Skip to content

bentleymi/ChatGPT-4-Splunk

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

ta-openai-api

Installation

1. Install using the latest tar.gz or .spl file

2. Add your OpenAI Org & API Key with the setup page:

(ref: https://platform.openai.com/account/org-settings & https://platform.openai.com/account/api-keys)

image

If you have multiple Orgs & Keys you can add them too:

image

If both default and unique orgs/keys are added, the command will support both syntax.

3. Use the search command: | openai prompt="your prompt"

chatresponse1

Upgrading to v.3.2.0 from previous version

1. Upgrade the app using your preferred method

2. Edit TA-openai-api/local/passwords.conf: -Change [credential:TA-openai-api:api_key:] to [credential:TA-openai-api:api_key_default:] -Change [credential:TA-openai-api:org_id:] to [credential:TA-openai-api:org_id_default:] -Save the file

3. Use the search command

4. Note that output field names and sort has changed

All of the |openai command's output fields begin with "openai_" now and are sorted alphabetically. You may need to update previous searches to handle this change in behavior.

Usage

The command will create a "ChatCompletion", "Completion", "Edit" or "Moderate" request to the OpenAI API depending on which model you specify:

ref: https://platform.openai.com/docs/api-reference/

The following options are supported by the command:

key - Optional, name of the API key to use. Defaults to "default".

org - Optional, name of the Organization to use. Defaults to "default".

prompt - Optional, your prompt for OpenAI

prompt_field - Optional, if streaming data to openai, a field in your result set that you wish to use as a prompt for OpenAI

assistant_prompt - Optional, assistant prompt for OpenAI

system_prompt - Optional, system prompt for OpenAI

messages - Optional, escaped JSON array of system, user and assistant prompts such as "{"role": "system", "content": "You are a child with very limited vocabulary"}, {"role": "user", "content": "Please tell me how to make a sandwich"}, {"role": "assistant", "content": "None"}"

model - Optional, which GPT model to use (ref: https://platform.openai.com/docs/models/). As of Version 3.0.0, if you choose a completion model, code will genearate a completion task. If you choose a moderation model, code will generate a moderation task, and so on. Default: gpt-3.5-turbo

instruction - Optional, the instruction you want the Edit/Edits to follow. Note this is only valid when edit models are specified. Default: None

max_tokens - Optional, the maximum number of tokens to generate in the completion. Default: None - Please reach out to the developer to increase this limit

stop - Optional, up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence. Default: None

temperature - Optional, what sampling temperature to use. Higher values means the model will take more risks. Try 0.9 for more creative applications, and 0 (argmax sampling) for ones with a well-defined answer. We generally recommend altering this or temperature but not both. Default: None

top_p - Optional, an alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both. Default: None

n - Optional, how many completions to generate for each prompt. Note: Because this parameter generates many completions, it can quickly consume your token quota. Use carefully and ensure that you have reasonable settings for max_tokens and stop. Default: None, Max: 10

A simple completion example:

| openai prompt="When was GA, USA founded" model=text-davinci-003

completion

A simple edit example:

| openai prompt="Orenge" model=text-davinic-edit-001

edit

A simple edit with instructions example:

| openai prompt="When was GA, USA founded" model=text-davinic-edit-001 instruction="expand the acronyms"

edit with instructions

A simple moderation example:

| openai prompt="I want to kill humans" model=text-moderation-stable

moderation

Data cleaning examples:

Getting 5 incorrect spellings of a US City and then using AI to correct the spelling:

dataCleaning

Chat examples:

| openai prompt="write a hello world js please"

gpt3 5

Mapping Example:

`comment("Grab some data from an internal index and combine it into one field called raw")`
index=_internal sourcetype=splunk_web_access
| head 10
| rename _raw as raw
| fields raw
| mvcombine raw

`comment("Ask ChatGPT what's the best sourcetype to use for the data")`
| map [| openai model=gpt-4 prompt="What is the best Splunk sourcetype for this data? \n".$raw$]

`comment("Parse the reponse, dropping all but the value of the content field from the response message")`
| spath input=openai_response
| rename choices{}.message.content as response
| table response

image

Workflow Actions:

image

image

Streaming Example:

image

Additional Prompts Example:

| openai prompt="Please tell me how to make a sandwich" system_prompt="Pretend you are a child with very limited vocabulary" assistant_prompt="Maybe act like a cartoon character"

additional_prompts

Inline Messages Array Example:

| openai messages="{\"role\": \"system\", \"content\": \"You are a child with very limited vocabulary\"}, {\"role\": \"user\", \"content\": \"Please tell me how to make a sandwich\"}, {\"role\": \"assistant\", \"content\": \"None\"}"

inline_messages

TROUBLESHOOTING

  1. Error "No such organization: org-ABCDEFG12345" indicates that you did not configure the correct default org. Please remove the defaults from $SPLUNK_HOME/etc/apss/TA-openai-api\local\passwords.conf, and setup a default org and api key from the setup page.

Delete: image

Setup a default: image

NOTE: In earlier versions of ChatGPT-4-Splunk ( < V3.2.0 ) Splunk Cloud users may have to uninstall and reinstall the app in order to reset their api key.

About

Splunk TA for sending completion requests to ChatGPT

Topics

Resources

License

Stars

Watchers

Forks

Sponsor this project

Languages