Skip to content

Commit c21d978

Browse files
nerpaulanerpaula
authored
DOC-534 | Add ArangoDB LLMs & Knowledge Graphs and LangChain content (#230)
* add llm and langchain content * add more content about KG, rename folder and title * apply to all versions * add link to colab and other ml tutorials
1 parent e4e4e11 commit c21d978

File tree

4 files changed

+228
-0
lines changed

4 files changed

+228
-0
lines changed

‎site/content/3.10/data-science/llm-knowledge-graphs.md

Lines changed: 76 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,76 @@
1+
---
2+
title: Large Language Models (LLMs) and Knowledge Graphs
3+
menuTitle: Large Language Models and Knowledge Graphs
4+
weight: 133
5+
description: >-
6+
Integrate large language models (LLMs) with knowledge graphs using ArangoDB
7+
archetype: default
8+
---
9+
{{< description >}}
10+
11+
Large language models (LLMs) and knowledge graphs are two prominent and
12+
contrasting concepts, each possessing unique characteristics and functionalities
13+
that significantly impact the methods we employ to extract valuable insights from
14+
constantly expanding and complex datasets.
15+
16+
LLMs, exemplified by OpenAI's ChatGPT, represent a class of powerful language
17+
transformers. These models leverage advanced neural networks to exhibit a
18+
remarkable proficiency in understanding, generating, and participating in
19+
contextually-aware conversations.
20+
21+
On the other hand, knowledge graphs contain carefully structured data and are
22+
designed to capture intricate relationships among discrete and seemingly
23+
unrelated information. With knowledge graphs, you can explore contextual
24+
insights and execute structured queries that reveal hidden connections within
25+
complex datasets.
26+
27+
ArangoDB's unique capabilities and flexible integration of knowledge graphs and
28+
LLMs provide a powerful and efficient solution for anyone seeking to extract
29+
valuable insights from diverse datasets.
30+
31+
## Knowledge Graphs
32+
33+
A knowledge graph can be thought of as a dynamic and interconnected network of
34+
real-world entities and the intricate relationships that exist between them.
35+
36+
Key aspects of knowledge graphs:
37+
- **Domain specific knowledge**: You can tailor knowledge graphs to specific
38+
domains and industries.
39+
- **Structured information**: Makes it easy to query, analyze, and extract
40+
meaningful insights from your data.
41+
- **Accessibility**: You can build a Semantic Web knowledge graph or using
42+
custom data.
43+
44+
LLMs can help distill knowledge graphs from natural language by performing
45+
the following tasks:
46+
- Entity discovery
47+
- Relation extraction
48+
- Coreference resolution
49+
- End-to-end knowledge graph construction
50+
- (Text) Embeddings
51+
52+
![ArangoDB Knowledge Graphs and LLMs](../../images/ArangoDB-knowledge-graphs-meets-llms.png)
53+
54+
## ArangoDB and LangChain
55+
56+
[LangChain](https://www.langchain.com/) is a framework for developing applications
57+
powered by language models.
58+
59+
LangChain enables applications that are:
60+
- Data-aware (connect a language model to other sources of data)
61+
- Agentic (allow a language model to interact with its environment)
62+
63+
The ArangoDB integration with LangChain provides you the ability to analyze
64+
data seamlessly via natural language, eliminating the need for query language
65+
design. By using LLM chat models such as OpenAI’s ChatGPT, you can "speak" to
66+
your data instead of querying it.
67+
68+
### Get started with ArangoDB QA chain
69+
70+
The [ArangoDB QA chain notebook](https://langchain-langchain.vercel.app/docs/use_cases/more/graph/graph_arangodb_qa.html)
71+
shows how to use LLMs to provide a natural language interface to an ArangoDB
72+
instance.
73+
74+
Run the notebook directly in [Google Colab](https://colab.research.google.com/github/arangodb/interactive_tutorials/blob/master/notebooks/Langchain.ipynb).
75+
76+
See also other [machine learning interactive tutorials](https://github.com/arangodb/interactive_tutorials#machine-learning).

‎site/content/3.11/data-science/llm-knowledge-graphs.md

Lines changed: 76 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,76 @@
1+
---
2+
title: Large Language Models (LLMs) and Knowledge Graphs
3+
menuTitle: Large Language Models and Knowledge Graphs
4+
weight: 133
5+
description: >-
6+
Integrate large language models (LLMs) with knowledge graphs using ArangoDB
7+
archetype: default
8+
---
9+
{{< description >}}
10+
11+
Large language models (LLMs) and knowledge graphs are two prominent and
12+
contrasting concepts, each possessing unique characteristics and functionalities
13+
that significantly impact the methods we employ to extract valuable insights from
14+
constantly expanding and complex datasets.
15+
16+
LLMs, exemplified by OpenAI's ChatGPT, represent a class of powerful language
17+
transformers. These models leverage advanced neural networks to exhibit a
18+
remarkable proficiency in understanding, generating, and participating in
19+
contextually-aware conversations.
20+
21+
On the other hand, knowledge graphs contain carefully structured data and are
22+
designed to capture intricate relationships among discrete and seemingly
23+
unrelated information. With knowledge graphs, you can explore contextual
24+
insights and execute structured queries that reveal hidden connections within
25+
complex datasets.
26+
27+
ArangoDB's unique capabilities and flexible integration of knowledge graphs and
28+
LLMs provide a powerful and efficient solution for anyone seeking to extract
29+
valuable insights from diverse datasets.
30+
31+
## Knowledge Graphs
32+
33+
A knowledge graph can be thought of as a dynamic and interconnected network of
34+
real-world entities and the intricate relationships that exist between them.
35+
36+
Key aspects of knowledge graphs:
37+
- **Domain specific knowledge**: You can tailor knowledge graphs to specific
38+
domains and industries.
39+
- **Structured information**: Makes it easy to query, analyze, and extract
40+
meaningful insights from your data.
41+
- **Accessibility**: You can build a Semantic Web knowledge graph or using
42+
custom data.
43+
44+
LLMs can help distill knowledge graphs from natural language by performing
45+
the following tasks:
46+
- Entity discovery
47+
- Relation extraction
48+
- Coreference resolution
49+
- End-to-end knowledge graph construction
50+
- (Text) Embeddings
51+
52+
![ArangoDB Knowledge Graphs and LLMs](../../images/ArangoDB-knowledge-graphs-meets-llms.png)
53+
54+
## ArangoDB and LangChain
55+
56+
[LangChain](https://www.langchain.com/) is a framework for developing applications
57+
powered by language models.
58+
59+
LangChain enables applications that are:
60+
- Data-aware (connect a language model to other sources of data)
61+
- Agentic (allow a language model to interact with its environment)
62+
63+
The ArangoDB integration with LangChain provides you the ability to analyze
64+
data seamlessly via natural language, eliminating the need for query language
65+
design. By using LLM chat models such as OpenAI’s ChatGPT, you can "speak" to
66+
your data instead of querying it.
67+
68+
### Get started with ArangoDB QA chain
69+
70+
The [ArangoDB QA chain notebook](https://langchain-langchain.vercel.app/docs/use_cases/more/graph/graph_arangodb_qa.html)
71+
shows how to use LLMs to provide a natural language interface to an ArangoDB
72+
instance.
73+
74+
Run the notebook directly in [Google Colab](https://colab.research.google.com/github/arangodb/interactive_tutorials/blob/master/notebooks/Langchain.ipynb).
75+
76+
See also other [machine learning interactive tutorials](https://github.com/arangodb/interactive_tutorials#machine-learning).

‎site/content/3.12/data-science/llm-knowledge-graphs.md

Lines changed: 76 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,76 @@
1+
---
2+
title: Large Language Models (LLMs) and Knowledge Graphs
3+
menuTitle: Large Language Models and Knowledge Graphs
4+
weight: 133
5+
description: >-
6+
Integrate large language models (LLMs) with knowledge graphs using ArangoDB
7+
archetype: default
8+
---
9+
{{< description >}}
10+
11+
Large language models (LLMs) and knowledge graphs are two prominent and
12+
contrasting concepts, each possessing unique characteristics and functionalities
13+
that significantly impact the methods we employ to extract valuable insights from
14+
constantly expanding and complex datasets.
15+
16+
LLMs, exemplified by OpenAI's ChatGPT, represent a class of powerful language
17+
transformers. These models leverage advanced neural networks to exhibit a
18+
remarkable proficiency in understanding, generating, and participating in
19+
contextually-aware conversations.
20+
21+
On the other hand, knowledge graphs contain carefully structured data and are
22+
designed to capture intricate relationships among discrete and seemingly
23+
unrelated information. With knowledge graphs, you can explore contextual
24+
insights and execute structured queries that reveal hidden connections within
25+
complex datasets.
26+
27+
ArangoDB's unique capabilities and flexible integration of knowledge graphs and
28+
LLMs provide a powerful and efficient solution for anyone seeking to extract
29+
valuable insights from diverse datasets.
30+
31+
## Knowledge Graphs
32+
33+
A knowledge graph can be thought of as a dynamic and interconnected network of
34+
real-world entities and the intricate relationships that exist between them.
35+
36+
Key aspects of knowledge graphs:
37+
- **Domain specific knowledge**: You can tailor knowledge graphs to specific
38+
domains and industries.
39+
- **Structured information**: Makes it easy to query, analyze, and extract
40+
meaningful insights from your data.
41+
- **Accessibility**: You can build a Semantic Web knowledge graph or using
42+
custom data.
43+
44+
LLMs can help distill knowledge graphs from natural language by performing
45+
the following tasks:
46+
- Entity discovery
47+
- Relation extraction
48+
- Coreference resolution
49+
- End-to-end knowledge graph construction
50+
- (Text) Embeddings
51+
52+
![ArangoDB Knowledge Graphs and LLMs](../../images/ArangoDB-knowledge-graphs-meets-llms.png)
53+
54+
## ArangoDB and LangChain
55+
56+
[LangChain](https://www.langchain.com/) is a framework for developing applications
57+
powered by language models.
58+
59+
LangChain enables applications that are:
60+
- Data-aware (connect a language model to other sources of data)
61+
- Agentic (allow a language model to interact with its environment)
62+
63+
The ArangoDB integration with LangChain provides you the ability to analyze
64+
data seamlessly via natural language, eliminating the need for query language
65+
design. By using LLM chat models such as OpenAI’s ChatGPT, you can "speak" to
66+
your data instead of querying it.
67+
68+
### Get started with ArangoDB QA chain
69+
70+
The [ArangoDB QA chain notebook](https://langchain-langchain.vercel.app/docs/use_cases/more/graph/graph_arangodb_qa.html)
71+
shows how to use LLMs to provide a natural language interface to an ArangoDB
72+
instance.
73+
74+
Run the notebook directly in [Google Colab](https://colab.research.google.com/github/arangodb/interactive_tutorials/blob/master/notebooks/Langchain.ipynb).
75+
76+
See also other [machine learning interactive tutorials](https://github.com/arangodb/interactive_tutorials#machine-learning).

‎site/content/images/ArangoDB-knowledge-graphs-meets-llms.png

413 KB
Loading

0 commit comments

Comments
 (0)