From e925867a7dbf76fb22a2119333832f7a28329e50 Mon Sep 17 00:00:00 2001
From: Vasilije <8619304+Vasilije1990@users.noreply.github.com>
Date: Mon, 25 Mar 2024 14:09:22 +0100
Subject: [PATCH] Added docs

---
 docs/blog/posts/cognee-library-release.md | 16 +++++-----------
 1 file changed, 5 insertions(+), 11 deletions(-)

diff --git a/docs/blog/posts/cognee-library-release.md b/docs/blog/posts/cognee-library-release.md
index 4c719594a..a1368b49f 100644
--- a/docs/blog/posts/cognee-library-release.md
+++ b/docs/blog/posts/cognee-library-release.md
@@ -28,22 +28,19 @@ With the integration of Keepi.ai, we encountered several challenges that made us
 
 Moving forward, we have adopted several new strategies, features, and design principles:
 
-<aside>
-💡 Propositions: Defined as atomic expressions within a text, each proposition encapsulates a unique factoid, conveyed in a succinct, standalone natural language format.
 
+### Propositions: 
+
+Defined as atomic expressions within a text, each proposition encapsulates a unique factoid, conveyed in a succinct, standalone natural language format.
 We employ Large Language Models (LLMs) to break down text into propositions and link them, forming graphs with propositions as nodes and their connections as edges. 
 For example,  "Grass is green", and "2 + 5 = 5"  are propositions. The first proposition has the truth value of "true" and the second "false". 
 The inspiration was found in the following paper: https://arxiv.org/pdf/2312.06648.pdf
 
-</aside>
 
 
 
-<aside>
 
-
-
-💡 Multilayer Graph Network:
+### Multilayer Graph Network:
 
 A cognitive multilayer networks is both a quantitative and interpretive framework for exploring the mental lexicon, the intricate cognitive system that stores information about known words/concepts.
 
@@ -55,18 +52,15 @@ For example, if "John Doe" authored two New York Times cooking articles, we coul
 
 We used concepts from psycholinguistics described here: https://arxiv.org/abs/1507.08539
 
-</aside>
 
 
 
-<aside>
-💡 Data Loader:
+### Data Loader:
 
 It’s vital that we address the technical challenges associated with Retrieval-Augmented Generation (RAG), such as metadata management, context retrieval, knowledge sanitization, and data enrichment.
 
 The solution lies in a dependable data pipeline capable of efficiently and scalably preparing and loading data in various formats from a range of different sources. For this purpose, we can use 'dlt' as our data loader, gaining access to over 28 supported data sources.
 
-</aside>
 
 To enhance the Pythonic interface, we streamlined the use of cognee into three primary methods. Users can now execute the following steps: