No description
Find a file
lxobr 9d9ea63236
fix: use default threading in Fastembed (#846)
<!-- .github/pull_request_template.md -->

## Description
<!-- Provide a clear description of the changes in this PR -->
- set the parallel option to None in Fastembed's embedding function

## DCO Affirmation
I affirm that all code in every commit of this pull request conforms to
the terms of the Topoteretes Developer Certificate of Origin.
2025-05-20 16:05:58 +02:00
.data Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
.dlt Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
.github feat: Test db examples (#817) 2025-05-16 09:30:47 +02:00
alembic fix: Fixes pipeline run status migration (#838) 2025-05-19 13:18:36 +02:00
assets fix: 812 anthropic fix (#822) 2025-05-16 10:52:44 +02:00
bin Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
cognee fix: use default threading in Fastembed (#846) 2025-05-20 16:05:58 +02:00
cognee-frontend fix: cognee docker image (#820) 2025-05-15 10:05:27 +02:00
cognee-mcp feat: Add developer rules (#833) 2025-05-19 13:16:58 +02:00
community Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
deployment Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
evals fix: Bump fast api users (#759) 2025-04-19 10:51:23 +02:00
examples feat: Test db examples (#817) 2025-05-16 09:30:47 +02:00
helm Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
licenses Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
logs feat: Add logging to file [COG-1715] (#672) 2025-03-28 16:13:56 +01:00
notebooks feat: OpenAI compatible route /api/v1/responses (#792) 2025-05-16 09:17:18 +02:00
profiling Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
tools Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
.dockerignore Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
.env.template Document collection of usage data and how to opt out (#767) 2025-04-22 23:52:34 +02:00
.gitignore Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
.pre-commit-config.yaml Feat: log pipeline status and pass it through pipeline [COG-1214] (#501) 2025-02-11 16:41:40 +01:00
.pylintrc fix: enable sqlalchemy adapter 2024-08-04 22:23:28 +02:00
.python-version chore: update python version to 3.11 2024-03-29 14:10:20 +01:00
alembic.ini Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
CODE_OF_CONDUCT.md Update CODE_OF_CONDUCT.md 2024-12-13 11:30:16 +01:00
cognee-gui.py Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
CONTRIBUTING.md fix: 812 anthropic fix (#822) 2025-05-16 10:52:44 +02:00
DCO.md Create DCO.md 2024-12-13 11:28:44 +01:00
docker-compose.yml Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
Dockerfile fix: cognee docker image (#820) 2025-05-15 10:05:27 +02:00
Dockerfile_modal feat: Adds modal parallel evaluation for retriever development (#844) 2025-05-20 15:16:13 +02:00
entrypoint.sh Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
LICENSE Update LICENSE 2024-03-30 11:57:07 +01:00
modal_deployment.py Revert "Clean up core cognee repo" 2025-05-15 10:46:01 +02:00
mypy.ini Improve processing, update networkx client, and Neo4j, and dspy (#69) 2024-04-20 19:05:40 +02:00
NOTICE.md add NOTICE file, reference CoC in contribution guidelines, add licenses folder for external licenses 2024-12-06 13:27:55 +00:00
poetry.lock fix: cognee docker image (#820) 2025-05-15 10:05:27 +02:00
pyproject.toml fix: exclude files from build (#828) 2025-05-15 14:57:46 +02:00
README.md Merge branch 'main' into dev 2025-05-15 13:08:35 +02:00
uv.lock fix: exclude files from build (#828) 2025-05-15 14:57:46 +02:00

Cognee Logo

cognee - Memory for AI Agents in 5 lines of code

Demo . Learn more · Join Discord

GitHub forks GitHub stars GitHub commits Github tag Downloads License Contributors

cognee - Memory for AI Agents  in 5 lines of code | Product Hunt

Build dynamic Agent memory using scalable, modular ECL (Extract, Cognify, Load) pipelines.

More on use-cases and evals

🌐 Available Languages : 🇵🇹 Português · 🇨🇳 [中文] · 🇷🇺 Русский

Why cognee?

Features

  • Interconnect and retrieve your past conversations, documents, images and audio transcriptions
  • Reduce hallucinations, 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 notebook or starter repo

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 for more information.

📦 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

pip install cognee

💻 Basic Usage

Setup

import os
os.environ["LLM_API_KEY"] = "YOUR OPENAI_API_KEY"

You can also set the variables by creating .env file, using our template. To use different LLM providers, for more info check out our documentation

Simple example

This script will run the default pipeline:

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.
  

cognee UI

You can also cognify your files and query using cognee UI.

Cognee UI 2

Try cognee UI out locally here.

Understand our architecture

cognee concept diagram

Demos

  1. What is AI memory:

Learn about cognee

  1. Simple GraphRAG demo

Simple GraphRAG demo

  1. cognee with Ollama

cognee with local models

Code of Conduct

We are committed to making open source an enjoyable and respectful experience for our community. See CODE_OF_CONDUCT for more information.

💫 Contributors

contributors

Star History

Star History Chart