:mag: AI orchestration framework to build customizable, production-ready LLM applications. Connect components (models, vector DBs, file converters) to pipelines or agents that can interact with your data. With advanced retrieval methods, it's best suited for building RAG, question answering, semantic search or conversational agent chatbots.
GraphDB is sheer impossible to run in colab notebooks and our tutorial notebook cannot be run on colab in its current form (only works locally). Further, licensing reasons complicate the setup: users are required to fill out a form before receiving a link to an installer via email.
Therefore, it would be nice to have an alternative to GraphDBKnowledgeGraph that also inherits from BaseKnowledgeGraph, provides the same functionality but does not use GraphDB, and can be executed in colab notebooks.
GraphDB is sheer impossible to run in colab notebooks and our tutorial notebook cannot be run on colab in its current form (only works locally). Further, licensing reasons complicate the setup: users are required to fill out a form before receiving a link to an installer via email. Therefore, it would be nice to have an alternative to GraphDBKnowledgeGraph that also inherits from BaseKnowledgeGraph, provides the same functionality but does not use GraphDB, and can be executed in colab notebooks.
As a starting point, this might be a good alternative (thanks @tanaysoni ): https://rdflib.readthedocs.io/en/stable/apidocs/rdflib.plugins.html#rdflib.plugins.memory.IOMemory
Besides implementation of this alternative, it also needs to be added to the tutorial on Question Answering on Knowledge Graphs.