To enhance multi-hop question-answering, RAGFlow adds a knowledge graph construction step between data extraction and indexing, as illustrated below. This step creates additional chunks from existing ones generated by your specified chunking method.
From v0.16.0 onward, RAGFlow supports constructing a knowledge graph on a dataset, allowing you to construct a *unified*graph across multiple files within your dataset. When a newly uploaded file starts parsing, the generated graph will automatically update.
Constructing a knowledge graph requires significant memory, computational resources, and tokens.
:::
## Scenarios
Knowledge graphs are especially useful for multi-hop question-answering involving *nested* logic. They outperform traditional extraction approaches when you are performing question answering on books or works with complex entities and relationships.
RAPTOR (Recursive Abstractive Processing for Tree Organized Retrieval) can also be used for multi-hop question-answering tasks. See [Enable RAPTOR](./enable_raptor.md) for details. You may use either approach or both, but ensure you understand the memory, computational, and token costs involved.
The types of the entities to extract from your dataset. The default types are: **organization**, **person**, **event**, and **category**. Add or remove types to suit your specific dataset.
- **General**: Use prompts provided by [GraphRAG](https://github.com/microsoft/graphrag) to extract entities and relationships.
- **Light**: (Default) Use prompts provided by [LightRAG](https://github.com/HKUDS/LightRAG) to extract entities and relationships. This option consumes fewer tokens, less memory, and fewer computational resources.
Whether to enable entity resolution. You can think of this as an entity deduplication switch. When enabled, the LLM will combine similar entities - e.g., '2025' and 'the year of 2025', or 'IT' and 'Information Technology' - to construct a more effective graph.
In a knowledge graph, a community is a cluster of entities linked by relationships. You can have the LLM generate an abstract for each community, known as a community report. See [here](https://www.microsoft.com/en-us/research/blog/graphrag-improving-global-search-via-dynamic-community-selection/) for more information. This indicates whether to generate community reports:
1. On the **Configuration** page of your dataset, switch on **Extract knowledge graph** or adjust its settings as needed, and click **Save** to confirm your changes.
- *The default knowledge graph configurations for your dataset are now set and files uploaded from this point onward will automatically use these settings during parsing.*
Yes, you can. Just one graph is generated per dataset. The smaller graphs of your files will be *combined* into one big, unified graph at the end of the graph extraction process.
To remove the generated knowledge graph, delete all related files in your dataset. Although the **Knowledge graph** entry will still be visible, the graph has actually been deleted.
All chunks of the created knowledge graph are stored in RAGFlow's document engine: either Elasticsearch or [Infinity](https://github.com/infiniflow/infinity).
### How to export a created knowledge graph?
Nope. Exporting a created knowledge graph is not supported. If you still consider this feature essential, please [raise an issue](https://github.com/infiniflow/ragflow/issues) explaining your use case and its importance.
