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

[Bug]: python code in example notebook for local search can not query context correctly #1424

Open
3 tasks done
lpb1 opened this issue Nov 20, 2024 · 1 comment
Open
3 tasks done
Labels
bug Something isn't working triage Default label assignment, indicates new issue needs reviewed by a maintainer

Comments

@lpb1
Copy link

lpb1 commented Nov 20, 2024

Do you need to file an issue?

  • I have searched the existing issues and this bug is not already filed.
  • My model is hosted on OpenAI or Azure. If not, please look at the "model providers" issue and don't file a new one here.
  • I believe this is a legitimate bug, not just a question. If this is a question, please use the Discussions area.

Describe the bug

The local search in python code can not get context with new v0.5.0. The cli command works well.

The two query are on same index with same question.

  1. python code query :
Do not include information where the supporting evidence for it is not provided.

---Target response length and format---

multiple paragraphs

---Data tables---

---Goal---

Generate a response of the target length and format that responds to the user's question, summarizing all information in the input data tables appropriate for the response length and format, and incorporating any relevant general knowledge.
  1. cli query:
Do not include information where the supporting evidence for it is not provided.

---Target response length and format---

Multiple Paragraphs

---Data tables---

[]

-----Entities-----
id|entity|description|number of relationships
99|AT-FAULT ACCIDENTS|At-fault Accidents are accidents deemed to be the responsibility of the insured based on various criteria, including MVR data and claims history.}|4
......
-----claims-----
id|entity|object_id|status|start_date|end_date|description
-----Sources-----
id|text
4| Date is used to determine
if the violation took place within the Accident and Violation Evaluation
Period or if the accident took place within the Extended Accident
....
---Goal---

Generate a response of the target length and format that responds to the user's question, summarizing all information in the input data tables appropriate for the response length and format, and incorporating any relevant general knowledge.

Steps to reproduce

No response

Expected Behavior

No response

GraphRAG Config Used

# Paste your config here

Logs and screenshots

No response

Additional Information

  • GraphRAG Version: v0.5.0
  • Operating System:
  • Python Version:
  • Related Issues:
@lpb1 lpb1 added bug Something isn't working triage Default label assignment, indicates new issue needs reviewed by a maintainer labels Nov 20, 2024
@andreiionut1411
Copy link

Duplicate #1335

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
bug Something isn't working triage Default label assignment, indicates new issue needs reviewed by a maintainer
Projects
None yet
Development

No branches or pull requests

2 participants