LlamaIndex: Add support for GraphRAG powered by MongodB

XMLWordPrintableJSON

    • Python Drivers
    • Hide

      1. What would you like to communicate to the user about this feature?
      2. Would you like the user to see examples of the syntax and/or executable code and its output?
      3. Which versions of the driver/connector does this apply to?

      Show
      1. What would you like to communicate to the user about this feature? 2. Would you like the user to see examples of the syntax and/or executable code and its output? 3. Which versions of the driver/connector does this apply to?
    • None
    • None
    • None
    • None
    • None
    • None

      Add knowledge graph support for MongoDB in LlamaIndex by implementing Property Graph Index functionality with MongoDB as the backing store.

      Context

      LlamaIndex recently introduced the Property Graph Index, which offers advantages over traditional knowledge graph representations. Currently, LlamaIndex has strong MongoDB integration for vector search, document storage, and key-value operations, but lacks native support for storing and querying property graphs in MongoDB. Link: 

      https://www.llamaindex.ai/blog/introducing-the-property-graph-index-a-powerful-new-way-to-build-knowledge-graphs-with-llms

      Definition of done

      •  Implement MongoDBPropertyGraphStore class that extends the PropertyGraphStore abstraction
      •  Support storing nodes with labels, properties, and relationships in MongoDB collections
      •  Enable querying nodes by ID, properties, and relationship traversal
      •  Implement basic graph operations (insert, update, delete nodes and relationships)
      •  Include comprehensive unit tests and integration tests
      •  Update documentation with MongoDB property graph examples

       

              Assignee:
              Casey Clements
              Reporter:
              Prakul Agarwal
              Votes:
              0 Vote for this issue
              Watchers:
              3 Start watching this issue

                Created:
                Updated: