Microsoft Copilot

microsoft copilot is an ai powered tool that provides intelligent query execution and data analysis to enhance security operations microsoft copilot is an ai driven platform that provides real time, contextual insights and answers by leveraging advanced language models the microsoft copilot connector for swimlane turbine allows users to execute queries and receive intelligent responses directly within their security workflows this integration enhances decision making and accelerates incident response by providing immediate access to ai generated information and suggestions, tailored to the specific needs of security professionals limitations none to date supported versions this connector supports the latest version of microsoft copilot prerequisites to effectively utilize the microsoft copilot connector within swimlane turbine, ensure you have the following api key authentication with the necessary parameters url endpoint for the microsoft copilot service api key a valid key to authenticate and authorize the integration capabilities this connector provides the following capabilities ask copilot ask copilot generates output using the selected model and the input text microsoft copilot's documentation for this action can be found here https //learn microsoft com/en us/azure/ai foundry/openai/reference#chat completions configurations api key authentication authenticates using an api key configuration parameters parameter description type required url azure openai endpoint url string required api key openai api key string required verify ssl verify ssl certificate boolean optional http proxy a proxy to route requests through string optional actions ask copilot executes a query with microsoft copilot using a specified prompt, deployment id, and api version to retrieve relevant results endpoint url /openai/deployments/{{deployment id}}/chat/completions method post input argument name type required description parameters api version string required api version to use for the request path parameters deployment id string required deployment id of the model which was deployed prompt string optional prompt to send to the model best of number optional generates best of completions server side and returns the "best" echo boolean optional echo back the prompt in addition to the completion frequency penalty number optional positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics logit bias object optional modify the likelihood of specified tokens appearing in the completion logprobs number optional include the log probabilities on the logprobs most likely output tokens, as well the chosen tokens max tokens number optional the maximum number of tokens that can be generated in the completion n number optional how many completions to generate for each prompt presence penalty number optional positive values penalize new tokens based on whether they appear in the text so far, decreasing the model's likelihood to talk about new topics seed number optional random number seed stop string optional up to four sequences where the api will stop generating further tokens stream boolean optional whether to stream back partial progress suffix string optional the suffix that comes after a completion of inserted text temperature number optional what sampling temperature to use, between 0 and 2 top p number optional what value to use for nucleus sampling user string optional a unique identifier representing your end user, which can help to monitor and detect abuse input example {"parameters" {"api version" "2024 02 15 preview"},"json body" {"prompt" "what is the capital of france?","best of" 1,"echo"\ false,"frequency penalty" 0,"logit bias" {},"logprobs" 5,"max tokens" 16,"n" 1,"presence penalty" 0,"seed" 42,"stop" "","stream"\ false,"suffix" "","temperature" 1,"top p" 1,"user" "user 1234567890"},"path parameters" {"deployment id" "gpt 4o mini"}} output parameter type description message string response message status code number http status code of the response reason string response reason phrase output example {"message" "paris is the capital and most populous city of france \nsituated on the seine ri ","status code" 200,"headers"\ null,"reason" "ok"} response headers header description example content type the media type of the resource application/json date the date and time at which the message was originated thu, 01 jan 2024 00 00 00 gmt