Development

.github/workflows/build-container.yaml

@@ -0,0 +1,85 @@
+name: Build and Push Container
+
+on:
+  push:
+    branches:
+      - main
+      - development
+
+jobs:
+  build-and-push:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+      packages: write
+
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+
+      - name: Install Poetry
+        run: pip install poetry==2.1.3
+
+      - name: Verify lockfile matches pyproject.toml
+        run: poetry check --lock
+
+      - name: Get version
+        id: version
+        run: echo "VERSION=$(grep '^version = ' pyproject.toml | sed 's/version = "\(.*\)"/\1/')" >> $GITHUB_OUTPUT
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log in to GitHub Container Registry
+        uses: docker/login-action@v3
+        with:
+          registry: ghcr.io
+          username: ${{ github.actor }}
+          password: ${{ secrets.GHCR_TOKEN }}
+
+      - name: Build and push Docker image (main)
+        if: github.ref == 'refs/heads/main'
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          platforms: linux/amd64
+          push: true
+          tags: |
+            ghcr.io/lumen-labs/brainapi:v${{ steps.version.outputs.VERSION }}
+            ghcr.io/lumen-labs/brainapi:latest
+          build-args: |
+            BUILD_DATE=${{ github.event.head_commit.timestamp }}
+            BUILD_SHA=${{ github.sha }}
+            CACHE_BUST=${{ github.run_number }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      - name: Build and push Docker image (development)
+        if: github.ref == 'refs/heads/development'
+        uses: docker/build-push-action@v5
+        with:
+          context: .
+          platforms: linux/amd64
+          push: true
+          tags: |
+            ghcr.io/lumen-labs/brainapi:development
+            ghcr.io/lumen-labs/brainapi:v${{ steps.version.outputs.VERSION }}-development
+          build-args: |
+            BUILD_DATE=${{ github.event.head_commit.timestamp }}
+            BUILD_SHA=${{ github.sha }}
+            CACHE_BUST=${{ github.run_number }}
+          cache-from: type=gha
+          cache-to: type=gha,mode=max
+
+      - name: Create Git tag (only on main branch)
+        if: github.ref == 'refs/heads/main'
+        run: |
+          git config --local user.email "action@github.com"
+          git config --local user.name "GitHub Action"
+          git tag -a v${{ steps.version.outputs.VERSION }} -m "Release v${{ steps.version.outputs.VERSION }}"
+          git push origin v${{ steps.version.outputs.VERSION }}

README.md

@@ -1,6 +1,6 @@
 <p align="center">
   <a href="https://discord.gg/VTngQTaeDf"><img src="https://img.shields.io/badge/Discord-Join%20Lumen%20Brain-5865F2?style=for-the-badge&logo=discord&logoColor=white" alt="Discord"/></a>
-  <img src="https://img.shields.io/badge/version-2.11.5--dev-blue?style=for-the-badge" alt="Version"/>
+  <img src="https://img.shields.io/badge/version-2.11.6--dev-blue?style=for-the-badge" alt="Version"/>
   <img src="https://img.shields.io/badge/python-3.11+-green?style=for-the-badge&logo=python&logoColor=white" alt="Python"/>
   <img src="https://img.shields.io/badge/license-AGPLv3%20%2B%20Commons%20Clause-purple?style=for-the-badge" alt="License"/>
 </p>

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "brainapi2"
-version = "2.11.5-dev"
+version = "2.11.6-dev"
 description = "Version 2.x.x of the BrainAPI memory layer."
 authors = [
     {name = "Christian",email = "alch.infoemail@gmail.com"}

src/constants/spacy_models.py

@@ -7,22 +7,17 @@
     "nl": "nl_core_news_sm",
     "pt": "pt_core_news_sm",
     "ru": "ru_core_news_sm",
-    "zh": "zh_core_news_sm",
+    "zh": "zh_core_web_sm",
     "ja": "ja_core_news_sm",
     "ko": "ko_core_news_sm",
     "ar": "ar_core_news_sm",
     "hi": "hi_core_news_sm",
     "bn": "bn_core_news_sm",
     "pa": "pa_core_news_sm",
-    "ta": "ta_core_news_sm",
-    "te": "te_core_news_sm",
     "ml": "ml_core_news_sm",
-    "tr": "tr_core_news_sm",
-    "vi": "vi_core_news_sm",
     "id": "id_core_news_sm",
     "ms": "ms_core_news_sm",
     "fil": "fil_core_news_sm",
-    "th": "th_core_news_sm",
     "lo": "lo_core_news_sm",
     "my": "my_core_news_sm",
     "km": "km_core_news_sm",

tests/test_spacy_fixes_verification.py

@@ -42,6 +42,17 @@ def test_builder_installs_models_via_spacy_model_names(self):
         self.assertIn("spacy download", dockerfile)
         self.assertIn("src.constants.spacy_models", dockerfile)
 
+    def test_chinese_uses_web_pipeline_name(self):
+        from src.constants.spacy_models import SPACY_MODEL_NAMES
+
+        self.assertEqual(SPACY_MODEL_NAMES["zh"], "zh_core_web_sm")
+
+    def test_no_languages_without_spacy_3_8_pipelines(self):
+        from src.constants.spacy_models import SPACY_MODEL_NAMES
+
+        for code in ("ta", "te", "th", "tr", "vi"):
+            self.assertNotIn(code, SPACY_MODEL_NAMES)
+
 
 class TestFastAPIRedirectSlashes(unittest.TestCase):
     def test_app_disables_trailing_slash_redirect(self):