feat: Add Support ChromaDB

.env.template

@@ -30,7 +30,7 @@ GRAPH_DATABASE_URL=
 GRAPH_DATABASE_USERNAME=
 GRAPH_DATABASE_PASSWORD=
 
-# "qdrant", "pgvector", "weaviate", "milvus" or "lancedb"
+# "qdrant", "pgvector", "weaviate", "milvus", "lancedb" or "chromadb"
 VECTOR_DB_PROVIDER="lancedb"
 # Not needed if using "lancedb" or "pgvector"
 VECTOR_DB_URL=

.github/workflows/test_chromadb.yml

@@ -0,0 +1,63 @@
+name: test | chromadb
+
+on:
+  workflow_dispatch:
+  pull_request:
+    types: [labeled, synchronize]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+env:
+  RUNTIME__LOG_LEVEL: ERROR
+
+jobs:
+  run_chromadb_integration_test:
+    name: chromadb test
+    runs-on: ubuntu-22.04
+    defaults:
+      run:
+        shell: bash
+    services:
+      chromadb:
+        image: chromadb/chroma:0.6.3
+        volumes:
+          - chroma-data:/chroma/chroma
+        ports:
+          - 3002:8000
+
+    steps:
+      - name: Check out
+        uses: actions/checkout@master
+
+      - name: Setup Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11.x'
+
+      - name: Install Poetry
+        uses: snok/[email protected]
+        with:
+          virtualenvs-create: true
+          virtualenvs-in-project: true
+          installer-parallel: true
+
+      - name: Install dependencies
+        run: poetry install --no-interaction
+
+      - name: Run chromadb test
+        env:
+          ENV: 'dev'
+          VECTOR_DB_PROVIDER: chromadb
+          VECTOR_DB_URL: http://localhost:3002
+          VECTOR_DB_KEY: test-token
+          LLM_MODEL: ${{ secrets.LLM_MODEL }}
+          LLM_ENDPOINT: ${{ secrets.LLM_ENDPOINT }}
+          LLM_API_KEY: ${{ secrets.LLM_API_KEY }}
+          LLM_API_VERSION: ${{ secrets.LLM_API_VERSION }}
+          EMBEDDING_MODEL: ${{ secrets.EMBEDDING_MODEL }}
+          EMBEDDING_ENDPOINT: ${{ secrets.EMBEDDING_ENDPOINT }}
+          EMBEDDING_API_KEY: ${{ secrets.EMBEDDING_API_KEY }}
+          EMBEDDING_API_VERSION: ${{ secrets.EMBEDDING_API_VERSION }}
+        run: poetry run python ./cognee/tests/test_chromadb.py

.gitignore

@@ -186,3 +186,6 @@ node_modules/
 
 # Evals
 SWE-bench_testsample/
+
+# ChromaDB Data
+.chromadb_data/

cognee/api/v1/settings/routers/get_settings_router.py

@@ -27,7 +27,13 @@ class LLMConfigInputDTO(InDTO):
 
 
 class VectorDBConfigInputDTO(InDTO):
-    provider: Union[Literal["lancedb"], Literal["qdrant"], Literal["weaviate"], Literal["pgvector"]]
+    provider: Union[
+        Literal["lancedb"],
+        Literal["chromadb"],
+        Literal["qdrant"],
+        Literal["weaviate"],
+        Literal["pgvector"],
+    ]
     url: str
     api_key: str