Add inference plugin and tests

.github/workflows/testing-integration.yaml

@@ -3,53 +3,27 @@ name: "Integration Tests"
   workflow_call: {}
 
 jobs:
-  # setup-index:
-  #   name: Setup proxyconfig test index
-  #   runs-on: ubuntu-latest
-  #   outputs:
-  #     index_name: ${{ steps.create-index.outputs.index_name }}
-  #   steps:
-  #     - uses: actions/checkout@v4
-  #     - name: Create index
-  #       id: create-index
-  #       uses: ./.github/actions/create-index
-  #       with:
-  #         PINECONE_API_KEY: ${{ secrets.PINECONE_API_KEY }}
-  #         NAME_PREFIX: 'proxyconfig-'
-  #         REGION: 'us-west-2'
-  #         CLOUD: 'aws'
-  #         DIMENSION: 1536
-  #         METRIC: 'cosine'
-
-  # proxy-config:
-  #   name: Proxy config tests
-  #   needs: [setup-index]
-  #   runs-on: ubuntu-latest
-  #   steps:
-  #     - uses: actions/checkout@v4
-  #     - uses: actions/setup-python@v5
-  #       with:
-  #         python-version: 3.9
-  #     - name: Setup Poetry
-  #       uses: ./.github/actions/setup-poetry
-  #     - name: 'Run integration tests (proxy config)'
-  #       run: |
-  #         poetry run pytest tests/integration/proxy_config -s -v
-  #       env:
-  #         PINECONE_API_KEY: '${{ secrets.PINECONE_API_KEY }}'
-  #         PINECONE_INDEX_NAME: ${{ needs.setup-index.outputs.index_name }}
-  #     - name: Upload logs
-  #       if: always()
-  #       uses: actions/upload-artifact@v4
-  #       with:
-  #         name: proxy_config_test_logs
-  #         path: tests/integration/proxy_config/logs
-  #     - name: Cleanup index
-  #       if: always()
-  #       uses: ./.github/actions/delete-index
-  #       with:
-  #         PINECONE_API_KEY: ${{ secrets.PINECONE_API_KEY }}
-  #         INDEX_NAME: ${{ needs.setup-index.outputs.index_name }}
+  plugin-inference:
+    name: Test inference plugin
+    runs-on: ubuntu-latest
+    strategy:
+      matrix:
+        python_version: [3.8, 3.12]
+    steps:
+      - uses: actions/checkout@v4
+      - name: 'Set up Python ${{ matrix.python_version }}'
+        uses: actions/setup-python@v5
+        with:
+          python-version: '${{ matrix.python_version }}'
+      - name: Setup Poetry
+        uses: ./.github/actions/setup-poetry
+        with:
+          include_grpc: 'true'
+      - name: 'Run integration tests'
+        run: poetry run pytest tests/integration/inference -s -vv
+        env:
+          PINECONE_DEBUG_CURL: 'true'
+          PINECONE_API_KEY: '${{ secrets.PINECONE_API_KEY }}'
 
   data-plane-serverless:
     name: Data plane serverless integration tests

pyproject.toml

@@ -68,6 +68,7 @@ lz4 = { version = ">=3.1.3", optional = true }
 protobuf = { version = "^4.25", optional = true }
 protoc-gen-openapiv2 = {version = "^0.0.1", optional = true }
 pinecone-plugin-interface = "^0.0.7"
+pinecone-plugin-inference = "1.0.2"
 
 [tool.poetry.group.types]
 optional = true

tests/integration/inference/conftest.py

@@ -0,0 +1,6 @@
+import pytest
+from ..helpers import get_environment_var
+
+@pytest.fixture()
+def api_key():
+    return get_environment_var("PINECONE_API_KEY")

tests/integration/inference/test_embed.py

@@ -0,0 +1,33 @@
+from pinecone import Pinecone
+from pinecone.grpc import PineconeGRPC
+
+class TestInferencePlugin:
+    def test_embed(self, api_key):
+        pc = Pinecone(api_key=api_key)
+
+        embedding_model = "multilingual-e5-large"
+        embeddings = pc.inference.embed(
+            model=embedding_model,
+            inputs=["The quick brown fox jumps over the lazy dog.", "lorem ipsum"],
+            parameters={"input_type": "query", "truncate": "END"},
+        )
+
+        assert len(embeddings.get("data")) == 2
+        assert len(embeddings.get("data")[0]["values"]) == 1024
+        assert len(embeddings.get("data")[1]["values"]) == 1024
+        assert embeddings.get("model") == embedding_model
+
+    def test_embed_grpc(self, api_key):
+        pc = PineconeGRPC(api_key=api_key)
+
+        embedding_model = "multilingual-e5-large"
+        embeddings = pc.inference.embed(
+            model=embedding_model,
+            inputs=["The quick brown fox jumps over the lazy dog.", "lorem ipsum"],
+            parameters={"input_type": "query", "truncate": "END"},
+        )
+
+        assert len(embeddings.get("data")) == 2
+        assert len(embeddings.get("data")[0]["values"]) == 1024
+        assert len(embeddings.get("data")[1]["values"]) == 1024
+        assert embeddings.get("model") == embedding_model