Get a generative AI profile - Fluid Topics - Latest

Fluid Topics API Reference Guide
Category
Reference Guides
Audience
public
Version
Latest

This web service allows users with the ADMIN role to get a generative AI profile.

For more information about generative AI profiles, see Generative AI.

Method Endpoint
GET 
/api/admin/ai/profiles/{id}

Response body

{
  "id": "f37323eb-5e72-402f-be99-ab53a46cca29",
  "profileType": "COMPLETION",
  "name": "summarize",
  "profileId": "summarize",
  "apiKey": "XXX",
  "customPrompt": "Can you write a concise and comprehensive summary of {topic}? The topic is formatted using HTML. Ignore the HTML formatting and focus on the actual text.\n\nYou must begin your message by \"Hi {name}!\".\n\nYou must be concise. Your message should be shorter than the original topic.",
  "numSemanticSearchResults": 5
}
Field Type Description
id String The unique identifier for the profile.
profileType String The type of the profile. Can be COMPLETION, CHATBOT, or TRANSLATION.
name String The name of the profile.
profileId String The profile ID of the profile.
apiKey String The API key for the Large Language Model (LLM) provider or translation provider.
customPrompt String The LLM prompt. The prompt can contain variables. Place variables in single curly brackets. Users can set the values of these variables when using the Query a large language model (LLM) web service.
numSemanticSearchResults Number The number of semantic search results provided to the large language model (LLM) when calling the Retrieval-augmented generation web service. The value can range from 1 to 20. By default, the value is 5.
numSemanticSearchResultsAfterRerank Number The number of semantic search results provided to the large language model (LLM) after reranking. The value must be smaller or equal to the value of the numSemanticSearchResults field.
ragPrompt String A Retrieval-augmented generation (RAG) prompt. Asks the user question to the LLM. It must have the {relevant_documents} and {chatbot_instructions} variables. {chatbot_instructions} dynamically contains the relevant documents (gotten through the Clustered semantic search web service), and {chatbot_instructions} is the customPrompt value.
ragHistoryPrompt String A Retrieval-augmented generation (RAG) history prompt. Asks the LLM to transform the user question and the conversation history into a standalone question asked to the LLM.
translationAdvancedSettings String Only with TRANSLATION profiles. Parameters for the translation engine. Accepts JSON as a string.
Return code Description
200 OK The profile was gotten successfully.
401 UNAUTHORIZED The authorization header is absent or invalid.

For a comprehensive list of all possible return codes, see Return codes.