docs/how_to/graph_constructing/

[giscus[bot]]

docs/how_to/graph_constructing/

In this guide we'll go over the basic ways of constructing a knowledge graph based on unstructured text. The constructured graph can then be used as knowledge base in a RAG application.

https://python.langchain.com/docs/how_to/graph_constructing/

[chocwaffles]

[chocwaffles]

[Lovi07]

What is the error you are getting?

[alibama]

is this still an issue? i'm interested in testing

[ladislav-urban]

We have tested if LLMGraphTransformer is able to construct a Knowledge Graph of quality comparable to WikiData on 1200 random Wikipedia pages. These are our results:
The node types are of good quality and expected names such as ‘Person’, ‘Organization’, ‘Document’, ‘Event’. The canonicalization process would eliminate types with the same meaning such as ‘Location’ and ‘Place’ or ‘Literary_work’ and ‘Book’.

The querying process needs to be aware of hierarchy of types such as ‘Organization’ -> ‘Educational_institution’. There are also nodes that end up without any type and are marked as ‘Entity’ . The post processing needs to look at the nodes that are of this type and categorize them into suitable types.

The node types do have exponential count distribution with a long tail of node types that do have 1 or few nodes. The node type ‘Document’ includes references to source data with relation type ‘mentions’. The nodes such as person do have attribute ‘id’ with a person's name as well as optional attributes such as ‘role’ .

If you are interested in more details you can see it at: https://www.dynocortex.com/news-and-blog/good-kg-created-by-ai/

[alibama]

great review = any insight on running with local models?

[ladislav-urban]

Hi Alibama, we have run it on Ollama but it turns out the results with GPT4-mini were just fine and cheap. So we use that at this moment.

[alibama]

Hey Ladislav! Thanks for the feedback. i think given the amount of content we're looking to process for the Lexipedia.xyz project

(https://huggingface.co/datasets/pile-of-law/pile-of-law & https://huggingface.co/datasets/free-law/Caselaw_Access_Project

and since we have almost free compute it's going to be worth testing ollama. Also read your article and thank you for producing and testing against wikidata = informative and hopeful

[yohj1Raphael]

If I want to further use the constructed knowledge graph as an external knowledge base, retrieve relevant subgraph information through RAG technology in response to user questions, how should I do it?