cognee: ein Open-Source-Framework für wissensgraphenbasierte RAG-Konstruktion, Kernprompts zum Lernen

Allgemeine Einführung

Cognee ist eine zuverlässige Datenschichtlösung für KI-Anwendungen und KI-Agenten. Sie wurde entwickelt, um LLM-Kontexte (Large Language Model) zu laden und zu erstellen, um genaue und interpretierbare KI-Lösungen durch Wissensgraphen und Vektorspeicher zu schaffen. Das Framework ermöglicht Kostenersparnis, Interpretierbarkeit und benutzergesteuerte Kontrolle, wodurch es sich für Forschung und Lehre eignet. Die offizielle Website bietet einführende Tutorials, konzeptionelle Übersichten, Lernmaterialien und verwandte Forschungsinformationen.

Die größte Stärke von cognee ist es, Daten zu sammeln, sie automatisch zu verarbeiten, Wissensgraphen zu erstellen und die Graphen mit verwandten Themen zu verknüpfen, um die Zusammenhänge in den Daten besser zu erkennen und die RAG Bietet die ultimative Interpretierbarkeit, wenn es um LLMs geht.

1) Daten hinzufügen, Daten automatisch identifizieren und auf der Grundlage von LLM verarbeiten, in Knowledge Graph extrahieren und speichern Vektordatenbank 2. die Vorteile sind: Kostenersparnis, Interpretierbarkeit - grafische Visualisierung der Daten, Kontrollierbarkeit - Integration in den Code, usw.

Funktionsliste

• ECL-RohrleitungenErmöglicht das Extrahieren, Erkennen und Laden von Daten, unterstützt die Verknüpfung und den Abruf von historischen Daten.
• Multi-Datenbank-UnterstützungUnterstützung für PostgreSQL, Weaviate, Qdrant, Neo4j, Milvus und andere Datenbanken.
• Verringerung von HalluzinationenReduzierung von Phantomphänomenen in KI-Anwendungen durch Optimierung des Pipeline-Designs.
• Freundlich für EntwicklerAusführliche Dokumentation und Beispiele, um die Schwelle für Entwickler zu senken.
• SkalierbarkeitModularer Aufbau für einfache Erweiterung und Anpassung.

Hilfe verwenden

Einbauverfahren

1. Installation mit pip::

   pip install cognee
   

   Oder installieren Sie eine spezielle Datenbankunterstützung:

   pip install 'cognee[<database>]'
   

   Installieren Sie zum Beispiel PostgreSQL und Neo4j-Unterstützung:

   pip install 'cognee[postgres, neo4j]'
   

2. Installation mit Poesie::

   poetry add cognee
   

   Oder installieren Sie eine spezielle Datenbankunterstützung:

   poetry add cognee -E <database>
   

   Installieren Sie zum Beispiel PostgreSQL und Neo4j-Unterstützung:

   poetry add cognee -E postgres -E neo4j
   

Verwendungsprozess

1. Einstellen des API-Schlüssels::

   import os
   os.environ["LLM_API_KEY"] = "YOUR_OPENAI_API_KEY"
   

   Oder:

   import cognee
   cognee.config.set_llm_api_key("YOUR_OPENAI_API_KEY")
   

2. Erstellen von .env-Dateien: Erstellen Sie eine .env-Datei und legen Sie den API-Schlüssel fest:

   LLM_API_KEY=YOUR_OPENAI_API_KEY
   

3. Nutzung verschiedener LLM-AnbieterSiehe die Dokumentation, um zu erfahren, wie verschiedene LLM-Anbieter konfiguriert werden können.
4. Ergebnisse der VisualisierungWenn Sie ein Netzwerk verwenden, erstellen Sie ein Graphistry-Konto und konfigurieren Sie es:

   cognee.config.set_graphistry_config({
   "username": "YOUR_USERNAME",
   "password": "YOUR_PASSWORD"
   })
   

Hauptfunktionen

1. DatenextraktionExtrahieren von Daten mithilfe der ECL-Pipeline von Cognee, die mehrere Datenquellen und -formate unterstützt.
2. Bewusstsein für DatenVerarbeitung und Analyse von Daten durch das kognitive Modul von Cognee zur Reduzierung von Halluzinationen.
3. Laden von DatenLaden von verarbeiteten Daten in eine Zieldatenbank oder einen Zielspeicher, wobei eine breite Palette von Datenbanken und Vektorspeichern unterstützt wird.

Ausgewählte Funktionen Bedienung Ablauf

1. Verknüpfung und Abruf von historischen DatenEinfache Verknüpfung und Abfrage von vergangenen Gesprächen, Dokumenten und Audiotranskriptionen dank des modularen Designs von Cognee.
2. Geringere Arbeitsbelastung der EntwicklerAusführliche Dokumentation und Beispiele, um die Schwelle für Entwickler zu senken und Entwicklungszeit und -kosten zu reduzieren.

Besuchen Sie die offizielle Website für weitere Informationen über Cognee-Rahmen
Lesen Sie einen Überblick über die Beherrschung der theoretischen Grundlagen von Cognee
Tutorials und Lernmaterialien für den Einstieg ansehen

Hauptbefehl der Eingabeaufforderung

classify_content: klassifizierte Inhalte

You are a classification engine and should classify content. Make sure to use one of the existing classification options nad not invent your own.
The possible classifications are:
{
"Natural Language Text": {
"type": "TEXT",
"subclass": [
"Articles, essays, and reports",
"Books and manuscripts",
"News stories and blog posts",
"Research papers and academic publications",
"Social media posts and comments",
"Website content and product descriptions",
"Personal narratives and stories"
]
},
"Structured Documents": {
"type": "TEXT",
"subclass": [
"Spreadsheets and tables",
"Forms and surveys",
"Databases and CSV files"
]
},
"Code and Scripts": {
"type": "TEXT",
"subclass": [
"Source code in various programming languages",
"Shell commands and scripts",
"Markup languages (HTML, XML)",
"Stylesheets (CSS) and configuration files (YAML, JSON, INI)"
]
},
"Conversational Data": {
"type": "TEXT",
"subclass": [
"Chat transcripts and messaging history",
"Customer service logs and interactions",
"Conversational AI training data"
]
},
"Educational Content": {
"type": "TEXT",
"subclass": [
"Textbook content and lecture notes",
"Exam questions and academic exercises",
"E-learning course materials"
]
},
"Creative Writing": {
"type": "TEXT",
"subclass": [
"Poetry and prose",
"Scripts for plays, movies, and television",
"Song lyrics"
]
},
"Technical Documentation": {
"type": "TEXT",
"subclass": [
"Manuals and user guides",
"Technical specifications and API documentation",
"Helpdesk articles and FAQs"
]
},
"Legal and Regulatory Documents": {
"type": "TEXT",
"subclass": [
"Contracts and agreements",
"Laws, regulations, and legal case documents",
"Policy documents and compliance materials"
]
},
"Medical and Scientific Texts": {
"type": "TEXT",
"subclass": [
"Clinical trial reports",
"Patient records and case notes",
"Scientific journal articles"
]
},
"Financial and Business Documents": {
"type": "TEXT",
"subclass": [
"Financial reports and statements",
"Business plans and proposals",
"Market research and analysis reports"
]
},
"Advertising and Marketing Materials": {
"type": "TEXT",
"subclass": [
"Ad copies and marketing slogans",
"Product catalogs and brochures",
"Press releases and promotional content"
]
},
"Emails and Correspondence": {
"type": "TEXT",
"subclass": [
"Professional and formal correspondence",
"Personal emails and letters"
]
},
"Metadata and Annotations": {
"type": "TEXT",
"subclass": [
"Image and video captions",
"Annotations and metadata for various media"
]
},
"Language Learning Materials": {
"type": "TEXT",
"subclass": [
"Vocabulary lists and grammar rules",
"Language exercises and quizzes"
]
},
"Audio Content": {
"type": "AUDIO",
"subclass": [
"Music tracks and albums",
"Podcasts and radio broadcasts",
"Audiobooks and audio guides",
"Recorded interviews and speeches",
"Sound effects and ambient sounds"
]
},
"Image Content": {
"type": "IMAGE",
"subclass": [
"Photographs and digital images",
"Illustrations, diagrams, and charts",
"Infographics and visual data representations",
"Artwork and paintings",
"Screenshots and graphical user interfaces"
]
},
"Video Content": {
"type": "VIDEO",
"subclass": [
"Movies and short films",
"Documentaries and educational videos",
"Video tutorials and how-to guides",
"Animated features and cartoons",
"Live event recordings and sports broadcasts"
]
},
"Multimedia Content": {
"type": "MULTIMEDIA",
"subclass": [
"Interactive web content and games",
"Virtual reality (VR) and augmented reality (AR) experiences",
"Mixed media presentations and slide decks",
"E-learning modules with integrated multimedia",
"Digital exhibitions and virtual tours"
]
},
"3D Models and CAD Content": {
"type": "3D_MODEL",
"subclass": [
"Architectural renderings and building plans",
"Product design models and prototypes",
"3D animations and character models",
"Scientific simulations and visualizations",
"Virtual objects for AR/VR environments"
]
},
"Procedural Content": {
"type": "PROCEDURAL",
"subclass": [
"Tutorials and step-by-step guides",
"Workflow and process descriptions",
"Simulation and training exercises",
"Recipes and crafting instructions"
]
}
}

generate_cog_layers: kognitive Schichten erzeugen

You are tasked with analyzing `{{ data_type }}` files, especially in a multilayer network context for tasks such as analysis, categorization, and feature extraction. Various layers can be incorporated to capture the depth and breadth of information contained within the {{ data_type }}.

These layers can help in understanding the content, context, and characteristics of the `{{ data_type }}`.

Your objective is to extract meaningful layers of information that will contribute to constructing a detailed multilayer network or knowledge graph.

Approach this task by considering the unique characteristics and inherent properties of the data at hand.

VERY IMPORTANT: The context you are working in is `{{ category_name }}` and the specific domain you are extracting data on is `{{ category_name }}`.

Guidelines for Layer Extraction:
Take into account: The content type, in this case, is: `{{ category_name }}`, should play a major role in how you decompose into layers.

Based on your analysis, define and describe the layers you've identified, explaining their relevance and contribution to understanding the dataset. Your independent identification of layers will enable a nuanced and multifaceted representation of the data, enhancing applications in knowledge discovery, content analysis, and information retrieval.

generate_graph_prompt: Graphische Eingabeaufforderungen erzeugen

You are a top-tier algorithm
designed for extracting information in structured formats to build a knowledge graph.
- **Nodes** represent entities and concepts. They're akin to Wikipedia nodes.
- **Edges** represent relationships between concepts. They're akin to Wikipedia links.
- The aim is to achieve simplicity and clarity in the
knowledge graph, making it accessible for a vast audience.
YOU ARE ONLY EXTRACTING DATA FOR COGNITIVE LAYER `{{ layer }}`
## 1. Labeling Nodes
- **Consistency**: Ensure you use basic or elementary types for node labels.
- For example, when you identify an entity representing a person,
always label it as **"Person"**.
Avoid using more specific terms like "mathematician" or "scientist".
- Include event, entity, time, or action nodes to the category.
- Classify the memory type as episodic or semantic.
- **Node IDs**: Never utilize integers as node IDs.
Node IDs should be names or human-readable identifiers found in the text.
## 2. Handling Numerical Data and Dates
- Numerical data, like age or other related information,
should be incorporated as attributes or properties of the respective nodes.
- **No Separate Nodes for Dates/Numbers**:
Do not create separate nodes for dates or numerical values.
Always attach them as attributes or properties of nodes.
- **Property Format**: Properties must be in a key-value format.
- **Quotation Marks**: Never use escaped single or double quotes within property values.
- **Naming Convention**: Use snake_case for relationship names, e.g., `acted_in`.
## 3. Coreference Resolution
- **Maintain Entity Consistency**:
When extracting entities, it's vital to ensure consistency.
If an entity, such as "John Doe", is mentioned multiple times
in the text but is referred to by different names or pronouns (e.g., "Joe", "he"),
always use the most complete identifier for that entity throughout the knowledge graph.
In this example, use "John Doe" as the entity ID.
Remember, the knowledge graph should be coherent and easily understandable,
so maintaining consistency in entity references is crucial.
## 4. Strict Compliance
Adhere to the rules strictly. Non-compliance will result in termination"""

read_query_prompt: Abfrageprompt lesen

from os import path
import logging
from cognee.root_dir import get_absolute_path

def read_query_prompt(prompt_file_name: str):
"""Read a query prompt from a file."""
try:
file_path = path.join(get_absolute_path("./infrastructure/llm/prompts"), prompt_file_name)

with open(file_path, "r", encoding = "utf-8") as file:
return file.read()
except FileNotFoundError:
logging.error(f"Error: Prompt file not found. Attempted to read: %s {file_path}")
return None
except Exception as e:
logging.error(f"An error occurred: %s {e}")
return None

render_prompt: Aufforderung zum Rendern

from jinja2 import Environment, FileSystemLoader, select_autoescape
from cognee.root_dir import get_absolute_path

def render_prompt(filename: str, context: dict) -> str:
"""Render a Jinja2 template asynchronously.
:param filename: The name of the template file to render.
:param context: The context to render the template with.
:return: The rendered template as a string."""

# Set the base directory relative to the cognee root directory
base_directory = get_absolute_path("./infrastructure/llm/prompts")

# Initialize the Jinja2 environment to load templates from the filesystem
env = Environment(
loader = FileSystemLoader(base_directory),
autoescape = select_autoescape(["html", "xml", "txt"])
)

# Load the template by name
template = env.get_template(filename)

# Render the template with the provided context
rendered_template = template.render(context)

return rendered_template

summarize_content: Zusammenfassung des Inhalts

You are a summarization engine and you should sumamarize content. Be brief and concise