Skip to main content
Version: DEV

Construct knowledge graph

Generate a knowledge graph for your dataset.

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.

Image

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.

WARNING

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.

NOTE

RAPTOR (Recursive Abstractive Processing for Tree Organized Retrieval) can also be used for multi-hop question-answering tasks. See Enable RAPTOR for details. You may use either approach or both, but ensure you understand the memory, computational, and token costs involved.

Prerequisites​

The system's default chat model is used to generate knowledge graph. Before proceeding, ensure that you have a chat model properly configured:

Set default models

Configurations​

Entity types (Required)​

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.

Method​

The method to use to construct knowledge graph:

  • General: Use prompts provided by GraphRAG to extract entities and relationships.
  • Light: (Default) Use prompts provided by LightRAG to extract entities and relationships. This option consumes fewer tokens, less memory, and fewer computational resources.

Entity resolution​

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.

  • (Default) Disable entity resolution.
  • Enable entity resolution. This option consumes more tokens.

Community report generation​

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 for more information. This indicates whether to generate community reports:

  • Generate community reports. This option consumes more tokens.
  • (Default) Do not generate community reports.

Procedure​

  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.
    • Files parsed before this update will retain their original knowledge graph settings.

  2. The knowledge graph of your dataset does not automatically update until a newly uploaded file is parsed.

    A Knowledge graph entry appears under Configuration once a knowledge graph is created.

  3. Click Knowledge graph to view the details of the generated graph.

  4. To use the created knowledge graph, do either of the following:

    • In the Chat setting panel of your chat app, switch on the Use knowledge graph toggle.
    • If you are using an agent, click the Retrieval agent component to specify the dataset(s) and switch on the Use knowledge graph toggle.

Frequently asked questions​

Can I have different knowledge graph settings for different files in my dataset?​

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.

Nope. The knowledge graph does not automatically update until a newly uploaded document is parsed.

How to remove a generated knowledge graph?​

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.

Where is the created knowledge graph stored?​

All chunks of the created knowledge graph are stored in RAGFlow's document engine: either Elasticsearch or 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 explaining your use case and its importance.