neo4j-graphrag-python
neo4j-graphrag-python copied to clipboard
neo4j
Neo4j GraphRAG for Python
### Description For me the retrieved context can be larger than the LLM context window, which makes me get an context window exceeded error. It would be nice to pass...
### Description It would be nice if one could set the embedding dimension for the embedder since one can set the embedding dimension for the `create_vector_index` function, which makes no...
# Description The additional arguments we previously introduced to the invoke function in LLMInterface broke compatibility with LangChain. This change introduces a new `LLMInterfaceV2` contract that is fully compatible with...
### Description neo4j-graphrag==1.10.0 depends on neo4j>=5.17.0,
### Question All, How can during running, not post run of SimpleKGPipeline with params ``` "additional_node_types": True, "additional_relationship_types": True, "additional_patterns": True, ``` 1. Customise the node extracted from SimpleKGPipeline, for...
The current implementation of the `VertexAIEmbeddings` class, found in the provided code snippet, uses the **deprecated `vertexai` SDK** for Google's Generative AI models. To ensure compatibility, access to the latest...
# Description > **Note** > > Adds support for optional node label filtering to the external retrievers: WeaviateNeo4jRetriever, QdrantNeo4jRetriever, and PineconeNeo4jRetriever. > > - Introduces an optional `node_label` parameter to...
When running a custom pipeline with a FixedSizeSplitter and a TextChunkEmbedder using OllamaEmbeddings I get weird warnings in the Ollama logs: ```sh Okt 07 15:44:57 mylab ollama[397923]: [GIN] 2025/10/07 -...
Hi team, Does the project support remove a specific imported document by document id? Thanks
I have 4txt files to make their kg, I wrote sanitize def to delete any citation between sentences and default neo4j prompt; but it makes empty json and in raw_response.txt...
