ci: enables ollama integration tests

.github/workflows/ci.yaml

@@ -34,3 +34,52 @@ jobs:
 
       - name: Run tests
         run: uv run pytest tests -m 'not integration'
+
+  # This runs integration tests of the OpenAI API, using Ollama to host models.
+  # This lets us test PRs from forks which can't access secrets like API keys.
+  ollama:
+    runs-on: ubuntu-latest
+
+    strategy:
+      matrix:
+        python-version:
+          # Only test the lastest python version.
+          - "3.12"
+        ollama-model:
+          # For quicker CI, use a smaller, tool-capable model than the default.
+          - "qwen2.5:0.5b"
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Install UV
+        run: curl -LsSf https://astral.sh/uv/install.sh | sh
+
+      - name: Source Cargo Environment
+        run: source $HOME/.cargo/env
+
+      - name: Set up Python
+        run: uv python install ${{ matrix.python-version }}
+
+      - name: Install Ollama
+        run: curl -fsSL https://ollama.com/install.sh | sh
+
+      - name: Start Ollama
+        run: |
+            # Run the background, in a way that survives to the next step
+            nohup ollama serve > ollama.log 2>&1 &
+
+            # Block using the ready endpoint
+            time curl --retry 5 --retry-connrefused --retry-delay 1 -sf http://localhost:11434
+
+      # Tests use OpenAI which does not have a mechanism to pull models. Run a
+      # simple prompt to (pull and) test the model first.
+      - name: Test Ollama model
+        run: ollama run $OLLAMA_MODEL hello || cat ollama.log
+        env:
+          OLLAMA_MODEL: ${{ matrix.ollama-model }}
+
+      - name: Run Ollama tests
+        run: uv run pytest tests -m integration -k ollama
+        env:
+          OLLAMA_MODEL: ${{ matrix.ollama-model }}

tests/providers/openai/test_ollama.py

@@ -1,5 +1,6 @@
 from typing import Tuple
 
+import os
 import pytest
 
 from exchange import Text
@@ -26,7 +27,7 @@ def test_ollama_completion_integration():
 
 def ollama_complete() -> Tuple[Message, Usage]:
     provider = OllamaProvider.from_env()
-    model = OLLAMA_MODEL
+    model = os.getenv("OLLAMA_MODEL", OLLAMA_MODEL)
     system = "You are a helpful assistant."
     messages = [Message.user("Hello")]
     return provider.complete(model=model, system=system, messages=messages, tools=None)

tests/test_integration.py

@@ -1,3 +1,4 @@
+import os
 import pytest
 from exchange.exchange import Exchange
 from exchange.message import Message
@@ -9,7 +10,7 @@
 too_long_chars = "x" * (2**20 + 1)
 
 cases = [
-    (get_provider("ollama"), OLLAMA_MODEL),
+    (get_provider("ollama"), os.getenv("OLLAMA_MODEL", OLLAMA_MODEL)),
     (get_provider("openai"), "gpt-4o-mini"),
     (get_provider("databricks"), "databricks-meta-llama-3-70b-instruct"),
     (get_provider("bedrock"), "anthropic.claude-3-5-sonnet-20240620-v1:0"),
@@ -46,7 +47,9 @@ def read_file(filename: str) -> str:
         Read the contents of the file.
 
         Args:
-            filename (str): The path to the file, which can be relative or absolute.
+            filename (str): The path to the file, which can be relative or
+            absolute. If it is a plain filename, it is assumed to be in the
+            current working directory.
 
         Returns:
             str: The contents of the file.