Skip to content

Update README of DivLog #129

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.

Sign up for GitHub

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

Merged
merged 3 commits into from
Apr 19, 2025
Merged

Update README of DivLog #129

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9b0e0a3
Update README.md
Siyuexi Apr 19, 2025
00fa404
Update README.md
Siyuexi Apr 19, 2025
6e2aa7a
Update README.md
Siyuexi Apr 19, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 3 additions & 2 deletions logparser/DivLog/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -35,7 +35,9 @@ rm -r results

#### Attention:

OpenAI has [shut down](https://platform.openai.com/docs/deprecations/2023-07-06-gpt-and-embeddings) the *Text Completion API* for the GPT-3 model series (`ada`,`babbage`,`curie`,`davinci`) as of January 4th, 2024. If you wish to apply the DivLog framework on other OpenAI *Chat Completion APIs* and re-run all the results, you may need to modify the API request in `BatchParse` of `DivLog.py`. Specifically, you need to replace the original API request design for GPT-3 models with the latest Chat Completion API:
OpenAI has [shut down](https://platform.openai.com/docs/deprecations/2023-07-06-gpt-and-embeddings) the *Text Completion API* for the GPT-3 model series (`ada`,`babbage`,`curie`,`davinci`) as of January 4th, 2024. We recommend you to use other *base models* (rather than *instruct models*) for replication of DivLog since the instruction alignment may affect the ICL capability. In addition, if you wish to use DivLog as a baseline for log parsing comparison, we suggest to use the *same* model as your own method since DivLog framework is *decoupled* with the model backbone.

However, if you wish to apply the DivLog framework on other OpenAI *Chat Completion APIs* (which are instruct models) and re-run all the results, you may need to modify the API request in `BatchParse` of `DivLog.py`. Specifically, you need to replace the original API request design for GPT-3 models with the latest Chat Completion API:

```python
### Replace it
Expand All @@ -48,7 +50,6 @@ response = openai.Completion.create(

More details about APIs can be found [here](https://platform.openai.com/docs/api-reference/chat).


### Benchmark

Running the benchmark script on Loghub_2k datasets, you could obtain the following results.
Expand Down
Loading