Uploaded image for project: 'Python Integrations'
  1. Python Integrations
  2. INTPYTHON-496

Investigate Community support of LightRAG

    • Type: Icon: Task Task
    • Resolution: Unresolved
    • Priority: Icon: Unknown Unknown
    • None
    • Affects Version/s: None
    • Component/s: AI/ML
    • 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

      We need a MongoDB implementation for LightRAG. In the LightRAG github codebase there is an initial (but not complete) implementation with Atlas already. There is a much complete implementation for PostGres, which does entity + vector + graph in PostGres itself.

      Context about LightRAG:

      LightRAG is a popular github repo (11k likes). This video goes into some details of the implementation: https://www.youtube.com/watch?v=oageL-1I0GE

      Context for the Urgency of the request:

      Two teams in Adobe are specifically interested in POC'ing an internal solution using LightRAG. They want to keep using MongoDB, but will be evaluating us against Postgres, which is another approved database they already have. They dont want to use a dedicated graph db like neo4j as they believe these graphs are going to be shallow enough to not requre adding a separate point graph solution.

       

            Assignee:
            casey.clements@mongodb.com Casey Clements
            Reporter:
            prakul.agarwal@mongodb.com Prakul Agarwal
            Votes:
            0 Vote for this issue
            Watchers:
            2 Start watching this issue

              Created:
              Updated:
              None
              None
              None
              None