ChatObject

This functionality requires an external account »

ChatObject[]

represents an ongoing conversation with a remote service.

ChatObject[init]

creates a new chat using the initialization parameters init.

ChatObject[…][prop]

extracts the property prop from the object.

Details and Options

  • ChatObject stores a full conversation together with the message metadata.
  • The initialization init can take the following parameters:
  • "string"static text
    LLMPrompt["name"]a repository prompt
    StringTemplate[…]templated text
    TemplateObject[…]template for creating a prompt
    Image[…]an image
    {prompt1,…}a list of prompts
    {msg1,…}a list of messages
  • Template objects are automatically converted to strings via TemplateObject[…][].
  • Prompt created with TemplateObject can contain text and images. Not every LLM supports image input.
  • When the initialization is a list of messages, each message must be an association with the following keys:
  • "Role"Stringrole of the participant
    "Content"contentcontent of the message
    "Timestamp"DateObjectmessage timestamp (optional)
  • Possible form of content are:
  • "text"a string
    Image[…]an image object
    <|"Type""Text","Data"data|>an explicit text part
    <|"Type""Image","Data"data|>an explicit image part (supports File[…] objects)
    {content1,…}multiple part content
  • Possible values for "Role" include:
  • "Assistant"LLM-generated message
    "System"system message
    "Tool"autogenerated tool response
    "User"user message
  • The following options can be specified:
  • AuthenticationAutomaticexplicit user ID and API key
    LLMEvaluator $LLMEvaluatorLLM configuration to use
  • LLMEvaluator can be set to an LLMConfiguration object or an association with any of the following keys:
  • "MaxTokens"maximum amount of tokens to generate
    "Model"base model
    "PromptDelimiter"string to insert between prompts
    "Prompts"initial prompts or LLMPromptGenerator objects
    "StopTokens"tokens on which to stop generation
    "Temperature"sampling temperature
    "ToolMethod"method to use for tool calling
    "Tools"list of LLMTool objects to make available
    "TopProbabilities"sampling classes cutoff
    "TotalProbabilityCutoff"sampling probability cutoff (nucleus sampling)
  • Valid forms of "Model" include:
  • namenamed model
    {service,name}named model from service
    <|"Service"service,"Name"name,"Task"task|>fully specified model
  • Supported services include:
  • "Anthropic"
    "OpenAI"
    "GoogleGemini"
  • "OpenAI"  "Anthropic"  "GoogleGemini"  "AlephAlpha"  "Cohere"  "DeepSeek"  "Groq"  "MistralAI"  "TogetherAI"
  • The generated text is sampled from a distribution. Details of the sampling can be specified using the following properties of the LLMEvaluator:
  • "Temperature"tAutomaticsample using a positive temperature t
    "TopProbabilities"kAutomaticsample only among the k highest-probability classes
    "TotalProbabilityCutoff"pAutomaticsample among the most probable choices with an accumulated probability of at least p (nucleus sampling)
  • The Automatic value of these parameters uses the default for the specified "Model".
  • Possible values for "ToolMethod" include:
  • Automaticuse tools when supported by service
    "Service"rely on the tool mechanism of service
    "Textual"used prompt-based tool calling
  • Possible values for Authentication are:
  • Automaticchoose the authentication scheme automatically
    Environmentcheck for a key in the environment variables
    SystemCredentialcheck for a key in the system keychain
    ServiceObject[…]inherit the authentication from a service object
    assocprovide explicit key and user ID
  • With AuthenticationAutomatic, the function checks the variable ToUpperCase[service]<>"_API_KEY" in Environment and SystemCredential; otherwise, it uses ServiceConnect[service].
  • When using Authenticationassoc, assoc can contain the following keys:
  • "ID"user identity
    "APIKey"API key used to authenticate
  • Properties of a chat object can be extracted using ChatObject[…][prop].
  • Possible values for prop include:
  • "ChatID"the unique ID of the conversation
    "FullText"string representation of the conversation
    "LLMEvaluator"the stored LLMConfiguration
    "Messages"a list of exchanged messages
    "Properties"a list of all the possible properties
    "Usage"cumulative API usage (calls, tokens, …)
    {prop1,…}a list of properties

Examples

open allclose all

Basic Examples  (2)

Create a new chat:

Add a message and a response to the conversation:

Get a list of all the messages:

Create a chat object with a tool:

Show the LLM answer together with the tool-calling steps:

Scope  (5)

Create an empty chat:

Create a chat with an initial prompt:

Create a chat from a list of messages:

Extract a chat property:

Extract a list of properties:

List all the available properties:

Options  (1)

LLMEvaluator  (1)

Create a chat that uses a specific model:

Wolfram Research (2023), ChatObject, Wolfram Language function, https://reference.wolfram.com/language/ref/ChatObject.html.

Text

Wolfram Research (2023), ChatObject, Wolfram Language function, https://reference.wolfram.com/language/ref/ChatObject.html.

CMS

Wolfram Language. 2023. "ChatObject." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/ChatObject.html.

APA

Wolfram Language. (2023). ChatObject. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/ChatObject.html

BibTeX

@misc{reference.wolfram_2024_chatobject, author="Wolfram Research", title="{ChatObject}", year="2023", howpublished="\url{https://reference.wolfram.com/language/ref/ChatObject.html}", note=[Accessed: 26-July-2024 ]}

BibLaTeX

@online{reference.wolfram_2024_chatobject, organization={Wolfram Research}, title={ChatObject}, year={2023}, url={https://reference.wolfram.com/language/ref/ChatObject.html}, note=[Accessed: 26-July-2024 ]}