cognee 0.3.4.dev4__py3-none-any.whl → 0.3.6__py3-none-any.whl

{cognee-0.3.4.dev4.dist-info → cognee-0.3.6.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: cognee
-Version: 0.3.4.dev4
+Version: 0.3.6
 Summary: Cognee - is a library for enriching LLM context with a semantic layer for better understanding and reasoning.
 Project-URL: Homepage, https://www.cognee.ai
 Project-URL: Repository, https://github.com/topoteretes/cognee
@@ -20,51 +20,44 @@ Requires-Dist: aiofiles<24.0.0,>=23.2.1
 Requires-Dist: aiohttp<4.0.0,>=3.11.14
 Requires-Dist: aiosqlite<1.0.0,>=0.20.0
 Requires-Dist: alembic<2,>=1.13.3
-Requires-Dist: baml-py<0.202.0,>=0.201.0
-Requires-Dist: dlt[sqlalchemy]<2,>=1.9.0
 Requires-Dist: fastapi-users[sqlalchemy]<15.0.0,>=14.0.1
 Requires-Dist: fastapi<1.0.0,>=0.115.7
+Requires-Dist: fastembed<=0.6.0
 Requires-Dist: filetype<2.0.0,>=1.2.0
+Requires-Dist: gunicorn<24,>=20.1.0
 Requires-Dist: instructor<2.0.0,>=1.9.1
 Requires-Dist: jinja2<4,>=3.1.3
-Requires-Dist: kuzu==0.11.0
+Requires-Dist: kuzu==0.11.3
 Requires-Dist: lancedb<1.0.0,>=0.24.0
-Requires-Dist: langfuse<3,>=2.32.0
 Requires-Dist: limits<5,>=4.4.1
-Requires-Dist: litellm<2.0.0,>=1.71.0
-Requires-Dist: matplotlib<4,>=3.8.3
+Requires-Dist: litellm>=1.76.0
 Requires-Dist: nbformat<6.0.0,>=5.7.0
 Requires-Dist: networkx<4,>=3.4.2
-Requires-Dist: nltk<4.0.0,>=3.9.1
 Requires-Dist: numpy<=4.0.0,>=1.26.4
-Requires-Dist: onnxruntime<2.0.0,>=1.0.0
-Requires-Dist: openai<2.0.0,>=1.80.1
-Requires-Dist: pandas<3.0.0,>=2.2.2
-Requires-Dist: pre-commit<5,>=4.0.1
+Requires-Dist: onnxruntime<=1.22.1
+Requires-Dist: openai>=1.80.1
 Requires-Dist: pydantic-settings<3,>=2.2.1
 Requires-Dist: pydantic<3.0.0,>=2.10.5
-Requires-Dist: pylance<1.0.0,>=0.22.0
+Requires-Dist: pylance<=0.36.0,>=0.22.0
 Requires-Dist: pympler<2.0.0,>=1.1
 Requires-Dist: pypdf<7.0.0,>=4.1.0
 Requires-Dist: python-dotenv<2.0.0,>=1.0.1
 Requires-Dist: python-magic-bin<0.5; platform_system == 'Windows'
 Requires-Dist: python-multipart<1.0.0,>=0.0.20
 Requires-Dist: rdflib<7.2.0,>=7.1.4
-Requires-Dist: s3fs[boto3]==2025.3.2
-Requires-Dist: scikit-learn<2,>=1.6.1
-Requires-Dist: sentry-sdk[fastapi]<3,>=2.9.0
 Requires-Dist: sqlalchemy<3.0.0,>=2.0.39
 Requires-Dist: structlog<26,>=25.2.0
 Requires-Dist: tiktoken<1.0.0,>=0.8.0
 Requires-Dist: typing-extensions<5.0.0,>=4.12.2
+Requires-Dist: uvicorn<1.0.0,>=0.34.0
+Requires-Dist: websockets<16.0.0,>=15.0.1
 Provides-Extra: anthropic
 Requires-Dist: anthropic>=0.27; extra == 'anthropic'
 Provides-Extra: api
-Requires-Dist: gunicorn<24,>=20.1.0; extra == 'api'
-Requires-Dist: uvicorn<1.0.0,>=0.34.0; extra == 'api'
-Requires-Dist: websockets<16.0.0,>=15.0.1; extra == 'api'
 Provides-Extra: aws
 Requires-Dist: s3fs[boto3]==2025.3.2; extra == 'aws'
+Provides-Extra: baml
+Requires-Dist: baml-py==0.206.0; extra == 'baml'
 Provides-Extra: chromadb
 Requires-Dist: chromadb<0.7,>=0.6; extra == 'chromadb'
 Requires-Dist: pypika==0.48.9; extra == 'chromadb'
@@ -86,30 +79,29 @@ Requires-Dist: mkdocs-minify-plugin<0.9,>=0.8.0; extra == 'dev'
 Requires-Dist: mkdocstrings[python]<0.27,>=0.26.2; extra == 'dev'
 Requires-Dist: mypy<2,>=1.7.1; extra == 'dev'
 Requires-Dist: notebook<8,>=7.1.0; extra == 'dev'
+Requires-Dist: pre-commit<5,>=4.0.1; extra == 'dev'
 Requires-Dist: pylint<4,>=3.0.3; extra == 'dev'
 Requires-Dist: pytest-asyncio<0.22,>=0.21.1; extra == 'dev'
 Requires-Dist: pytest-cov<7.0.0,>=6.1.1; extra == 'dev'
 Requires-Dist: pytest<8,>=7.4.0; extra == 'dev'
-Requires-Dist: ruff<1.0.0,>=0.9.2; extra == 'dev'
+Requires-Dist: ruff<=0.13.1,>=0.9.2; extra == 'dev'
 Requires-Dist: tweepy<5.0.0,>=4.14.0; extra == 'dev'
 Provides-Extra: distributed
 Requires-Dist: modal<2.0.0,>=1.0.5; extra == 'distributed'
+Provides-Extra: dlt
+Requires-Dist: dlt[sqlalchemy]<2,>=1.9.0; extra == 'dlt'
 Provides-Extra: docs
-Requires-Dist: unstructured[csv,doc,docx,epub,md,odt,org,ppt,pptx,rst,rtf,tsv,xlsx]<19,>=0.18.1; extra == 'docs'
+Requires-Dist: unstructured[csv,doc,docx,epub,md,odt,org,pdf,ppt,pptx,rst,rtf,tsv,xlsx]<19,>=0.18.1; extra == 'docs'
 Provides-Extra: evals
 Requires-Dist: gdown<6,>=5.2.0; extra == 'evals'
+Requires-Dist: matplotlib<4,>=3.8.3; extra == 'evals'
+Requires-Dist: pandas<3.0.0,>=2.2.2; extra == 'evals'
 Requires-Dist: plotly<7,>=6.0.0; extra == 'evals'
-Provides-Extra: falkordb
-Requires-Dist: falkordb<2.0.0,>=1.0.9; extra == 'falkordb'
-Provides-Extra: gemini
-Requires-Dist: google-generativeai<0.9,>=0.8.4; extra == 'gemini'
+Requires-Dist: scikit-learn<2,>=1.6.1; extra == 'evals'
 Provides-Extra: graphiti
 Requires-Dist: graphiti-core<0.8,>=0.7.0; extra == 'graphiti'
 Provides-Extra: groq
 Requires-Dist: groq<1.0.0,>=0.8.0; extra == 'groq'
-Provides-Extra: gui
-Requires-Dist: pyside6<7,>=6.8.3; extra == 'gui'
-Requires-Dist: qasync<0.28,>=0.27.1; extra == 'gui'
 Provides-Extra: huggingface
 Requires-Dist: transformers<5,>=4.46.3; extra == 'huggingface'
 Provides-Extra: langchain
@@ -119,6 +111,9 @@ Provides-Extra: llama-index
 Requires-Dist: llama-index-core<0.13,>=0.12.11; extra == 'llama-index'
 Provides-Extra: mistral
 Requires-Dist: mistral-common<2,>=1.5.2; extra == 'mistral'
+Provides-Extra: monitoring
+Requires-Dist: langfuse<3,>=2.32.0; extra == 'monitoring'
+Requires-Dist: sentry-sdk[fastapi]<3,>=2.9.0; extra == 'monitoring'
 Provides-Extra: neo4j
 Requires-Dist: neo4j<6,>=5.28.0; extra == 'neo4j'
 Provides-Extra: neptune
@@ -146,7 +141,7 @@ Description-Content-Type: text/markdown
 
   <br />
 
-  cognee - Memory for AI Agents in 5 lines of code
+  cognee - Memory for AI Agents in 6 lines of code
 
   <p align="center">
   <a href="https://www.youtube.com/watch?v=1bezuvLwJmw&t=2s">Demo</a>
@@ -184,11 +179,9 @@ Description-Content-Type: text/markdown
 
 
 
-**🚀 We launched Cogwit beta (Fully-hosted AI Memory): Sign up [here](https://platform.cognee.ai/)! 🚀**
 
-Build dynamic memory for Agents and replace RAG using scalable, modular ECL (Extract, Cognify, Load) pipelines.
 
-More on [use-cases](https://docs.cognee.ai/use-cases) and [evals](https://github.com/topoteretes/cognee/tree/main/evals)
+Build dynamic memory for Agents and replace RAG using scalable, modular ECL (Extract, Cognify, Load) pipelines.
 
   <p align="center">
   🌐 Available Languages
@@ -211,53 +204,50 @@ More on [use-cases](https://docs.cognee.ai/use-cases) and [evals](https://github
 </div>
 
 
-## Features
-
-- Interconnect and retrieve your past conversations, documents, images and audio transcriptions
-- Replaces RAG systems and reduces developer effort, and cost.
-- Load data to graph and vector databases using only Pydantic
-- Manipulate your data while ingesting from 30+ data sources
 
 ## Get Started
 
 Get started quickly with a Google Colab  <a href="https://colab.research.google.com/drive/1jHbWVypDgCLwjE71GSXhRL3YxYhCZzG1?usp=sharing">notebook</a> , <a href="https://deepnote.com/workspace/cognee-382213d0-0444-4c89-8265-13770e333c02/project/cognee-demo-78ffacb9-5832-4611-bb1a-560386068b30/notebook/Notebook-1-75b24cda566d4c24ab348f7150792601?utm_source=share-modal&utm_medium=product-shared-content&utm_campaign=notebook&utm_content=78ffacb9-5832-4611-bb1a-560386068b30">Deepnote notebook</a> or  <a href="https://github.com/topoteretes/cognee/tree/main/cognee-starter-kit">starter repo</a>
 
 
+## About cognee
 
+cognee works locally and stores your data on your device.
+Our hosted solution is just our deployment of OSS cognee on Modal, with the goal of making development and productionization easier.
 
-## Contributing
-Your contributions are at the core of making this a true open source project. Any contributions you make are **greatly appreciated**. See [`CONTRIBUTING.md`](CONTRIBUTING.md) for more information.
-
-
+Self-hosted package:
 
+- Interconnects any kind of documents: past conversations, files, images, and audio transcriptions
+- Replaces RAG systems with a memory layer based on graphs and vectors
+- Reduces developer effort and cost, while increasing quality and precision
+- Provides Pythonic data pipelines that manage data ingestion from 30+ data sources
+- Is highly customizable with custom tasks, pipelines, and a set of built-in search endpoints
 
+Hosted platform:
+- Includes a managed UI and a [hosted solution](https://www.cognee.ai)
 
-## 📦 Installation
 
-You can install Cognee using either **pip**, **poetry**, **uv** or any other python package manager.
 
-Cognee supports Python 3.10 to 3.13
+## Self-Hosted (Open Source)
 
-### With pip
 
-```bash
-pip install cognee
-```
+### 📦 Installation
 
-## Local Cognee installation
+You can install Cognee using either **pip**, **poetry**, **uv** or any other python package manager.
 
-You can install the local Cognee repo using **uv**, **pip** and **poetry**.
-For local pip installation please make sure your pip version is above version 21.3.
+Cognee supports Python 3.10 to 3.12
 
-### with UV with all optional dependencies
+#### With uv
 
 ```bash
-uv sync --all-extras
+uv pip install cognee
 ```
 
-## 💻 Basic Usage
+Detailed instructions can be found in our [docs](https://docs.cognee.ai/getting-started/installation#environment-configuration)
+
+### 💻 Basic Usage
 
-### Setup
+#### Setup
 
 ```
 import os
@@ -266,10 +256,14 @@ os.environ["LLM_API_KEY"] = "YOUR OPENAI_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>
+To use different LLM providers, for more info check out our <a href="https://docs.cognee.ai/setup-configuration/llm-providers">documentation</a>
+
+
+#### Simple example
+
 
 
-### Simple example
+##### Python
 
 This script will run the default pipeline:
 
@@ -280,13 +274,16 @@ 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.")
+    await cognee.add("Cognee turns documents into AI memory.")
 
     # Generate the knowledge graph
     await cognee.cognify()
 
+    # Add memory algorithms to the graph
+    await cognee.memify()
+
     # Query the knowledge graph
-    results = await cognee.search("Tell me about NLP")
+    results = await cognee.search("What does cognee do?")
 
     # Display the results
     for result in results:
@@ -299,43 +296,38 @@ if __name__ == '__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.
+  Cognee turns documents into AI memory.
 
 ```
+##### Via CLI
 
-## Our paper is out! <a href="https://arxiv.org/abs/2505.24478" target="_blank" rel="noopener noreferrer">Read here</a>
+Let's get the basics covered
 
-<div style="text-align: center">
-  <img src="assets/cognee-paper.png" alt="cognee paper" width="100%" />
-</div>
-
-</div>
-
-## Cognee UI
+```
+cognee-cli add "Cognee turns documents into AI memory."
 
-You can also cognify your files and query using cognee UI.
+cognee-cli cognify
 
-<img src="assets/cognee-new-ui.webp" width="100%" alt="Cognee UI 2"></a>
+cognee-cli search "What does cognee do?"
+cognee-cli delete --all
 
-### Installation for UI
+```
+or run
+```
+cognee-cli -ui
+```
 
-To use the cognee UI with full functionality, you need to install cognee with API dependencies:
 
-```bash
-pip install 'cognee[api]'
-```
+</div>
 
-The UI requires backend server functionality (uvicorn and other API dependencies) which are not included in the default cognee installation to keep it lightweight.
 
-### Running the UI
+### Hosted Platform
 
-Try cognee UI by running ``` cognee-cli -ui ``` command on your terminal.
+Get up and running in minutes with automatic updates, analytics, and enterprise security.
 
-## Understand our architecture
+1. Sign up on [cogwit](https://www.cognee.ai)
+2. Add your API key to local UI and sync your data to Cogwit
 
-<div style="text-align: center">
-  <img src="assets/cognee_diagram.png" alt="cognee concept diagram" width="100%" />
-</div>
 
 
 
@@ -354,22 +346,26 @@ Try cognee UI by running ``` cognee-cli -ui ``` command on your terminal.
 [cognee with local models](https://github.com/user-attachments/assets/8621d3e8-ecb8-4860-afb2-5594f2ee17db)
 
 
-## Code of Conduct
-
-We are committed to making open source an enjoyable and respectful experience for our community. See <a href="https://github.com/topoteretes/cognee/blob/main/CODE_OF_CONDUCT.md"><code>CODE_OF_CONDUCT</code></a> for more information.
-
-## 💫 Contributors
+## Contributing
+Your contributions are at the core of making this a true open source project. Any contributions you make are **greatly appreciated**. See [`CONTRIBUTING.md`](CONTRIBUTING.md) for more information.
 
-<a href="https://github.com/topoteretes/cognee/graphs/contributors">
-  <img alt="contributors" src="https://contrib.rocks/image?repo=topoteretes/cognee"/>
-</a>
 
-## Sponsors
+## Code of Conduct
 
-Thanks to the following companies for sponsoring the ongoing development of cognee.
+We are committed to making open source an enjoyable and respectful experience for our community. See <a href="https://github.com/topoteretes/cognee/blob/main/CODE_OF_CONDUCT.md"><code>CODE_OF_CONDUCT</code></a> for more information.
 
-- [GitHub's Secure Open Source Fund](https://resources.github.com/github-secure-open-source-fund/)
+## Citation
 
-## Star History
+We now have a paper you can cite:
 
-[![Star History Chart](https://api.star-history.com/svg?repos=topoteretes/cognee&type=Date)](https://star-history.com/#topoteretes/cognee&Date)
+```bibtex
+@misc{markovic2025optimizinginterfaceknowledgegraphs,
+      title={Optimizing the Interface Between Knowledge Graphs and LLMs for Complex Reasoning}, 
+      author={Vasilije Markovic and Lazar Obradovic and Laszlo Hajdu and Jovan Pavlovic},
+      year={2025},
+      eprint={2505.24478},
+      archivePrefix={arXiv},
+      primaryClass={cs.AI},
+      url={https://arxiv.org/abs/2505.24478}, 
+}
+```