improve dependencies and bump to 0.0.2

.gitignore

@@ -1,5 +1,6 @@
 .env
 .venv
+dist/
 data/
 __pycache__/
 .*_cache

CONTRIBUTING.md

@@ -13,7 +13,7 @@ cd sparql-llm
 
 ## 🐣 Install dependencies
 
-> This repository uses [`hatch`](https://hatch.pypa.io/latest/) to easily handle scripts and virtual environments. Checkout the `pyproject.toml` file for more details on the scripts available. You can also just install dependencies with `pip install .` and run the python scripts in `src`
+> This repository uses [`hatch`](https://hatch.pypa.io/latest/) to easily handle scripts and virtual environments. Checkout the `pyproject.toml` file for more details on the scripts available. You can also just install dependencies with `pip install ".[chat,test]"` and run the python scripts in `src`
 
 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:
 

Dockerfile

@@ -13,7 +13,7 @@ RUN pip install --upgrade pip
 COPY . /app/
 # COPY ./scripts/prestart.sh /app/
 
-RUN pip install -e "."
+RUN pip install -e ".[chat]"
 
 ENV PYTHONPATH=/app
 ENV MODULE_NAME=src.sparql_llm.api

LICENSE.txt

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2024-present Vincent Emonet <[email protected]>
+Copyright (c) 2024-present SIB Swiss Institute of Bioinformatics
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -28,7 +28,7 @@ This repository contains:
 This package requires Python >=3.9, install it from the git repository with:
 
 ```bash
-pip install git+https://github.com/sib-swiss/sparql-llm.git
+pip install sparql-llm
 ```
 
 ### SPARQL query examples loader

pyproject.toml

@@ -6,10 +6,14 @@ build-backend = "hatchling.build"
 requires-python = ">=3.9"
 name = "sparql-llm"
 description = "Reusable components and complete webapp to improve Large Language Models (LLMs) capabilities when generating SPARQL queries for a given set of endpoints, using Retrieval-Augmented Generation (RAG) and SPARQL query validation from the endpoint schema."
-license = "MIT"
+readme = "README.md"
+license = { file = "LICENSE.txt" }
 authors = [
     { name = "Vincent Emonet", email = "[email protected]" },
 ]
+maintainers = [
+    { name = "Vincent Emonet", email = "[email protected]" },
+]
 keywords = [
     "SPARQL",
     "LLM",
@@ -26,23 +30,21 @@ dynamic = ["version"]
 dependencies = [
     "requests",
     "rdflib",
-    "openai",
     "bs4",
-    "fastembed",
-    "qdrant_client",
-    "fastapi",
     "langchain",
     "langchain-core",
     "curies-rs >=0.1.3",
-    "pydantic >=2.0.0",
-    "pydantic-settings",
 ]
 
 
 [project.optional-dependencies]
-web = [
-    "qdrant_client",
+chat = [
     "fastapi",
+    "pydantic >=2.0.0",
+    "pydantic-settings",
+    "openai",
+    "qdrant_client",
+    "fastembed",
 ]
 test = [
     "pytest",
@@ -83,7 +85,7 @@ PIP_EXTRA_INDEX_URL = "https://aiinfra.pkgs.visualstudio.com/PublicPackages/_pac
 [tool.hatch.envs.default]
 features = [
     "test",
-    "web",
+    "chat",
 ]
 post-install-commands = []
 

src/sparql_llm/__init__.py

@@ -1,6 +1,6 @@
 """Utilities to improve LLMs capabilities when working with SPARQL and RDF."""
 
-__version__ = "0.0.1"
+__version__ = "0.0.2"
 
 from .void_to_shex import get_shex_dict_from_void
 from .validate_sparql import validate_sparql_with_void