"Cohere" (Service Connection)
This service connection requires an external account »
Use the Cohere API with the Wolfram Language.
Connecting & Authenticating
ServiceConnect["Cohere"] creates a connection to the Cohere API. If a previously saved connection can be found, it will be used; otherwise, a new authentication request will be launched.
Requests
ServiceExecute["Cohere","request",params] sends a request to the Cohere API, using parameters params. The following gives possible requests.
"TestConnection" — returns Success for working connection, Failure otherwise
Text
"Completion" — create text completion for a given prompt
| "Prompt" | (required) | the prompt for which to generate completions | |
| "MaxTokens" | Automatic | maximum number of tokens to generate | |
| "FrequencyPenalty" | Automatic | penalize tokens based on their existing frequency in the text so far (between -2 and 2) | |
| "Model" | Automatic | name of the model to use | |
| "N" | Automatic | number of completions to return | |
| "PresencePenalty" | Automatic | penalize new tokens based on whether they appear in the text so far | |
| "StopTokens" | Automatic | strings where the API will stop generating further tokens | |
| "Stream" | False | return the result as server-sent events | |
| "Temperature" | Automatic | sampling temperature | |
| "TopProbabilities" | Automatic | sample only among the k highest-probability classes | |
| "TotalProbabilityCutoff" | Automatic | an alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with the requested probability mass |
"Chat" — create a response for the given chat conversation
| "Messages" | (required) | a list of messages in the conversation, each given as an association with "Role" and "Content" keys | |
| "MaxTokens" | Automatic | maximum number of tokens to generate | |
| "Model" | Automatic | name of the model to use | |
| "StopTokens" | Automatic | strings where the API will stop generating further tokens | |
| "Stream" | False | return the result as server-sent events | |
| "Temperature" | Automatic | sampling temperature | |
| "Tools" | Automatic | one or more LLMTool objects available to the model | |
| "TopProbabilities" | Automatic | sample only among the k highest-probability classes | |
| "TotalProbabilityCutoff" | Automatic | an alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with the requested probability mass |
"Embedding" — create an embedding vector representing the input text
| "Input" | (required) | one text or a list of texts to get embeddings for | |
| "Model" | Automatic | name of the model to use |
Model Lists
"ChatModelList" — list models available for the "Chat" request
"EmbeddingModelList" — list models available for the "Embedding" request