You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
:author: Michael Hunger, Tomaz Bratanic, Oskar Hane
6
+
:category: labs
7
+
:tags: llm, genai, generative ai, large language models, integrations, rag, vector search, retrieval augmented generation, llamaindex, langchain, haystack, frameworks
8
+
:neo4j-versions: 5.X
9
+
:page-pagination:
10
+
:page-product: GenAI Frameworks
11
+
12
+
While current foundation models (language, image, speech, embeddings) are available through APIs and can be used just with a http request or a few lines of code, the devil is as always in the details. It is not just about a single API call but full applications, workflows and architectures.
13
+
14
+
In the last years a number of really powerful open-source orchestration libraries have been developed, many with a large contributor community and a lot of momentum.
15
+
Even the large cloud providers and AI companies contributed and are using these libraries as in this fast moving world it is hard to keep up otherwise.
16
+
17
+
Those libraries cover a number of aspects:
18
+
19
+
- LLM usage, including Prompt and Output
20
+
- Embedding generation
21
+
- Vector and database integration
22
+
- RAG workflows
23
+
- Agentic workflows
24
+
- Monitoring, Observability and Deployment
25
+
26
+
== GenAI Frameworks
27
+
28
+
Neo4j and our community have contributed integrations to many of these frameworks. You can find overviews of these integrations in the pages of this section, as well as code examples, tutorials and more.
29
+
30
+
* xref:langchain.adoc[LangChain (Python)]
31
+
* xref:langchain-js.adoc[LangChainJS]
32
+
* xref:llamaindex.adoc[LLamaIndex]
33
+
* xref:spring-ai.adoc[Spring AI]
34
+
* xref:langchain4j.adoc[LangChain4j]
35
+
* xref:haystack.adoc[Haystack]
36
+
* xref:semantic-kernel.adoc[Semantic Kernel]
37
+
* xref:dspy.adoc[DSPy]
38
+
39
+
== GraphAcademy Courses
40
+
41
+
If you want to learn how LLMs and Knowledge Graphs combine to improve GenAI applications, check out the https://graphacademy.neo4j.com/categories/llms/?ref=genai-docs[Neo4j & LLM courses on GraphAcademy^].
Knowledge Graphs can provide rich context to ground Large Language Models (LLMs) for enabling GenAI applications using Graph RAG (Retrieval Augmented Generation)
16
-
The real world data captured in the graph avoids hallucination and provides a rich source of information for the LLMs to generate answers, summaries and suggestions from.
15
+
Knowledge graphs bring more accurate responses, rich context, and explainability to each generative AI model interaction.
16
+
By combining knowledge graphs with native vector search, you get the best of both worlds with Graph RAG (Retrieval Augmented Generation).
17
17
18
-
LLMs can be used to extract entities and their relationships from unstructured text to build up and enrich knowledge graphs.
18
+
Language models also can be used to extract entities and their relationships from unstructured text to build up and enrich knowledge graphs.
19
19
20
-
Learn more at: https://neo4j.com/generativeai/
20
+
== How to get started
21
21
22
-
The Neo4j GenAI Ecosystem is a collection of tools and integrations that make it easy to use LLMs with Neo4j.
22
+
1. For an high level overview, have a look at https://neo4j.com/generativeai/[neo4j.com/genai^]
23
+
2. Use the xref:llm-graph-builder.adoc[LLM-Knowledge Graph Builder] to turn your own documents into a knowledge graph
24
+
3. If you want to learn more take one of the https://graphacademy.neo4j.com/categories/llms/?ref=genai-docs[GenAI GraphAcademy courses^]
25
+
4. Pick your xref:genai-frameworks.adoc[GenAI framework of choice] and start building your own GenAI applications with Neo4j
The Neo4j GenAI Ecosystem is a collection of tools and integrations that make it easy to use LLMs with Neo4j.
36
+
32
37
=== GraphRAG
33
38
39
+
GraphRAG combines an ingestion process that extracts entities and relationships from unstructured text and further uses graph algorithms for enrichment and summarization.
40
+
The retrieval step then uses the knowledge graph in combination with vector search to navigate to more relevant information than just the initial text chunks.
In Neo4j Labs we built a number of tools, to demonstrate the power of combining graphs with LLMs. All these tools are open source, you can use and contribute to them or learn and build your own.
The Neo4j LLM Knowledge Graph Builder is an https://llm-graph-builder.neo4jlabs.com/[online application^] for turning unstructured text into a knowledge graph, it provides a magical text to graph experience.
0 commit comments