gmakstutis/cognee
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

refactor: Change text size

Browse source 
Changed text size to be more readable and uniform across the notebook

Refactor #COG-382
This commit is contained in:
Igor Ilic 2024-10-08 16:50:23 +02:00
parent e74f9ad45a
commit e80e36f3dc
1 changed files with 22 additions and 32 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

54
notebooks/cognee_demo.ipynb
View file

@ -21,9 +21,9 @@
"source": [
"## Let's talk about the problem first\n",
"\n",
"### - Since LLMs appeared, people have tried to personalize them.\n",
"### - People do \"prompt engineering\" and add specific instructions to the LLM\n",
"### - \"Become a sales agent\" or \"Become a programmer\""
"#### - Since LLMs appeared, people have tried to personalize them.\n",
"#### - People do \"prompt engineering\" and add specific instructions to the LLM\n",
"#### - \"Become a sales agent\" or \"Become a programmer\""
]
},
{
@ -46,7 +46,7 @@
"source": [
"## The next solution was RAGs \n",
"\n",
"RAGs (Retrieval Augmented Generation) are systems that connect to a vector store and search for similar data so they can enrich LLM response."
"#### RAGs (Retrieval Augmented Generation) are systems that connect to a vector store and search for similar data so they can enrich LLM response."
]
},
{
@ -67,7 +67,7 @@
"id": "b6a98710-a14b-4a14-bb56-d3ae055e94d9",
"metadata": {},
"source": [
"## The problem lies in the nature of the search. If you just find some keywords, and return one or many documents from vectorstore this way, you will have an issue with the the way you would use to organise and prioritise documents. \n"
"#### The problem lies in the nature of the search. If you just find some keywords, and return one or many documents from vectorstore this way, you will have an issue with the the way you would use to organise and prioritise documents. \n"
]
},
{
@ -76,9 +76,9 @@
"metadata": {},
"source": [
"## If you search for \"I like apples\", what will you get:\n",
"### 1. I dislike fruits\n",
"### 2. I am a vegan\n",
"### 3. I don't like apples"
"#### 1. I dislike fruits\n",
"#### 2. I am a vegan\n",
"#### 3. I don't like apples"
]
},
{
@ -87,8 +87,8 @@
"metadata": {},
"source": [
"## Semantic similarity search is not magic\n",
"### If you search for an apple, the closest thing you get is that you don't like apples.\n",
"### Would it be nice to have a semantic model LLMs could use?\n"
"#### If you search for an apple, the closest thing you get is that you don't like apples.\n",
"#### Would it be nice to have a semantic model LLMs could use?\n"
]
},
{
@ -118,8 +118,8 @@
"metadata": {},
"source": [
"### Our goal is to:\n",
"- create a semantic representation of the data \n",
"- split the data into a multilayer graph network containing propositions"
"#### - create a semantic representation of the data \n",
"#### - split the data into a multilayer graph network containing propositions"
]
},
{
@ -148,19 +148,9 @@
"id": "3540ce30-2b22-4ece-8516-8d5ff2a405fe",
"metadata": {},
"source": [
"- Multilayer network is cognitive multilayer networks as a quantitative and interpretative framework for investigating the mental lexicon. \n",
"- The mental lexicon is a complex cognitive system representing information about the words/concepts that one knows\n",
"Article 2"
]
},
{
"cell_type": "markdown",
"id": "0a21f1cf-ff91-43e6-bd05-39e5ee885790",
"metadata": {},
"source": [
"\n",
"- Propositions are defined as atomic expressions within text, each encapsulating a distinct factoid and presented in a concise, self-contained natural language format.\n",
"Article 1"
"#### - Multilayer network is cognitive multilayer networks as a quantitative and interpretative framework for investigating the mental lexicon. \n",
"#### - The mental lexicon is a complex cognitive system representing information about the words/concepts that one knows Article 2\n",
"#### - Propositions are defined as atomic expressions within text, each encapsulating a distinct factoid and presented in a concise, self-contained natural language format. Article 1"
]
},
{
@ -208,7 +198,7 @@
"id": "0587d91d",
"metadata": {},
"source": [
"First let's define some data that we will cognify and perform a search on"
"#### First let's define some data that we will cognify and perform a search on"
]
},
{
@ -472,7 +462,7 @@
"id": "4415446a",
"metadata": {},
"source": [
"Please add the necessary environment information bellow:"
"#### Please add the necessary environment information bellow:"
]
},
{
@ -533,7 +523,7 @@
"id": "383d6971",
"metadata": {},
"source": [
"After we have defined and gathered our data let's add it to cognee "
"#### After we have defined and gathered our data let's add it to cognee "
]
},
{
@ -558,7 +548,7 @@
"id": "0f15c5b1",
"metadata": {},
"source": [
"All good, let's cognify it."
"#### All good, let's cognify it."
]
},
{
@ -644,7 +634,7 @@
"id": "219a6d41",
"metadata": {},
"source": [
"We get the url to the graph on graphistry in the notebook cell bellow, showing nodes and connections made by the cognify process."
"#### We get the url to the graph on graphistry in the notebook cell bellow, showing nodes and connections made by the cognify process."
]
},
{
@ -672,7 +662,7 @@
"id": "59e6c3c3",
"metadata": {},
"source": [
"We can also do a search on the data to explore the knowledge."
"#### We can also do a search on the data to explore the knowledge."
]
},
{
@ -716,7 +706,7 @@
"id": "288ab570",
"metadata": {},
"source": [
"# Give us a star if you like it!\n",
"## Give us a star if you like it!\n",
"https://github.com/topoteretes/cognee"
]
}