What Is Graph
RAG?
Discover the transformative potential of Retrieval
Augmented Generation (RAG), a method that enhances
large language models (LLMs) with external knowledge
for more accurate, contextual question answering. See
how RAG can evolve into Graph RAG (or GraphRAG)
which uses knowledge graphs (KG) as a source of
context or factual information. Ontotext products and
services streamline a range of Graph RAG patterns,
opening up new possibilities for chatbots, natural
language querying and information extraction.
Graph Database | Graph RAG
Reading Time: 10 min
LinkedIn
Facebook
Email
Compartilhar
All Fundamentals
The topic of interfacing in natural language with knowledge graphs
has gained tremendous popularity. Moreover, as per Gartner, this
will be a trend that stays and transforms a lot of the computer
systems interactions we are used to. The first major step in this
direction, seems to be natural language querying (NLQ) – lately
everyone seems to want to ask natural language questions on their
own data.
Using out-of-the-box large language model (LLM) chatbots for
question answering in enterprises can rarely be helpful, as they
don’t encode domain specific proprietary knowledge about the
organization activities that would actually bring value to a
conversational interface for information extraction. This is where the
Graph RAG approach enters the scene as an ideal solution to tailor
an LLM to meet your specific requirements.
What is RAG?
Graph RAG includes a graph database as a source of the
contextual information sent to the LLM. Providing the LLM with
textual chunks extracted from larger sized documents can lack the
necessary context, factual correctness and language accuracy for
the LLM to understand the received chunks in depth. Unlike sending
plain text chunks of documents to the LLM, Graph RAG can also
provide structured entity information to the LLM combining the entity
textual description with its many properties and relationships, thus
encouraging deeper insights facilitated by the LLM. With Graph
RAG each record in the vector database can have contextually rich
representation increasing the understandability of specific
terminology, so the LLM can make better sense of specific subject
domains. Graph RAG can be combined with the standard RAG
approach to get the best of both worlds – the structure and accuracy
of the graph representation combined with the vastness of textual
content.
This approach is the cheapest and most standard way to enhance
LLMs with additional knowledge for the purposes of answering a
question. In addition, it is shown to reduce the tendency of LLMs for
hallucination, as the generation adheres more to the information
from the context, which is generally reliable. Due to this nature of
the approach, RAG emerged as the most popular way to augment
the output of generative models.
Cost of Implementation (% of finetuning)
Besides question-answering RAG can also be used for many
natural language processing tasks, such as information extraction
from text, recommendations, sentiment analysis and
summarization, to name a few.
How to do RAG?
KNOWLEDGE MODEL: The foundation for a Graph RAG is the
taxonomy you use
to create a knowledge graph. With PoolParty, you can start building
a taxonomy
from scratch or use your pre-existing taxonomies. You can also
purchase WAND
taxonomies or import free publicly-available taxonomies to get
started quicker.
KNOWLEDGE BASE: Since the RAG draws from your own
document and data
repository,, the only thing you need is to tag the items with semantic
concepts
using the PoolParty Extractor. The tagged knowledge base + the
knowledge
model culminates in a knowledge graph that is then infused with the
LLM.
LLM: So that you feel most secure in the LLM that’s used for this
RAG application,
you can decide which LLM you want to invest in. There are free
LLMs available on
the market, more precise paid LLMs, and your own pre-trained LLM
if you have
one. PoolParty is designed to integrate with the LLM you feel most
comfortable
with in terms of data security and cost.
Besides question-answering RAG can also be used for many
natural language processing tasks, such as information extraction
from text, recommendations, sentiment analysis and
summarization, to name a few.
The other aspects of the RAG, such as the semantic search and
recommender
system, all fall into place once these 3 items have been taken care
of. Since our
architecture relies on a semantic layer, it is easy to build a
multi-RAG infrastructure
that serves different departments or use cases if that level of
specificity is needed.
As simple as the basic implementation is, you need to take into
account a list of challenges and considerations to ensure good
quality of the results:
● Data quality and relevance is crucial for the effectiveness of
Graph RAG, so questions such as how to fetch the most
relevant content to send the LLM and how much content to
send it should be considered.
● Handling dynamic knowledge is usually difficult as one needs
to constantly update the vector index with new data.
Depending on the size of the data this can impose further
challenges such as efficiency and scalability of the system.
● Transparency of the generated results is important to make
the system trustworthy and usable. There are techniques for
prompt engineering that can be used to stimulate the LLM to
explain the source of the information included in the answer.
The Different Varieties of Graph
RAG
We can summarize several varieties of Graph RAG, depending on
the nature of the questions, the domain and information in the
knowledge graph at hand
GraphRAG Varieties
Vanilla Chunky Vector RAG
Type 1: Graph as a Metadata Store
Type 2: Graph as an Expert
Type 3: Talk to your Graph
Semantic Metadata
Domain Knowledge
Factual Data
Type of Graph Needed
Content Hub
Domain Knowledge Model
Data Fabric
The Result
Extract and summarize information from a few relevant document chunks, loss of
original structure
Precise filtering based on metadata. Explainability via references to the relevant
documents and concepts
Get richer results! Domain knowledge helps retrieval of relevant documents that a
vanilla vector DB would miss
Extract relevant factual information. Get accuracy and analytical depth from structured
queries via chat
Besides the Standard RAG, hwich is good for minor knowledge
extraction and summarisation wen have the following graph
enriched RAG models.
● Graph as a Content Hub: Extract relevant chunks of
documents and ask the LLM to answer using them. This
variety requires a KG containing relevant textual content and
metadata about it as well as integration with a vector
database.
● Graph as а Subject Matter Expert: Extract descriptions of
concepts and entities relevant to the natural language (NL)
question and pass those to the LLM as additional “semantic
context”. The description should ideally include relationships
between the concepts. This variety requires a KG with a
comprehensive conceptual model, including relevant
ontologies, taxonomies or other entity descriptions. The
implementation requires entity linking or another mechanism
for the identification of concepts relevant to the question.
● Graph as a Database: Map (part of) the NL question to a
graph query, execute the query and ask the LLM to
summarize the results. This variety requires a graph that
holds relevant factual information. The implementation of such
a pattern requires some sort of NL-to-Graph-query tool and
entity linking.
How Graphwise makes Graph
RAG easier
Graphwise GraphDB provides numerous integrations which enable
users to create their own Graph RAG implementation quickly and
efficiently. GraphDB’s Similarity plugin is an easy tool to create an
embedding index of your content for free and use SPARQL to query
this index for the top K entities or pieces of content closest to the
user question.
For more complex use cases, which require higher precision of the
results, GraphDB also provides the ChatGPT Retrieval Plugin
Connector through which you can index your content in a vector
database using a state-of-the-art embeddings generation model and
run powerful queries against this vector database. Moreover, the
plugin takes care to continuously sync the state of the knowledge in
GraphDB with the vector database in a transactionally-safe manner,
which means new data will be immediately available for an LLM
integration.
The ChatGPT Retrieval Plugin Connector, similarly to other
GraphDB plugins, allows you to precisely configure what data you
want to pull from your knowledge graph and store as embeddings in
an external vector database. It’s not limited to textual fields, it can
also convert structured data about RDF entities into text
embeddings. The connection to the vector database is managed by
the ChatGPT Retrieval Plugin – hence the name of the connector.
This is an open-source tool, developed and maintained by OpenAI
under an MIT license. Its function is to index and query content. To
index content, the plugin receives a piece of text, splits it down into
manageable parts or “chunks”, creates vector embeddings for each
chunk using OpenAI’s embedding model, and stores these
embeddings in a vector database. The plugin is compatible with
numerous databases, including some of the most popular ones in
the last few years, such as Weaviate, Pinecone and Elasticsearch.
Online Demos powered by
Graphwise
Knowledge Hub
Gather knowledge on sustainability and ESG issues.
GraphRAG provides accurate and personalised answers and
recommendations.
www.knowledge-hub.eco
