Merge pull request #1670 from Vasilije1990/master

feat: add cognee, AI memory framework to the list
2026-10-01 17:08:30 +02:00 · 2025-06-01 13:54:59 +02:00
parent 832af64e3b 63d33b5f0a
commit 53dcecdcc7
2 changed files with 86 additions and 0 deletions
@@ -11,6 +11,7 @@ partition: build
 | [Airbyte](/documentation/data-management/airbyte/)           | Data integration platform specialising in ELT pipelines.                                           |
 | [Airflow](/documentation/data-management/airflow/)           | Platform designed for developing, scheduling, and monitoring batch-oriented workflows.             |
 | [CocoIndex](/documentation/data-management/cocoindex/)           | High performance ETL framework to transform data for AI, with real-time incremental processing     |
+| [Cognee](/documentation/data-management/cognee/)             | AI memory frameworks that allows loading from 30+ data sources to graph and vector stores          |
 | [Connect](/documentation/data-management/redpanda/)          | Declarative data-agnostic streaming service for efficient, stateless processing.                   |
 | [Confluent](/documentation/data-management/confluent/)       | Fully-managed data streaming platform with a cloud-native Apache Kafka engine.                     |
 | [DLT](/documentation/data-management/dlt/)                   | Python library to simplify data loading processes between several sources and destinations.        |
@@ -0,0 +1,85 @@
+---
+title: cognee
+---
+
+# cognee
+
+[cognee](https://www.cognee.ai) is a memory management tool for AI Apps and Agents
+
+Qdrant is available as a native built-in vector database to store and retrieve embeddings.
+
+
+
+
+## 📦 Installation
+
+You can install Cognee using either **pip**, **poetry**, **uv** or any other python package manager.
+Cognee supports Python 3.8 to 3.12
+
+### With pip
+
+```bash
+pip install cognee
+```
+
+## Local Cognee installation
+
+You can install the local Cognee repo using **pip**, **poetry** and **uv**.
+For local pip installation please make sure your pip version is above version 21.3.
+
+### with UV with all optional dependencies
+
+```bash
+uv sync --all-extras
+```
+
+## 💻 Basic Usage
+
+### Setup
+
+```
+import os
+os.environ["LLM_API_KEY"] = "YOUR OPENAI_API_KEY"
+VECTOR_DB_PROVIDER="qdrant"
+VECTOR_DB_URL=https://url-to-your-qdrant-cloud-instance.cloud.qdrant.io:6333
+VECTOR_DB_KEY=your-qdrant-api-key
+
+```
+
+You can also set the variables by creating .env file, using our <a href="https://github.com/topoteretes/cognee/blob/main/.env.template">template.</a>
+To use different LLM providers, for more info check out our <a href="https://docs.cognee.ai">documentation</a>
+
+
+### Simple example
+
+This script will run the default pipeline:
+
+```python
+import cognee
+import asyncio
+
+
+async def main():
+    # Add text to cognee
+    await cognee.add("Natural language processing (NLP) is an interdisciplinary subfield of computer science and information retrieval.")
+
+    # Generate the knowledge graph
+    await cognee.cognify()
+
+    # Query the knowledge graph
+    results = await cognee.search("Tell me about NLP")
+
+    # Display the results
+    for result in results:
+        print(result)
+
+
+if __name__ == '__main__':
+    asyncio.run(main())
+
+```
+Example output:
+```
+  Natural Language Processing (NLP) is a cross-disciplinary and interdisciplinary field that involves computer science and information retrieval. It focuses on the interaction between computers and human language, enabling machines to understand and process natural language.
+
+```