refactor: simplified the installation of torch and sentence-transformers

.github/workflows/ci.yaml

@@ -32,15 +32,17 @@ jobs:
         with:
           version: ${{ steps.poetry-version.outputs.poetry-version }}
           virtualenvs-in-project: true
-      # Installing torch (CPU) and sentence-transformers with pip to avoid poetry's issues in installing torch.
-      # Installing llama-cpp-python without NVIDIA CUDA acceleration.
+
+      - name: Get llama-cpp version
+        id: llama-cpp-version
+        run: echo "llama-cpp-version=$(cat llama_cpp_version)" >> "$GITHUB_OUTPUT"
+
+      # Installing dependencies and llama-cpp-python without NVIDIA CUDA acceleration.
       - name: Setup environment
         run: |
           poetry lock --check
           poetry install --no-root --no-ansi
-          . .venv/bin/activate && pip3 install torch~=2.1.2 torchvision torchaudio --index-url https://download.pytorch.org/whl/cpu
-          . .venv/bin/activate && pip3 install sentence-transformers~=2.2.2
-          . .venv/bin/activate && pip3 install llama-cpp-python~=0.2.23
+          . .venv/bin/activate && pip3 install llama-cpp-python~=${{ steps.llama-cpp-version.outputs.llama-cpp-version }}
 
       - name: Run tests
         run: |

Makefile

@@ -1,4 +1,7 @@
-.PHONY: clean test
+.PHONY: check install setup update test clean
+
+file=llama_cpp_version
+llama_cpp_version=`cat $(file)`
 
 check:
 	which pip3
@@ -9,11 +12,8 @@ install:
 	mkdir -p .venv
 	poetry config virtualenvs.in-project true
 	poetry install --no-root --no-ansi
-	echo "Installing torch and sentence-transformers with pip to avoid poetry's issues in installing torch... (it doesn't install CUDA dependencies)"
-	. .venv/bin/activate && pip3 install torch~=2.1.2 torchvision torchaudio
-	. .venv/bin/activate && pip3 install sentence-transformers~=2.2.2
 	echo "Installing llama-cpp-python with pip to get NVIDIA CUDA acceleration"
-	. .venv/bin/activate && CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip3 install llama-cpp-python==0.2.28
+	. .venv/bin/activate && CMAKE_ARGS="-DLLAMA_CUBLAS=on" pip3 install llama-cpp-python==$(llama_cpp_version)
 
 install_pre_commit:
 	poetry run pre-commit install

README.md

@@ -1,5 +1,6 @@
 # RAG (Retrieval-augmented generation) ChatBot
 [![CI](https://github.com/umbertogriffo/rag-chatbot/workflows/CI/badge.svg)](https://github.com/umbertogriffo/rag-chatbot/actions/workflows/ci.yaml)
+[![pre-commit](https://img.shields.io/badge/pre--commit-enabled-brightgreen?logo=pre-commit)](https://github.com/pre-commit/pre-commit)
 [![Code style: Ruff](https://img.shields.io/endpoint?url=https://raw.githubusercontent.com/astral-sh/ruff/main/assets/badge/v2.json)](https://github.com/astral-sh/ruff)
 
 > [!IMPORTANT]

llama_cpp_version

@@ -0,0 +1 @@
+0.2.28