From 9b0e0a30b9526597aa6fa28e33f9f422d312658f Mon Sep 17 00:00:00 2001 From: Junjielong Xu <50619651+Siyuexi@users.noreply.github.com> Date: Sat, 19 Apr 2025 17:11:06 +0800 Subject: [PATCH 1/3] Update README.md --- logparser/DivLog/README.md | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/logparser/DivLog/README.md b/logparser/DivLog/README.md index a5f6cc9..6a46757 100755 --- a/logparser/DivLog/README.md +++ b/logparser/DivLog/README.md @@ -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 replicate DivLog since the instruction alignment may affect the ICL capability. Since DivLog framework is *decoupled* with the model backbone, we recommend to use the *same* model as your own method if you wish to use DivLog as a baseline for log parsing comparison. + +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 @@ -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. From 00fa40455972d94807b0cc0757d68dbef18ebe48 Mon Sep 17 00:00:00 2001 From: Junjielong Xu <50619651+Siyuexi@users.noreply.github.com> Date: Sat, 19 Apr 2025 17:16:06 +0800 Subject: [PATCH 2/3] Update README.md --- logparser/DivLog/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/logparser/DivLog/README.md b/logparser/DivLog/README.md index 6a46757..68e3b42 100755 --- a/logparser/DivLog/README.md +++ b/logparser/DivLog/README.md @@ -35,7 +35,7 @@ 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. We recommend you to use other *base models* (rather than *instruct models*) for replicate DivLog since the instruction alignment may affect the ICL capability. Since DivLog framework is *decoupled* with the model backbone, we recommend to use the *same* model as your own method if you wish to use DivLog as a baseline for log parsing comparison. +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 replicate 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: From 6e2aa7ac34b5b54d0641c34a7eca56ea1401917f Mon Sep 17 00:00:00 2001 From: Junjielong Xu <50619651+Siyuexi@users.noreply.github.com> Date: Sat, 19 Apr 2025 17:16:47 +0800 Subject: [PATCH 3/3] Update README.md --- logparser/DivLog/README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/logparser/DivLog/README.md b/logparser/DivLog/README.md index 68e3b42..885f554 100755 --- a/logparser/DivLog/README.md +++ b/logparser/DivLog/README.md @@ -35,7 +35,7 @@ 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. We recommend you to use other *base models* (rather than *instruct models*) for replicate 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. +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: