchain-rdf

🦉 Utilities to improve LLMs capabilities when working with SPARQL endpoints and RDF knowledge graphs, compatible with LangChain
https://github.com/vemonet/langchain-rdf

langchain llm rdf sparql

Last synced: 2 months ago
JSON representation

🦉 Utilities to improve LLMs capabilities when working with SPARQL endpoints and RDF knowledge graphs, compatible with LangChain

Host: GitHub
URL: https://github.com/vemonet/langchain-rdf
Owner: vemonet
License: mit
Created: 2024-01-08T17:26:08.000Z (about 1 year ago)
Default Branch: main
Last Pushed: 2024-09-12T09:38:30.000Z (4 months ago)
Last Synced: 2024-09-12T20:49:03.993Z (4 months ago)
Topics: langchain, llm, rdf, sparql
Language: Jupyter Notebook
Homepage:
Size: 71.3 KB
Stars: 5
Watchers: 2
Forks: 1
Open Issues: 0
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
- Citation: CITATION.cff

Awesome Lists containing this project

README

# LangChain RDF

[![Test package](https://github.com/vemonet/langchain-rdf/actions/workflows/test.yml/badge.svg)](https://github.com/vemonet/langchain-rdf/actions/workflows/test.yml)

[![Hatch project](https://img.shields.io/badge/%F0%9F%A5%9A-Hatch-4051b5.svg)](https://github.com/pypa/hatch) [![linting - Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/charliermarsh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff) [![code style - Black](https://img.shields.io/badge/code%20style-black-000000.svg)](https://github.com/psf/black) [![types - Mypy](https://img.shields.io/badge/types-Mypy-blue.svg)](https://github.com/python/mypy)

Loaders and utils to work with [RDF](https://www.w3.org/RDF/) data using [LangChain](https://python.langchain.com):

* `OntologyLoader`: load OWL ontology classes and properties in your vectorstore
* `SparqlExamplesLoader`: load SPARQL query examples to your vectorstore. SPARQL queries are retrieved from a SPARQL endpoint where they are stored using the SHACL ontology, with a human readable description.

## 📦️ Installation

This package requires Python >=3.8, install it from the git repository with:

```bash
pip install git+https://github.com/vemonet/langchain-rdf.git
```

## 🪄 Usage

> [!NOTE]
>
> Refer to [LangChain documentation](https://python.langchain.com/v0.2/docs/) to figure out how to best integrate documents loaders to your stack, or check our complete notebook examples, using only open source components, running locally, with conversation memory:
>
> * [Notebook example of the OWL ontology loader](https://github.com/vemonet/langchain-rdf/blob/main/notebooks/rag_ontology.ipynb)
> * [Notebook example of the SPARQL query examples loader](https://github.com/vemonet/langchain-rdf/blob/main/notebooks/rag_sparql.ipynb)

### OWL ontology loader

```python
from langchain_rdf import OntologyLoader

loader = OntologyLoader("https://semanticscience.org/ontology/sio.owl", format="xml")
documents = loader.load()
print(len(documents))
```

### SPARQL query examples

```python
from langchain_rdf import SparqlExamplesLoader

loader = SparqlExamplesLoader("https://sparql.uniprot.org/sparql/")
documents = loader.load()
print(len(documents))
```

## 🧑‍💻 Development setup

The final section of the README is for if you want to run the package in development, and get involved by making a code contribution.

### 📥️ Clone

Clone the repository:

```bash
git clone https://github.com/vemonet/langchain-rdf
cd langchain-rdf
```
### 🐣 Install dependencies

Install [Hatch](https://hatch.pypa.io), this will automatically handle virtual environments and make sure all dependencies are installed when you run a script in the project:

```bash
pipx install hatch
```

### ☑️ Run tests

Make sure the existing tests still work by running the test suite and linting checks. Note that any pull requests to the fairworkflows repository on github will automatically trigger running of the test suite;

```bash
hatch run test
```

To display all logs when debugging:

```bash
hatch run test -s
```

### ♻️ Reset the environment

In case you are facing issues with dependencies not updating properly you can easily reset the virtual environment with:

```bash
hatch env prune
```

Manually trigger installing the dependencies in a local virtual environment:

```bash
hatch -v env create
```

### 🏷️ New release process

The deployment of new releases is done automatically by a GitHub Action workflow when a new release is created on GitHub. To release a new version:

1. Make sure the `PYPI_TOKEN` secret has been defined in the GitHub repository (in Settings > Secrets > Actions). You can get an API token from PyPI at [pypi.org/manage/account](https://pypi.org/manage/account).
2. Increment the `version` number in the `pyproject.toml` file in the root folder of the repository.

```bash
hatch version fix
```

3. Create a new release on GitHub, which will automatically trigger the publish workflow, and publish the new release to PyPI.

You can also build and publish from your computer:

```bash
hatch build
hatch publish
```