search

circlemind-ai / fast-graphrag

RAG that intelligently adapts to your use case, data, and queries
MIT License
2.11k stars 88 forks source link

RuntimeError: Cannot return the results in a contiguous 2D array. Probably ef or M is too small #22

Closed oliveiracwb closed 4 days ago

oliveiracwb commented 6 days ago

Describe the bug RuntimeError: Cannot return the results in a contiguous 2D array. Probably ef or M is too small

To Reproduce Steps to reproduce the behavior:

  1. Simple document in UTF
  2. Simple query: ´´ from fast_graphrag import GraphRAG

DOMAIN = "Quais os elementos envolvidos na história abaixo."

EXAMPLE_QUERIES = [ "Quais são os personagens, elementos e datas envolvidas e como elas se relacionam ?" ]

ENTITY_TYPES = ["Pessoas", "Lugares", "Datas"]

grag = GraphRAG( working_dir="./book_example", domain=DOMAIN, example_queries="\n".join(EXAMPLE_QUERIES), entity_types=ENTITY_TYPES )

with open("./book.txt") as f: grag.insert(f.read())

print(grag.query("Quais os elementos envolvidos?").response) ´´

liukidar commented 6 days ago

This should have been fixed with the last commit, please try!

liukidar commented 4 days ago

Please feel free to reopen this is the issue persist, but I believe it should be fixed now.

oliveiracwb commented 14 hours ago

I wanted to let you know that the issue has been resolved, and everything is working perfectly now. Thank you so much for your prompt attention and support!