cognee-community-vector-adapter-redis 0.0.1__tar.gz → 0.1.0__tar.gz

{cognee_community_vector_adapter_redis-0.0.1 → cognee_community_vector_adapter_redis-0.1.0}/.gitignore

@@ -13,5 +13,12 @@ wheels/
 .env
 
 # Cognee system
+# for backward compatibility
 .cognee-data
 .cognee-system
+
+# for new version
+.cognee_data
+.cognee_system
+.data_storage
+*.log

{cognee_community_vector_adapter_redis-0.0.1 → cognee_community_vector_adapter_redis-0.1.0}/PKG-INFO

@@ -1,10 +1,12 @@
 Metadata-Version: 2.4
 Name: cognee-community-vector-adapter-redis
-Version: 0.0.1
+Version: 0.1.0
 Summary: Redis vector database adapter for cognee
 Requires-Python: <=3.13,>=3.11
-Requires-Dist: cognee>=0.2.0.dev0
+Requires-Dist: cognee==0.5.2
+Requires-Dist: instructor>=1.11
 Requires-Dist: redisvl<=1.0.0,>=0.6.0
+Requires-Dist: starlette>=0.48.0
 Description-Content-Type: text/markdown
 
 <div align="center" dir="auto">
@@ -17,7 +19,7 @@ Description-Content-Type: text/markdown
     <br />
 
 [![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
-![Language](https://img.shields.io/badge/python-3.8+-blue.svg)
+![Language](https://img.shields.io/badge/python-3.11+-blue.svg)
 
 [![Powered by RedisVL](https://img.shields.io/badge/Powered%20by-RedisVL-red.svg)](https://github.com/redis/redis-vl-python)
 
@@ -44,10 +46,19 @@ Description-Content-Type: text/markdown
 
 ## Installation
 
+If published, the package can be simply installed via pip:
+
 ```bash
 pip install cognee-community-vector-adapter-redis
 ```
 
+In case it is not published yet, you can use poetry to locally build the adapter package:
+
+```bash
+pip install poetry
+poetry install # run this command in the directory containing the pyproject.toml file
+```
+
 ## Prerequisites
 
 You need a Redis instance with the Redis Search module enabled. You can use:
@@ -71,96 +82,115 @@ uv run examples/example.py
 ## Usage
 
 ```python
-from cognee.infrastructure.databases.vector.embeddings.EmbeddingEngine import EmbeddingEngine
-from cognee_community_vector_adapter_redis import RedisAdapter
-
-# Initialize your embedding engine
-embedding_engine = EmbeddingEngine(
-    model="your-model",
-    # ... other config
-)
-
-# Create Redis adapter
-redis_adapter = RedisAdapter(
-    url="redis://localhost:6379",  # Redis connection URL
-    embedding_engine=embedding_engine,
-    api_key=None  # Optional, not used for Redis but part of interface
-)
+import os
+import asyncio
+from cognee import config, prune, add, cognify, search, SearchType
+
+# Import the register module to enable Redis support
+from cognee_community_vector_adapter_redis import register
+
+async def main():
+    # Configure Redis as vector database
+    config.set_vector_db_config({
+        "vector_db_provider": "redis",
+        "vector_db_url": os.getenv("VECTOR_DB_URL", "redis://localhost:6379"),
+        "vector_db_key": os.getenv("VECTOR_DB_KEY", "your-api-key"),  # Optional
+    })
+    
+    # Optional: Clean previous data
+    await prune.prune_data()
+    await prune.prune_system()
+    
+    # Add your content
+    await add("""
+    Natural language processing (NLP) is an interdisciplinary
+    subfield of computer science and information retrieval.
+    """)
+    
+    # Process with cognee
+    await cognify()
+    
+    # Search
+    search_results = await search(
+        query_type=SearchType.GRAPH_COMPLETION, 
+        query_text="Tell me about NLP"
+    )
+    
+    for result in search_results:
+        print("Search result:", result)
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
 
-# Create a collection
-await redis_adapter.create_collection("my_collection")
+## Configuration
 
-# Add data points
-from cognee.infrastructure.engine import DataPoint
+Configure Redis as your vector database in cognee:
 
-data_points = [
-    DataPoint(id="1", text="Hello world", metadata={"index_fields": ["text"]}),
-    DataPoint(id="2", text="Redis vector search", metadata={"index_fields": ["text"]})
-]
+- `vector_db_provider`: Set to "redis"
+- `vector_db_url`: Redis connection URL (e.g., "redis://localhost:6379")
+- `vector_db_key`: Optional API key parameter (for compatibility, not used by Redis)
 
-await redis_adapter.create_data_points("my_collection", data_points)
+### Environment Variables
 
-# Search for similar vectors
-results = await redis_adapter.search(
-    collection_name="my_collection",
-    query_text="Hello Redis",
-    limit=10
-)
+Set the following environment variables or pass them directly in the config:
 
-# Search with pre-computed vector
-query_vector = await redis_adapter.embed_data(["Hello Redis"])
-results = await redis_adapter.search(
-    collection_name="my_collection",
-    query_vector=query_vector[0],
-    limit=10,
-    with_vector=True  # Include vectors in results
-)
+```bash
+export VECTOR_DB_URL="redis://localhost:6379"
+export VECTOR_DB_KEY="optional-key"  # Not used by Redis
+```
 
-# Batch search
-results = await redis_adapter.batch_search(
-    collection_name="my_collection", 
-    query_texts=["query1", "query2"],
-    limit=5
-)
+### Connection URL Examples
 
-# Retrieve specific data points
-retrieved = await redis_adapter.retrieve(
-    collection_name="my_collection",
-    data_point_ids=["1", "2"]
-)
+```python
+# Local Redis
+config.set_vector_db_config({
+    "vector_db_provider": "redis",
+    "vector_db_url": "redis://localhost:6379"
+})
 
-# Delete data points
-await redis_adapter.delete_data_points(
-    collection_name="my_collection",
-    data_point_ids=["1"]
-)
+# Redis with authentication
+config.set_vector_db_config({
+    "vector_db_provider": "redis", 
+    "vector_db_url": "redis://user:password@localhost:6379"
+})
 
-# Check if collection exists
-exists = await redis_adapter.has_collection("my_collection")
+# Redis with SSL
+config.set_vector_db_config({
+    "vector_db_provider": "redis",
+    "vector_db_url": "rediss://localhost:6380"
+})
 ```
 
-## Configuration
+## Requirements
 
-The Redis adapter supports the following configuration options:
+- Python >= 3.11, <= 3.13
+- redisvl >= 0.6.0, <= 1.0.0
+- cognee >= 0.2.0.dev0
 
-- `url`: Redis connection URL (e.g., "redis://localhost:6379", "redis://user:pass@host:port")
-- `embedding_engine`: The `EmbeddingEngine` to use for text vectorization (required)
-- `api_key`: Optional API key parameter (not used for Redis but part of the interface)
+## Advanced Usage
 
-### Connection URL Examples
+For direct adapter usage (advanced users only):
 
 ```python
-# Local Redis
-redis_adapter = RedisAdapter(url="redis://localhost:6379", embedding_engine=engine)
+from cognee.infrastructure.databases.vector.embeddings.EmbeddingEngine import EmbeddingEngine
+from cognee_community_vector_adapter_redis import RedisAdapter
+from cognee.infrastructure.engine import DataPoint
 
-# Redis with authentication
-redis_adapter = RedisAdapter(url="redis://user:password@localhost:6379", embedding_engine=engine)
+# Initialize embedding engine and adapter
+embedding_engine = EmbeddingEngine(model="your-model")
+redis_adapter = RedisAdapter(
+    url="redis://localhost:6379",
+    embedding_engine=embedding_engine
+)
 
-# Redis with SSL
-redis_adapter = RedisAdapter(url="rediss://localhost:6380", embedding_engine=engine)
+# Direct adapter operations
+await redis_adapter.create_collection("my_collection")
+data_points = [DataPoint(id="1", text="Hello", metadata={"index_fields": ["text"]})]
+await redis_adapter.create_data_points("my_collection", data_points)
+results = await redis_adapter.search("my_collection", query_text="Hello", limit=10)
 ```
 
-
 ## Error Handling
 
 The adapter includes comprehensive error handling:

{cognee_community_vector_adapter_redis-0.0.1 → cognee_community_vector_adapter_redis-0.1.0}/README.md

@@ -8,7 +8,7 @@
     <br />
 
 [![License: Apache 2.0](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
-![Language](https://img.shields.io/badge/python-3.8+-blue.svg)
+![Language](https://img.shields.io/badge/python-3.11+-blue.svg)
 
 [![Powered by RedisVL](https://img.shields.io/badge/Powered%20by-RedisVL-red.svg)](https://github.com/redis/redis-vl-python)
 
@@ -35,10 +35,19 @@
 
 ## Installation
 
+If published, the package can be simply installed via pip:
+
 ```bash
 pip install cognee-community-vector-adapter-redis
 ```
 
+In case it is not published yet, you can use poetry to locally build the adapter package:
+
+```bash
+pip install poetry
+poetry install # run this command in the directory containing the pyproject.toml file
+```
+
 ## Prerequisites
 
 You need a Redis instance with the Redis Search module enabled. You can use:
@@ -62,96 +71,115 @@ uv run examples/example.py
 ## Usage
 
 ```python
-from cognee.infrastructure.databases.vector.embeddings.EmbeddingEngine import EmbeddingEngine
-from cognee_community_vector_adapter_redis import RedisAdapter
-
-# Initialize your embedding engine
-embedding_engine = EmbeddingEngine(
-    model="your-model",
-    # ... other config
-)
-
-# Create Redis adapter
-redis_adapter = RedisAdapter(
-    url="redis://localhost:6379",  # Redis connection URL
-    embedding_engine=embedding_engine,
-    api_key=None  # Optional, not used for Redis but part of interface
-)
+import os
+import asyncio
+from cognee import config, prune, add, cognify, search, SearchType
+
+# Import the register module to enable Redis support
+from cognee_community_vector_adapter_redis import register
+
+async def main():
+    # Configure Redis as vector database
+    config.set_vector_db_config({
+        "vector_db_provider": "redis",
+        "vector_db_url": os.getenv("VECTOR_DB_URL", "redis://localhost:6379"),
+        "vector_db_key": os.getenv("VECTOR_DB_KEY", "your-api-key"),  # Optional
+    })
+    
+    # Optional: Clean previous data
+    await prune.prune_data()
+    await prune.prune_system()
+    
+    # Add your content
+    await add("""
+    Natural language processing (NLP) is an interdisciplinary
+    subfield of computer science and information retrieval.
+    """)
+    
+    # Process with cognee
+    await cognify()
+    
+    # Search
+    search_results = await search(
+        query_type=SearchType.GRAPH_COMPLETION, 
+        query_text="Tell me about NLP"
+    )
+    
+    for result in search_results:
+        print("Search result:", result)
+
+if __name__ == "__main__":
+    asyncio.run(main())
+```
 
-# Create a collection
-await redis_adapter.create_collection("my_collection")
+## Configuration
 
-# Add data points
-from cognee.infrastructure.engine import DataPoint
+Configure Redis as your vector database in cognee:
 
-data_points = [
-    DataPoint(id="1", text="Hello world", metadata={"index_fields": ["text"]}),
-    DataPoint(id="2", text="Redis vector search", metadata={"index_fields": ["text"]})
-]
+- `vector_db_provider`: Set to "redis"
+- `vector_db_url`: Redis connection URL (e.g., "redis://localhost:6379")
+- `vector_db_key`: Optional API key parameter (for compatibility, not used by Redis)
 
-await redis_adapter.create_data_points("my_collection", data_points)
+### Environment Variables
 
-# Search for similar vectors
-results = await redis_adapter.search(
-    collection_name="my_collection",
-    query_text="Hello Redis",
-    limit=10
-)
+Set the following environment variables or pass them directly in the config:
 
-# Search with pre-computed vector
-query_vector = await redis_adapter.embed_data(["Hello Redis"])
-results = await redis_adapter.search(
-    collection_name="my_collection",
-    query_vector=query_vector[0],
-    limit=10,
-    with_vector=True  # Include vectors in results
-)
+```bash
+export VECTOR_DB_URL="redis://localhost:6379"
+export VECTOR_DB_KEY="optional-key"  # Not used by Redis
+```
 
-# Batch search
-results = await redis_adapter.batch_search(
-    collection_name="my_collection", 
-    query_texts=["query1", "query2"],
-    limit=5
-)
+### Connection URL Examples
 
-# Retrieve specific data points
-retrieved = await redis_adapter.retrieve(
-    collection_name="my_collection",
-    data_point_ids=["1", "2"]
-)
+```python
+# Local Redis
+config.set_vector_db_config({
+    "vector_db_provider": "redis",
+    "vector_db_url": "redis://localhost:6379"
+})
 
-# Delete data points
-await redis_adapter.delete_data_points(
-    collection_name="my_collection",
-    data_point_ids=["1"]
-)
+# Redis with authentication
+config.set_vector_db_config({
+    "vector_db_provider": "redis", 
+    "vector_db_url": "redis://user:password@localhost:6379"
+})
 
-# Check if collection exists
-exists = await redis_adapter.has_collection("my_collection")
+# Redis with SSL
+config.set_vector_db_config({
+    "vector_db_provider": "redis",
+    "vector_db_url": "rediss://localhost:6380"
+})
 ```
 
-## Configuration
+## Requirements
 
-The Redis adapter supports the following configuration options:
+- Python >= 3.11, <= 3.13
+- redisvl >= 0.6.0, <= 1.0.0
+- cognee >= 0.2.0.dev0
 
-- `url`: Redis connection URL (e.g., "redis://localhost:6379", "redis://user:pass@host:port")
-- `embedding_engine`: The `EmbeddingEngine` to use for text vectorization (required)
-- `api_key`: Optional API key parameter (not used for Redis but part of the interface)
+## Advanced Usage
 
-### Connection URL Examples
+For direct adapter usage (advanced users only):
 
 ```python
-# Local Redis
-redis_adapter = RedisAdapter(url="redis://localhost:6379", embedding_engine=engine)
+from cognee.infrastructure.databases.vector.embeddings.EmbeddingEngine import EmbeddingEngine
+from cognee_community_vector_adapter_redis import RedisAdapter
+from cognee.infrastructure.engine import DataPoint
 
-# Redis with authentication
-redis_adapter = RedisAdapter(url="redis://user:password@localhost:6379", embedding_engine=engine)
+# Initialize embedding engine and adapter
+embedding_engine = EmbeddingEngine(model="your-model")
+redis_adapter = RedisAdapter(
+    url="redis://localhost:6379",
+    embedding_engine=embedding_engine
+)
 
-# Redis with SSL
-redis_adapter = RedisAdapter(url="rediss://localhost:6380", embedding_engine=engine)
+# Direct adapter operations
+await redis_adapter.create_collection("my_collection")
+data_points = [DataPoint(id="1", text="Hello", metadata={"index_fields": ["text"]})]
+await redis_adapter.create_data_points("my_collection", data_points)
+results = await redis_adapter.search("my_collection", query_text="Hello", limit=10)
 ```
 
-
 ## Error Handling
 
 The adapter includes comprehensive error handling:

{cognee_community_vector_adapter_redis-0.0.1 → cognee_community_vector_adapter_redis-0.1.0}/__init__.py

@@ -1,3 +1,3 @@
 from .redis_adapter import RedisAdapter
 
-__all__ = ["RedisAdapter"] 
+__all__ = ["RedisAdapter"]