Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Doc] README Updates for Neo4J Dataprep, GraphRAG, #1428

Open
edlee123 opened this issue Mar 18, 2025 · 1 comment
Open

[Doc] README Updates for Neo4J Dataprep, GraphRAG, #1428

edlee123 opened this issue Mar 18, 2025 · 1 comment
Assignees
Labels
A1 high prority feature New feature or request

Comments

@edlee123
Copy link

This issue documents inconsistencies in environment variables for Neo4j Dataprep across different files within the GenAIComps and GenAIExamples repositories. These inconsistencies can lead to confusion and deployment issues.

DATAPREP_PORT:

  • GenAIComps/tests/dataprep/test_dataprep_neo4j_on_intel_hpu.sh: 11103.
  • GenAIComps/comps/dataprep/src/README_neo4j_llamaindex.md: 6004.
  • GenAIExamples/GraphRAG/README.md: Mentions both 11103 and 6007 for dataprep ingest (can use environment variable instead of hardcode).

TEI_EMBEDDER_PORT:

  • GenAIComps/tests/dataprep/test_dataprep_neo4j_on_intel_hpu.sh: 12006
  • GenAIComps/comps/dataprep/src/README_neo4j_llamaindex.md: 11633
  • GenAIExamples/GraphRAG/README.md: 6006

NEO4J_URI / NEO4J_URL:

  • GenAIComps/tests/dataprep/test_dataprep_neo4j_on_intel_hpu.sh sets NEO4J_URL.
  • GenAIComps/comps/dataprep/src/README_neo4j_llamaindex.md sets both to the same value.
  • GenAIExamples/GraphRAG/README.md sets NEO4J_URI.

NEO4J_PLUGINS:

  • GenAIComps/tests/dataprep/test_dataprep_neo4j_on_intel_hpu.sh: Sets NEO4J_PLUGINS to ["apoc"].
  • GenAIComps/comps/dataprep/src/README_neo4j_llamaindex.md: Does not explicitly set or mention NEO4J_PLUGINS.
  • GenAIExamples/GraphRAG/README.md: Does not explicitly set or mention NEO4J_PLUGINS.

NEO4J_PORT2:

  • GenAIComps/tests/dataprep/test_dataprep_neo4j_on_intel_hpu.sh: Sets NEO4J_PORT2 to 7687 (and also mentions a commented-out alternative 11632).
  • GenAIComps/comps/dataprep/src/README_neo4j_llamaindex.md: Sets NEO4J_PORT2 to 7687 (and also mentions a commented-out alternative 11632). It also sets NEO4J_URI and NEO4J_URL using this port.
  • GenAIExamples/GraphRAG/README.md: Does not explicitly set NEO4J_PORT2, but it does mention it in the context of NEO4J_URI and in a table showing port 7687.

Recommendation:

We can choose one set of ports, environment variables e.g. from the unit test, and update accordingly GenAIComps/comps/dataprep/src/README_neo4j_llamaindex.md and GenAIExamples/GraphRAG/README.md.

Roo Prompt (FYI):
"Could you take a look at these files below and check for inconsistencies between them e.g. environment variables, ports? GenAIExamples/GraphRAG/README.md
GenAIComps/tests/dataprep/test_dataprep_neo4j_on_intel_hpu.sh
GenAIComps/comps/dataprep/src/README_neo4j_llamaindex.md"

"Could you also summarize the differences between the files for environment variable NEO4J_PLUGINS=["apoc"], and NEO4J PORT2?"

Perhaps checks of unit tests vs. README can be automated with LLM?

@yinghu5 yinghu5 added A1 high prority feature New feature or request labels Mar 19, 2025
@edlee123
Copy link
Author

Note: I'm working on a tool to generate this kind of review for all READMEs vs. unit tests.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
A1 high prority feature New feature or request
Projects
None yet
Development

No branches or pull requests

4 participants