|
1 | 1 | --- |
2 | | -title: Memgraph's AI Ecosystem |
| 2 | +title: Memgraph's AI ecosystem |
3 | 3 | description: Explore key features, such as community detection, node embeddings, and graph neural networks, alongside integrations with popular AI libraries like LangChain and LlamaIndex, to create powerful, data-driven GenAI solutions. |
4 | 4 | --- |
5 | 5 |
|
6 | 6 | import { Callout } from 'nextra/components' |
7 | 7 | import {CommunityLinks} from '/components/social-card/CommunityLinks' |
8 | 8 |
|
9 | | -# Memgraph's AI Ecosystem |
| 9 | +# Memgraph's AI ecosystem |
10 | 10 |
|
11 | | -To learn about Memgraph's key features to build AI apps, explore the following |
12 | | -pages: |
| 11 | +AI drives a wide range of innovations, from machine learning (ML) models to |
| 12 | +natural language processing (NLP) systems and beyond. These technologies |
| 13 | +frequently intersect, enabling the creation of powerful applications with |
| 14 | +Generative AI (GenAI), including advanced chatbots and agents. |
13 | 15 |
|
14 | | -- [GraphRAG](/ai-ecosystem/graph-rag) |
15 | | -- [Machine learning](/ai-ecosystem/machine-learning) |
| 16 | +## What You'll Find Here |
16 | 17 |
|
| 18 | +This section of Memgraph’s documentation is your guide to using Memgraph for AI: |
17 | 19 |
|
18 | | -AI spans multiple areas like machine learning (ML), natural language processing |
19 | | -(NLP), and knowledge representation and reasoning (KRR), often overlapping to |
20 | | -create advanced systems. A key example is **Generative AI (GenAI)**, which generates |
21 | | -new content like text or images. Large Language Models (LLMs) power many GenAI |
22 | | -apps, but getting them to work with your custom data can be challenging. |
23 | | - |
24 | | -Fine-tuning LLMs to incorporate custom data is often complex, slow, and costly. |
25 | | -Plus, frequent updates make it inefficient. |
26 | | - |
27 | | -**Retrieval-Augmented Generation (RAG)** solves this by enhancing LLMs with |
28 | | -external data sources, enabling dynamic, scalable knowledge updates. Traditional |
29 | | -RAG is based on vector structure with vector databases, and it has proven to be |
30 | | -a great solution in many use cases. Still, it often falls short when retrieving |
31 | | -crucial knowledge from complex datasets. That is where GraphRAG excels. |
32 | | - |
33 | | -**GraphRAG** improves on this by using knowledge graphs and graph features (e.g., |
34 | | -community detection, neighborhood analysis) for more accurate retrieval and |
35 | | -data-rich insights. This hybrid approach provides better context and performance |
36 | | -for GenAI applications. |
37 | | - |
38 | | -Memgraph has been a popular choice in AI, especially for cases that utilize |
39 | | -[machine learning](/ai-ecosystem/machine-learning). It also proves to be a great |
40 | | -choice to build a [GraphRAG](/ai-ecosystem/graph-rag). |
| 20 | +- [Building GenAI apps with GraphRAG](/ai-ecosystem/graph-rag): See how knowledge graphs enable more |
| 21 | + efficient and scalable RAG systems. |
| 22 | +- [AI integrations with Memgraph](/ai-ecosystem/integrations): We have several integrations with popular |
| 23 | + AI frameworks to help you customize and build your own GenAI application from |
| 24 | + scratch. Some of the libraries that support Memgraph |
| 25 | + include **LangChain** and **LlamaIndex**. |
| 26 | +- [GraphChat in Memgraph Lab](/ai-ecosystem/graphchat): Explore how natural language querying |
| 27 | + (GraphChat) ties into the GraphRAG ecosystem, making complex graphs accessible |
| 28 | + to everyone. |
| 29 | +- [Machine learning with Memgraph](/ai-ecosystem/machine-learning): Learn how Memgraph powers ML workflows |
| 30 | + with graph-powered insights. |
41 | 31 |
|
42 | 32 | <CommunityLinks/> |
0 commit comments