1258 lines
627 KiB
Text
1258 lines
627 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": null,
|
||
"id": "df16431d0f48b006",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T11:53:59.351640Z",
|
||
"start_time": "2024-12-24T11:53:59.347420Z"
|
||
}
|
||
},
|
||
"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",
|
||
"\"\"\"\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "9086abf3af077ab4",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T11:53:59.365410Z",
|
||
"start_time": "2024-12-24T11:53:59.363662Z"
|
||
}
|
||
},
|
||
"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": null,
|
||
"id": "a9de0cc07f798b7f",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T11:53:59.372957Z",
|
||
"start_time": "2024-12-24T11:53:59.371152Z"
|
||
}
|
||
},
|
||
"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": null,
|
||
"id": "185ff1c102d06111",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T11:53:59.961140Z",
|
||
"start_time": "2024-12-24T11:53:59.959103Z"
|
||
}
|
||
},
|
||
"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": null,
|
||
"id": "d55ce4c58f8efb67",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T11:54:00.656495Z",
|
||
"start_time": "2024-12-24T11:54:00.654716Z"
|
||
}
|
||
},
|
||
"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": null,
|
||
"id": "ca4ecc32721ad332",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T11:54:01.184899Z",
|
||
"start_time": "2024-12-24T11:54:01.183028Z"
|
||
}
|
||
},
|
||
"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": null,
|
||
"id": "bce39dc6",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T11:54:04.417315Z",
|
||
"start_time": "2024-12-24T11:54:04.414132Z"
|
||
}
|
||
},
|
||
"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": null,
|
||
"id": "9f1a1dbd",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T11:54:16.672999Z",
|
||
"start_time": "2024-12-24T11:54:07.425202Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"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": null,
|
||
"id": "904df61ba484a8e5",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T11:54:28.313862Z",
|
||
"start_time": "2024-12-24T11:54:23.756587Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"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": null,
|
||
"id": "7c431fdef4921ae0",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T11:54:44.728010Z",
|
||
"start_time": "2024-12-24T11:54:44.723877Z"
|
||
}
|
||
},
|
||
"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 check_permissions_on_documents, classify_documents, extract_chunks_from_documents\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",
|
||
"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(extract_chunks_from_documents), # Extract text chunks based on the document type.\n",
|
||
" Task(extract_graph_from_data, graph_model = KnowledgeGraph, task_config = { \"batch_size\": 10 }), # 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_tasks(tasks, data_documents)\n",
|
||
"\n",
|
||
" async for result in pipeline:\n",
|
||
" print(result)\n",
|
||
" except Exception as error:\n",
|
||
" raise error\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "f0a91b99c6215e09",
|
||
"metadata": {
|
||
"ExecuteTime": {
|
||
"end_time": "2024-12-24T11:55:26.027386Z",
|
||
"start_time": "2024-12-24T11:54:47.384342Z"
|
||
}
|
||
},
|
||
"outputs": [],
|
||
"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": "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",
|
||
"# from dotenv import load_dotenv \n",
|
||
"graphistry.login(username=os.getenv(\"GRAPHISTRY_USERNAME\"), password=os.getenv(\"GRAPHISTRY_PASSWORD\"))\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 [dict(\n",
|
||
" id = str(result[\"id\"]),\n",
|
||
" payload = result[\"payload\"],\n",
|
||
" score = result[\"_distance\"],\n",
|
||
" ) for result in result_values]\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(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(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(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(\n",
|
||
" [result.metrics_data[0].score for result in eval_results.test_results]\n",
|
||
")\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(\n",
|
||
" [result.metrics_data[0].score for result in eval_results.test_results]\n",
|
||
")\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(\n",
|
||
" [result.metrics_data[0].score for result in eval_results.test_results]\n",
|
||
")\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(\n",
|
||
" [result.metrics_data[0].score for result in eval_results.test_results]\n",
|
||
")\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": "cognee-c83GrcRT-py3.11",
|
||
"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": "3.11.10"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|