3850e9c7a1
<!-- .github/pull_request_template.md --> ## Description Notebook and python example for cognee simple example ## 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 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **New Features** - Introduced an interactive demo showcasing asynchronous document processing and querying for key insights from a sample text. - **Documentation** - Added an in-depth, step-by-step guide in a Jupyter Notebook that walks users through setup, configuration, querying, and visualizing processed data. <!-- end of auto-generated comment: release notes by coderabbit.ai -->
175 lines
3.8 KiB
Text
175 lines
3.8 KiB
Text
{
|
|
"cells": [
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "efb41c9e450b5a29",
|
|
"metadata": {},
|
|
"source": [
|
|
"# Cognee GraphRAG Simple Example"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"id": "982b897a29a26f7d",
|
|
"metadata": {},
|
|
"source": [
|
|
"!pip install cognee==0.1.26"
|
|
],
|
|
"outputs": [],
|
|
"execution_count": null
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "f51e92e9fdcf77b7",
|
|
"metadata": {},
|
|
"source": [
|
|
" By default cognee uses OpenAI's gpt-4o-mini LLM model.\n",
|
|
"\n",
|
|
" Provide your OpenAI LLM API KEY in the step bellow. Here's a guide on how to get your [OpenAI API key](https://help.openai.com/en/articles/4936850-where-do-i-find-my-openai-api-key)."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"id": "initial_id",
|
|
"metadata": {},
|
|
"source": [
|
|
"import os\n",
|
|
"\n",
|
|
"os.environ[\"LLM_API_KEY\"] = \"\""
|
|
],
|
|
"outputs": [],
|
|
"execution_count": null
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "f1fec64bc573bb",
|
|
"metadata": {},
|
|
"source": [
|
|
"In this step we'll get the location of the file to store and process."
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"id": "5805c346f03d8070",
|
|
"metadata": {},
|
|
"source": [
|
|
"current_directory = os.getcwd()\n",
|
|
"file_path = os.path.join(current_directory, \"data\", \"alice_in_wonderland.txt\")"
|
|
],
|
|
"outputs": [],
|
|
"execution_count": null
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "2826a80ca1ad0438",
|
|
"metadata": {},
|
|
"source": [
|
|
"Give the file location to cognee to save it and process its contents"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"id": "875763366723ee48",
|
|
"metadata": {},
|
|
"source": [
|
|
"import cognee\n",
|
|
"await cognee.add(file_path)\n",
|
|
"await cognee.cognify()"
|
|
],
|
|
"outputs": [],
|
|
"execution_count": null
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "4944567387ec5821",
|
|
"metadata": {},
|
|
"source": [
|
|
"Your data is ready to be queried:"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"id": "29b3a1e3279100d2",
|
|
"metadata": {},
|
|
"source": [
|
|
"await cognee.search(\"List me all the influential characters in Alice in Wonderland.\")"
|
|
],
|
|
"outputs": [],
|
|
"execution_count": null
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"id": "883ce50d2d9dc584",
|
|
"metadata": {},
|
|
"source": [
|
|
"await cognee.search(\"How did Alice end up in Wonderland?\")"
|
|
],
|
|
"outputs": [],
|
|
"execution_count": null
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"id": "677e1bc52aa078b6",
|
|
"metadata": {},
|
|
"source": [
|
|
"await cognee.search(\"Tell me about Alice's personality.\")"
|
|
],
|
|
"outputs": [],
|
|
"execution_count": null
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "fd521e182fb66d49",
|
|
"metadata": {},
|
|
"source": [
|
|
"Bonus: See your processed data visualized in a knowledge graph"
|
|
]
|
|
},
|
|
{
|
|
"cell_type": "code",
|
|
"id": "6effdae590b795d3",
|
|
"metadata": {},
|
|
"source": [
|
|
"import webbrowser\n",
|
|
"import os\n",
|
|
"from cognee.api.v1.visualize.visualize import visualize_graph\n",
|
|
"html = await visualize_graph()\n",
|
|
"home_dir = os.path.expanduser(\"~\")\n",
|
|
"html_file = os.path.join(home_dir, \"graph_visualization.html\")\n",
|
|
"display(html_file)\n",
|
|
"webbrowser.open(f\"file://{html_file}\")"
|
|
],
|
|
"outputs": [],
|
|
"execution_count": null
|
|
},
|
|
{
|
|
"cell_type": "markdown",
|
|
"id": "f0945d6f1d962ab",
|
|
"metadata": {},
|
|
"source": [
|
|
"For more examples and information on how Cognee GraphRAG works checkout our other more detailed notebooks."
|
|
]
|
|
}
|
|
],
|
|
"metadata": {
|
|
"kernelspec": {
|
|
"display_name": "Cognee Env",
|
|
"language": "python",
|
|
"name": "venv"
|
|
},
|
|
"language_info": {
|
|
"codemirror_mode": {
|
|
"name": "ipython",
|
|
"version": 3
|
|
},
|
|
"file_extension": ".py",
|
|
"mimetype": "text/x-python",
|
|
"name": "python",
|
|
"nbconvert_exporter": "python",
|
|
"pygments_lexer": "ipython3",
|
|
"version": "3.12.8"
|
|
}
|
|
},
|
|
"nbformat": 4,
|
|
"nbformat_minor": 5
|
|
}
|