chore: build workflow

Author: samuelint

.github/workflows/build.yml

@@ -0,0 +1,40 @@
+name: Build
+
+on:
+  pull_request:
+  workflow_call:
+    secrets:
+      OPENAI_API_KEY:
+        required: true
+      ANTHROPIC_API_KEY:
+        required: true
+
+jobs:
+  build:
+    name: Build & Test
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.x"
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install poetry
+          poetry install
+
+      - name: Run tests
+        run: |
+          poetry run pytest
+
+      - name: Build
+        run: |
+          pip install poetry
+          poetry build
+
+      - uses: actions/upload-artifact@v4
+        with:
+          path: ./dist

tests/test_functional/models_configuration.py

@@ -16,6 +16,10 @@
     },
 ]
 
+n_gpu_layers = (
+    0  # -1 to offload on GPU. Until GPU is supported on Github, must be run on CPU
+)
+
 
 def _model_local_path(model) -> str:
     return os.path.join(
@@ -30,7 +34,11 @@ def _create_models_settings():
     for model in models_to_test:
         local_path = _model_local_path(model)
         models.append(
-            ModelSettings(model=local_path, model_alias=model["alias"], n_gpu_layers=-1)
+            ModelSettings(
+                model=local_path,
+                model_alias=model["alias"],
+                n_gpu_layers=n_gpu_layers,
+            )
         )
 
     return models
@@ -41,7 +49,7 @@ def create_llama(request) -> Llama:
 
     return Llama(
         model_path=local_path,
-        n_gpu_layers=-1,
+        n_gpu_layers=n_gpu_layers,
     )