From d6cc63db8fddf977339b52cc230261d5e703222f Mon Sep 17 00:00:00 2001 From: Vasilije <8619304+Vasilije1990@users.noreply.github.com> Date: Wed, 5 Mar 2025 18:14:06 -0800 Subject: [PATCH] Update README.md (#609) ## Description ## 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 --- README.md | 176 ++++++++++++------------------------------------------ 1 file changed, 38 insertions(+), 138 deletions(-) diff --git a/README.md b/README.md index dcec40601..b2096f331 100644 --- a/README.md +++ b/README.md @@ -1,4 +1,4 @@ -
+
Cognee Logo @@ -7,6 +7,15 @@ cognee - memory layer for AI apps and Agents +

+ Learn more + · + Join Discord + · + Demo +

+ + [![GitHub forks](https://img.shields.io/github/forks/topoteretes/cognee.svg?style=social&label=Fork&maxAge=2592000)](https://GitHub.com/topoteretes/cognee/network/) [![GitHub stars](https://img.shields.io/github/stars/topoteretes/cognee.svg?style=social&label=Star&maxAge=2592000)](https://GitHub.com/topoteretes/cognee/stargazers/) [![GitHub commits](https://badgen.net/github/commits/topoteretes/cognee)](https://GitHub.com/topoteretes/cognee/commit/) @@ -15,26 +24,38 @@ [![License](https://img.shields.io/github/license/topoteretes/cognee?colorA=00C586&colorB=000000)](https://github.com/topoteretes/cognee/blob/main/LICENSE) [![Contributors](https://img.shields.io/github/contributors/topoteretes/cognee?colorA=00C586&colorB=000000)](https://github.com/topoteretes/cognee/graphs/contributors) - We build for developers who need a reliable, production-ready data layer for AI applications -
- -# What is cognee? - -Cognee implements scalable, modular ECL (Extract, Cognify, Load) pipelines that allow you to interconnect and retrieve past conversations, documents, and audio transcriptions while reducing hallucinations, developer effort, and cost. - -Cognee merges graph and vector databases to uncover hidden relationships and new patterns in your data. You can automatically model, load and retrieve entities and objects representing your business domain and analyze their relationships, uncovering insights that neither vector stores nor graph stores alone can provide. Learn more about use-cases [here](https://docs.cognee.ai/use_cases). + AI Agent responses you can rely on. -Try it in a Google Colab notebook or have a look at our documentation. -If you have questions, join our Discord community. +Build dynamic Agent memory using scalable, modular ECL (Extract, Cognify, Load) pipelines. -Have you seen cognee's starter repo? Check it out! +More on [use-cases](https://docs.cognee.ai/use_cases).
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 + + + + + ## 📦 Installation @@ -46,17 +67,6 @@ You can install Cognee using either **pip**, **poetry**, **uv** or any other pyt pip install cognee ``` -### With poetry - -```bash -poetry add cognee -``` - -### With uv -```bash -uv add cognee -``` - ## 💻 Basic Usage ### Setup @@ -66,12 +76,8 @@ import os os.environ["LLM_API_KEY"] = "YOUR OPENAI_API_KEY" ``` -or -``` -import cognee -cognee.config.set_llm_api_key("YOUR_OPENAI_API_KEY") -``` -You can also set the variables by creating .env file, here is our template. + +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 @@ -92,11 +98,8 @@ from cognee.modules.search.types import SearchType async def main(): # Create a clean slate for cognee -- reset data and system state - print("Resetting cognee data...") await cognee.prune.prune_data() await cognee.prune.prune_system(metadata=True) - print("Data reset complete.\n") - # cognee knowledge graph will be created based on this text text = """ Natural language processing (NLP) is an interdisciplinary @@ -107,17 +110,6 @@ async def main(): print(text.strip()) # Add the text, and make it available for cognify await cognee.add(text) - print("Text added successfully.\n") - - - print("Running cognify to create knowledge graph...\n") - print("Cognify process steps:") - print("1. Classifying the document: Determining the type and category of the input text.") - print("2. Checking permissions: Ensuring the user has the necessary rights to process the text.") - print("3. Extracting text chunks: Breaking down the text into sentences or phrases for analysis.") - print("4. Adding data points: Storing the extracted chunks for processing.") - print("5. Generating knowledge graph: Extracting entities and relationships to form a knowledge graph.") - print("6. Summarizing text: Creating concise summaries of the content for quick insights.\n") # Use LLMs and cognee to create knowledge graph await cognee.cognify() @@ -149,103 +141,25 @@ if __name__ == '__main__': asyncio.run(main()) ``` -When you run this script, you will see step-by-step messages in the console that help you trace the execution flow and understand what the script is doing at each stage. -A version of this example is here: `examples/python/simple_example.py` +For more advanced usage, have a look at our documentation. ## Understand our architecture -Cognee consists of tasks that can be grouped into pipelines. -Each task can be an independent part of business logic, that can be tied to other tasks to form a pipeline. -These tasks persist data into your memory store enabling you to search for relevant context of past conversations, documents, or any other data you have stored.
cognee concept diagram
-## Vector retrieval, Graphs and LLMs -Cognee supports a variety of tools and services for different operations: -- **Modular**: Cognee is modular by nature, using tasks grouped into pipelines +## Demos -- **Local Setup**: By default, LanceDB runs locally with NetworkX and OpenAI. - -- **Vector Stores**: Cognee supports LanceDB, Qdrant, PGVector and Weaviate for vector storage. - -- **Language Models (LLMs)**: You can use either Anyscale or Ollama as your LLM provider. - -- **Graph Stores**: In addition to NetworkX, Neo4j is also supported for graph storage. - -- **User management**: Create individual user graphs and manage permissions - -## Demo - -Check out our demo notebook [here](https://github.com/topoteretes/cognee/blob/main/notebooks/cognee_demo.ipynb) or watch the Youtube video below +What is AI memory: [](https://www.youtube.com/watch?v=fI4hDzguN5k "Learn about cognee: 55") -## Install Cognee with specific database support -Support for various databases and vector stores is available through extras. -Please see the [Cognee Quickstart Guide](https://docs.cognee.ai/quickstart/) for important configuration information. - -### With pip - -To install Cognee with support for specific databases use the appropriate command below. Replace \ with the name of the database you need. -```bash -pip install 'cognee[]' -``` - -Replace \ with any of the following databases: -- postgres -- weaviate -- qdrant -- neo4j -- milvus - -Installing Cognee with PostgreSQL and Neo4j support example: -```bash -pip install 'cognee[postgres, neo4j]' -``` - -### With poetry - -To install Cognee with support for specific databases use the appropriate command below. Replace \ with the name of the database you need. -```bash -poetry add cognee -E -``` -Replace \ with any of the following databases: -- postgres -- weaviate -- qdrant -- neo4j -- milvus - -Installing Cognee with PostgreSQL and Neo4j support example: -```bash -poetry add cognee -E postgres -E neo4j -``` - -## Working with local Cognee - -Install dependencies inside the cloned repository: - -```bash -poetry config virtualenvs.in-project true -poetry self add poetry-plugin-shell -poetry install -poetry shell -``` - - -## Run Cognee API server - -Please see the [Cognee Quickstart Guide](https://docs.cognee.ai/quickstart/) for important configuration information. - -```bash -docker compose up -``` ## Contributing @@ -267,17 +181,3 @@ We are committed to making open source an enjoyable and respectful experience fo [![Star History Chart](https://api.star-history.com/svg?repos=topoteretes/cognee&type=Date)](https://star-history.com/#topoteretes/cognee&Date) -## Vector & Graph Databases Implementation State - - - -| Name | Type | Current state (Mac/Linux) | Known Issues | Current state (Windows) | Known Issues | -|----------|--------------------|---------------------------|--------------|-------------------------|--------------| -| Qdrant | Vector | Stable ✅ | | Unstable ❌ | | -| Weaviate | Vector | Stable ✅ | | Unstable ❌ | | -| LanceDB | Vector | Stable ✅ | | Stable ✅ | | -| Neo4j | Graph | Stable ✅ | | Stable ✅ | | -| NetworkX | Graph | Stable ✅ | | Stable ✅ | | -| FalkorDB | Vector/Graph | Stable ✅ | | Unstable ❌ | | -| PGVector | Vector | Stable ✅ | | Unstable ❌ | | -| Milvus | Vector | Stable ✅ | | Unstable ❌ | |