|
1 | 1 | = Creating Knowledge Graphs from Unstructured Data
|
2 | 2 |
|
3 | 3 | Creating graph structures from unstructured text using https://neo4j.com/blog/machine-learning/accelerating-towards-natural-language-search-graphs/[NLP techniques like Spacy, Stanford NLP, OpenNLTK^] etc. has been a long-standing possibility.
|
4 |
| -Those usually required fine-tuning of the NLP models on the specific domain and language of the text to be processed and substaintial NLP skills to get the best results. |
| 4 | +Those usually required fine-tuning of the NLP models on the specific domain and language of the text to be processed and substantial NLP skills to get the best results. |
5 | 5 |
|
6 |
| -The rise of promptable modern day Large Language Models (LLMs) with strong language skills across many languages and domains, extended the capabilities massively. |
7 |
| -The LLMs can be instructured with detailed prompts (instructions, examples, schema, existing entities, output formatting) to extract, and de-duplicate entities and relationships from unstructured text, images and audio fragments. |
| 6 | +The rise of prompt-able modern day Large Language Models (LLMs) with strong language skills across many languages and domains, extended the capabilities massively. |
| 7 | +The LLMs can be instructed with detailed prompts (instructions, examples, schema, existing entities, output formatting) to extract, and de-duplicate entities and relationships from unstructured text, images and audio fragments. |
8 | 8 | The extracted information is returned in a structured JSON format and can be stored in a graph database like Neo4j and linked back to the source documents and additional metadata.
|
9 | 9 |
|
10 | 10 | This allows to build Knowledge Graphs (KGs) from unstructured data and integrate them with existing structured data in Neo4j.
|
@@ -77,9 +77,9 @@ Those generated Knowledge Graphs can then be used with the https://neo4j.com/doc
|
77 | 77 |
|
78 | 78 | The https://neo4j.com/labs/genai-ecosystem/llm-graph-builder/[LLM Knowledge Graph Builder^] is an easy to use tool for building Knowledge Graphs from unstructured text.
|
79 | 79 |
|
80 |
| -It uses the LangChain LLMGraphTransformer under the hood, but provides a simple UI to extract entities and relations from uploaded PDFs, Office Documents, Web pages or Youtube video transccripts. |
| 80 | +It uses the LangChain LLMGraphTransformer under the hood, but provides a simple UI to extract entities and relations from uploaded PDFs, Office Documents, Web pages or YouTube video transcripts. |
81 | 81 | It extracts first a lexical graph (Document, Chunk and their relationships) and then uses the chosen LLM to extract entities and relations. Optionally it enriches the graph community summaries and embeddings.
|
82 |
| -You can specifiy a graph schema to guide the extraction process and visualize the extracted graphs. |
| 82 | +You can specify a graph schema to guide the extraction process and visualize the extracted graphs. |
83 | 83 |
|
84 | 84 | image::https://dist.neo4j.com/wp-content/uploads/20240618104511/build-kg-genai-e1718732751482.png[width=600]
|
85 | 85 |
|
|
0 commit comments