diff --git a/.github/workflows/ci.yml b/.github/workflows/ci.yml
new file mode 100644
index 0000000..ddc62d4
--- /dev/null
+++ b/.github/workflows/ci.yml
@@ -0,0 +1,30 @@
+name: CI
+
+on:
+  push:
+    branches: [main]
+  pull_request:
+
+jobs:
+  tests:
+    strategy:
+      matrix:
+        os: [ubuntu-latest, windows-laest, macos-latest]
+    runs-on: ${{ matrix.os }}
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+          cache: 'pip'
+      - name: Install the project dependencies
+        run: |
+          pip install --upgrade pip
+          make install-dev
+      - name: Run lint
+        run: |
+          make lint-check
+      - name: Run tests
+        run: |
+          make tests
\ No newline at end of file
diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml
new file mode 100644
index 0000000..53f4169
--- /dev/null
+++ b/.github/workflows/release.yml
@@ -0,0 +1,34 @@
+name: Release
+
+on:
+  release:
+    types: [released]
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Install Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+          cache: 'pip'
+      - name: Install pypa/build
+        run: pip install build --user
+      - name: Install the project dependencies
+        run: make install
+      - name: Build wheel and tarball
+        run: python -m build . --outdir dist/
+  
+  pypi-publish:
+    name: Publish to PyPI
+    needs:
+      - build
+    runs-on: ubuntu-latest
+    permissions:
+      # IMPORTANT: this permission is mandatory for trusted publishing
+      id-token: write 
+    steps:
+      - name: Publish package distributions to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
\ No newline at end of file
diff --git a/Makefile b/Makefile
index efebc18..b1aced4 100644
--- a/Makefile
+++ b/Makefile
@@ -12,5 +12,5 @@ lint-check:
 	ruff format . --check
 	ruff check **/*.py 
 
-test:
-	pytest -n auto 
\ No newline at end of file
+tests:
+	pytest -n 5 
\ No newline at end of file
diff --git a/chromacache/__init__.py b/chromacache/__init__.py
index 128c0bf..90e0536 100644
--- a/chromacache/__init__.py
+++ b/chromacache/__init__.py
@@ -1,2 +1,2 @@
-from .chromacache import ChromaCache
+from .chromacache import *
 from .embedding_functions import *
diff --git a/chromacache/chromacache.py b/chromacache/chromacache.py
index ba4cf28..36e73e8 100644
--- a/chromacache/chromacache.py
+++ b/chromacache/chromacache.py
@@ -1,14 +1,5 @@
-try:
-    import chromadb
-    from chromadb import Documents, EmbeddingFunction, Embeddings
-except Exception:
-    __import__("pysqlite3")
-    import sys
-
-    sys.modules["sqlite3"] = sys.modules.pop("pysqlite3")
-
-    import chromadb
-    from chromadb import EmbeddingFunction
+import chromadb
+from chromadb import Documents, EmbeddingFunction, Embeddings
 
 
 class ChromaCache:
diff --git a/chromacache/embedding_functions/AbstractEmbeddingFunction.py b/chromacache/embedding_functions/AbstractEmbeddingFunction.py
index a01ff07..3652b52 100644
--- a/chromacache/embedding_functions/AbstractEmbeddingFunction.py
+++ b/chromacache/embedding_functions/AbstractEmbeddingFunction.py
@@ -1,11 +1,3 @@
-try:
-    __import__("pysqlite3")
-    import sys
-
-    sys.modules["sqlite3"] = sys.modules.pop("pysqlite3")
-except Exception:
-    pass
-
 from abc import ABC, abstractmethod
 
 import tiktoken
@@ -70,7 +62,7 @@ def __call__(self, input: Documents) -> Embeddings:
         """Wrapper that truncates the documents, encodes them
 
         Args:
-            documents (Documents): List of documents
+            input (Documents): List of documents
 
         Returns:
             Embeddings: the encoded sentences
diff --git a/chromacache/embedding_functions/__init__.py b/chromacache/embedding_functions/__init__.py
index b7a8116..6862128 100644
--- a/chromacache/embedding_functions/__init__.py
+++ b/chromacache/embedding_functions/__init__.py
@@ -5,3 +5,13 @@
 from .OpenAIEmbeddingFunction import OpenAIEmbeddingFunction
 from .SentenceTransformerEmbeddingFunction import SentenceTransformerEmbeddingFunction
 from .VoyageAIEmbeddingFunction import VoyageAIEmbeddingFunction
+
+__all__ = [
+    "AbstractEmbeddingFunction",
+    "CohereEmbeddingFunction",
+    "LaserEmbeddingFunction",
+    "MistralAIEmbeddingFunction",
+    "OpenAIEmbeddingFunction",
+    "SentenceTransformerEmbeddingFunction",
+    "VoyageAIEmbeddingFunction",
+]
diff --git a/pyproject.toml b/pyproject.toml
index e90731f..a8c7096 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -2,6 +2,9 @@
 requires = ["setuptools>=69.0", "wheel"]
 build-backend = "setuptools.build_meta"
 
+[tool.setuptools.packages.find]
+exclude = ["tests"]
+
 [project]
 name = "chromacache"
 version = "0.0.1"
@@ -22,12 +25,15 @@ dependencies = [
   "voyageai>=0.1.6",
   "tiktoken>=0.5.2",
   "openai>=1.6.1",
-  "chromadb>=0.4.21",
+  "chromadb>=0.5.3",
   "python-dotenv>=1.0.1",
-  "cohere==4.41",
-  "laser_encoders==0.0.1",
-  "sentence-transformers==2.2.2",
-  "mistralai==0.0.12"
+  "cohere>=4.41",
+  "laser_encoders>=0.0.1",
+  "sentence-transformers>=2.2.2",
+  "mistralai>=0.0.12",
+  "fairseq>=0.12",
+  "hydra-core==1.3.2",
+  "omegaconf==2.3.0"
 ]
 
 [project.urls]
@@ -36,9 +42,6 @@ Homepage = "https://github.com/Lyon-NLP/chroma_cache"
 [project.optional-dependencies]
 dev = ["ruff>=0.0.254", "pytest", "pytest-xdist"]
 
-[tool.setuptools.packages.find]
-exclude = ["tests", "results"]
-
 [tool.ruff]
 target-version = "py38"
 
diff --git a/tests/embedding_functions/test_AbstractEmbeddingFunction.py b/tests/embedding_functions/test_AbstractEmbeddingFunction.py
index 578f1c0..6b2e76d 100644
--- a/tests/embedding_functions/test_AbstractEmbeddingFunction.py
+++ b/tests/embedding_functions/test_AbstractEmbeddingFunction.py
@@ -29,7 +29,7 @@ def test_truncate_documents(tokenizer, sentences):
     )
 
     assert len(truncated_sentences) == len(sentences)
-    
+
     tokenized_truncated_sentences = [tokenizer.encode(s) for s in truncated_sentences]
     for truncated_sentence in tokenized_truncated_sentences:
         assert len(truncated_sentence) <= max_token_length