Description

This Elasticsearch Watcher job is integrating your Elastic Observability implementation with the OpenAI API for ChatGPT similar use cases. In the version you can download it is used to ask for a list of reasons and solutions of error messages that occur. At the moment of writing the ChatGPT API is not available, however the existing API for completion is providing very similar results.

To do that the Watcher job is query within an index called es-err every minute. When there is something the Watcher transform part is sending the error message to the API and in a second step indexing the results.

In order to use the Watcher job you may need to change the input and output indices based on your use case. The watcher job is not adapted to the Elastic Common Schema (ECS). You also need to register for the API of OpenAI to get the necessary API Key. When doing that the first time you get 18$ to spend for free.

Why analysing error messages with ChatGPT?

There are several advantages to using ChatGPT results when analyzing error messages in IT applications, including:

  1. Natural language understanding: ChatGPT is trained on a large corpus of text and has the ability to understand and respond to human language, making it easier for you to interpret and analyze error messages in a more human-friendly way.
  2. Quick and accurate analysis: ChatGPT can provide quick and accurate analysis of error messages, helping you to identify the root cause of the problem and take appropriate action.
  3. Improved efficiency: By automating the analysis process, ChatGPT can save you time and increase your efficiency, allowing you to focus on more important tasks.
  4. Increased accuracy: ChatGPT is trained on a large amount of data and uses state-of-the-art machine learning techniques, which can lead to increased accuracy in the analysis of error messages.
  5. Cost-effectiveness: Using ChatGPT for error message analysis can be cost-effective compared to hiring a specialist or developing custom tools for the same purpose.

Overall, ChatGPT can provide valuable support in the analysis of error messages in IT applications, allowing you to quickly and accurately identify and resolve issues, and improve the reliability and stability of your systems.

This original article and watcher job was found at https://mar1.hashnode.dev/unlocking-the-power-of-aiops-with-chatgpt-and-elasticsearch

Tested versions
ECS compliant

You must log in to submit a review.

Related downloads

Move to next ILM phase Watcher

This watcher job is moving specific indices based on e.g. disc usage into the next ILM phase.

Watch to detect large shards

This watch is getting data from the Elasticsearch shards API directly and checking for large shards.

Watcher History Dashboard

This dashboard shows the history of executed watcher jobs.

Uptime watch using Heartbeat data

This watch checks the availability of your Heartbeat observed services. It will trigger an alert whenever at least one of your services is down.

Kibana alerting enhancement

This bundle enhances the Kibana alerting experience. Storing all relevant information in indices and visualize the data in dashboards.

These downloads could be also interesting for you

Plex ingest node pipeline

A plex ingest node pipeline to parse logs from Plex for Elasticsearch

Filebeat Log analysis canvas example

This is a simple canvas dashboard example that analyzes logs created by Filebeat.

Sigma Windows inbuilt detection rules

A collection of rules based on the Sigma rules for Windows (inbuilt folder) based on Winlogbeat data .

Terraform Elasticsearch environments

Terraform example scripts to deploy Elastic Cloud Clusters + all necessary components in AWS and GCP

Watch to detect large shards

This watch is getting data from the Elasticsearch shards API directly and checking for large shards.

Uptime watch using Heartbeat data

This watch checks the availability of your Heartbeat observed services. It will trigger an alert whenever at least one of your services is down.