NVIDIA / NVIDIA/GenerativeAIExamples

Knowledge Graph Rag (Community) - Steps Missing

Open
#281 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
4.2k
Forks
1.1k
Avg merge
10h 15m
Merged PRs (30d)
1

Description

I am trying to run the Community Graph RAG example as mentioned here. But it looks like there are some steps missing between 6 and 7. When I am doing the python server.py as mentioned in Step 7 I am getting the following error

Traceback (most recent call last):
  File "D:\KnowledgeGrpahRAG\GenerativeAIExamples\community\knowledge_graph_rag\backend\server.py", line 18, in <module>
    from routers import ui_backend,chat,evaluation,visualization
  File "D:\KnowledgeGrpahRAG\GenerativeAIExamples\community\knowledge_graph_rag\backend\routers\chat.py", line 42, in <module>
    KG_GRAPHML_PATH = os.path.join(DATA_DIR, "knowledge_graph.graphml")
  File "C:\Users\avish\AppData\Local\Programs\Python\Python310\lib\ntpath.py", line 104, in join
    path = os.fspath(path)
TypeError: expected str, bytes or os.PathLike object, not NoneType

It is looking for knowledge_graph.graphml which possibly is created through some other scripts but not mentioned there. Possibly it will need pre-execution of lc_graph.py under utils folder. Any help to figure out what to do would be appreciated.

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Read the Community Graph RAG instructions around Steps 6 and 7, then inspect community/knowledge_graph_rag/backend/server.py and the mentioned utils/lc_graph.py. Document the missing prerequisite or generation step for knowledge_graph.graphml so a user can follow the example and start server.py without the reported error.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, documentation
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.