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

Investigate using LLM (e.g. ChapGPT) as a Processor #225

Closed
chadell opened this issue Mar 28, 2023 · 7 comments
Closed

Investigate using LLM (e.g. ChapGPT) as a Processor #225

chadell opened this issue Mar 28, 2023 · 7 comments
Assignees
Labels
status: gathering feedback Further discussion is needed to determine this issue's scope and/or implementation type: minor feature

Comments

@chadell
Copy link
Collaborator

chadell commented Mar 28, 2023

Proposed Functionality

New LLM (Large Language Model) allow a sophisticated language processing that could get data from structures/unstructured notifications and retrieve part or total of the necessary information.

Use Case

This could avoid having to write custom parser for all Providers

@jvanderaa
Copy link
Contributor

I think this is a great idea. I was also thinking through the idea of send it to a LLM when parsing fails. So allow for a conditional.

@chadell
Copy link
Collaborator Author

chadell commented Mar 29, 2023

Yes, my idea would be to make it the last resort when the known parser failed or there is no parser at all.
Preliminary testing looks good!

@chadell chadell added status: gathering feedback Further discussion is needed to determine this issue's scope and/or implementation type: minor feature labels Mar 29, 2023
@KedharnathGoud
Copy link

We can use something like https://github.com/gventuri/pandas-ai

@AndriusV4
Copy link

Hi, this idea would be amazing if implemented. Was wondering is this still in testing phase?
I have multiple providers that are not supported by the library, so just checking if I should start writing customer parsers for it or are there any plans to implement LLM parser in the near future that could help with this?

Thanks!

@chadell
Copy link
Collaborator Author

chadell commented Oct 2, 2023

Hi @AndriusV4 , this is something we definitely want to explore, but we have not started yet.
Any contribution in this direction would be welcome!

@chadell chadell self-assigned this Oct 19, 2023
@chadell
Copy link
Collaborator Author

chadell commented Oct 19, 2023

I already have PoC that allows parsing only using Machine Learning:

$ circuit-maintenance-parser --data-file "tests/unit/data/aws/aws1.eml" --data-type email 

Circuit Maintenance Notification #0
{
  "account": "aaaaa",
  "circuits": [
    {
      "circuit_id": "aaaaa-00000001",
      "impact": "OUTAGE"
    },
    {
      "circuit_id": "aaaaa-00000002",
      "impact": "OUTAGE"
    },
    {
      "circuit_id": "aaaaa-00000003",
      "impact": "OUTAGE"
    },
    {
      "circuit_id": "aaaaa-00000004",
      "impact": "OUTAGE"
    },
    {
      "circuit_id": "aaaaa-00000005",
      "impact": "OUTAGE"
    },
    {
      "circuit_id": "aaaaa-00000006",
      "impact": "OUTAGE"
    }
  ],
  "end": 1621522800,
  "maintenance_id": "d9f256dcae6c34a4d7c353b19f02957c",
  "organizer": "unknown",
  "provider": "genericprovider",
  "sequence": 1,
  "stamp": 1620337976,
  "start": 1621497600,
  "status": "CONFIRMED",
  "summary": "Planned maintenance has been scheduled on an AWS Direct Connect router in A Block, New York, NY from Thu, 20 May 2021 08:00:00 GMT to Thu, 20 May 2021 14:00:00 GMT for 6 hours.",
  "uid": "0"
}

@chadell chadell mentioned this issue Oct 20, 2023
3 tasks
@chadell
Copy link
Collaborator Author

chadell commented Nov 15, 2023

done in #245

@chadell chadell closed this as completed Nov 15, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
status: gathering feedback Further discussion is needed to determine this issue's scope and/or implementation type: minor feature
Projects
None yet
Development

No branches or pull requests

4 participants