Milvus vector db

.env.template

@@ -14,7 +14,7 @@ GRAPH_DATABASE_URL=
 GRAPH_DATABASE_USERNAME=
 GRAPH_DATABASE_PASSWORD=
 
-# "qdrant", "pgvector", "weaviate" or "lancedb"
+# "qdrant", "pgvector", "weaviate", "milvus" or "lancedb"
 VECTOR_DB_PROVIDER="lancedb"
 # Not needed if using "lancedb" or "pgvector"
 VECTOR_DB_URL=

.github/workflows/test_milvus.yml

@@ -0,0 +1,64 @@
+name: test | milvus
+
+on:
+  workflow_dispatch:
+  pull_request:
+    branches:
+      - main
+    types: [labeled, synchronize]
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.ref }}
+  cancel-in-progress: true
+
+env:
+  RUNTIME__LOG_LEVEL: ERROR
+  ENV: 'dev'
+
+jobs:
+  get_docs_changes:
+    name: docs changes
+    uses: ./.github/workflows/get_docs_changes.yml
+
+  run_milvus:
+    name: test
+    needs: get_docs_changes
+    if: needs.get_docs_changes.outputs.changes_outside_docs == 'true' && ${{ github.event.label.name == 'run-checks' }}
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+    defaults:
+      run:
+        shell: bash
+
+    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
+        # https://github.com/snok/install-poetry#running-on-windows
+        uses: snok/[email protected]
+        with:
+          virtualenvs-create: true
+          virtualenvs-in-project: true
+          installer-parallel: true
+
+      - name: Install dependencies
+        run: poetry install -E milvus --no-interaction
+
+      - name: Run default basic pipeline
+        env:
+          ENV: 'dev'
+          LLM_API_KEY: ${{ secrets.OPENAI_API_KEY }}
+        run: poetry run python ./cognee/tests/test_milvus.py
+
+      - name: Clean up disk space
+        run: |
+          sudo rm -rf ~/.cache
+          sudo rm -rf /tmp/*
+          df -h

README.md

@@ -53,6 +53,12 @@ pip install 'cognee[qdrant]'
 pip install 'cognee[neo4j]'
 ```
 
+### With pip with Milvus support
+
+```bash
+pip install 'cognee[milvus]'
+```
+
 ### With poetry
 
 ```bash
@@ -83,6 +89,12 @@ poetry add cognee -E qdrant
 poetry add cognee -E neo4j
 ```
 
+### With poetry with Milvus support
+
+```bash
+poetry add cognee -E milvus
+```
+
 
 ## 💻 Basic Usage
 
@@ -356,12 +368,13 @@ pip install cognee
   }
 </style>
 
-| Name             | Type               | Current state     | Known Issues                          |
-|------------------|--------------------|-------------------|---------------------------------------|
-| Qdrant           | Vector             | Stable &#x2705;   |                                       |
-| Weaviate         | Vector             | Stable &#x2705;   |                                       |
-| LanceDB          | Vector             | Stable &#x2705;   |                                       |
-| Neo4j            | Graph              | Stable &#x2705;   |                                       |
-| NetworkX         | Graph              | Stable &#x2705;   |                                       |
-| FalkorDB         | Vector/Graph       | Unstable &#x274C; |                                       |
-| PGVector         | Vector             | Unstable &#x274C; | Postgres DB returns the Timeout error |
+| Name     | Type               | Current state     | Known Issues |
+|----------|--------------------|-------------------|--------------|
+| Qdrant   | Vector             | Stable &#x2705;   |              |
+| Weaviate | Vector             | Stable &#x2705;   |              |
+| LanceDB  | Vector             | Stable &#x2705;   |              |
+| Neo4j    | Graph              | Stable &#x2705;   |              |
+| NetworkX | Graph              | Stable &#x2705;   |              |
+| FalkorDB | Vector/Graph       | Unstable &#x274C; |              |
+| PGVector | Vector             | Stable &#x2705;   |              |
+| Milvus   | Vector             | Stable &#x2705;   |              |

cognee/infrastructure/databases/vector/create_vector_engine.py

@@ -1,11 +1,13 @@
 from typing import Dict
 
+
 class VectorConfig(Dict):
     vector_db_url: str
     vector_db_port: str
     vector_db_key: str
     vector_db_provider: str
 
+
 def create_vector_engine(config: VectorConfig, embedding_engine):
     if config["vector_db_provider"] == "weaviate":
         from .weaviate_db import WeaviateAdapter
@@ -16,24 +18,37 @@ def create_vector_engine(config: VectorConfig, embedding_engine):
         return WeaviateAdapter(
             config["vector_db_url"],
             config["vector_db_key"],
-            embedding_engine = embedding_engine
+            embedding_engine=embedding_engine
         )
 
     elif config["vector_db_provider"] == "qdrant":
         if not (config["vector_db_url"] and config["vector_db_key"]):
             raise EnvironmentError("Missing requred Qdrant credentials!")
-      
+
         from .qdrant.QDrantAdapter import QDrantAdapter
 
         return QDrantAdapter(
-            url = config["vector_db_url"],
-            api_key = config["vector_db_key"],
-            embedding_engine = embedding_engine
+            url=config["vector_db_url"],
+            api_key=config["vector_db_key"],
+            embedding_engine=embedding_engine
+        )
+
+    elif config['vector_db_provider'] == 'milvus':
+        from .milvus.MilvusAdapter import MilvusAdapter
+
+        if not config["vector_db_url"]:
+            raise EnvironmentError("Missing required Milvus credentials!")
+
+        return MilvusAdapter(
+            url=config["vector_db_url"],
+            api_key=config['vector_db_key'],
+            embedding_engine=embedding_engine
         )
 
+
     elif config["vector_db_provider"] == "pgvector":
         from cognee.infrastructure.databases.relational import get_relational_config
-        
+
         # Get configuration for postgres database
         relational_config = get_relational_config()
         db_username = relational_config.db_username
@@ -52,8 +67,8 @@ def create_vector_engine(config: VectorConfig, embedding_engine):
         from .pgvector.PGVectorAdapter import PGVectorAdapter
 
         return PGVectorAdapter(
-            connection_string, 
-            config["vector_db_key"], 
+            connection_string,
+            config["vector_db_key"],
             embedding_engine,
         )
 
@@ -64,16 +79,16 @@ def create_vector_engine(config: VectorConfig, embedding_engine):
         from ..hybrid.falkordb.FalkorDBAdapter import FalkorDBAdapter
 
         return FalkorDBAdapter(
-            database_url = config["vector_db_url"],
-            database_port = config["vector_db_port"],
-            embedding_engine = embedding_engine,
+            database_url=config["vector_db_url"],
+            database_port=config["vector_db_port"],
+            embedding_engine=embedding_engine,
         )
 
     else:
         from .lancedb.LanceDBAdapter import LanceDBAdapter
 
         return LanceDBAdapter(
-            url = config["vector_db_url"],
-            api_key = config["vector_db_key"],
-            embedding_engine = embedding_engine,
+            url=config["vector_db_url"],
+            api_key=config["vector_db_key"],
+            embedding_engine=embedding_engine,
         )