Zachary Blumenfeld
Zachary Blumenfeld
Having a way to load example datasets is super helpful for people exploring, learning, and demoing. As such I re-implemented the kg_chat `load` endpoint that was taken out in #29...
Currently 5.11
The Graph Generator will infer "Document" labeled nodes when generating graphs. However, this conflicts with concept of the source Document node. Is there any way to force the generator to...
Note: I Haven't tested this end-to-end with the course yet. I have just used it in the past to work with my own demos. I would recommend testing yourself before...
## Running notebook as-is results in error  ## Using same schema as set in [setup.sql](setup.sql) fixes this though 
Regarding stuff like this in kg writer: https://github.com/neo4j/neo4j-graphrag-python/blob/main/src/neo4j_graphrag/experimental/components/kg_writer.py#L103 For unique node ids/keys used in loading, you want to use a Constraint: Either [Key](https://neo4j.com/docs/cypher-manual/current/constraints/#node-key) or [Uniqueness](https://neo4j.com/docs/cypher-manual/current/constraints/#unique-node-property) constraint. Key is like uniqueness...
Often we just want to define node labels, or just node labels and relationship types. We may not know a good `potential_schema`, especially while developing on new data. Currently, these...
Currently, `create_vector_index` will fail if the index already exists. I also don't have a method in this package, AFAIK, to check if an index already exists. I think it's important...