9ba2e0d6c1
<!-- .github/pull_request_template.md --> ## Description <!-- Provide a clear description of the changes in this PR --> ## 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 enhanced visualization capabilities that let users launch a dedicated server for visual displays. - **Documentation** - Updated several interactive notebooks to include execution outputs and expanded explanatory content for better user guidance. - **Style** - Refined formatting and layout across notebooks to ensure consistent presentation and improved readability. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Igor Ilic <30923996+dexters1@users.noreply.github.com>
1573 lines
768 KiB
Text
1573 lines
768 KiB
Text
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "d35ac8ce-0f92-46f5-9ba4-a46970f0ce19",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Cognee - Get Started"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "bd981778-0c84-4542-8e6f-1a7712184873",
|
||
"metadata": {
|
||
"editable": true,
|
||
"slideshow": {
|
||
"slide_type": ""
|
||
},
|
||
"tags": []
|
||
},
|
||
"source": [
|
||
"## Let's talk about the problem first\n",
|
||
"\n",
|
||
"### Large Language Models (LLMs) have become powerful tools for generating text and answering questions, but they still have several limitations and challenges. Below is an overview of some of the biggest problems with the results they produce:\n",
|
||
"\n",
|
||
"### 1. Hallucinations and Misinformation\n",
|
||
"- Hallucinations: LLMs sometimes produce outputs that are factually incorrect or entirely fabricated. This phenomenon is known as \"hallucination.\" Even if an LLM seems confident, the information it provides might not be reliable.\n",
|
||
"- Misinformation: Misinformation can be subtle or glaring, ranging from minor inaccuracies to entirely fictitious events, sources, or data.\n",
|
||
"\n",
|
||
"### 2. Lack of Contextual Understanding\n",
|
||
"- LLMs can recognize and replicate patterns in language but don’t have true comprehension. This can lead to responses that are coherent but miss nuanced context or deeper meaning.\n",
|
||
"- They can misinterpret multi-turn conversations, leading to confusion in maintaining context over a long dialogue.\n",
|
||
"\n",
|
||
"### 3. Inconsistent Reliability\n",
|
||
"- Depending on the prompt, LLMs might produce inconsistent responses to similar questions or tasks. For example, the same query might result in conflicting answers when asked in slightly different ways.\n",
|
||
"- This inconsistency can undermine trust in the model's outputs, especially in professional or academic settings.\n",
|
||
"\n",
|
||
"### 4. Inability to Access Real-Time Information\n",
|
||
"- Most LLMs are trained on data up to a specific point and cannot access or generate information on current events or emerging trends unless updated. This can make them unsuitable for inquiries requiring up-to-date information.\n",
|
||
"- Real-time browsing capabilities can help, but they are not universally available.\n",
|
||
"\n",
|
||
"### 5. Lack of Personalization and Adaptability\n",
|
||
"- LLMs do not naturally adapt to individual preferences or learning styles unless explicitly programmed to do so. This limits their usefulness in providing personalized recommendations or support.\n",
|
||
"\n",
|
||
"### 6. Difficulty with Highly Technical or Niche Domains\n",
|
||
"- LLMs may struggle with highly specialized or technical topics where domain-specific knowledge is required.\n",
|
||
"- They can produce technically plausible but inaccurate or incomplete information, which can be misleading in areas like law, medicine, or scientific research.\n",
|
||
"\n",
|
||
"### 7. Ambiguity in Response Generation\n",
|
||
"- LLMs might not always specify their level of certainty, making it hard to gauge when they are speculating or providing less confident answers.\n",
|
||
"- They lack a mechanism to say “I don’t know,” which can lead to responses that are less useful or potentially misleading."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "d8e606b1-94d3-43ce-bb4b-dbadff7f4ca6",
|
||
"metadata": {},
|
||
"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."
|
||
]
|
||
},
|
||
{
|
||
"attachments": {
|
||
"df72c97a-cb3b-4e3c-bd68-d7bc986353c6.png": {
|
||
"image/png": "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"
|
||
}
|
||
},
|
||
"cell_type": "markdown",
|
||
"id": "23e74f22-f43c-4f03-afe0-b423cbaa412a",
|
||
"metadata": {},
|
||
"source": [
|
||
"\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "1bf1fa3631dc03ed",
|
||
"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"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "5029110f",
|
||
"metadata": {},
|
||
"source": [
|
||
""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "390e0d0805096f80",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Semantic similarity search is not magic\n",
|
||
"#### The most similar result isn't the most relevant one. \n",
|
||
"#### If you search for documents in which the sentiment expressed is \"I like apples.\", one of the closest results you get are documents in which the sentiment expressed is \"I don't like apples.\"\n",
|
||
"#### Wouldn't it be nice to have a semantic model LLMs could use?\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "b900f830-8e9e-4272-b198-594606da4457",
|
||
"metadata": {},
|
||
"source": [
|
||
"# That is where Cognee comes in"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "d3ae099a-1bbb-4f13-9bcb-c0f778d50e91",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### Cognee assists developers in introducing greater predictability and management into their Retrieval-Augmented Generation (RAG) workflows through the use of graph architectures, vector stores, and auto-optimizing pipelines. Displaying information as a graph is the clearest way to grasp the content of your documents. Crucially, graphs allow systematic navigation and extraction of data from documents based on their hierarchy.\n",
|
||
"\n",
|
||
"#### Cognee lets you create tasks and contextual pipelines of tasks that enable composable GraphRAG, where you have full control of all the elements of the pipeline from ingestion until graph creation. "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "785383b0-87b5-4a0a-be3f-e809aa284e30",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Core Concepts"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "3540ce30-2b22-4ece-8516-8d5ff2a405fe",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Concept 1: Data Pipelines"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "7e47bae4-d27d-4430-a134-e1b381378f5c",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Most of the data we provide to a system can be categorized as unstructured, semi-structured, or structured. Rows from a database would belong to structured data, jsons to semi-structured data, and logs that we input into the system could be considered unstructured. To organize and process this data, we need to ensure we have custom loaders for all data types, which can help us unify and organize it properly."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "2f9c9376-8c68-4397-9081-d260cddcbd25",
|
||
"metadata": {},
|
||
"source": [
|
||
""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "7c87c5cf",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### In the example above, we have a pipeline in which data has been imported from various sources, normalized, and stored in a database. "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "bd435d1d",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Concept 2: Data Enrichment with LLMs"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "836d35ef",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### LLMs are adept at processing unstructured data. They can easily extract summaries, keywords, and other useful information from documents. We use function calling with Pydantic models to extract information from the unstructured data. "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "5bc1681c",
|
||
"metadata": {},
|
||
"source": [
|
||
""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "c6f428a8",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### We decompose the loaded content into graphs, allowing us to more precisely map out the relationships between entities and concepts."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "34c2227f",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Concept 3: Graphs"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "7ec176f5",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### Knowledge graphs simply map out knowledge, linking specific facts and their connections. When Large Language Models (LLMs) process text, they infer these links, leading to occasional inaccuracies due to their probabilistic nature. Clearly defined relationships enhance their accuracy. This structured approach can extend beyond concepts to document layouts, pages, or other organizational schemas."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "ff454731",
|
||
"metadata": {},
|
||
"source": [
|
||
""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "5b3b58d3",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Concept 4: Vector and Graph Retrieval"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "3555db8b",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### Cognee lets you use multiple vector and graph retrieval methods to find the most relevant information."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "d2d5e844",
|
||
"metadata": {},
|
||
"source": [
|
||
"## Concept 5: Auto-Optimizing Pipelines"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "6979a010",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### Integrating knowledge graphs into Retrieval-Augmented Generation (RAG) pipelines leads to an intriguing outcome: the system's adeptness at contextual understanding allows it to be evaluated in a way Machine Learning (ML) engineers are accustomed to. This involves bombarding the RAG system with hundreds of synthetic questions, enabling the knowledge graph to evolve and refine its context autonomously over time. This method paves the way for developing self-improving memory engines that can adapt to new data and user feedback."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "074f0ea8-c659-4736-be26-be4b0e5ac665",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Demo time"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "0587d91d",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### First let's define some data that we will cognify and perform a search on"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"id": "df16431d0f48b006",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:32:37.309629Z",
|
||
"start_time": "2025-02-09T21:32:37.305105Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"job_position = \"\"\"Senior Data Scientist (Machine Learning)\n",
|
||
"\n",
|
||
"Company: TechNova Solutions\n",
|
||
"Location: San Francisco, CA\n",
|
||
"\n",
|
||
"Job Description:\n",
|
||
"\n",
|
||
"TechNova Solutions is seeking a Senior Data Scientist specializing in Machine Learning to join our dynamic analytics team. The ideal candidate will have a strong background in developing and deploying machine learning models, working with large datasets, and translating complex data into actionable insights.\n",
|
||
"\n",
|
||
"Responsibilities:\n",
|
||
"\n",
|
||
"Develop and implement advanced machine learning algorithms and models.\n",
|
||
"Analyze large, complex datasets to extract meaningful patterns and insights.\n",
|
||
"Collaborate with cross-functional teams to integrate predictive models into products.\n",
|
||
"Stay updated with the latest advancements in machine learning and data science.\n",
|
||
"Mentor junior data scientists and provide technical guidance.\n",
|
||
"Qualifications:\n",
|
||
"\n",
|
||
"Master’s or Ph.D. in Data Science, Computer Science, Statistics, or a related field.\n",
|
||
"5+ years of experience in data science and machine learning.\n",
|
||
"Proficient in Python, R, and SQL.\n",
|
||
"Experience with deep learning frameworks (e.g., TensorFlow, PyTorch).\n",
|
||
"Strong problem-solving skills and attention to detail.\n",
|
||
"Candidate CVs\n",
|
||
"\"\"\""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"id": "9086abf3af077ab4",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:32:37.869475Z",
|
||
"start_time": "2025-02-09T21:32:37.867374Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"job_1 = \"\"\"\n",
|
||
"CV 1: Relevant\n",
|
||
"Name: Dr. Emily Carter\n",
|
||
"Contact Information:\n",
|
||
"\n",
|
||
"Email: emily.carter@example.com\n",
|
||
"Phone: (555) 123-4567\n",
|
||
"Summary:\n",
|
||
"\n",
|
||
"Senior Data Scientist with over 8 years of experience in machine learning and predictive analytics. Expertise in developing advanced algorithms and deploying scalable models in production environments.\n",
|
||
"\n",
|
||
"Education:\n",
|
||
"\n",
|
||
"Ph.D. in Computer Science, Stanford University (2014)\n",
|
||
"B.S. in Mathematics, University of California, Berkeley (2010)\n",
|
||
"Experience:\n",
|
||
"\n",
|
||
"Senior Data Scientist, InnovateAI Labs (2016 – Present)\n",
|
||
"Led a team in developing machine learning models for natural language processing applications.\n",
|
||
"Implemented deep learning algorithms that improved prediction accuracy by 25%.\n",
|
||
"Collaborated with cross-functional teams to integrate models into cloud-based platforms.\n",
|
||
"Data Scientist, DataWave Analytics (2014 – 2016)\n",
|
||
"Developed predictive models for customer segmentation and churn analysis.\n",
|
||
"Analyzed large datasets using Hadoop and Spark frameworks.\n",
|
||
"Skills:\n",
|
||
"\n",
|
||
"Programming Languages: Python, R, SQL\n",
|
||
"Machine Learning: TensorFlow, Keras, Scikit-Learn\n",
|
||
"Big Data Technologies: Hadoop, Spark\n",
|
||
"Data Visualization: Tableau, Matplotlib\n",
|
||
"\"\"\""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"id": "a9de0cc07f798b7f",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:32:38.269062Z",
|
||
"start_time": "2025-02-09T21:32:38.267194Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"job_2 = \"\"\"\n",
|
||
"CV 2: Relevant\n",
|
||
"Name: Michael Rodriguez\n",
|
||
"Contact Information:\n",
|
||
"\n",
|
||
"Email: michael.rodriguez@example.com\n",
|
||
"Phone: (555) 234-5678\n",
|
||
"Summary:\n",
|
||
"\n",
|
||
"Data Scientist with a strong background in machine learning and statistical modeling. Skilled in handling large datasets and translating data into actionable business insights.\n",
|
||
"\n",
|
||
"Education:\n",
|
||
"\n",
|
||
"M.S. in Data Science, Carnegie Mellon University (2013)\n",
|
||
"B.S. in Computer Science, University of Michigan (2011)\n",
|
||
"Experience:\n",
|
||
"\n",
|
||
"Senior Data Scientist, Alpha Analytics (2017 – Present)\n",
|
||
"Developed machine learning models to optimize marketing strategies.\n",
|
||
"Reduced customer acquisition cost by 15% through predictive modeling.\n",
|
||
"Data Scientist, TechInsights (2013 – 2017)\n",
|
||
"Analyzed user behavior data to improve product features.\n",
|
||
"Implemented A/B testing frameworks to evaluate product changes.\n",
|
||
"Skills:\n",
|
||
"\n",
|
||
"Programming Languages: Python, Java, SQL\n",
|
||
"Machine Learning: Scikit-Learn, XGBoost\n",
|
||
"Data Visualization: Seaborn, Plotly\n",
|
||
"Databases: MySQL, MongoDB\n",
|
||
"\"\"\""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"id": "185ff1c102d06111",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:32:38.738093Z",
|
||
"start_time": "2025-02-09T21:32:38.736147Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"job_3 = \"\"\"\n",
|
||
"CV 3: Relevant\n",
|
||
"Name: Sarah Nguyen\n",
|
||
"Contact Information:\n",
|
||
"\n",
|
||
"Email: sarah.nguyen@example.com\n",
|
||
"Phone: (555) 345-6789\n",
|
||
"Summary:\n",
|
||
"\n",
|
||
"Data Scientist specializing in machine learning with 6 years of experience. Passionate about leveraging data to drive business solutions and improve product performance.\n",
|
||
"\n",
|
||
"Education:\n",
|
||
"\n",
|
||
"M.S. in Statistics, University of Washington (2014)\n",
|
||
"B.S. in Applied Mathematics, University of Texas at Austin (2012)\n",
|
||
"Experience:\n",
|
||
"\n",
|
||
"Data Scientist, QuantumTech (2016 – Present)\n",
|
||
"Designed and implemented machine learning algorithms for financial forecasting.\n",
|
||
"Improved model efficiency by 20% through algorithm optimization.\n",
|
||
"Junior Data Scientist, DataCore Solutions (2014 – 2016)\n",
|
||
"Assisted in developing predictive models for supply chain optimization.\n",
|
||
"Conducted data cleaning and preprocessing on large datasets.\n",
|
||
"Skills:\n",
|
||
"\n",
|
||
"Programming Languages: Python, R\n",
|
||
"Machine Learning Frameworks: PyTorch, Scikit-Learn\n",
|
||
"Statistical Analysis: SAS, SPSS\n",
|
||
"Cloud Platforms: AWS, Azure\n",
|
||
"\"\"\""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"id": "d55ce4c58f8efb67",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:32:39.237542Z",
|
||
"start_time": "2025-02-09T21:32:39.235742Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"job_4 = \"\"\"\n",
|
||
"CV 4: Not Relevant\n",
|
||
"Name: David Thompson\n",
|
||
"Contact Information:\n",
|
||
"\n",
|
||
"Email: david.thompson@example.com\n",
|
||
"Phone: (555) 456-7890\n",
|
||
"Summary:\n",
|
||
"\n",
|
||
"Creative Graphic Designer with over 8 years of experience in visual design and branding. Proficient in Adobe Creative Suite and passionate about creating compelling visuals.\n",
|
||
"\n",
|
||
"Education:\n",
|
||
"\n",
|
||
"B.F.A. in Graphic Design, Rhode Island School of Design (2012)\n",
|
||
"Experience:\n",
|
||
"\n",
|
||
"Senior Graphic Designer, CreativeWorks Agency (2015 – Present)\n",
|
||
"Led design projects for clients in various industries.\n",
|
||
"Created branding materials that increased client engagement by 30%.\n",
|
||
"Graphic Designer, Visual Innovations (2012 – 2015)\n",
|
||
"Designed marketing collateral, including brochures, logos, and websites.\n",
|
||
"Collaborated with the marketing team to develop cohesive brand strategies.\n",
|
||
"Skills:\n",
|
||
"\n",
|
||
"Design Software: Adobe Photoshop, Illustrator, InDesign\n",
|
||
"Web Design: HTML, CSS\n",
|
||
"Specialties: Branding and Identity, Typography\n",
|
||
"\"\"\""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"id": "ca4ecc32721ad332",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:32:39.740387Z",
|
||
"start_time": "2025-02-09T21:32:39.738768Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"job_5 = \"\"\"\n",
|
||
"CV 5: Not Relevant\n",
|
||
"Name: Jessica Miller\n",
|
||
"Contact Information:\n",
|
||
"\n",
|
||
"Email: jessica.miller@example.com\n",
|
||
"Phone: (555) 567-8901\n",
|
||
"Summary:\n",
|
||
"\n",
|
||
"Experienced Sales Manager with a strong track record in driving sales growth and building high-performing teams. Excellent communication and leadership skills.\n",
|
||
"\n",
|
||
"Education:\n",
|
||
"\n",
|
||
"B.A. in Business Administration, University of Southern California (2010)\n",
|
||
"Experience:\n",
|
||
"\n",
|
||
"Sales Manager, Global Enterprises (2015 – Present)\n",
|
||
"Managed a sales team of 15 members, achieving a 20% increase in annual revenue.\n",
|
||
"Developed sales strategies that expanded customer base by 25%.\n",
|
||
"Sales Representative, Market Leaders Inc. (2010 – 2015)\n",
|
||
"Consistently exceeded sales targets and received the 'Top Salesperson' award in 2013.\n",
|
||
"Skills:\n",
|
||
"\n",
|
||
"Sales Strategy and Planning\n",
|
||
"Team Leadership and Development\n",
|
||
"CRM Software: Salesforce, Zoho\n",
|
||
"Negotiation and Relationship Building\n",
|
||
"\"\"\""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "4415446a",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### Please add the necessary environment information bellow:"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 22,
|
||
"id": "bce39dc6",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:31:46.855966Z",
|
||
"start_time": "2025-02-09T21:31:46.847681Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import os\n",
|
||
"\n",
|
||
"# Setting environment variables\n",
|
||
"if \"GRAPHISTRY_USERNAME\" not in os.environ:\n",
|
||
" os.environ[\"GRAPHISTRY_USERNAME\"] = \"\"\n",
|
||
"\n",
|
||
"if \"GRAPHISTRY_PASSWORD\" not in os.environ:\n",
|
||
" os.environ[\"GRAPHISTRY_PASSWORD\"] = \"\"\n",
|
||
"\n",
|
||
"if \"LLM_API_KEY\" not in os.environ:\n",
|
||
" os.environ[\"LLM_API_KEY\"] = \"\"\n",
|
||
"\n",
|
||
"# \"neo4j\" or \"networkx\"\n",
|
||
"os.environ[\"GRAPH_DATABASE_PROVIDER\"] = \"networkx\"\n",
|
||
"# Not needed if using networkx\n",
|
||
"# os.environ[\"GRAPH_DATABASE_URL\"]=\"\"\n",
|
||
"# os.environ[\"GRAPH_DATABASE_USERNAME\"]=\"\"\n",
|
||
"# os.environ[\"GRAPH_DATABASE_PASSWORD\"]=\"\"\n",
|
||
"\n",
|
||
"# \"pgvector\", \"qdrant\", \"weaviate\" or \"lancedb\"\n",
|
||
"os.environ[\"VECTOR_DB_PROVIDER\"] = \"lancedb\"\n",
|
||
"# Not needed if using \"lancedb\" or \"pgvector\"\n",
|
||
"# os.environ[\"VECTOR_DB_URL\"]=\"\"\n",
|
||
"# os.environ[\"VECTOR_DB_KEY\"]=\"\"\n",
|
||
"\n",
|
||
"# Relational Database provider \"sqlite\" or \"postgres\"\n",
|
||
"os.environ[\"DB_PROVIDER\"] = \"sqlite\"\n",
|
||
"\n",
|
||
"# Database name\n",
|
||
"os.environ[\"DB_NAME\"] = \"cognee_db\"\n",
|
||
"\n",
|
||
"# Postgres specific parameters (Only if Postgres or PGVector is used)\n",
|
||
"# os.environ[\"DB_HOST\"]=\"127.0.0.1\"\n",
|
||
"# os.environ[\"DB_PORT\"]=\"5432\"\n",
|
||
"# os.environ[\"DB_USERNAME\"]=\"cognee\"\n",
|
||
"# os.environ[\"DB_PASSWORD\"]=\"cognee\""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 7,
|
||
"id": "9f1a1dbd",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:32:56.703003Z",
|
||
"start_time": "2025-02-09T21:32:47.375684Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"INFO:httpx:HTTP Request: GET https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json \"HTTP/1.1 200 OK\"/Users/vasilije/cognee/.venv/lib/python3.11/site-packages/pydantic/_internal/_config.py:341: UserWarning: Valid config keys have changed in V2:\n",
|
||
"* 'fields' has been removed\n",
|
||
" warnings.warn(message, UserWarning)\n",
|
||
"WARNING:cognee.infrastructure.databases.graph.networkx.adapter:File /Users/vasilije/cognee/cognee/.cognee_system/databases/cognee_graph.pkl not found. Initializing an empty graph.INFO:cognee.infrastructure.databases.graph.networkx.adapter:Graph deleted successfully./Users/vasilije/cognee/.venv/lib/python3.11/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html\n",
|
||
" from .autonotebook import tqdm as notebook_tqdm\n",
|
||
"INFO:cognee.infrastructure.databases.relational.sqlalchemy.SqlAlchemyAdapter:Database deleted successfully."
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Reset the cognee system with the following command:\n",
|
||
"\n",
|
||
"import cognee\n",
|
||
"\n",
|
||
"await cognee.prune.prune_data()\n",
|
||
"await cognee.prune.prune_system(metadata=True)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "383d6971",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### After we have defined and gathered our data let's add it to cognee "
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 8,
|
||
"id": "904df61ba484a8e5",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:33:07.412263Z",
|
||
"start_time": "2025-02-09T21:33:04.807282Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"\u001b[92m16:33:04 - LiteLLM:INFO\u001b[0m: utils.py:2784 - \n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:LiteLLM:\n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:run_tasks(tasks: [Task], data):Pipeline run started: `add_pipeline`INFO:run_tasks(tasks: [Task], data):Coroutine task started: `resolve_data_directories`INFO:run_tasks(tasks: [Task], data):Coroutine task started: `ingest_data`"
|
||
]
|
||
},
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"User 82d373be-4a32-433b-9ee3-d107780eccc2 has registered.\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"/Users/vasilije/cognee/.venv/lib/python3.11/site-packages/dlt/destinations/impl/sqlalchemy/merge_job.py:194: SAWarning: Table 'file_metadata' already exists within the given MetaData - not copying.\n",
|
||
" staging_table_obj = table_obj.to_metadata(\n",
|
||
"/Users/vasilije/cognee/.venv/lib/python3.11/site-packages/dlt/destinations/impl/sqlalchemy/merge_job.py:229: SAWarning: implicitly coercing SELECT object to scalar subquery; please use the .scalar_subquery() method to produce a scalar subquery.\n",
|
||
" order_by=order_dir_func(order_by_col),\n",
|
||
"INFO:run_tasks(tasks: [Task], data):Coroutine task completed: `ingest_data`INFO:run_tasks(tasks: [Task], data):Coroutine task completed: `resolve_data_directories`INFO:run_tasks(tasks: [Task], data):Pipeline run completed: `add_pipeline`"
|
||
]
|
||
},
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Pipeline file_load_from_filesystem load step completed in 0.03 seconds\n",
|
||
"1 load package(s) were loaded to destination sqlalchemy and into dataset main\n",
|
||
"The sqlalchemy destination used sqlite:////Users/vasilije/cognee/cognee/.cognee_system/databases/cognee_db location to store data\n",
|
||
"Load package 1739136787.3077161 is LOADED and contains no failed jobs\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import cognee\n",
|
||
"\n",
|
||
"await cognee.add([job_1, job_2, job_3, job_4, job_5, job_position], \"example\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "0f15c5b1",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### All good, let's cognify it."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 9,
|
||
"id": "7c431fdef4921ae0",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:33:21.450585Z",
|
||
"start_time": "2025-02-09T21:33:21.446326Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"from cognee.shared.data_models import KnowledgeGraph\n",
|
||
"from cognee.modules.data.models import Dataset, Data\n",
|
||
"from cognee.modules.data.methods.get_dataset_data import get_dataset_data\n",
|
||
"from cognee.modules.cognify.config import get_cognify_config\n",
|
||
"from cognee.modules.pipelines.tasks.Task import Task\n",
|
||
"from cognee.modules.pipelines import run_tasks\n",
|
||
"from cognee.modules.users.models import User\n",
|
||
"from cognee.tasks.documents import (\n",
|
||
" check_permissions_on_documents,\n",
|
||
" classify_documents,\n",
|
||
" extract_chunks_from_documents,\n",
|
||
")\n",
|
||
"from cognee.infrastructure.llm import get_max_chunk_tokens\n",
|
||
"from cognee.tasks.graph import extract_graph_from_data\n",
|
||
"from cognee.tasks.storage import add_data_points\n",
|
||
"from cognee.tasks.summarization import summarize_text\n",
|
||
"\n",
|
||
"\n",
|
||
"async def run_cognify_pipeline(dataset: Dataset, user: User = None):\n",
|
||
" data_documents: list[Data] = await get_dataset_data(dataset_id=dataset.id)\n",
|
||
"\n",
|
||
" try:\n",
|
||
" cognee_config = get_cognify_config()\n",
|
||
"\n",
|
||
" tasks = [\n",
|
||
" Task(classify_documents),\n",
|
||
" Task(check_permissions_on_documents, user=user, permissions=[\"write\"]),\n",
|
||
" Task(\n",
|
||
" extract_chunks_from_documents, max_chunk_tokens=get_max_chunk_tokens()\n",
|
||
" ), # Extract text chunks based on the document type.\n",
|
||
" Task(\n",
|
||
" extract_graph_from_data, graph_model=KnowledgeGraph, task_config={\"batch_size\": 10}\n",
|
||
" ), # Generate knowledge graphs from the document chunks.\n",
|
||
" Task(\n",
|
||
" summarize_text,\n",
|
||
" summarization_model=cognee_config.summarization_model,\n",
|
||
" task_config={\"batch_size\": 10},\n",
|
||
" ),\n",
|
||
" Task(add_data_points, task_config={\"batch_size\": 10}),\n",
|
||
" ]\n",
|
||
"\n",
|
||
" pipeline_run = run_tasks(tasks, dataset.id, data_documents, \"cognify_pipeline\")\n",
|
||
" pipeline_run_status = None\n",
|
||
"\n",
|
||
" async for run_status in pipeline_run:\n",
|
||
" pipeline_run_status = run_status\n",
|
||
"\n",
|
||
" except Exception as error:\n",
|
||
" raise error"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 10,
|
||
"id": "f0a91b99c6215e09",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:33:50.228396Z",
|
||
"start_time": "2025-02-09T21:33:27.935791Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"INFO:run_tasks(tasks: [Task], data):Pipeline run started: `default_pipeline`INFO:run_tasks(tasks: [Task], data):Coroutine task started: `classify_documents`INFO:run_tasks(tasks: [Task], data):Coroutine task started: `check_permissions_on_documents`INFO:run_tasks(tasks: [Task], data):Async generator task started: `extract_chunks_from_documents`INFO:run_tasks(tasks: [Task], data):Coroutine task started: `extract_graph_from_data`\u001b[92m16:33:27 - LiteLLM:INFO\u001b[0m: utils.py:2784 - \n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:LiteLLM:\n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openai\u001b[92m16:33:27 - LiteLLM:INFO\u001b[0m: utils.py:2784 - \n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:LiteLLM:\n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openai\u001b[92m16:33:27 - LiteLLM:INFO\u001b[0m: utils.py:2784 - \n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openai\u001b[92m16:33:27 - LiteLLM:INFO\u001b[0m: utils.py:2784 - \n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:LiteLLM:\n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openai\u001b[92m16:33:27 - LiteLLM:INFO\u001b[0m: utils.py:2784 - \n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:LiteLLM:\n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openai\u001b[92m16:33:28 - LiteLLM:INFO\u001b[0m: utils.py:2784 - \n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:LiteLLM:\n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:LiteLLM:\n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiWARNING:cognee.infrastructure.databases.graph.networkx.adapter:File /Users/vasilije/cognee/cognee/.cognee_system/databases/cognee_graph.pkl not found. Initializing an empty graph./Users/vasilije/cognee/.venv/lib/python3.11/site-packages/pydantic/main.py:1522: RuntimeWarning: fields may not start with an underscore, ignoring \"__tablename__\"\n",
|
||
" warnings.warn(f'fields may not start with an underscore, ignoring \"{f_name}\"', RuntimeWarning)\n",
|
||
"INFO:run_tasks(tasks: [Task], data):Coroutine task started: `summarize_text`\u001b[92m16:33:42 - LiteLLM:INFO\u001b[0m: utils.py:2784 - \n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:LiteLLM:\n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openai\u001b[92m16:33:42 - LiteLLM:INFO\u001b[0m: utils.py:2784 - \n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:LiteLLM:\n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openai\u001b[92m16:33:42 - LiteLLM:INFO\u001b[0m: utils.py:2784 - \n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:LiteLLM:\n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openai\u001b[92m16:33:42 - LiteLLM:INFO\u001b[0m: utils.py:2784 - \n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:LiteLLM:\n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openai\u001b[92m16:33:42 - LiteLLM:INFO\u001b[0m: utils.py:2784 - \n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:LiteLLM:\n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openai\u001b[92m16:33:42 - LiteLLM:INFO\u001b[0m: utils.py:2784 - \n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:LiteLLM:\n",
|
||
"LiteLLM completion() model= gpt-4o-mini; provider = openaiINFO:run_tasks(tasks: [Task], data):Coroutine task started: `add_data_points`INFO:run_tasks(tasks: [Task], data):Coroutine task completed: `add_data_points`INFO:run_tasks(tasks: [Task], data):Coroutine task completed: `summarize_text`INFO:run_tasks(tasks: [Task], data):Coroutine task completed: `extract_graph_from_data`INFO:run_tasks(tasks: [Task], data):Async generator task completed: `extract_chunks_from_documents`INFO:run_tasks(tasks: [Task], data):Coroutine task completed: `check_permissions_on_documents`INFO:run_tasks(tasks: [Task], data):Coroutine task completed: `classify_documents`INFO:run_tasks(tasks: [Task], data):Pipeline run completed: `default_pipeline`"
|
||
]
|
||
},
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"[TextSummary(id=UUID('df63669a-803c-59aa-8952-f86f76bbcf15'), created_at=1739136826551, updated_at=1739136826551, version=1, topological_rank=0, metadata={'index_fields': ['text']}, text='Senior Data Scientist (Machine Learning) position at TechNova Solutions in San Francisco, CA', made_from=DocumentChunk(id=UUID('ac9c63ea-0f2e-50d9-86e7-acb43491d65a'), created_at=1739136807954, updated_at=1739136807954, version=1, topological_rank=0, metadata={'index_fields': ['text']}, text='Senior Data Scientist (Machine Learning)\\n\\nCompany: TechNova Solutions\\nLocation: San Francisco, CA\\n\\nJob Description:\\n\\nTechNova Solutions is seeking a Senior Data Scientist specializing in Machine Learning to join our dynamic analytics team. The ideal candidate will have a strong background in developing and deploying machine learning models, working with large datasets, and translating complex data into actionable insights.\\n\\nResponsibilities:\\n\\nDevelop and implement advanced machine learning algorithms and models.\\nAnalyze large, complex datasets to extract meaningful patterns and insights.\\nCollaborate with cross-functional teams to integrate predictive models into products.\\nStay updated with the latest advancements in machine learning and data science.\\nMentor junior data scientists and provide technical guidance.\\nQualifications:\\n\\nMaster’s or Ph.D. in Data Science, Computer Science, Statistics, or a related field.\\n5+ years of experience in data science and machine learning.\\nProficient in Python, R, and SQL.\\nExpe rience with deep learning frameworks (e.g., TensorFlow, PyTorch).\\nStrong problem-solving skills and attention to detail.\\nCandidate CVs\\n', word_count=153, token_count=228, chunk_index=0, cut_type='sentence_cut', is_part_of=TextDocument(id=UUID('130dc251-4be9-5a64-8ae1-5f7cd5bca54d'), created_at=1739136807947, updated_at=1739136807947, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='text_81a5a96a9a7325d40521ea453778ebe0', raw_data_location='/Users/vasilije/cognee/cognee/.data_storage/data/text_81a5a96a9a7325d40521ea453778ebe0.txt', external_metadata='{}', mime_type='text/plain', type='text'), pydantic_type='DocumentChunk', contains=[Entity(id=UUID('453a45c9-14e7-5b73-adb8-55991096fef0'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='technova solutions', is_a=EntityType(id=UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='company', description='company', pydantic_type='EntityType'), description='A technology company seeking a Senior Data Scientist specializing in Machine Learning.', pydantic_type='Entity'), Entity(id=UUID('198e2ab8-75e9-5931-97ab-da9a5a8e188c'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='san francisco, ca', is_a=EntityType(id=UUID('19dd7d4d-a966-5ed5-82a0-6ae377761a29'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='location', description='location', pydantic_type='EntityType'), description='Location of TechNova Solutions.', pydantic_type='Entity'), Entity(id=UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='senior data scientist', is_a=EntityType(id=UUID('03e4ce4a-d531-5a2a-a4f7-9fab8955bf60'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='job title', description='job title', pydantic_type='EntityType'), description='Position specializing in machine learning at TechNova Solutions.', pydantic_type='Entity'), Entity(id=UUID('5187986a-7305-5a63-b057-8f2c097419eb'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='machine learning', is_a=EntityType(id=UUID('0198571b-3e94-50ea-8b9f-19e3a31080c0'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='field', description='field', pydantic_type='EntityType'), description='Field of expertise required for the Senior Data Scientist position.', pydantic_type='Entity'), Entity(id=UUID('d6545b21-153c-58ba-be47-46e5216521a3'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='data science', is_a=EntityType(id=UUID('0198571b-3e94-50ea-8b9f-19e3a31080c0'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='field', description='field', pydantic_type='EntityType'), description='Field relevant to the Senior Data Scientist role.', pydantic_type='Entity'), Entity(id=UUID('c95db510-e2ee-5a00-bded-20bbcb50c492'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='python', is_a=EntityType(id=UUID('80d409bb-e431-5939-a1ad-3acd96267128'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='programming language', description='programming language', pydantic_type='EntityType'), description='Programming language required for the Senior Data Scientist position.', pydantic_type='Entity'), Entity(id=UUID('39bd9707-8098-52ed-9cbf-bbdd26b963fb'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='r', is_a=EntityType(id=UUID('80d409bb-e431-5939-a1ad-3acd96267128'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='programming language', description='programming language', pydantic_type='EntityType'), description='Programming language required for the Senior Data Scientist position.', pydantic_type='Entity'), Entity(id=UUID('1ff6821a-b207-5050-83e9-37ff67a27d03'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='sql', is_a=EntityType(id=UUID('80d409bb-e431-5939-a1ad-3acd96267128'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='programming language', description='programming language', pydantic_type='EntityType'), description='Programming language required for the Senior Data Scientist position.', pydantic_type='Entity'), Entity(id=UUID('6e72f6f5-0452-5d42-a4e8-4aba6a614cb1'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='tensorflow', is_a=EntityType(id=UUID('36a32bd3-8880-547a-949b-8447477d1ef5'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='framework', description='framework', pydantic_type='EntityType'), description='Deep learning framework experience required for the Senior Data Scientist position.', pydantic_type='Entity'), Entity(id=UUID('c0d95499-de6b-5fcf-b0f5-9cbf427ad5c6'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='pytorch', is_a=EntityType(id=UUID('36a32bd3-8880-547a-949b-8447477d1ef5'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='framework', description='framework', pydantic_type='EntityType'), description='Deep learning framework experience required for the Senior Data Scientist position.', pydantic_type='Entity'), Entity(id=UUID('cf03961a-14e0-5a0e-b208-bcf89f6326d6'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='master’s or ph.d. in data science, computer science, statistics', is_a=EntityType(id=UUID('f0cf12c5-3311-567e-a047-0116c1fc54e4'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='qualification', description='qualification', pydantic_type='EntityType'), description='Educational requirement for the Senior Data Scientist position.', pydantic_type='Entity'), Entity(id=UUID('2127fedf-b2d0-555d-9081-6e5951df3285'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='5+ years of experience in data science and machine learning', is_a=EntityType(id=UUID('874712b4-2760-5b8d-8708-12e52cfdf1e7'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='experience requirement', description='experience requirement', pydantic_type='EntityType'), description='Experience requirement for the Senior Data Scientist position.', pydantic_type='Entity'), Entity(id=UUID('2d55fb94-607c-5998-baf3-b18a2fb8a3fe'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='strong problem-solving skills and attention to detail', is_a=EntityType(id=UUID('37976df5-c5db-5a80-8dcc-780c39cbedb3'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='skill', description='skill', pydantic_type='EntityType'), description='Skill requirement for the Senior Data Scientist position.', pydantic_type='Entity')])), TextSummary(id=UUID('5963b173-a698-5179-9680-f24a2e5ae275'), created_at=1739136826551, updated_at=1739136826551, version=1, topological_rank=0, metadata={'index_fields': ['text']}, text='Data Scientist with extensive expertise in machine learning and statistical analysis, adept at managing large datasets and converting data into practical business strategies.', made_from=DocumentChunk(id=UUID('9e864329-dc94-5df5-b451-5e9ce33f66ec'), created_at=1739136807961, updated_at=1739136807961, version=1, topological_rank=0, metadata={'index_fields': ['text']}, text='\\nCV 2: Relevant\\nName: Michael Rodriguez\\nContact Information:\\n\\nEmail: michael.rodriguez@example.com\\nPhone: (555) 234-5678\\nSummary:\\n\\nData Scientist with a strong background in machine learning and statistical modeling. Skilled in handling large datasets and translating data into actionable business insights.\\n\\nEducation:\\n\\nM.S. in Data Science, Carnegie Mellon University (2013)\\nB.S. in Computer Science, University of Michigan (2011)\\nExperience:\\n\\nSenior Data Scientist, Alpha Analytics (2017 – Present)\\nDeveloped machine learning models to optimize marketing strategies.\\nReduced customer acquisition cost by 15% through predictive modeling.\\nData Scientist, TechInsights (2013 – 2017)\\nAnalyzed user behavior data to improve product features.\\nImplemented A/B testing frameworks to evaluate product changes.\\nSkills:\\n\\nProgramming Languages: Python, Java, SQL\\nMachine Learning: Scikit-Learn, XGBoost\\nData Visualization: Seaborn, Plotly\\nDatabases: MySQL, MongoDB\\n', word_count=108, token_count=218, chunk_index=0, cut_type='sentence_cut', is_part_of=TextDocument(id=UUID('5ba85987-4585-51fa-91d4-cd5ed28932ba'), created_at=1739136807947, updated_at=1739136807947, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='text_f0f63a5c88dbbeef1eca23d32848220c', raw_data_location='/Users/vasilije/cognee/cognee/.data_storage/data/text_f0f63a5c88dbbeef1eca23d32848220c.txt', external_metadata='{}', mime_type='text/plain', type='text'), pydantic_type='DocumentChunk', contains=[Entity(id=UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='michael rodriguez', is_a=EntityType(id=UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='person', description='person', pydantic_type='EntityType'), description='Data Scientist with a strong background in machine learning and statistical modeling.', pydantic_type='Entity'), Entity(id=UUID('5534e0b0-d0c4-5ab9-82e9-91bed36f70bd'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='carnegie mellon university', is_a=EntityType(id=UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='organization', description='organization', pydantic_type='EntityType'), description='University where Michael Rodriguez completed his M.S. in Data Science.', pydantic_type='Entity'), Entity(id=UUID('0af613e0-c11b-550d-ada2-2c2aa6550884'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='university of michigan', is_a=EntityType(id=UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='organization', description='organization', pydantic_type='EntityType'), description='University where Michael Rodriguez completed his B.S. in Computer Science.', pydantic_type='Entity'), Entity(id=UUID('04a91fef-8a07-5d50-8f1b-46f3afeec497'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='alpha analytics', is_a=EntityType(id=UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='organization', description='organization', pydantic_type='EntityType'), description='Company where Michael Rodriguez works as a Senior Data Scientist.', pydantic_type='Entity'), Entity(id=UUID('3f848ed6-902f-5a8e-9577-cb67f8c17acd'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='techinsights', is_a=EntityType(id=UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='organization', description='organization', pydantic_type='EntityType'), description='Company where Michael Rodriguez worked as a Data Scientist.', pydantic_type='Entity'), Entity(id=UUID('c72287e7-5530-5507-bd52-f903075f568c'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='2017', is_a=EntityType(id=UUID('d61d99ac-b291-5666-9748-3e80e1c8b56a'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='date', description='date', pydantic_type='EntityType'), description='Year when Michael Rodriguez started working at Alpha Analytics.', pydantic_type='Entity'), Entity(id=UUID('9b5f11a6-00ba-5a7a-b856-f584cb2656fb'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='2013', is_a=EntityType(id=UUID('d61d99ac-b291-5666-9748-3e80e1c8b56a'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='date', description='date', pydantic_type='EntityType'), description='Year when Michael Rodriguez started working at TechInsights and completed his M.S.', pydantic_type='Entity'), Entity(id=UUID('f1ccd810-2a0c-578c-b1ee-92580359c202'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='2011', is_a=EntityType(id=UUID('d61d99ac-b291-5666-9748-3e80e1c8b56a'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='date', description='date', pydantic_type='EntityType'), description='Year when Michael Rodriguez completed his B.S. in Computer Science.', pydantic_type='Entity')])), TextSummary(id=UUID('739b26cc-b2ab-559a-a992-1d95d4c62bea'), created_at=1739136826551, updated_at=1739136826551, version=1, topological_rank=0, metadata={'index_fields': ['text']}, text='Senior Data Scientist with 8+ years in machine learning and predictive analytics, skilled in creating advanced algorithms and deploying scalable models.', made_from=DocumentChunk(id=UUID('2c01732f-3a58-5cf5-8edf-d2067c75758d'), created_at=1739136807965, updated_at=1739136807965, version=1, topological_rank=0, metadata={'index_fields': ['text']}, text='\\nCV 1: Relevant\\nName: Dr. Emily Carter\\nContact Information:\\n\\nEmail: emily.carter@example.com\\nPhone: (555) 123-4567\\nSummary:\\n\\nSenior Data Scientist with over 8 years of experience in machine learning and predictive analytics. Expertise in developing advanced algorithms and deploying scalable models in production environments.\\n\\nEducation:\\n\\nPh.D. in Computer Science, Stanford University (2014)\\nB.S. in Mathematics, University of California, Berkeley (2010)\\nExperience:\\n\\nSenior Data Scientist, InnovateAI Labs (2016 – Present)\\nLed a team in developing machine learning models for natural language processing applications.\\nImplemented deep learning algorithms that improved prediction accuracy by 25%.\\nCollaborated with cross-functional teams to integrate models into cloud-based platforms.\\nData Scientist, DataWave Analytics (2014 – 2016)\\nDeveloped predictive models for customer segmentation and churn analysis.\\nAnalyzed large datasets using Hadoop and Spark frameworks.\\nSkills:\\n\\nProgramming Languages: Python, R, SQL\\nMachin e Learning: TensorFlow, Keras, Scikit-Learn\\nBig Data Technologies: Hadoop, Spark\\nData Visualization: Tableau, Matplotlib\\n', word_count=133, token_count=252, chunk_index=0, cut_type='sentence_cut', is_part_of=TextDocument(id=UUID('681317e0-82a2-5867-81c2-3556769e6698'), created_at=1739136807947, updated_at=1739136807947, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='text_85410f4ad1197f5974aef9aed6f103c8', raw_data_location='/Users/vasilije/cognee/cognee/.data_storage/data/text_85410f4ad1197f5974aef9aed6f103c8.txt', external_metadata='{}', mime_type='text/plain', type='text'), pydantic_type='DocumentChunk', contains=[Entity(id=UUID('29e771c8-4c3f-52de-9511-6b705878e130'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='dr. emily carter', is_a=EntityType(id=UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='person', description='person', pydantic_type='EntityType'), description='Senior Data Scientist with over 8 years of experience in machine learning and predictive analytics.', pydantic_type='Entity'), Entity(id=UUID('ce8b394a-b30e-52fc-b80a-6352edc60e5b'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='stanford university', is_a=EntityType(id=UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='organization', description='organization', pydantic_type='EntityType'), description='A prestigious university located in California, known for its research programs.', pydantic_type='Entity'), Entity(id=UUID('2c02c93c-9cd1-56b8-9cc0-55ff0b290e57'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='university of california, berkeley', is_a=EntityType(id=UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='organization', description='organization', pydantic_type='EntityType'), description='A public research university in California, known for its academic excellence.', pydantic_type='Entity'), Entity(id=UUID('9780afb1-dccc-53eb-9a30-c0d4ce033711'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='innovateai labs', is_a=EntityType(id=UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='organization', description='organization', pydantic_type='EntityType'), description='A company that specializes in artificial intelligence and machine learning.', pydantic_type='Entity'), Entity(id=UUID('50d0a685-5300-544f-b081-edca4b625886'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='datawave analytics', is_a=EntityType(id=UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='organization', description='organization', pydantic_type='EntityType'), description='A company focused on data analytics and insights for business.', pydantic_type='Entity'), Entity(id=UUID('1625b880-9c57-5753-806b-5ffd2a0480dd'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='big data technologies', is_a=EntityType(id=UUID('dd9713b7-dc20-5101-aad0-1c4216811147'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='concept', description='concept', pydantic_type='EntityType'), description='Technologies used to handle large volumes of data that traditional data processing applications cannot manage.', pydantic_type='Entity'), Entity(id=UUID('2707e7b1-3947-5a9b-b2f3-e5bb3cadb6a7'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='data visualization', is_a=EntityType(id=UUID('dd9713b7-dc20-5101-aad0-1c4216811147'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='concept', description='concept', pydantic_type='EntityType'), description='The graphical representation of information and data.', pydantic_type='Entity')])), TextSummary(id=UUID('582a5af9-bddf-58a4-988d-20d060d23936'), created_at=1739136826551, updated_at=1739136826551, version=1, topological_rank=0, metadata={'index_fields': ['text']}, text='Data Scientist with a focus on machine learning and 6 years of experience in utilizing data to enhance business solutions and product efficacy.', made_from=DocumentChunk(id=UUID('db8ea487-bbac-5d2a-86e5-46d92b1a4681'), created_at=1739136807969, updated_at=1739136807969, version=1, topological_rank=0, metadata={'index_fields': ['text']}, text='\\nCV 3: Relevant\\nName: Sarah Nguyen\\nContact Information:\\n\\nEmail: sarah.nguyen@example.com\\nPhone: (555) 345-6789\\nSummary:\\n\\nData Scientist specializing in machine learning with 6 years of experience. Passionate about leveraging data to drive business solutions and improve product performance.\\n\\nEducation:\\n\\nM.S. in Statistics, University of Washington (2014)\\nB.S. in Applied Mathematics, University of Texas at Austin (2012)\\nExperience:\\n\\nData Scientist, QuantumTech (2016 – Present)\\nDesigned and implemented machine learning algorithms for financial forecasting.\\nImproved model efficiency by 20% through algorithm optimization.\\nJunior Data Scientist, DataCore Solutions (2014 – 2016)\\nAssisted in developing predictive models for supply chain optimization.\\nConducted data cleaning and preprocessing on large datasets.\\nSkills:\\n\\nProgramming Languages: Python, R\\nMachine Learning Frameworks: PyTorch, Scikit-Learn\\nStatistical Analysis: SAS, SPSS\\nCloud Platforms: AWS, Azure\\n', word_count=110, token_count=216, chunk_index=0, cut_type='sentence_cut', is_part_of=TextDocument(id=UUID('9acc9e48-cae1-581f-8f4f-051c761015fc'), created_at=1739136807947, updated_at=1739136807947, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='text_f8c7482e727f228001b0046ed68d656f', raw_data_location='/Users/vasilije/cognee/cognee/.data_storage/data/text_f8c7482e727f228001b0046ed68d656f.txt', external_metadata='{}', mime_type='text/plain', type='text'), pydantic_type='DocumentChunk', contains=[Entity(id=UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='sarah nguyen', is_a=EntityType(id=UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='person', description='person', pydantic_type='EntityType'), description='Data Scientist specializing in machine learning with 6 years of experience.', pydantic_type='Entity'), Entity(id=UUID('d82673ff-ff5e-5436-bc8b-2967d4301b4f'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='m.s. in statistics', is_a=EntityType(id=UUID('a49b283a-ce92-50e0-b7fa-ca7c628eb01a'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='degree', description='degree', pydantic_type='EntityType'), description='Master of Science in Statistics from University of Washington', pydantic_type='Entity'), Entity(id=UUID('5abf79a8-2cdc-56a9-b78a-fd8150e9e891'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='b.s. in applied mathematics', is_a=EntityType(id=UUID('a49b283a-ce92-50e0-b7fa-ca7c628eb01a'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='degree', description='degree', pydantic_type='EntityType'), description='Bachelor of Science in Applied Mathematics from University of Texas at Austin', pydantic_type='Entity'), Entity(id=UUID('0d980f2a-09dd-581e-acc3-cc2d87c1bab4'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='quantumtech', is_a=EntityType(id=UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='company', description='company', pydantic_type='EntityType'), description='Company where Sarah Nguyen works as a Data Scientist', pydantic_type='Entity'), Entity(id=UUID('95ac0551-38fc-5187-a422-533aeb7e8db0'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='datacore solutions', is_a=EntityType(id=UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='company', description='company', pydantic_type='EntityType'), description='Company where Sarah Nguyen worked as a Junior Data Scientist', pydantic_type='Entity'), Entity(id=UUID('ec847cd7-8e31-51b2-bc9a-cb5467d2de9b'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='machine learning algorithms', is_a=EntityType(id=UUID('dd9713b7-dc20-5101-aad0-1c4216811147'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='concept', description='concept', pydantic_type='EntityType'), description='Algorithms designed and implemented for financial forecasting', pydantic_type='Entity')])), TextSummary(id=UUID('0f88fb55-8639-5272-bd78-3b0113969988'), created_at=1739136826551, updated_at=1739136826551, version=1, topological_rank=0, metadata={'index_fields': ['text']}, text='Experienced Graphic Designer', made_from=DocumentChunk(id=UUID('46acf40e-e5e3-53df-8908-8b9d4cf0fa82'), created_at=1739136807972, updated_at=1739136807972, version=1, topological_rank=0, metadata={'index_fields': ['text']}, text='\\nCV 4: Not Relevant\\nName: David Thompson\\nContact Information:\\n\\nEmail: david.thompson@example.com\\nPhone: (555) 456-7890\\nSummary:\\n\\nCreative Graphic Designer with over 8 years of experience in visual design and branding. Proficient in Adobe Creative Suite and passionate about creating compelling visuals.\\n\\nEducation:\\n\\nB.F.A. in Graphic Design, Rhode Island School of Design (2012)\\nExperience:\\n\\nSenior Graphic Designer, CreativeWorks Agency (2015 – Present)\\nLed design projects for clients in various industries.\\nCreated branding materials that increased client engagement by 30%.\\nGraphic Designer, Visual Innovations (2012 – 2015)\\nDesigned marketing collateral, including brochures, logos, and websites.\\nCollaborated with the marketing team to develop cohesive brand strategies.\\nSkills:\\n\\nDesign Software: Adobe Photoshop, Illustrator, InDesign\\nWeb Design: HTML, CSS\\nSpecialties: Branding and Identity, Typography\\n', word_count=108, token_count=202, chunk_index=0, cut_type='sentence_cut', is_part_of=TextDocument(id=UUID('f8846763-c7bc-565a-a9a3-6e59aa075142'), created_at=1739136807947, updated_at=1739136807947, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='text_9abf20fa7defd7e49296c51b4e38edf2', raw_data_location='/Users/vasilije/cognee/cognee/.data_storage/data/text_9abf20fa7defd7e49296c51b4e38edf2.txt', external_metadata='{}', mime_type='text/plain', type='text'), pydantic_type='DocumentChunk', contains=[Entity(id=UUID('a4777597-06c7-562c-bc44-56f74571a01a'), created_at=1739136819424, updated_at=1739136819424, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='david thompson', is_a=EntityType(id=UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='person', description='person', pydantic_type='EntityType'), description='Creative Graphic Designer with over 8 years of experience in visual design and branding.', pydantic_type='Entity'), Entity(id=UUID('60b027fe-7bb4-535d-8a47-19f1a491591b'), created_at=1739136819425, updated_at=1739136819425, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='rhode island school of design', is_a=EntityType(id=UUID('d625a269-8f40-5359-ad5f-e3b5fde1e477'), created_at=1739136819425, updated_at=1739136819425, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='educationalinstitution', description='educationalinstitution', pydantic_type='EntityType'), description='A prestigious institution for art and design education.', pydantic_type='Entity'), Entity(id=UUID('ca20272a-3e88-552f-92fe-491e23f117f8'), created_at=1739136819425, updated_at=1739136819425, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='creativeworks agency', is_a=EntityType(id=UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='company', description='company', pydantic_type='EntityType'), description='A design agency serving various clients in different industries.', pydantic_type='Entity'), Entity(id=UUID('1e97bb97-4d29-5fb8-863a-15ab51f1dd46'), created_at=1739136819425, updated_at=1739136819425, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='visual innovations', is_a=EntityType(id=UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='company', description='company', pydantic_type='EntityType'), description='A company focusing on marketing collateral design.', pydantic_type='Entity')])), TextSummary(id=UUID('6dbd0158-8a64-54f6-9765-c329e2224f89'), created_at=1739136826551, updated_at=1739136826551, version=1, topological_rank=0, metadata={'index_fields': ['text']}, text='Sales Manager with a proven record of boosting sales and cultivating high-performing teams. Strong leadership and interpersonal communication skills.', made_from=DocumentChunk(id=UUID('3a3e38bc-f351-52c8-8ebc-44e7359a4482'), created_at=1739136807976, updated_at=1739136807976, version=1, topological_rank=0, metadata={'index_fields': ['text']}, text=\"\\nCV 5: Not Relevant\\nName: Jessica Miller\\nContact Information:\\n\\nEmail: jessica.miller@example.com\\nPhone: (555) 567-8901\\nSummary:\\n\\nExperienced Sales Manager with a strong track record in driving sales growth and building high-performing teams. Excellent communication and leadership skills.\\n\\nEducation:\\n\\nB.A. in Business Administration, University of Southern California (2010)\\nExperience:\\n\\nSales Manager, Global Enterprises (2015 – Present)\\nManaged a sales team of 15 members, achieving a 20% increase in annual revenue.\\nDeveloped sales strategies that expanded customer base by 25%.\\nSales Representative, Market Leaders Inc. (2010 – 2015)\\nConsistently exceeded sales targets and received the 'Top Salesperson' award in 2013.\\nSkills:\\n\\nSales Strategy and Planning\\nTeam Leadership and Development\\nCRM Software: Salesforce, Zoho\\nNegotiation and Relationship Building\\n\", word_count=102, token_count=198, chunk_index=0, cut_type='sentence_cut', is_part_of=TextDocument(id=UUID('fe77a82d-eb85-5e0e-b25b-bdb83e44b972'), created_at=1739136807947, updated_at=1739136807947, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='text_9b35c7df1f5d4dc84e78270c0bf9cac6', raw_data_location='/Users/vasilije/cognee/cognee/.data_storage/data/text_9b35c7df1f5d4dc84e78270c0bf9cac6.txt', external_metadata='{}', mime_type='text/plain', type='text'), pydantic_type='DocumentChunk', contains=[Entity(id=UUID('36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932'), created_at=1739136819425, updated_at=1739136819425, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='jessica miller', is_a=EntityType(id=UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='person', description='person', pydantic_type='EntityType'), description='Experienced Sales Manager with a strong track record in driving sales growth and building high-performing teams. Excellent communication and leadership skills.', pydantic_type='Entity'), Entity(id=UUID('f39d6c00-689b-5fd2-9021-893b28ac6ff2'), created_at=1739136819425, updated_at=1739136819425, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='university of southern california', is_a=EntityType(id=UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='organization', description='organization', pydantic_type='EntityType'), description='University located in Southern California.', pydantic_type='Entity'), Entity(id=UUID('5c32691d-c0e4-5378-9aab-dda8b0fa3931'), created_at=1739136819425, updated_at=1739136819425, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='global enterprises', is_a=EntityType(id=UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='organization', description='organization', pydantic_type='EntityType'), description='Company where Jessica Miller works as a Sales Manager.', pydantic_type='Entity'), Entity(id=UUID('67544857-983a-5152-801d-4fc9d35d14e4'), created_at=1739136819425, updated_at=1739136819425, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='market leaders inc.', is_a=EntityType(id=UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), created_at=1739136819423, updated_at=1739136819423, version=1, topological_rank=0, metadata={'index_fields': ['name']}, name='organization', description='organization', pydantic_type='EntityType'), description='Company where Jessica Miller worked as a Sales Representative.', pydantic_type='Entity')]))]\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from cognee.modules.users.methods import get_default_user\n",
|
||
"from cognee.modules.data.methods import get_datasets_by_name\n",
|
||
"\n",
|
||
"user = await get_default_user()\n",
|
||
"\n",
|
||
"datasets = await get_datasets_by_name([\"example\"], user.id)\n",
|
||
"\n",
|
||
"await run_cognify_pipeline(datasets[0], user)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 3,
|
||
"id": "9dd29caf28c272d1",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:42:39.479622Z",
|
||
"start_time": "2025-02-09T21:42:39.469795Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"INFO:root:([(UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), {'created_at': 1739138108472, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 8, 472000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'text': 'Senior Data Scientist (Machine Learning)\\n\\nCompany: TechNova Solutions\\nLocation: San Francisco, CA\\n\\nJob Description:\\n\\nTechNova Solutions is seeking a Senior Data Scientist specializing in Machine Learning to join our dynamic analytics team. The ideal candidate will have a strong background in developing and deploying machine learning models, working with large datasets, and translating complex data into actionable insights.\\n\\nResponsibilities:\\n\\nDevelop and implement advanced machine learning algorithms and models.\\nAnalyze large, complex datasets to extract meaningful patterns and insights.\\nCollaborate with cross-functional teams to integrate predictive models into products.\\nStay updated with the latest advancements in machine learning and data science.\\nMentor junior data scientists and provide technical guidance.\\nQualifications:\\n\\nMaster’s or Ph.D. in Data Science, Computer Science, Statistics, or a related field.\\n5+ years of experience in data science and machine learning.\\nProficient in Python, R, and SQL.\\nExpe rience with deep learning frameworks (e.g., TensorFlow, PyTorch).\\nStrong problem-solving skills and attention to detail.\\nCandidate CVs\\n', 'word_count': 153, 'token_count': 228, 'chunk_index': 0, 'cut_type': 'sentence_cut', 'pydantic_type': 'DocumentChunk', 'id': UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6')}), (UUID('005aa235-96be-5334-bc8a-cdc1180561e3'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'experience with deep learning frameworks (e.g., tensorflow, pytorch)', 'description': 'Experience with deep learning frameworks required for the Senior Data Scientist position.', 'pydantic_type': 'Entity', 'id': UUID('005aa235-96be-5334-bc8a-cdc1180561e3')}), (UUID('f0cf12c5-3311-567e-a047-0116c1fc54e4'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'qualification', 'description': 'qualification', 'pydantic_type': 'EntityType', 'id': UUID('f0cf12c5-3311-567e-a047-0116c1fc54e4')}), (UUID('198e2ab8-75e9-5931-97ab-da9a5a8e188c'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'san francisco, ca', 'description': 'The location of TechNova Solutions.', 'pydantic_type': 'Entity', 'id': UUID('198e2ab8-75e9-5931-97ab-da9a5a8e188c')}), (UUID('19dd7d4d-a966-5ed5-82a0-6ae377761a29'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'location', 'description': 'location', 'pydantic_type': 'EntityType', 'id': UUID('19dd7d4d-a966-5ed5-82a0-6ae377761a29')}), (UUID('8a9b7137-f981-5f96-8df0-dea78cdf1dda'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'strong problem-solving skills and attention to detail', 'description': 'Soft skills required for the Senior Data Scientist position.', 'pydantic_type': 'Entity', 'id': UUID('8a9b7137-f981-5f96-8df0-dea78cdf1dda')}), (UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'senior data scientist', 'description': 'A position specializing in Machine Learning within the analytics team.', 'pydantic_type': 'Entity', 'id': UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5')}), (UUID('03e4ce4a-d531-5a2a-a4f7-9fab8955bf60'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'job_title', 'description': 'job_title', 'pydantic_type': 'EntityType', 'id': UUID('03e4ce4a-d531-5a2a-a4f7-9fab8955bf60')}), (UUID('453a45c9-14e7-5b73-adb8-55991096fef0'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'technova solutions', 'description': 'A company seeking to hire a Senior Data Scientist specializing in Machine Learning.', 'pydantic_type': 'Entity', 'id': UUID('453a45c9-14e7-5b73-adb8-55991096fef0')}), (UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'company', 'description': 'company', 'pydantic_type': 'EntityType', 'id': UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219')}), (UUID('171a185d-c76c-539b-9520-9d1afd84dc4c'), {'created_at': 1739138108465, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 8, 465000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'text_81a5a96a9a7325d40521ea453778ebe0', 'raw_data_location': '/Users/vasilije/cognee/cognee/.data_storage/data/text_81a5a96a9a7325d40521ea453778ebe0.txt', 'external_metadata': '{}', 'mime_type': 'text/plain', 'type': 'text', 'id': UUID('171a185d-c76c-539b-9520-9d1afd84dc4c')}), (UUID('702366d5-21a2-5f25-a4d9-ea9794bae4fe'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'masters or ph.d. in data science, computer science, statistics, or a related field', 'description': 'Educational qualification required for the Senior Data Scientist position.', 'pydantic_type': 'Entity', 'id': UUID('702366d5-21a2-5f25-a4d9-ea9794bae4fe')}), (UUID('c35072da-4e2e-575e-acd4-5cc4682e3a2b'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'proficient in python, r, and sql', 'description': 'Technical skills required for the Senior Data Scientist position.', 'pydantic_type': 'Entity', 'id': UUID('c35072da-4e2e-575e-acd4-5cc4682e3a2b')}), (UUID('fe5ea90b-e586-5492-a7a4-71b918c71a20'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': '5+ years of experience in data science and machine learning', 'description': 'Experience required for the Senior Data Scientist position.', 'pydantic_type': 'Entity', 'id': UUID('fe5ea90b-e586-5492-a7a4-71b918c71a20')}), (UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), {'created_at': 1739138108479, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 8, 479000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'text': '\\nCV 2: Relevant\\nName: Michael Rodriguez\\nContact Information:\\n\\nEmail: michael.rodriguez@example.com\\nPhone: (555) 234-5678\\nSummary:\\n\\nData Scientist with a strong background in machine learning and statistical modeling. Skilled in handling large datasets and translating data into actionable business insights.\\n\\nEducation:\\n\\nM.S. in Data Science, Carnegie Mellon University (2013)\\nB.S. in Computer Science, University of Michigan (2011)\\nExperience:\\n\\nSenior Data Scientist, Alpha Analytics (2017 – Present)\\nDeveloped machine learning models to optimize marketing strategies.\\nReduced customer acquisition cost by 15% through predictive modeling.\\nData Scientist, TechInsights (2013 – 2017)\\nAnalyzed user behavior data to improve product features.\\nImplemented A/B testing frameworks to evaluate product changes.\\nSkills:\\n\\nProgramming Languages: Python, Java, SQL\\nMachine Learning: Scikit-Learn, XGBoost\\nData Visualization: Seaborn, Plotly\\nDatabases: MySQL, MongoDB\\n', 'word_count': 108, 'token_count': 218, 'chunk_index': 0, 'cut_type': 'sentence_cut', 'pydantic_type': 'DocumentChunk', 'id': UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84')}), (UUID('0af613e0-c11b-550d-ada2-2c2aa6550884'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'university of michigan', 'description': 'University known for its programs in computer science and engineering.', 'pydantic_type': 'Entity', 'id': UUID('0af613e0-c11b-550d-ada2-2c2aa6550884')}), (UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'organization', 'description': 'organization', 'pydantic_type': 'EntityType', 'id': UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d')}), (UUID('5534e0b0-d0c4-5ab9-82e9-91bed36f70bd'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'carnegie mellon university', 'description': 'University known for its programs in data science and engineering.', 'pydantic_type': 'Entity', 'id': UUID('5534e0b0-d0c4-5ab9-82e9-91bed36f70bd')}), (UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'michael rodriguez', 'description': 'Data Scientist with a strong background in machine learning and statistical modeling.', 'pydantic_type': 'Entity', 'id': UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9')}), (UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'person', 'description': 'person', 'pydantic_type': 'EntityType', 'id': UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134')}), (UUID('175cf99b-d9e7-5d16-a8af-d4ce31ee96d1'), {'created_at': 1739138108465, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 8, 465000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'text_f0f63a5c88dbbeef1eca23d32848220c', 'raw_data_location': '/Users/vasilije/cognee/cognee/.data_storage/data/text_f0f63a5c88dbbeef1eca23d32848220c.txt', 'external_metadata': '{}', 'mime_type': 'text/plain', 'type': 'text', 'id': UUID('175cf99b-d9e7-5d16-a8af-d4ce31ee96d1')}), (UUID('04a91fef-8a07-5d50-8f1b-46f3afeec497'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'alpha analytics', 'description': 'Company where Michael Rodriguez works as a Senior Data Scientist.', 'pydantic_type': 'Entity', 'id': UUID('04a91fef-8a07-5d50-8f1b-46f3afeec497')}), (UUID('3f848ed6-902f-5a8e-9577-cb67f8c17acd'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'techinsights', 'description': 'Company where Michael Rodriguez worked as a Data Scientist.', 'pydantic_type': 'Entity', 'id': UUID('3f848ed6-902f-5a8e-9577-cb67f8c17acd')}), (UUID('1895e0c8-8f54-5c45-9f41-8891f0330576'), {'created_at': 1739138108484, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 8, 484000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'text': \"\\nCV 5: Not Relevant\\nName: Jessica Miller\\nContact Information:\\n\\nEmail: jessica.miller@example.com\\nPhone: (555) 567-8901\\nSummary:\\n\\nExperienced Sales Manager with a strong track record in driving sales growth and building high-performing teams. Excellent communication and leadership skills.\\n\\nEducation:\\n\\nB.A. in Business Administration, University of Southern California (2010)\\nExperience:\\n\\nSales Manager, Global Enterprises (2015 – Present)\\nManaged a sales team of 15 members, achieving a 20% increase in annual revenue.\\nDeveloped sales strategies that expanded customer base by 25%.\\nSales Representative, Market Leaders Inc. (2010 – 2015)\\nConsistently exceeded sales targets and received the 'Top Salesperson' award in 2013.\\nSkills:\\n\\nSales Strategy and Planning\\nTeam Leadership and Development\\nCRM Software: Salesforce, Zoho\\nNegotiation and Relationship Building\\n\", 'word_count': 102, 'token_count': 198, 'chunk_index': 0, 'cut_type': 'sentence_cut', 'pydantic_type': 'DocumentChunk', 'id': UUID('1895e0c8-8f54-5c45-9f41-8891f0330576')}), (UUID('5c32691d-c0e4-5378-9aab-dda8b0fa3931'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'global enterprises', 'description': 'A global company involved in various sectors, known for its sales and marketing strategies.', 'pydantic_type': 'Entity', 'id': UUID('5c32691d-c0e4-5378-9aab-dda8b0fa3931')}), (UUID('f39d6c00-689b-5fd2-9021-893b28ac6ff2'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'university of southern california', 'description': 'A private research university located in Los Angeles, California.', 'pydantic_type': 'Entity', 'id': UUID('f39d6c00-689b-5fd2-9021-893b28ac6ff2')}), (UUID('36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'jessica miller', 'description': 'An experienced Sales Manager with a strong track record in driving sales growth and building high-performing teams.', 'pydantic_type': 'Entity', 'id': UUID('36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932')}), (UUID('7071b7bb-2de3-59ee-83f2-31f8e5c9f9eb'), {'created_at': 1739138108466, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 8, 466000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'text_9b35c7df1f5d4dc84e78270c0bf9cac6', 'raw_data_location': '/Users/vasilije/cognee/cognee/.data_storage/data/text_9b35c7df1f5d4dc84e78270c0bf9cac6.txt', 'external_metadata': '{}', 'mime_type': 'text/plain', 'type': 'text', 'id': UUID('7071b7bb-2de3-59ee-83f2-31f8e5c9f9eb')}), (UUID('94952c93-3432-581b-b6a6-101266596c46'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'market leaders inc.', 'description': 'A company that focuses on sales and marketing in various industries.', 'pydantic_type': 'Entity', 'id': UUID('94952c93-3432-581b-b6a6-101266596c46')}), (UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), {'created_at': 1739138108490, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 8, 490000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'text': '\\nCV 1: Relevant\\nName: Dr. Emily Carter\\nContact Information:\\n\\nEmail: emily.carter@example.com\\nPhone: (555) 123-4567\\nSummary:\\n\\nSenior Data Scientist with over 8 years of experience in machine learning and predictive analytics. Expertise in developing advanced algorithms and deploying scalable models in production environments.\\n\\nEducation:\\n\\nPh.D. in Computer Science, Stanford University (2014)\\nB.S. in Mathematics, University of California, Berkeley (2010)\\nExperience:\\n\\nSenior Data Scientist, InnovateAI Labs (2016 – Present)\\nLed a team in developing machine learning models for natural language processing applications.\\nImplemented deep learning algorithms that improved prediction accuracy by 25%.\\nCollaborated with cross-functional teams to integrate models into cloud-based platforms.\\nData Scientist, DataWave Analytics (2014 – 2016)\\nDeveloped predictive models for customer segmentation and churn analysis.\\nAnalyzed large datasets using Hadoop and Spark frameworks.\\nSkills:\\n\\nProgramming Languages: Python, R, SQL\\nMachin e Learning: TensorFlow, Keras, Scikit-Learn\\nBig Data Technologies: Hadoop, Spark\\nData Visualization: Tableau, Matplotlib\\n', 'word_count': 133, 'token_count': 252, 'chunk_index': 0, 'cut_type': 'sentence_cut', 'pydantic_type': 'DocumentChunk', 'id': UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7')}), (UUID('5187986a-7305-5a63-b057-8f2c097419eb'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'machine learning', 'description': 'Field of expertise related to predictive analytics and algorithms.', 'pydantic_type': 'Entity', 'id': UUID('5187986a-7305-5a63-b057-8f2c097419eb')}), (UUID('dd9713b7-dc20-5101-aad0-1c4216811147'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'concept', 'description': 'concept', 'pydantic_type': 'EntityType', 'id': UUID('dd9713b7-dc20-5101-aad0-1c4216811147')}), (UUID('2c02c93c-9cd1-56b8-9cc0-55ff0b290e57'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'university of california, berkeley', 'description': 'University where B.S. in Mathematics was obtained.', 'pydantic_type': 'Entity', 'id': UUID('2c02c93c-9cd1-56b8-9cc0-55ff0b290e57')}), (UUID('ce8b394a-b30e-52fc-b80a-6352edc60e5b'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'stanford university', 'description': 'Reputed university where Ph.D. in Computer Science was obtained.', 'pydantic_type': 'Entity', 'id': UUID('ce8b394a-b30e-52fc-b80a-6352edc60e5b')}), (UUID('29e771c8-4c3f-52de-9511-6b705878e130'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'dr. emily carter', 'description': 'Senior Data Scientist with over 8 years of experience in machine learning and predictive analytics.', 'pydantic_type': 'Entity', 'id': UUID('29e771c8-4c3f-52de-9511-6b705878e130')}), (UUID('cdb36296-ac37-550a-b87b-1453084103d2'), {'created_at': 1739138108466, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 8, 466000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'text_85410f4ad1197f5974aef9aed6f103c8', 'raw_data_location': '/Users/vasilije/cognee/cognee/.data_storage/data/text_85410f4ad1197f5974aef9aed6f103c8.txt', 'external_metadata': '{}', 'mime_type': 'text/plain', 'type': 'text', 'id': UUID('cdb36296-ac37-550a-b87b-1453084103d2')}), (UUID('9780afb1-dccc-53eb-9a30-c0d4ce033711'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'innovateai labs', 'description': 'Current workplace of Dr. Emily Carter as Senior Data Scientist.', 'pydantic_type': 'Entity', 'id': UUID('9780afb1-dccc-53eb-9a30-c0d4ce033711')}), (UUID('50d0a685-5300-544f-b081-edca4b625886'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'datawave analytics', 'description': 'Previous workplace of Dr. Emily Carter as Data Scientist.', 'pydantic_type': 'Entity', 'id': UUID('50d0a685-5300-544f-b081-edca4b625886')}), (UUID('bd548acf-d36e-5537-b6b0-2ec09de6c9b0'), {'created_at': 1739138120744, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 744000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'predictive analytics', 'description': 'Application of statistical techniques to analyze current and historical data.', 'pydantic_type': 'Entity', 'id': UUID('bd548acf-d36e-5537-b6b0-2ec09de6c9b0')}), (UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), {'created_at': 1739138108494, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 8, 494000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'text': '\\nCV 4: Not Relevant\\nName: David Thompson\\nContact Information:\\n\\nEmail: david.thompson@example.com\\nPhone: (555) 456-7890\\nSummary:\\n\\nCreative Graphic Designer with over 8 years of experience in visual design and branding. Proficient in Adobe Creative Suite and passionate about creating compelling visuals.\\n\\nEducation:\\n\\nB.F.A. in Graphic Design, Rhode Island School of Design (2012)\\nExperience:\\n\\nSenior Graphic Designer, CreativeWorks Agency (2015 – Present)\\nLed design projects for clients in various industries.\\nCreated branding materials that increased client engagement by 30%.\\nGraphic Designer, Visual Innovations (2012 – 2015)\\nDesigned marketing collateral, including brochures, logos, and websites.\\nCollaborated with the marketing team to develop cohesive brand strategies.\\nSkills:\\n\\nDesign Software: Adobe Photoshop, Illustrator, InDesign\\nWeb Design: HTML, CSS\\nSpecialties: Branding and Identity, Typography\\n', 'word_count': 108, 'token_count': 202, 'chunk_index': 0, 'cut_type': 'sentence_cut', 'pydantic_type': 'DocumentChunk', 'id': UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343')}), (UUID('2b53eab9-73b6-533a-bdd5-7f6a47229013'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'design skills', 'description': 'Skills related to graphic design possessed by David Thompson.', 'pydantic_type': 'Entity', 'id': UUID('2b53eab9-73b6-533a-bdd5-7f6a47229013')}), (UUID('37976df5-c5db-5a80-8dcc-780c39cbedb3'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'skill', 'description': 'skill', 'pydantic_type': 'EntityType', 'id': UUID('37976df5-c5db-5a80-8dcc-780c39cbedb3')}), (UUID('ca20272a-3e88-552f-92fe-491e23f117f8'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'creativeworks agency', 'description': 'Agency where David Thompson is currently working as a Senior Graphic Designer.', 'pydantic_type': 'Entity', 'id': UUID('ca20272a-3e88-552f-92fe-491e23f117f8')}), (UUID('60b027fe-7bb4-535d-8a47-19f1a491591b'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'rhode island school of design', 'description': 'Art and design school where David Thompson obtained his degree.', 'pydantic_type': 'Entity', 'id': UUID('60b027fe-7bb4-535d-8a47-19f1a491591b')}), (UUID('912b273c-683d-53ea-8ffe-aadef0b84237'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'educational institution', 'description': 'educational institution', 'pydantic_type': 'EntityType', 'id': UUID('912b273c-683d-53ea-8ffe-aadef0b84237')}), (UUID('a4777597-06c7-562c-bc44-56f74571a01a'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'david thompson', 'description': 'Creative Graphic Designer with over 8 years of experience in visual design and branding.', 'pydantic_type': 'Entity', 'id': UUID('a4777597-06c7-562c-bc44-56f74571a01a')}), (UUID('ce5f3fc6-bff1-55a6-ae3c-b77e3ac60360'), {'created_at': 1739138108466, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 8, 466000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'text_9abf20fa7defd7e49296c51b4e38edf2', 'raw_data_location': '/Users/vasilije/cognee/cognee/.data_storage/data/text_9abf20fa7defd7e49296c51b4e38edf2.txt', 'external_metadata': '{}', 'mime_type': 'text/plain', 'type': 'text', 'id': UUID('ce5f3fc6-bff1-55a6-ae3c-b77e3ac60360')}), (UUID('1e97bb97-4d29-5fb8-863a-15ab51f1dd46'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'visual innovations', 'description': 'Company where David Thompson worked as a Graphic Designer from 2012 to 2015.', 'pydantic_type': 'Entity', 'id': UUID('1e97bb97-4d29-5fb8-863a-15ab51f1dd46')}), (UUID('7e3df89c-2691-580b-84dc-378cb1df3db6'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'adobe creative suite', 'description': 'Suite of design software proficiently used by David Thompson.', 'pydantic_type': 'Entity', 'id': UUID('7e3df89c-2691-580b-84dc-378cb1df3db6')}), (UUID('2d66edc2-1e14-55ab-8304-680b514a597a'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'software', 'description': 'software', 'pydantic_type': 'EntityType', 'id': UUID('2d66edc2-1e14-55ab-8304-680b514a597a')}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), {'created_at': 1739138108498, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 8, 498000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'text': '\\nCV 3: Relevant\\nName: Sarah Nguyen\\nContact Information:\\n\\nEmail: sarah.nguyen@example.com\\nPhone: (555) 345-6789\\nSummary:\\n\\nData Scientist specializing in machine learning with 6 years of experience. Passionate about leveraging data to drive business solutions and improve product performance.\\n\\nEducation:\\n\\nM.S. in Statistics, University of Washington (2014)\\nB.S. in Applied Mathematics, University of Texas at Austin (2012)\\nExperience:\\n\\nData Scientist, QuantumTech (2016 – Present)\\nDesigned and implemented machine learning algorithms for financial forecasting.\\nImproved model efficiency by 20% through algorithm optimization.\\nJunior Data Scientist, DataCore Solutions (2014 – 2016)\\nAssisted in developing predictive models for supply chain optimization.\\nConducted data cleaning and preprocessing on large datasets.\\nSkills:\\n\\nProgramming Languages: Python, R\\nMachine Learning Frameworks: PyTorch, Scikit-Learn\\nStatistical Analysis: SAS, SPSS\\nCloud Platforms: AWS, Azure\\n', 'word_count': 110, 'token_count': 216, 'chunk_index': 0, 'cut_type': 'sentence_cut', 'pydantic_type': 'DocumentChunk', 'id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85')}), (UUID('6b726763-e259-5e91-b505-85284f8ea5ea'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'sas', 'description': 'Statistical analysis tool used by Sarah Nguyen.', 'pydantic_type': 'Entity', 'id': UUID('6b726763-e259-5e91-b505-85284f8ea5ea')}), (UUID('c3ae2063-1a7e-5e88-8448-64bd3c844185'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'statistical analysis tool', 'description': 'statistical analysis tool', 'pydantic_type': 'EntityType', 'id': UUID('c3ae2063-1a7e-5e88-8448-64bd3c844185')}), (UUID('0d980f2a-09dd-581e-acc3-cc2d87c1bab4'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'quantumtech', 'description': 'Current employer of Sarah Nguyen, where she works as a Data Scientist.', 'pydantic_type': 'Entity', 'id': UUID('0d980f2a-09dd-581e-acc3-cc2d87c1bab4')}), (UUID('8b431923-4aa2-5886-a661-b8de0f888a9b'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'azure', 'description': 'Cloud platform used by Sarah Nguyen.', 'pydantic_type': 'Entity', 'id': UUID('8b431923-4aa2-5886-a661-b8de0f888a9b')}), (UUID('d84d991a-dab3-5c36-8806-df076ccb731b'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'cloud platform', 'description': 'cloud platform', 'pydantic_type': 'EntityType', 'id': UUID('d84d991a-dab3-5c36-8806-df076ccb731b')}), (UUID('c0d95499-de6b-5fcf-b0f5-9cbf427ad5c6'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'pytorch', 'description': 'Machine learning framework used by Sarah Nguyen.', 'pydantic_type': 'Entity', 'id': UUID('c0d95499-de6b-5fcf-b0f5-9cbf427ad5c6')}), (UUID('9ffe9ce7-8938-5a5c-8d03-5f1a4c5210a1'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'machine learning framework', 'description': 'machine learning framework', 'pydantic_type': 'EntityType', 'id': UUID('9ffe9ce7-8938-5a5c-8d03-5f1a4c5210a1')}), (UUID('a7410871-cef6-50c8-a473-e2d6fe86d039'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': '(555) 345-6789', 'description': 'Contact Phone for Sarah Nguyen.', 'pydantic_type': 'Entity', 'id': UUID('a7410871-cef6-50c8-a473-e2d6fe86d039')}), (UUID('974b5a05-a3db-5f43-995f-61e05155c1b9'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'phone', 'description': 'phone', 'pydantic_type': 'EntityType', 'id': UUID('974b5a05-a3db-5f43-995f-61e05155c1b9')}), (UUID('c95db510-e2ee-5a00-bded-20bbcb50c492'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'python', 'description': 'Programming language used by Sarah Nguyen.', 'pydantic_type': 'Entity', 'id': UUID('c95db510-e2ee-5a00-bded-20bbcb50c492')}), (UUID('80d409bb-e431-5939-a1ad-3acd96267128'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'programming language', 'description': 'programming language', 'pydantic_type': 'EntityType', 'id': UUID('80d409bb-e431-5939-a1ad-3acd96267128')}), (UUID('dd92c2f4-7895-5c1d-9050-e377ece182bf'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'sarah.nguyen@example.com', 'description': 'Contact Email for Sarah Nguyen.', 'pydantic_type': 'Entity', 'id': UUID('dd92c2f4-7895-5c1d-9050-e377ece182bf')}), (UUID('dfa1b90a-397e-59c3-acf8-071fa2509968'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'email', 'description': 'email', 'pydantic_type': 'EntityType', 'id': UUID('dfa1b90a-397e-59c3-acf8-071fa2509968')}), (UUID('3edcdf3f-25af-57a3-8878-8008bd7ea05a'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'aws', 'description': 'Cloud platform used by Sarah Nguyen.', 'pydantic_type': 'Entity', 'id': UUID('3edcdf3f-25af-57a3-8878-8008bd7ea05a')}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'sarah nguyen', 'description': 'Data Scientist specializing in machine learning with 6 years of experience.', 'pydantic_type': 'Entity', 'id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785')}), (UUID('4bee5f9c-846b-50f7-96fd-3e5889872b10'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'spss', 'description': 'Statistical analysis tool used by Sarah Nguyen.', 'pydantic_type': 'Entity', 'id': UUID('4bee5f9c-846b-50f7-96fd-3e5889872b10')}), (UUID('c689d93a-230a-566a-a4e6-8e461e56586c'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'scikit-learn', 'description': 'Machine learning framework used by Sarah Nguyen.', 'pydantic_type': 'Entity', 'id': UUID('c689d93a-230a-566a-a4e6-8e461e56586c')}), (UUID('f0019b36-93bf-5cc7-9600-f9d09069deac'), {'created_at': 1739138108466, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 8, 466000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'text_f8c7482e727f228001b0046ed68d656f', 'raw_data_location': '/Users/vasilije/cognee/cognee/.data_storage/data/text_f8c7482e727f228001b0046ed68d656f.txt', 'external_metadata': '{}', 'mime_type': 'text/plain', 'type': 'text', 'id': UUID('f0019b36-93bf-5cc7-9600-f9d09069deac')}), (UUID('9acb7f23-e27d-5dd4-8e1b-cc477a1113e6'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'm.s. in statistics, university of washington', 'description': \"Master's degree in Statistics obtained from the University of Washington in 2014.\", 'pydantic_type': 'Entity', 'id': UUID('9acb7f23-e27d-5dd4-8e1b-cc477a1113e6')}), (UUID('14cd23b8-44a8-5f7d-9209-fcec2d2dc222'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'education', 'description': 'education', 'pydantic_type': 'EntityType', 'id': UUID('14cd23b8-44a8-5f7d-9209-fcec2d2dc222')}), (UUID('c7536b57-3e1e-57c2-b503-3c6205957b31'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'b.s. in applied mathematics, university of texas at austin', 'description': \"Bachelor's degree in Applied Mathematics obtained from the University of Texas at Austin in 2012.\", 'pydantic_type': 'Entity', 'id': UUID('c7536b57-3e1e-57c2-b503-3c6205957b31')}), (UUID('39bd9707-8098-52ed-9cbf-bbdd26b963fb'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'r', 'description': 'Programming language used by Sarah Nguyen.', 'pydantic_type': 'Entity', 'id': UUID('39bd9707-8098-52ed-9cbf-bbdd26b963fb')}), (UUID('95ac0551-38fc-5187-a422-533aeb7e8db0'), {'created_at': 1739138120745, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 20, 745000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['name']}, 'name': 'datacore solutions', 'description': 'Previous employer of Sarah Nguyen as a Junior Data Scientist.', 'pydantic_type': 'Entity', 'id': UUID('95ac0551-38fc-5187-a422-533aeb7e8db0')}), (UUID('de387ad4-db59-5e5e-9304-4ce928640167'), {'created_at': 1739138128041, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 28, 41000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'text': 'Senior Data Scientist specializing in Machine Learning', 'id': UUID('de387ad4-db59-5e5e-9304-4ce928640167')}), (UUID('7900efe7-29c5-5683-ac96-1d7df66aec4a'), {'created_at': 1739138128041, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 28, 41000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'text': 'Experienced Data Scientist with expertise in machine learning and statistical analysis, adept at managing extensive datasets and converting data into actionable insights for businesses.', 'id': UUID('7900efe7-29c5-5683-ac96-1d7df66aec4a')}), (UUID('011f3a3d-0f8e-57c9-a304-2de884537798'), {'created_at': 1739138128041, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 28, 41000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'text': 'Sales Manager with extensive experience in increasing revenue and cultivating high-performing teams. Strong leadership and communication abilities.', 'id': UUID('011f3a3d-0f8e-57c9-a304-2de884537798')}), (UUID('e775362d-2d3b-511a-adc3-f07677fdb108'), {'created_at': 1739138128041, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 28, 41000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'text': 'Senior Data Scientist with 8+ years in machine learning and predictive analytics, specializing in advanced algorithms and scalable model deployment.', 'id': UUID('e775362d-2d3b-511a-adc3-f07677fdb108')}), (UUID('fc117dca-b919-516f-9761-94e217a86348'), {'created_at': 1739138128041, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 28, 41000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'text': 'David Thompson is an innovative Graphic Designer with over 8 years of expertise in visual design and branding. Highly skilled in Adobe Creative Suite, he is dedicated to producing impactful visuals.', 'id': UUID('fc117dca-b919-516f-9761-94e217a86348')}), (UUID('6391d484-88e4-5842-b3eb-95a84d942802'), {'created_at': 1739138128041, 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 28, 41000, tzinfo=datetime.timezone.utc), 'version': 1, 'topological_rank': 0, 'metadata': {'index_fields': ['text']}, 'text': 'Data Scientist with a focus on machine learning and 6 years of expertise. Committed to using data to enhance business strategies and optimize product outcomes.', 'id': UUID('6391d484-88e4-5842-b3eb-95a84d942802')})], [(UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), UUID('005aa235-96be-5334-bc8a-cdc1180561e3'), 'contains', {'source_node_id': UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), 'target_node_id': UUID('005aa235-96be-5334-bc8a-cdc1180561e3'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242485, tzinfo=datetime.timezone.utc)}), (UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), UUID('198e2ab8-75e9-5931-97ab-da9a5a8e188c'), 'contains', {'source_node_id': UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), 'target_node_id': UUID('198e2ab8-75e9-5931-97ab-da9a5a8e188c'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242487, tzinfo=datetime.timezone.utc)}), (UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), UUID('8a9b7137-f981-5f96-8df0-dea78cdf1dda'), 'contains', {'source_node_id': UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), 'target_node_id': UUID('8a9b7137-f981-5f96-8df0-dea78cdf1dda'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242488, tzinfo=datetime.timezone.utc)}), (UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), 'contains', {'source_node_id': UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), 'target_node_id': UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242490, tzinfo=datetime.timezone.utc)}), (UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), UUID('453a45c9-14e7-5b73-adb8-55991096fef0'), 'contains', {'source_node_id': UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), 'target_node_id': UUID('453a45c9-14e7-5b73-adb8-55991096fef0'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242491, tzinfo=datetime.timezone.utc)}), (UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), UUID('171a185d-c76c-539b-9520-9d1afd84dc4c'), 'is_part_of', {'source_node_id': UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), 'target_node_id': UUID('171a185d-c76c-539b-9520-9d1afd84dc4c'), 'relationship_name': 'is_part_of', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242492, tzinfo=datetime.timezone.utc)}), (UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), UUID('702366d5-21a2-5f25-a4d9-ea9794bae4fe'), 'contains', {'source_node_id': UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), 'target_node_id': UUID('702366d5-21a2-5f25-a4d9-ea9794bae4fe'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242493, tzinfo=datetime.timezone.utc)}), (UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), UUID('c35072da-4e2e-575e-acd4-5cc4682e3a2b'), 'contains', {'source_node_id': UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), 'target_node_id': UUID('c35072da-4e2e-575e-acd4-5cc4682e3a2b'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242495, tzinfo=datetime.timezone.utc)}), (UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), UUID('fe5ea90b-e586-5492-a7a4-71b918c71a20'), 'contains', {'source_node_id': UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), 'target_node_id': UUID('fe5ea90b-e586-5492-a7a4-71b918c71a20'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242496, tzinfo=datetime.timezone.utc)}), (UUID('005aa235-96be-5334-bc8a-cdc1180561e3'), UUID('f0cf12c5-3311-567e-a047-0116c1fc54e4'), 'is_a', {'source_node_id': UUID('005aa235-96be-5334-bc8a-cdc1180561e3'), 'target_node_id': UUID('f0cf12c5-3311-567e-a047-0116c1fc54e4'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242486, tzinfo=datetime.timezone.utc)}), (UUID('198e2ab8-75e9-5931-97ab-da9a5a8e188c'), UUID('19dd7d4d-a966-5ed5-82a0-6ae377761a29'), 'is_a', {'source_node_id': UUID('198e2ab8-75e9-5931-97ab-da9a5a8e188c'), 'target_node_id': UUID('19dd7d4d-a966-5ed5-82a0-6ae377761a29'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242488, tzinfo=datetime.timezone.utc)}), (UUID('8a9b7137-f981-5f96-8df0-dea78cdf1dda'), UUID('f0cf12c5-3311-567e-a047-0116c1fc54e4'), 'is_a', {'source_node_id': UUID('8a9b7137-f981-5f96-8df0-dea78cdf1dda'), 'target_node_id': UUID('f0cf12c5-3311-567e-a047-0116c1fc54e4'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242489, tzinfo=datetime.timezone.utc)}), (UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), UUID('03e4ce4a-d531-5a2a-a4f7-9fab8955bf60'), 'is_a', {'source_node_id': UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), 'target_node_id': UUID('03e4ce4a-d531-5a2a-a4f7-9fab8955bf60'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242490, tzinfo=datetime.timezone.utc)}), (UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), UUID('198e2ab8-75e9-5931-97ab-da9a5a8e188c'), 'located_in', {'relationship_name': 'located_in', 'source_node_id': UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), 'target_node_id': UUID('198e2ab8-75e9-5931-97ab-da9a5a8e188c'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39554, tzinfo=datetime.timezone.utc)}), (UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), UUID('702366d5-21a2-5f25-a4d9-ea9794bae4fe'), 'requires_qualification', {'relationship_name': 'requires_qualification', 'source_node_id': UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), 'target_node_id': UUID('702366d5-21a2-5f25-a4d9-ea9794bae4fe'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39555, tzinfo=datetime.timezone.utc)}), (UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), UUID('c35072da-4e2e-575e-acd4-5cc4682e3a2b'), 'requires_qualification', {'relationship_name': 'requires_qualification', 'source_node_id': UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), 'target_node_id': UUID('c35072da-4e2e-575e-acd4-5cc4682e3a2b'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39556, tzinfo=datetime.timezone.utc)}), (UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), UUID('005aa235-96be-5334-bc8a-cdc1180561e3'), 'requires_qualification', {'relationship_name': 'requires_qualification', 'source_node_id': UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), 'target_node_id': UUID('005aa235-96be-5334-bc8a-cdc1180561e3'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39556, tzinfo=datetime.timezone.utc)}), (UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), UUID('fe5ea90b-e586-5492-a7a4-71b918c71a20'), 'requires_qualification', {'relationship_name': 'requires_qualification', 'source_node_id': UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), 'target_node_id': UUID('fe5ea90b-e586-5492-a7a4-71b918c71a20'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39557, tzinfo=datetime.timezone.utc)}), (UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), UUID('8a9b7137-f981-5f96-8df0-dea78cdf1dda'), 'requires_qualification', {'relationship_name': 'requires_qualification', 'source_node_id': UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), 'target_node_id': UUID('8a9b7137-f981-5f96-8df0-dea78cdf1dda'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39558, tzinfo=datetime.timezone.utc)}), (UUID('453a45c9-14e7-5b73-adb8-55991096fef0'), UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), 'is_a', {'source_node_id': UUID('453a45c9-14e7-5b73-adb8-55991096fef0'), 'target_node_id': UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242492, tzinfo=datetime.timezone.utc)}), (UUID('453a45c9-14e7-5b73-adb8-55991096fef0'), UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), 'is_hiring', {'relationship_name': 'is_hiring', 'source_node_id': UUID('453a45c9-14e7-5b73-adb8-55991096fef0'), 'target_node_id': UUID('435dbd37-ab20-503c-9e99-ab8b8a3484e5'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39552, tzinfo=datetime.timezone.utc)}), (UUID('702366d5-21a2-5f25-a4d9-ea9794bae4fe'), UUID('f0cf12c5-3311-567e-a047-0116c1fc54e4'), 'is_a', {'source_node_id': UUID('702366d5-21a2-5f25-a4d9-ea9794bae4fe'), 'target_node_id': UUID('f0cf12c5-3311-567e-a047-0116c1fc54e4'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242494, tzinfo=datetime.timezone.utc)}), (UUID('c35072da-4e2e-575e-acd4-5cc4682e3a2b'), UUID('f0cf12c5-3311-567e-a047-0116c1fc54e4'), 'is_a', {'source_node_id': UUID('c35072da-4e2e-575e-acd4-5cc4682e3a2b'), 'target_node_id': UUID('f0cf12c5-3311-567e-a047-0116c1fc54e4'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242495, tzinfo=datetime.timezone.utc)}), (UUID('fe5ea90b-e586-5492-a7a4-71b918c71a20'), UUID('f0cf12c5-3311-567e-a047-0116c1fc54e4'), 'is_a', {'source_node_id': UUID('fe5ea90b-e586-5492-a7a4-71b918c71a20'), 'target_node_id': UUID('f0cf12c5-3311-567e-a047-0116c1fc54e4'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242496, tzinfo=datetime.timezone.utc)}), (UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), UUID('0af613e0-c11b-550d-ada2-2c2aa6550884'), 'contains', {'source_node_id': UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), 'target_node_id': UUID('0af613e0-c11b-550d-ada2-2c2aa6550884'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242497, tzinfo=datetime.timezone.utc)}), (UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), UUID('5534e0b0-d0c4-5ab9-82e9-91bed36f70bd'), 'contains', {'source_node_id': UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), 'target_node_id': UUID('5534e0b0-d0c4-5ab9-82e9-91bed36f70bd'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242499, tzinfo=datetime.timezone.utc)}), (UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), 'contains', {'source_node_id': UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), 'target_node_id': UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242500, tzinfo=datetime.timezone.utc)}), (UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), UUID('175cf99b-d9e7-5d16-a8af-d4ce31ee96d1'), 'is_part_of', {'source_node_id': UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), 'target_node_id': UUID('175cf99b-d9e7-5d16-a8af-d4ce31ee96d1'), 'relationship_name': 'is_part_of', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242501, tzinfo=datetime.timezone.utc)}), (UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), UUID('04a91fef-8a07-5d50-8f1b-46f3afeec497'), 'contains', {'source_node_id': UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), 'target_node_id': UUID('04a91fef-8a07-5d50-8f1b-46f3afeec497'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242502, tzinfo=datetime.timezone.utc)}), (UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), UUID('3f848ed6-902f-5a8e-9577-cb67f8c17acd'), 'contains', {'source_node_id': UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), 'target_node_id': UUID('3f848ed6-902f-5a8e-9577-cb67f8c17acd'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242503, tzinfo=datetime.timezone.utc)}), (UUID('0af613e0-c11b-550d-ada2-2c2aa6550884'), UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'is_a', {'source_node_id': UUID('0af613e0-c11b-550d-ada2-2c2aa6550884'), 'target_node_id': UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242498, tzinfo=datetime.timezone.utc)}), (UUID('5534e0b0-d0c4-5ab9-82e9-91bed36f70bd'), UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'is_a', {'source_node_id': UUID('5534e0b0-d0c4-5ab9-82e9-91bed36f70bd'), 'target_node_id': UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242499, tzinfo=datetime.timezone.utc)}), (UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), 'is_a', {'source_node_id': UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), 'target_node_id': UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242500, tzinfo=datetime.timezone.utc)}), (UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), UUID('5534e0b0-d0c4-5ab9-82e9-91bed36f70bd'), 'earned_degree', {'relationship_name': 'earned_degree', 'source_node_id': UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), 'target_node_id': UUID('5534e0b0-d0c4-5ab9-82e9-91bed36f70bd'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39558, tzinfo=datetime.timezone.utc)}), (UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), UUID('0af613e0-c11b-550d-ada2-2c2aa6550884'), 'earned_degree', {'relationship_name': 'earned_degree', 'source_node_id': UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), 'target_node_id': UUID('0af613e0-c11b-550d-ada2-2c2aa6550884'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39559, tzinfo=datetime.timezone.utc)}), (UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), UUID('04a91fef-8a07-5d50-8f1b-46f3afeec497'), 'works_at', {'relationship_name': 'works_at', 'source_node_id': UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), 'target_node_id': UUID('04a91fef-8a07-5d50-8f1b-46f3afeec497'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39559, tzinfo=datetime.timezone.utc)}), (UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), UUID('3f848ed6-902f-5a8e-9577-cb67f8c17acd'), 'worked_at', {'relationship_name': 'worked_at', 'source_node_id': UUID('73ae630f-7b09-5dce-8c18-45d0a57b30f9'), 'target_node_id': UUID('3f848ed6-902f-5a8e-9577-cb67f8c17acd'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39560, tzinfo=datetime.timezone.utc)}), (UUID('04a91fef-8a07-5d50-8f1b-46f3afeec497'), UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'is_a', {'source_node_id': UUID('04a91fef-8a07-5d50-8f1b-46f3afeec497'), 'target_node_id': UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242502, tzinfo=datetime.timezone.utc)}), (UUID('3f848ed6-902f-5a8e-9577-cb67f8c17acd'), UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'is_a', {'source_node_id': UUID('3f848ed6-902f-5a8e-9577-cb67f8c17acd'), 'target_node_id': UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242503, tzinfo=datetime.timezone.utc)}), (UUID('1895e0c8-8f54-5c45-9f41-8891f0330576'), UUID('5c32691d-c0e4-5378-9aab-dda8b0fa3931'), 'contains', {'source_node_id': UUID('1895e0c8-8f54-5c45-9f41-8891f0330576'), 'target_node_id': UUID('5c32691d-c0e4-5378-9aab-dda8b0fa3931'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242505, tzinfo=datetime.timezone.utc)}), (UUID('1895e0c8-8f54-5c45-9f41-8891f0330576'), UUID('f39d6c00-689b-5fd2-9021-893b28ac6ff2'), 'contains', {'source_node_id': UUID('1895e0c8-8f54-5c45-9f41-8891f0330576'), 'target_node_id': UUID('f39d6c00-689b-5fd2-9021-893b28ac6ff2'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242507, tzinfo=datetime.timezone.utc)}), (UUID('1895e0c8-8f54-5c45-9f41-8891f0330576'), UUID('36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932'), 'contains', {'source_node_id': UUID('1895e0c8-8f54-5c45-9f41-8891f0330576'), 'target_node_id': UUID('36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242508, tzinfo=datetime.timezone.utc)}), (UUID('1895e0c8-8f54-5c45-9f41-8891f0330576'), UUID('7071b7bb-2de3-59ee-83f2-31f8e5c9f9eb'), 'is_part_of', {'source_node_id': UUID('1895e0c8-8f54-5c45-9f41-8891f0330576'), 'target_node_id': UUID('7071b7bb-2de3-59ee-83f2-31f8e5c9f9eb'), 'relationship_name': 'is_part_of', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242509, tzinfo=datetime.timezone.utc)}), (UUID('1895e0c8-8f54-5c45-9f41-8891f0330576'), UUID('94952c93-3432-581b-b6a6-101266596c46'), 'contains', {'source_node_id': UUID('1895e0c8-8f54-5c45-9f41-8891f0330576'), 'target_node_id': UUID('94952c93-3432-581b-b6a6-101266596c46'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242510, tzinfo=datetime.timezone.utc)}), (UUID('5c32691d-c0e4-5378-9aab-dda8b0fa3931'), UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'is_a', {'source_node_id': UUID('5c32691d-c0e4-5378-9aab-dda8b0fa3931'), 'target_node_id': UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242506, tzinfo=datetime.timezone.utc)}), (UUID('f39d6c00-689b-5fd2-9021-893b28ac6ff2'), UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'is_a', {'source_node_id': UUID('f39d6c00-689b-5fd2-9021-893b28ac6ff2'), 'target_node_id': UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242507, tzinfo=datetime.timezone.utc)}), (UUID('f39d6c00-689b-5fd2-9021-893b28ac6ff2'), UUID('36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932'), 'holds_degree', {'relationship_name': 'holds_degree', 'source_node_id': UUID('f39d6c00-689b-5fd2-9021-893b28ac6ff2'), 'target_node_id': UUID('36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39562, tzinfo=datetime.timezone.utc)}), (UUID('36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932'), UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), 'is_a', {'source_node_id': UUID('36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932'), 'target_node_id': UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242509, tzinfo=datetime.timezone.utc)}), (UUID('36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932'), UUID('5c32691d-c0e4-5378-9aab-dda8b0fa3931'), 'works_at', {'relationship_name': 'works_at', 'source_node_id': UUID('36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932'), 'target_node_id': UUID('5c32691d-c0e4-5378-9aab-dda8b0fa3931'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39561, tzinfo=datetime.timezone.utc)}), (UUID('36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932'), UUID('94952c93-3432-581b-b6a6-101266596c46'), 'worked_at', {'relationship_name': 'worked_at', 'source_node_id': UUID('36a5e3c8-c5f5-5ab5-8d59-ea69d8b36932'), 'target_node_id': UUID('94952c93-3432-581b-b6a6-101266596c46'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39561, tzinfo=datetime.timezone.utc)}), (UUID('94952c93-3432-581b-b6a6-101266596c46'), UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'is_a', {'source_node_id': UUID('94952c93-3432-581b-b6a6-101266596c46'), 'target_node_id': UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242510, tzinfo=datetime.timezone.utc)}), (UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), UUID('5187986a-7305-5a63-b057-8f2c097419eb'), 'contains', {'source_node_id': UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), 'target_node_id': UUID('5187986a-7305-5a63-b057-8f2c097419eb'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242511, tzinfo=datetime.timezone.utc)}), (UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), UUID('2c02c93c-9cd1-56b8-9cc0-55ff0b290e57'), 'contains', {'source_node_id': UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), 'target_node_id': UUID('2c02c93c-9cd1-56b8-9cc0-55ff0b290e57'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242513, tzinfo=datetime.timezone.utc)}), (UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), UUID('ce8b394a-b30e-52fc-b80a-6352edc60e5b'), 'contains', {'source_node_id': UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), 'target_node_id': UUID('ce8b394a-b30e-52fc-b80a-6352edc60e5b'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242514, tzinfo=datetime.timezone.utc)}), (UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), UUID('29e771c8-4c3f-52de-9511-6b705878e130'), 'contains', {'source_node_id': UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), 'target_node_id': UUID('29e771c8-4c3f-52de-9511-6b705878e130'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242516, tzinfo=datetime.timezone.utc)}), (UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), UUID('cdb36296-ac37-550a-b87b-1453084103d2'), 'is_part_of', {'source_node_id': UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), 'target_node_id': UUID('cdb36296-ac37-550a-b87b-1453084103d2'), 'relationship_name': 'is_part_of', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242517, tzinfo=datetime.timezone.utc)}), (UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), UUID('9780afb1-dccc-53eb-9a30-c0d4ce033711'), 'contains', {'source_node_id': UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), 'target_node_id': UUID('9780afb1-dccc-53eb-9a30-c0d4ce033711'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242517, tzinfo=datetime.timezone.utc)}), (UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), UUID('50d0a685-5300-544f-b081-edca4b625886'), 'contains', {'source_node_id': UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), 'target_node_id': UUID('50d0a685-5300-544f-b081-edca4b625886'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242519, tzinfo=datetime.timezone.utc)}), (UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), UUID('bd548acf-d36e-5537-b6b0-2ec09de6c9b0'), 'contains', {'source_node_id': UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), 'target_node_id': UUID('bd548acf-d36e-5537-b6b0-2ec09de6c9b0'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242520, tzinfo=datetime.timezone.utc)}), (UUID('5187986a-7305-5a63-b057-8f2c097419eb'), UUID('dd9713b7-dc20-5101-aad0-1c4216811147'), 'is_a', {'source_node_id': UUID('5187986a-7305-5a63-b057-8f2c097419eb'), 'target_node_id': UUID('dd9713b7-dc20-5101-aad0-1c4216811147'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242512, tzinfo=datetime.timezone.utc)}), (UUID('2c02c93c-9cd1-56b8-9cc0-55ff0b290e57'), UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'is_a', {'source_node_id': UUID('2c02c93c-9cd1-56b8-9cc0-55ff0b290e57'), 'target_node_id': UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242514, tzinfo=datetime.timezone.utc)}), (UUID('ce8b394a-b30e-52fc-b80a-6352edc60e5b'), UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'is_a', {'source_node_id': UUID('ce8b394a-b30e-52fc-b80a-6352edc60e5b'), 'target_node_id': UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242515, tzinfo=datetime.timezone.utc)}), (UUID('29e771c8-4c3f-52de-9511-6b705878e130'), UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), 'is_a', {'source_node_id': UUID('29e771c8-4c3f-52de-9511-6b705878e130'), 'target_node_id': UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242516, tzinfo=datetime.timezone.utc)}), (UUID('29e771c8-4c3f-52de-9511-6b705878e130'), UUID('ce8b394a-b30e-52fc-b80a-6352edc60e5b'), 'obtained_degree', {'relationship_name': 'obtained_degree', 'source_node_id': UUID('29e771c8-4c3f-52de-9511-6b705878e130'), 'target_node_id': UUID('ce8b394a-b30e-52fc-b80a-6352edc60e5b'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39562, tzinfo=datetime.timezone.utc)}), (UUID('29e771c8-4c3f-52de-9511-6b705878e130'), UUID('2c02c93c-9cd1-56b8-9cc0-55ff0b290e57'), 'obtained_degree', {'relationship_name': 'obtained_degree', 'source_node_id': UUID('29e771c8-4c3f-52de-9511-6b705878e130'), 'target_node_id': UUID('2c02c93c-9cd1-56b8-9cc0-55ff0b290e57'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39563, tzinfo=datetime.timezone.utc)}), (UUID('29e771c8-4c3f-52de-9511-6b705878e130'), UUID('9780afb1-dccc-53eb-9a30-c0d4ce033711'), 'works_at', {'relationship_name': 'works_at', 'source_node_id': UUID('29e771c8-4c3f-52de-9511-6b705878e130'), 'target_node_id': UUID('9780afb1-dccc-53eb-9a30-c0d4ce033711'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39564, tzinfo=datetime.timezone.utc)}), (UUID('29e771c8-4c3f-52de-9511-6b705878e130'), UUID('50d0a685-5300-544f-b081-edca4b625886'), 'worked_at', {'relationship_name': 'worked_at', 'source_node_id': UUID('29e771c8-4c3f-52de-9511-6b705878e130'), 'target_node_id': UUID('50d0a685-5300-544f-b081-edca4b625886'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39564, tzinfo=datetime.timezone.utc)}), (UUID('29e771c8-4c3f-52de-9511-6b705878e130'), UUID('5187986a-7305-5a63-b057-8f2c097419eb'), 'expertise_in', {'relationship_name': 'expertise_in', 'source_node_id': UUID('29e771c8-4c3f-52de-9511-6b705878e130'), 'target_node_id': UUID('5187986a-7305-5a63-b057-8f2c097419eb'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39565, tzinfo=datetime.timezone.utc)}), (UUID('29e771c8-4c3f-52de-9511-6b705878e130'), UUID('bd548acf-d36e-5537-b6b0-2ec09de6c9b0'), 'expertise_in', {'relationship_name': 'expertise_in', 'source_node_id': UUID('29e771c8-4c3f-52de-9511-6b705878e130'), 'target_node_id': UUID('bd548acf-d36e-5537-b6b0-2ec09de6c9b0'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39565, tzinfo=datetime.timezone.utc)}), (UUID('9780afb1-dccc-53eb-9a30-c0d4ce033711'), UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'is_a', {'source_node_id': UUID('9780afb1-dccc-53eb-9a30-c0d4ce033711'), 'target_node_id': UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242518, tzinfo=datetime.timezone.utc)}), (UUID('50d0a685-5300-544f-b081-edca4b625886'), UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'is_a', {'source_node_id': UUID('50d0a685-5300-544f-b081-edca4b625886'), 'target_node_id': UUID('d3d7b6b4-9b0d-52e8-9e09-a9e9cf4b5a4d'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242519, tzinfo=datetime.timezone.utc)}), (UUID('bd548acf-d36e-5537-b6b0-2ec09de6c9b0'), UUID('dd9713b7-dc20-5101-aad0-1c4216811147'), 'is_a', {'source_node_id': UUID('bd548acf-d36e-5537-b6b0-2ec09de6c9b0'), 'target_node_id': UUID('dd9713b7-dc20-5101-aad0-1c4216811147'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242521, tzinfo=datetime.timezone.utc)}), (UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), UUID('2b53eab9-73b6-533a-bdd5-7f6a47229013'), 'contains', {'source_node_id': UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), 'target_node_id': UUID('2b53eab9-73b6-533a-bdd5-7f6a47229013'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242522, tzinfo=datetime.timezone.utc)}), (UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), UUID('ca20272a-3e88-552f-92fe-491e23f117f8'), 'contains', {'source_node_id': UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), 'target_node_id': UUID('ca20272a-3e88-552f-92fe-491e23f117f8'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242523, tzinfo=datetime.timezone.utc)}), (UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), UUID('60b027fe-7bb4-535d-8a47-19f1a491591b'), 'contains', {'source_node_id': UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), 'target_node_id': UUID('60b027fe-7bb4-535d-8a47-19f1a491591b'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242524, tzinfo=datetime.timezone.utc)}), (UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), UUID('a4777597-06c7-562c-bc44-56f74571a01a'), 'contains', {'source_node_id': UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), 'target_node_id': UUID('a4777597-06c7-562c-bc44-56f74571a01a'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242525, tzinfo=datetime.timezone.utc)}), (UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), UUID('ce5f3fc6-bff1-55a6-ae3c-b77e3ac60360'), 'is_part_of', {'source_node_id': UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), 'target_node_id': UUID('ce5f3fc6-bff1-55a6-ae3c-b77e3ac60360'), 'relationship_name': 'is_part_of', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242527, tzinfo=datetime.timezone.utc)}), (UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), UUID('1e97bb97-4d29-5fb8-863a-15ab51f1dd46'), 'contains', {'source_node_id': UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), 'target_node_id': UUID('1e97bb97-4d29-5fb8-863a-15ab51f1dd46'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242527, tzinfo=datetime.timezone.utc)}), (UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), UUID('7e3df89c-2691-580b-84dc-378cb1df3db6'), 'contains', {'source_node_id': UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), 'target_node_id': UUID('7e3df89c-2691-580b-84dc-378cb1df3db6'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242528, tzinfo=datetime.timezone.utc)}), (UUID('2b53eab9-73b6-533a-bdd5-7f6a47229013'), UUID('37976df5-c5db-5a80-8dcc-780c39cbedb3'), 'is_a', {'source_node_id': UUID('2b53eab9-73b6-533a-bdd5-7f6a47229013'), 'target_node_id': UUID('37976df5-c5db-5a80-8dcc-780c39cbedb3'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242523, tzinfo=datetime.timezone.utc)}), (UUID('ca20272a-3e88-552f-92fe-491e23f117f8'), UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), 'is_a', {'source_node_id': UUID('ca20272a-3e88-552f-92fe-491e23f117f8'), 'target_node_id': UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242524, tzinfo=datetime.timezone.utc)}), (UUID('60b027fe-7bb4-535d-8a47-19f1a491591b'), UUID('912b273c-683d-53ea-8ffe-aadef0b84237'), 'is_a', {'source_node_id': UUID('60b027fe-7bb4-535d-8a47-19f1a491591b'), 'target_node_id': UUID('912b273c-683d-53ea-8ffe-aadef0b84237'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242525, tzinfo=datetime.timezone.utc)}), (UUID('a4777597-06c7-562c-bc44-56f74571a01a'), UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), 'is_a', {'source_node_id': UUID('a4777597-06c7-562c-bc44-56f74571a01a'), 'target_node_id': UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242526, tzinfo=datetime.timezone.utc)}), (UUID('a4777597-06c7-562c-bc44-56f74571a01a'), UUID('60b027fe-7bb4-535d-8a47-19f1a491591b'), 'obtained_degree', {'relationship_name': 'obtained_degree', 'source_node_id': UUID('a4777597-06c7-562c-bc44-56f74571a01a'), 'target_node_id': UUID('60b027fe-7bb4-535d-8a47-19f1a491591b'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39566, tzinfo=datetime.timezone.utc)}), (UUID('a4777597-06c7-562c-bc44-56f74571a01a'), UUID('ca20272a-3e88-552f-92fe-491e23f117f8'), 'employed_at', {'relationship_name': 'employed_at', 'source_node_id': UUID('a4777597-06c7-562c-bc44-56f74571a01a'), 'target_node_id': UUID('ca20272a-3e88-552f-92fe-491e23f117f8'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39566, tzinfo=datetime.timezone.utc)}), (UUID('a4777597-06c7-562c-bc44-56f74571a01a'), UUID('1e97bb97-4d29-5fb8-863a-15ab51f1dd46'), 'previously_employed_at', {'relationship_name': 'previously_employed_at', 'source_node_id': UUID('a4777597-06c7-562c-bc44-56f74571a01a'), 'target_node_id': UUID('1e97bb97-4d29-5fb8-863a-15ab51f1dd46'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39567, tzinfo=datetime.timezone.utc)}), (UUID('a4777597-06c7-562c-bc44-56f74571a01a'), UUID('7e3df89c-2691-580b-84dc-378cb1df3db6'), 'proficient_in', {'relationship_name': 'proficient_in', 'source_node_id': UUID('a4777597-06c7-562c-bc44-56f74571a01a'), 'target_node_id': UUID('7e3df89c-2691-580b-84dc-378cb1df3db6'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39568, tzinfo=datetime.timezone.utc)}), (UUID('a4777597-06c7-562c-bc44-56f74571a01a'), UUID('2b53eab9-73b6-533a-bdd5-7f6a47229013'), 'has_skills', {'relationship_name': 'has_skills', 'source_node_id': UUID('a4777597-06c7-562c-bc44-56f74571a01a'), 'target_node_id': UUID('2b53eab9-73b6-533a-bdd5-7f6a47229013'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39568, tzinfo=datetime.timezone.utc)}), (UUID('1e97bb97-4d29-5fb8-863a-15ab51f1dd46'), UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), 'is_a', {'source_node_id': UUID('1e97bb97-4d29-5fb8-863a-15ab51f1dd46'), 'target_node_id': UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242528, tzinfo=datetime.timezone.utc)}), (UUID('7e3df89c-2691-580b-84dc-378cb1df3db6'), UUID('2d66edc2-1e14-55ab-8304-680b514a597a'), 'is_a', {'source_node_id': UUID('7e3df89c-2691-580b-84dc-378cb1df3db6'), 'target_node_id': UUID('2d66edc2-1e14-55ab-8304-680b514a597a'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242529, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('6b726763-e259-5e91-b505-85284f8ea5ea'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('6b726763-e259-5e91-b505-85284f8ea5ea'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242530, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('0d980f2a-09dd-581e-acc3-cc2d87c1bab4'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('0d980f2a-09dd-581e-acc3-cc2d87c1bab4'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242531, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('8b431923-4aa2-5886-a661-b8de0f888a9b'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('8b431923-4aa2-5886-a661-b8de0f888a9b'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242532, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('c0d95499-de6b-5fcf-b0f5-9cbf427ad5c6'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('c0d95499-de6b-5fcf-b0f5-9cbf427ad5c6'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242533, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('a7410871-cef6-50c8-a473-e2d6fe86d039'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('a7410871-cef6-50c8-a473-e2d6fe86d039'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242534, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('c95db510-e2ee-5a00-bded-20bbcb50c492'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('c95db510-e2ee-5a00-bded-20bbcb50c492'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242535, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('dd92c2f4-7895-5c1d-9050-e377ece182bf'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('dd92c2f4-7895-5c1d-9050-e377ece182bf'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242537, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('3edcdf3f-25af-57a3-8878-8008bd7ea05a'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('3edcdf3f-25af-57a3-8878-8008bd7ea05a'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242538, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242539, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('4bee5f9c-846b-50f7-96fd-3e5889872b10'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('4bee5f9c-846b-50f7-96fd-3e5889872b10'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242540, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('c689d93a-230a-566a-a4e6-8e461e56586c'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('c689d93a-230a-566a-a4e6-8e461e56586c'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242541, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('f0019b36-93bf-5cc7-9600-f9d09069deac'), 'is_part_of', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('f0019b36-93bf-5cc7-9600-f9d09069deac'), 'relationship_name': 'is_part_of', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242543, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('9acb7f23-e27d-5dd4-8e1b-cc477a1113e6'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('9acb7f23-e27d-5dd4-8e1b-cc477a1113e6'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242543, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('c7536b57-3e1e-57c2-b503-3c6205957b31'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('c7536b57-3e1e-57c2-b503-3c6205957b31'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242544, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('39bd9707-8098-52ed-9cbf-bbdd26b963fb'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('39bd9707-8098-52ed-9cbf-bbdd26b963fb'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242545, tzinfo=datetime.timezone.utc)}), (UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), UUID('95ac0551-38fc-5187-a422-533aeb7e8db0'), 'contains', {'source_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'target_node_id': UUID('95ac0551-38fc-5187-a422-533aeb7e8db0'), 'relationship_name': 'contains', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242547, tzinfo=datetime.timezone.utc)}), (UUID('6b726763-e259-5e91-b505-85284f8ea5ea'), UUID('c3ae2063-1a7e-5e88-8448-64bd3c844185'), 'is_a', {'source_node_id': UUID('6b726763-e259-5e91-b505-85284f8ea5ea'), 'target_node_id': UUID('c3ae2063-1a7e-5e88-8448-64bd3c844185'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242530, tzinfo=datetime.timezone.utc)}), (UUID('0d980f2a-09dd-581e-acc3-cc2d87c1bab4'), UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), 'is_a', {'source_node_id': UUID('0d980f2a-09dd-581e-acc3-cc2d87c1bab4'), 'target_node_id': UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242531, tzinfo=datetime.timezone.utc)}), (UUID('8b431923-4aa2-5886-a661-b8de0f888a9b'), UUID('d84d991a-dab3-5c36-8806-df076ccb731b'), 'is_a', {'source_node_id': UUID('8b431923-4aa2-5886-a661-b8de0f888a9b'), 'target_node_id': UUID('d84d991a-dab3-5c36-8806-df076ccb731b'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242532, tzinfo=datetime.timezone.utc)}), (UUID('c0d95499-de6b-5fcf-b0f5-9cbf427ad5c6'), UUID('9ffe9ce7-8938-5a5c-8d03-5f1a4c5210a1'), 'is_a', {'source_node_id': UUID('c0d95499-de6b-5fcf-b0f5-9cbf427ad5c6'), 'target_node_id': UUID('9ffe9ce7-8938-5a5c-8d03-5f1a4c5210a1'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242534, tzinfo=datetime.timezone.utc)}), (UUID('a7410871-cef6-50c8-a473-e2d6fe86d039'), UUID('974b5a05-a3db-5f43-995f-61e05155c1b9'), 'is_a', {'source_node_id': UUID('a7410871-cef6-50c8-a473-e2d6fe86d039'), 'target_node_id': UUID('974b5a05-a3db-5f43-995f-61e05155c1b9'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242535, tzinfo=datetime.timezone.utc)}), (UUID('c95db510-e2ee-5a00-bded-20bbcb50c492'), UUID('80d409bb-e431-5939-a1ad-3acd96267128'), 'is_a', {'source_node_id': UUID('c95db510-e2ee-5a00-bded-20bbcb50c492'), 'target_node_id': UUID('80d409bb-e431-5939-a1ad-3acd96267128'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242536, tzinfo=datetime.timezone.utc)}), (UUID('dd92c2f4-7895-5c1d-9050-e377ece182bf'), UUID('dfa1b90a-397e-59c3-acf8-071fa2509968'), 'is_a', {'source_node_id': UUID('dd92c2f4-7895-5c1d-9050-e377ece182bf'), 'target_node_id': UUID('dfa1b90a-397e-59c3-acf8-071fa2509968'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242537, tzinfo=datetime.timezone.utc)}), (UUID('3edcdf3f-25af-57a3-8878-8008bd7ea05a'), UUID('d84d991a-dab3-5c36-8806-df076ccb731b'), 'is_a', {'source_node_id': UUID('3edcdf3f-25af-57a3-8878-8008bd7ea05a'), 'target_node_id': UUID('d84d991a-dab3-5c36-8806-df076ccb731b'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242538, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), 'is_a', {'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('d072ba0f-e1a9-58bf-9974-e1802adc8134'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242540, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('dd92c2f4-7895-5c1d-9050-e377ece182bf'), 'has_email', {'relationship_name': 'has_email', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('dd92c2f4-7895-5c1d-9050-e377ece182bf'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39568, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('a7410871-cef6-50c8-a473-e2d6fe86d039'), 'has_phone', {'relationship_name': 'has_phone', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('a7410871-cef6-50c8-a473-e2d6fe86d039'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39569, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('9acb7f23-e27d-5dd4-8e1b-cc477a1113e6'), 'has_education', {'relationship_name': 'has_education', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('9acb7f23-e27d-5dd4-8e1b-cc477a1113e6'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39569, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('c7536b57-3e1e-57c2-b503-3c6205957b31'), 'has_education', {'relationship_name': 'has_education', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('c7536b57-3e1e-57c2-b503-3c6205957b31'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39570, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('0d980f2a-09dd-581e-acc3-cc2d87c1bab4'), 'works_at', {'relationship_name': 'works_at', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('0d980f2a-09dd-581e-acc3-cc2d87c1bab4'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39570, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('95ac0551-38fc-5187-a422-533aeb7e8db0'), 'worked_at', {'relationship_name': 'worked_at', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('95ac0551-38fc-5187-a422-533aeb7e8db0'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39571, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('c95db510-e2ee-5a00-bded-20bbcb50c492'), 'has_skill', {'relationship_name': 'has_skill', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('c95db510-e2ee-5a00-bded-20bbcb50c492'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39572, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('39bd9707-8098-52ed-9cbf-bbdd26b963fb'), 'has_skill', {'relationship_name': 'has_skill', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('39bd9707-8098-52ed-9cbf-bbdd26b963fb'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39572, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('c0d95499-de6b-5fcf-b0f5-9cbf427ad5c6'), 'has_skill', {'relationship_name': 'has_skill', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('c0d95499-de6b-5fcf-b0f5-9cbf427ad5c6'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39573, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('c689d93a-230a-566a-a4e6-8e461e56586c'), 'has_skill', {'relationship_name': 'has_skill', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('c689d93a-230a-566a-a4e6-8e461e56586c'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39573, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('6b726763-e259-5e91-b505-85284f8ea5ea'), 'has_skill', {'relationship_name': 'has_skill', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('6b726763-e259-5e91-b505-85284f8ea5ea'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39574, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('4bee5f9c-846b-50f7-96fd-3e5889872b10'), 'has_skill', {'relationship_name': 'has_skill', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('4bee5f9c-846b-50f7-96fd-3e5889872b10'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39574, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('3edcdf3f-25af-57a3-8878-8008bd7ea05a'), 'has_skill', {'relationship_name': 'has_skill', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('3edcdf3f-25af-57a3-8878-8008bd7ea05a'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39574, tzinfo=datetime.timezone.utc)}), (UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), UUID('8b431923-4aa2-5886-a661-b8de0f888a9b'), 'has_skill', {'relationship_name': 'has_skill', 'source_node_id': UUID('4d8dda57-2681-5264-a2bd-e2ddfe66a785'), 'target_node_id': UUID('8b431923-4aa2-5886-a661-b8de0f888a9b'), 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 24, 39575, tzinfo=datetime.timezone.utc)}), (UUID('4bee5f9c-846b-50f7-96fd-3e5889872b10'), UUID('c3ae2063-1a7e-5e88-8448-64bd3c844185'), 'is_a', {'source_node_id': UUID('4bee5f9c-846b-50f7-96fd-3e5889872b10'), 'target_node_id': UUID('c3ae2063-1a7e-5e88-8448-64bd3c844185'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242541, tzinfo=datetime.timezone.utc)}), (UUID('c689d93a-230a-566a-a4e6-8e461e56586c'), UUID('9ffe9ce7-8938-5a5c-8d03-5f1a4c5210a1'), 'is_a', {'source_node_id': UUID('c689d93a-230a-566a-a4e6-8e461e56586c'), 'target_node_id': UUID('9ffe9ce7-8938-5a5c-8d03-5f1a4c5210a1'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242542, tzinfo=datetime.timezone.utc)}), (UUID('9acb7f23-e27d-5dd4-8e1b-cc477a1113e6'), UUID('14cd23b8-44a8-5f7d-9209-fcec2d2dc222'), 'is_a', {'source_node_id': UUID('9acb7f23-e27d-5dd4-8e1b-cc477a1113e6'), 'target_node_id': UUID('14cd23b8-44a8-5f7d-9209-fcec2d2dc222'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242544, tzinfo=datetime.timezone.utc)}), (UUID('c7536b57-3e1e-57c2-b503-3c6205957b31'), UUID('14cd23b8-44a8-5f7d-9209-fcec2d2dc222'), 'is_a', {'source_node_id': UUID('c7536b57-3e1e-57c2-b503-3c6205957b31'), 'target_node_id': UUID('14cd23b8-44a8-5f7d-9209-fcec2d2dc222'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242545, tzinfo=datetime.timezone.utc)}), (UUID('39bd9707-8098-52ed-9cbf-bbdd26b963fb'), UUID('80d409bb-e431-5939-a1ad-3acd96267128'), 'is_a', {'source_node_id': UUID('39bd9707-8098-52ed-9cbf-bbdd26b963fb'), 'target_node_id': UUID('80d409bb-e431-5939-a1ad-3acd96267128'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242546, tzinfo=datetime.timezone.utc)}), (UUID('95ac0551-38fc-5187-a422-533aeb7e8db0'), UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), 'is_a', {'source_node_id': UUID('95ac0551-38fc-5187-a422-533aeb7e8db0'), 'target_node_id': UUID('a6ed6bf1-fe31-5dfe-8ab4-484691fdf219'), 'relationship_name': 'is_a', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242547, tzinfo=datetime.timezone.utc)}), (UUID('de387ad4-db59-5e5e-9304-4ce928640167'), UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), 'made_from', {'source_node_id': UUID('de387ad4-db59-5e5e-9304-4ce928640167'), 'target_node_id': UUID('6fd664a9-0f63-5010-b252-28cf0a2427b6'), 'relationship_name': 'made_from', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242482, tzinfo=datetime.timezone.utc)}), (UUID('7900efe7-29c5-5683-ac96-1d7df66aec4a'), UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), 'made_from', {'source_node_id': UUID('7900efe7-29c5-5683-ac96-1d7df66aec4a'), 'target_node_id': UUID('9abf5135-7560-5815-9fc4-2bc94ef06f84'), 'relationship_name': 'made_from', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242497, tzinfo=datetime.timezone.utc)}), (UUID('011f3a3d-0f8e-57c9-a304-2de884537798'), UUID('1895e0c8-8f54-5c45-9f41-8891f0330576'), 'made_from', {'source_node_id': UUID('011f3a3d-0f8e-57c9-a304-2de884537798'), 'target_node_id': UUID('1895e0c8-8f54-5c45-9f41-8891f0330576'), 'relationship_name': 'made_from', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242504, tzinfo=datetime.timezone.utc)}), (UUID('e775362d-2d3b-511a-adc3-f07677fdb108'), UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), 'made_from', {'source_node_id': UUID('e775362d-2d3b-511a-adc3-f07677fdb108'), 'target_node_id': UUID('bae8a2f4-0bb7-5ef5-bd7e-19e279a1baf7'), 'relationship_name': 'made_from', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242511, tzinfo=datetime.timezone.utc)}), (UUID('fc117dca-b919-516f-9761-94e217a86348'), UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), 'made_from', {'source_node_id': UUID('fc117dca-b919-516f-9761-94e217a86348'), 'target_node_id': UUID('b96b0301-3c8b-5261-87d4-4d3d427a2343'), 'relationship_name': 'made_from', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242522, tzinfo=datetime.timezone.utc)}), (UUID('6391d484-88e4-5842-b3eb-95a84d942802'), UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'made_from', {'source_node_id': UUID('6391d484-88e4-5842-b3eb-95a84d942802'), 'target_node_id': UUID('4320268e-16b7-5866-baa5-2eaa07fbaf85'), 'relationship_name': 'made_from', 'updated_at': datetime.datetime(2025, 2, 9, 21, 55, 31, 242529, tzinfo=datetime.timezone.utc)})])INFO:cognee.modules.visualization.cognee_network_visualization:Graph visualization saved as /Users/vasilije/cognee/notebooks/.artifacts/graph_visualization.htmlINFO:root:The HTML file has been stored at path: /Users/vasilije/cognee/notebooks/.artifacts/graph_visualization.html"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import pathlib\n",
|
||
"import os\n",
|
||
"from cognee.api.v1.visualize import visualize_graph\n",
|
||
"\n",
|
||
"# Use the current working directory instead of __file__:\n",
|
||
"notebook_dir = pathlib.Path.cwd()\n",
|
||
"\n",
|
||
"graph_file_path = (notebook_dir / \".artifacts\" / \"graph_visualization.html\").resolve()\n",
|
||
"\n",
|
||
"# Make sure to convert to string if visualize_graph expects a string\n",
|
||
"b = await visualize_graph(str(graph_file_path))"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 40,
|
||
"id": "9f941848c418d713",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:42:59.312945Z",
|
||
"start_time": "2025-02-09T21:42:59.311015Z"
|
||
}
|
||
},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"serving at port 8001\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"import http.server\n",
|
||
"import socketserver\n",
|
||
"from threading import Thread\n",
|
||
"\n",
|
||
"PORT = 8001\n",
|
||
"\n",
|
||
"\n",
|
||
"class ServerThread(Thread):\n",
|
||
" def run(self):\n",
|
||
" Handler = http.server.SimpleHTTPRequestHandler\n",
|
||
" with socketserver.TCPServer((\"\", PORT), Handler) as httpd:\n",
|
||
" print(\"serving at port\", PORT)\n",
|
||
" httpd.serve_forever()\n",
|
||
"\n",
|
||
"\n",
|
||
"ServerThread().start()"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"id": "77d5794d-3561-4c9c-a001-df7d6b0c1968",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"INFO:httpx:HTTP Request: GET https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json \"HTTP/1.1 200 OK\"/Users/vasilije/cognee/.venv/lib/python3.11/site-packages/pydantic/_internal/_config.py:341: UserWarning: Valid config keys have changed in V2:\n",
|
||
"* 'fields' has been removed\n",
|
||
" warnings.warn(message, UserWarning)\n"
|
||
]
|
||
},
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"Visualization server running at: http://0.0.0.0:8002\n"
|
||
]
|
||
},
|
||
{
|
||
"data": {
|
||
"text/plain": [
|
||
"<function cognee.shared.utils.start_visualization_server.<locals>.shutdown()>"
|
||
]
|
||
},
|
||
"execution_count": 1,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
},
|
||
{
|
||
"name": "stderr",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"127.0.0.1 - - [09/Feb/2025 20:43:16] \"GET /.artifacts/graph_visualization.html HTTP/1.1\" 200 -\n",
|
||
"127.0.0.1 - - [09/Feb/2025 20:43:17] code 404, message File not found\n",
|
||
"127.0.0.1 - - [09/Feb/2025 20:43:17] \"GET /favicon.ico HTTP/1.1\" 404 -\n",
|
||
"127.0.0.1 - - [09/Feb/2025 20:46:43] \"GET /.artifacts/graph_visualization.html HTTP/1.1\" 200 -\n",
|
||
"127.0.0.1 - - [09/Feb/2025 20:47:14] \"GET /.artifacts/graph_visualization.html HTTP/1.1\" 200 -\n",
|
||
"127.0.0.1 - - [09/Feb/2025 20:47:37] \"GET /.artifacts/graph_visualization.html HTTP/1.1\" 304 -\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"from cognee.api.v1.visualize import visualization_server\n",
|
||
"\n",
|
||
"visualization_server(port=8002)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "765bc42a143e98af",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2025-02-09T21:46:07.783693Z",
|
||
"start_time": "2025-02-09T21:46:07.780709Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "e1382358-433c-4cd0-8535-9e103f821034",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 17,
|
||
"id": "6332d5bc-882f-49d5-8496-582e3954567a",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"\n",
|
||
" <iframe\n",
|
||
" width=\"800\"\n",
|
||
" height=\"600\"\n",
|
||
" src=\"http://127.0.0.1:8002/.artifacts/graph_visualization.html\"\n",
|
||
" frameborder=\"0\"\n",
|
||
" allowfullscreen\n",
|
||
" \n",
|
||
" ></iframe>\n",
|
||
" "
|
||
],
|
||
"text/plain": [
|
||
"<IPython.lib.display.IFrame at 0x358677190>"
|
||
]
|
||
},
|
||
"execution_count": 17,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"from IPython.display import IFrame, display, HTML\n",
|
||
"\n",
|
||
"IFrame(\"http://127.0.0.1:8002/.artifacts/graph_visualization.html\", width=800, height=600)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 20,
|
||
"id": "030c6aac-650c-42dc-a89b-d21a5f422474",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"data": {
|
||
"text/html": [
|
||
"\n",
|
||
" <iframe\n",
|
||
" width=\"800\"\n",
|
||
" height=\"600\"\n",
|
||
" src=\"http://127.0.0.1:8002/.artifacts/graph_visualization.html\"\n",
|
||
" frameborder=\"0\"\n",
|
||
" allowfullscreen\n",
|
||
" \n",
|
||
" ></iframe>\n",
|
||
" "
|
||
],
|
||
"text/plain": [
|
||
"<IPython.lib.display.IFrame at 0x35fbbf610>"
|
||
]
|
||
},
|
||
"execution_count": 20,
|
||
"metadata": {},
|
||
"output_type": "execute_result"
|
||
}
|
||
],
|
||
"source": [
|
||
"from IPython.display import IFrame, display, HTML\n",
|
||
"\n",
|
||
"IFrame(\"http://127.0.0.1:8002/.artifacts/graph_visualization.html\", width=800, height=600)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"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."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "080389e5",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-29T16:55:51.378129Z",
|
||
"start_time": "2024-12-29T16:55:46.922951Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"import os\n",
|
||
"from cognee.shared.utils import render_graph\n",
|
||
"from cognee.infrastructure.databases.graph import get_graph_engine\n",
|
||
"import graphistry\n",
|
||
"\n",
|
||
"# from dotenv import load_dotenv\n",
|
||
"graphistry.login(\n",
|
||
" username=os.getenv(\"GRAPHISTRY_USERNAME\"), password=os.getenv(\"GRAPHISTRY_PASSWORD\")\n",
|
||
")\n",
|
||
"\n",
|
||
"graph_engine = await get_graph_engine()\n",
|
||
"\n",
|
||
"graph_url = await render_graph(graph_engine.graph)\n",
|
||
"print(graph_url)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "8f69caa0e353a889",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-29T16:56:06.571404Z",
|
||
"start_time": "2024-12-29T16:56:06.569280Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"graph_engine = await get_graph_engine()\n",
|
||
"print(graph_url)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "59e6c3c3",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### We can also do a search on the data to explore the knowledge."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "e5e7dfc8",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T13:44:16.575843Z",
|
||
"start_time": "2024-12-24T13:44:16.047897Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"async def search(\n",
|
||
" vector_engine,\n",
|
||
" collection_name: str,\n",
|
||
" query_text: str = None,\n",
|
||
"):\n",
|
||
" query_vector = (await vector_engine.embedding_engine.embed_text([query_text]))[0]\n",
|
||
"\n",
|
||
" connection = await vector_engine.get_connection()\n",
|
||
" collection = await connection.open_table(collection_name)\n",
|
||
"\n",
|
||
" results = await collection.vector_search(query_vector).limit(10).to_pandas()\n",
|
||
"\n",
|
||
" result_values = list(results.to_dict(\"index\").values())\n",
|
||
"\n",
|
||
" return [\n",
|
||
" dict(\n",
|
||
" id=str(result[\"id\"]),\n",
|
||
" payload=result[\"payload\"],\n",
|
||
" score=result[\"_distance\"],\n",
|
||
" )\n",
|
||
" for result in result_values\n",
|
||
" ]\n",
|
||
"\n",
|
||
"\n",
|
||
"from cognee.infrastructure.databases.vector import get_vector_engine\n",
|
||
"\n",
|
||
"vector_engine = get_vector_engine()\n",
|
||
"results = await search(vector_engine, \"Entity_name\", \"sarah.nguyen@example.com\")\n",
|
||
"for result in results:\n",
|
||
" print(result)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "81fa2b00",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### We normalize search output scores so the lower the score of the search result is the higher the chance that it's what you're looking for. In the example above we have searched for node entities in the knowledge graph related to \"sarah.nguyen@example.com\""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "1b94ff96",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### In the example bellow we'll use cognee search to summarize information regarding the node most related to \"sarah.nguyen@example.com\" in the knowledge graph"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "21a3e9a6",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from cognee.api.v1.search import SearchType\n",
|
||
"\n",
|
||
"node = (await vector_engine.search(\"Entity_name\", \"sarah.nguyen@example.com\"))[0]\n",
|
||
"node_name = node.payload[\"text\"]\n",
|
||
"\n",
|
||
"search_results = await cognee.search(query_type=SearchType.SUMMARIES, query_text=node_name)\n",
|
||
"print(\"\\n\\Extracted summaries are:\\n\")\n",
|
||
"for result in search_results:\n",
|
||
" print(f\"{result}\\n\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "fd6e5fe2",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### In this example we'll use cognee search to find chunks in which the node most related to \"sarah.nguyen@example.com\" is a part of"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "c7a8abff",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"search_results = await cognee.search(query_type=SearchType.CHUNKS, query_text=node_name)\n",
|
||
"print(\"\\n\\nExtracted chunks are:\\n\")\n",
|
||
"for result in search_results:\n",
|
||
" print(f\"{result}\\n\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "47f0112f",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### In this example we'll use cognee search to give us insights from the knowledge graph related to the node most related to \"sarah.nguyen@example.com\""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "706a3954",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"search_results = await cognee.search(query_type=SearchType.INSIGHTS, query_text=node_name)\n",
|
||
"print(\"\\n\\nExtracted sentences are:\\n\")\n",
|
||
"for result in search_results:\n",
|
||
" print(f\"{result}\\n\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "c9ffa271",
|
||
"metadata": {},
|
||
"source": [
|
||
"### Now let's add evals"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "afae18ac6a794925",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T13:46:09.644509Z",
|
||
"start_time": "2024-12-24T13:46:04.538592Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"!pip install \"cognee[deepeval]\""
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "5f36b67668fdb646",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T15:29:11.123483Z",
|
||
"start_time": "2024-12-24T15:29:11.120888Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"source": [
|
||
"from evals.eval_on_hotpot import deepeval_answers, answer_qa_instance\n",
|
||
"from evals.qa_dataset_utils import load_qa_dataset\n",
|
||
"from evals.qa_metrics_utils import get_metrics\n",
|
||
"from evals.qa_context_provider_utils import qa_context_providers\n",
|
||
"from pathlib import Path\n",
|
||
"from tqdm import tqdm\n",
|
||
"import statistics\n",
|
||
"import random"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "de91ee0a",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"num_samples = 10 # With cognee, it takes ~1m10s per sample\n",
|
||
"dataset_name_or_filename = \"hotpotqa\"\n",
|
||
"dataset = load_qa_dataset(dataset_name_or_filename)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "04bbea26",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"context_provider_name = \"cognee\"\n",
|
||
"context_provider = qa_context_providers[context_provider_name]"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "1194d32c",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"random.seed(42)\n",
|
||
"instances = dataset if not num_samples else random.sample(dataset, num_samples)\n",
|
||
"\n",
|
||
"out_path = \"out\"\n",
|
||
"if not Path(out_path).exists():\n",
|
||
" Path(out_path).mkdir()\n",
|
||
"contexts_filename = out_path / Path(\n",
|
||
" f\"contexts_{dataset_name_or_filename.split('.')[0]}_{context_provider_name}.json\"\n",
|
||
")\n",
|
||
"\n",
|
||
"answers = []\n",
|
||
"for instance in tqdm(instances, desc=\"Getting answers\"):\n",
|
||
" answer = await answer_qa_instance(instance, context_provider, contexts_filename)\n",
|
||
" answers.append(answer)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "7e8e491a",
|
||
"metadata": {},
|
||
"source": [
|
||
"#### Define Metrics for Evaluation and Calculate Score\n",
|
||
"**Options**: \n",
|
||
"- **Correctness**: Is the actual output factually correct based on the expected output?\n",
|
||
"- **Comprehensiveness**: How much detail does the answer provide to cover all aspects and details of the question?\n",
|
||
"- **Diversity**: How varied and rich is the answer in providing different perspectives and insights on the question?\n",
|
||
"- **Empowerment**: How well does the answer help the reader understand and make informed judgements about the topic?\n",
|
||
"- **Directness**: How specifically and clearly does the answer address the question?\n",
|
||
"- **F1 Score**: the harmonic mean of the precision and recall, using word-level Exact Match\n",
|
||
"- **EM Score**: the rate at which the predicted strings exactly match their references, ignoring white spaces and capitalization."
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "a65c70dd",
|
||
"metadata": {},
|
||
"source": [
|
||
"##### Calculate `\"Correctness\"`"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "ede84200",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"metric_name_list = [\"Correctness\"]\n",
|
||
"eval_metrics = get_metrics(metric_name_list)\n",
|
||
"eval_results = await deepeval_answers(instances, answers, eval_metrics[\"deepeval_metrics\"])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "df790d87",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"Correctness = statistics.mean(\n",
|
||
" [result.metrics_data[0].score for result in eval_results.test_results]\n",
|
||
")\n",
|
||
"print(Correctness)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "a3dad48f",
|
||
"metadata": {},
|
||
"source": [
|
||
"##### Calculating `\"Comprehensiveness\"`"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "20f98ae2",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"metric_name_list = [\"Comprehensiveness\"]\n",
|
||
"eval_metrics = get_metrics(metric_name_list)\n",
|
||
"eval_results = await deepeval_answers(instances, answers, eval_metrics[\"deepeval_metrics\"])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "b35110d3",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"Comprehensiveness = statistics.mean(\n",
|
||
" [result.metrics_data[0].score for result in eval_results.test_results]\n",
|
||
")\n",
|
||
"print(Comprehensiveness)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "9020eaaa",
|
||
"metadata": {},
|
||
"source": [
|
||
"##### Calculating `\"Diversity\"`"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "f5aa9c70",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"metric_name_list = [\"Diversity\"]\n",
|
||
"eval_metrics = get_metrics(metric_name_list)\n",
|
||
"eval_results = await deepeval_answers(instances, answers, eval_metrics[\"deepeval_metrics\"])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "fa460a81",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"Diversity = statistics.mean([result.metrics_data[0].score for result in eval_results.test_results])\n",
|
||
"print(Diversity)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "636b37f2",
|
||
"metadata": {},
|
||
"source": [
|
||
"##### Calculating`\"Empowerment\"`"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "1a685df3",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"metric_name_list = [\"Empowerment\"]\n",
|
||
"eval_metrics = get_metrics(metric_name_list)\n",
|
||
"eval_results = await deepeval_answers(instances, answers, eval_metrics[\"deepeval_metrics\"])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "44125ae7",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"Empowerment = statistics.mean(\n",
|
||
" [result.metrics_data[0].score for result in eval_results.test_results]\n",
|
||
")\n",
|
||
"print(Empowerment)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "5837fa32",
|
||
"metadata": {},
|
||
"source": [
|
||
"##### Calculating `\"Directness\"`"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "1f6b32b6",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"metric_name_list = [\"Directness\"]\n",
|
||
"eval_metrics = get_metrics(metric_name_list)\n",
|
||
"eval_results = await deepeval_answers(instances, answers, eval_metrics[\"deepeval_metrics\"])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "91c79165",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"Directness = statistics.mean([result.metrics_data[0].score for result in eval_results.test_results])\n",
|
||
"print(Directness)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "912293c4",
|
||
"metadata": {},
|
||
"source": [
|
||
"##### Calculating `\"F1\"`"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "a80d6f2e",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"metric_name_list = [\"F1\"]\n",
|
||
"eval_metrics = get_metrics(metric_name_list)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "4e644f1f",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"eval_results = await deepeval_answers(instances, answers, eval_metrics[\"deepeval_metrics\"])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "12d00f5e",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"F1_score = statistics.mean([result.metrics_data[0].score for result in eval_results.test_results])\n",
|
||
"print(F1_score)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "68680dd7",
|
||
"metadata": {},
|
||
"source": [
|
||
"##### Calculating `\"EM\"`"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "dfe28005",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"metric_name_list = [\"EM\"]\n",
|
||
"eval_metrics = get_metrics(metric_name_list)\n",
|
||
"eval_results = await deepeval_answers(instances, answers, eval_metrics[\"deepeval_metrics\"])"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "01dffe4d",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"EM = statistics.mean([result.metrics_data[0].score for result in eval_results.test_results])\n",
|
||
"print(EM)"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "markdown",
|
||
"id": "288ab570",
|
||
"metadata": {},
|
||
"source": [
|
||
"# Give us a star if you like it!\n",
|
||
"https://github.com/topoteretes/cognee"
|
||
]
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "Python 3 (ipykernel)",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.11.0"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|