WOLFRAM

Wolfram Language & System Documentation Center
Wolfram Language Home Page »

ChatSubmit
✖
ChatSubmit

New in 14.2[Experimental]

✖
ChatSubmit[chat,prompt]

submits prompt to be appended with its follow-ups to the ChatObject chat asynchronously.

Details and Options

  • ChatSubmit is used to continue the conversation in a ChatObject asynchronously.
  • ChatSubmit requires external service authentication, billing and internet connectivity.
  • Possible values for prompt include:
  • "text"static text
    LLMPrompt["name"]a repository prompt
    StringTemplate[…]templated text
    TemplateObject[…]template for creating a prompt
    Image[…]an image
    {prompt1,…}a list of prompts
  • Prompt created with TemplateObject can contain text and images. Not every LLM supports image input.
  • ChatSubmit returns a TaskObject[…].
  • The following options can be specified:
  • Authentication Inheritedexplicit user ID and API key
    HandlerFunctions how to handle generated events
    HandlerFunctionsKeys Automaticparameters to supply to handler functions
    LLMEvaluator InheritedLLM configuration to use
  • During the asynchronous execution of ChatSubmit, various events can be generated.
  • Events triggered by the LLM:
  • "ContentChunkReceived"incremental message content received
    "StoppingReasonReceived"stopping reason for the generation received
    "MetadataReceived"other metadata received
    "ToolRequestReceived"LLMToolRequest[…] received
    "UsageInformationReceived"incremental usage information received
  • Events triggered by local processing:
  • "ChatObjectGenerated"the final ChatObject[…] generated
    "ToolResponseGenerated"an LLMToolResponse[…] generated
  • Events triggered by the task framework:
  • "FailureOccurred"failure generated during the computation
    "TaskFinished"task completely finished
    "TaskRemoved"task being removed
    "TaskStarted"task started
    "TaskStatusChanged"task status changed
  • HandlerFunctionsf uses f for all the events.
  • With the specification HandlerFunctions-><|…,"eventi"->fi,…|>, fi[assoc] is evaluated whenever eventi is generated. The elements of assoc have keys specified by the setting for HandlerFunctionsKeys.
  • Possible keys specified by HandlerFunctionsKeys include:
  • "ChatObject"modified ChatObject[…]
    "ContentChunk"a message part
    "EventName"the name of the event being handled
    "Failure"failure object generated if task failed
    "Model"model used to generate the message
    "Role"role of the message author
    "StoppingReason"why the generation has stopped
    "Task"the task object generated by ChatSubmit
    "TaskStatus"the status of the task
    "TaskUUID"unique task identifier
    "Timestamp"timestamp of the message
    "ToolRequest"received LLMToolRequest[…]
    "ToolResponse"last generated LLMToolResponse[…]
    "UsageIncrement"token usage update
    {key1,…}a list of keys
    Allall the keys
    Automatickeys lexically present in HandlerFunctions
  • Values that have not yet been received are given as Missing["NotAvailable"].
  • If LLMEvaluator is set to Inherited, the LLM configuration specified in chat is used.
  • 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|>fully specified model
  • Prompts specified in "Prompts" are prepended to the messages in chat with role set as "System".
  • Multiple prompts are separated by the "PromptDelimiter" property.
  • 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:
  • "Service"rely on the tool mechanism of service
    "Textual"use prompt-based tool calling
  • Possible values for Authentication are:
  • Automaticchoose the authentication scheme automatically
    Inheritedinherit settings from chat
    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
  • ChatSubmit uses machine learning. Its methods, training sets and biases included therein may change and yield varied results in different versions of the Wolfram Language.

Examples

open allclose all

Basic Examples  (2)Summary of the most common use cases

Create a new chat:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-6m4n3b
Out[1]=1

Add a message to the conversation and submit it for a response, assigning the result to res:

In[3]:=3
✖
https://wolfram.com/xid/05fczwzf6u-s88bip
Out[3]=3

Inspect the generated conversation:

In[4]:=4
✖
https://wolfram.com/xid/05fczwzf6u-d6fr33
Out[4]=4

Retrieve the generated response chunks from a multimodal model as they are received:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-ov4ikc
Out[1]=1

Show all the generation steps:

In[2]:=2
✖
https://wolfram.com/xid/05fczwzf6u-1yf71i
Out[2]=2

Scope  (2)Survey of the scope of standard use cases

Start a new conversation asynchronously:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-y7l7jg
Out[1]=1

Inspect the task current status:

In[2]:=2
✖
https://wolfram.com/xid/05fczwzf6u-zbin9u
Out[2]=2

Inspect the generated conversation:

In[3]:=3
✖
https://wolfram.com/xid/05fczwzf6u-z76nkb
Out[3]=3

Continue an existing conversation asynchronously:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-oxbxlz
Out[1]=1

Inspect the generated conversation:

In[2]:=2
✖
https://wolfram.com/xid/05fczwzf6u-gshst4
Out[2]=2

Options  (14)Common values & functionality for each option

Authentication  (4)

Provide an authentication key for the API:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-gij216
Out[1]=1

Look for the key in the system keychain:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-63jm2c
Out[1]=1

Specify the name of the key:

In[2]:=2
✖
https://wolfram.com/xid/05fczwzf6u-8e4ef
Out[2]=2

Look for the key in the system environment:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-bplzbz
Out[1]=1

Authenticate via a service object:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-f8oogn
Out[1]=1
In[2]:=2
✖
https://wolfram.com/xid/05fczwzf6u-h0ngpw
Out[2]=2

HandlerFunctions  (2)

Print all generated event names in the messages window:

In[2]:=2
✖
https://wolfram.com/xid/05fczwzf6u-3peq4q
Out[2]=2

Capture the service-generated failure for an non-existing model:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-8lxl0f
Out[1]=1

HandlerFunctionsKeys  (3)

List explicitly the handler function keys to be passed to the handler functions:

In[2]:=2
✖
https://wolfram.com/xid/05fczwzf6u-rfnob8
Out[2]=2

Set HandlerFunctionsKeys values to be inferred lexically from the slots present in the handler functions (default):

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-2s4in6
Out[1]=1

Include all available handler function keys in the handler function argument:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-2z9joh
Out[1]=1

LLMEvaluator  (5)

Specify the service used to generate the answer:

In[2]:=2
✖
https://wolfram.com/xid/05fczwzf6u-pywhgx
Out[2]=2

Specify both the service and the model:

In[3]:=3
✖
https://wolfram.com/xid/05fczwzf6u-jtxab8
Out[3]=3

By default, the text generation continues until a termination token is generated:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-4deaiq
Out[1]=1

Limit the amount of generated samples (tokens):

In[2]:=2
✖
https://wolfram.com/xid/05fczwzf6u-d6g3qu
Out[2]=2

Specify that the sampling should be performed at zero temperature:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-dtptgp
Out[1]=1

Specify a high temperature to get more variation in the generation:

In[2]:=2
✖
https://wolfram.com/xid/05fczwzf6u-82mbhu
Out[2]=2

Compare results:

In[3]:=3
✖
https://wolfram.com/xid/05fczwzf6u-vzw58
Out[3]=3
Out[3]=3

Specify the maximum cumulative probability before cutting off the distribution:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-grgwys
Out[1]=1

Specify a prompt to be automatically added to the conversation:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-8irbhm
Out[1]=1

Applications  (1)Sample problems that can be solved with this function

Tool Calling  (1)

Define a tool that can be called by the LLM:

In[1]:=1
✖
https://wolfram.com/xid/05fczwzf6u-qu60qf
Out[1]=1

Instantiate a chat object with the tool:

In[9]:=9
✖
https://wolfram.com/xid/05fczwzf6u-u94wuw
Out[9]=9

Ask a question that can get a precise answer using the tool:

In[10]:=10
✖
https://wolfram.com/xid/05fczwzf6u-0dzhd4
Out[10]=10

Inspect the generated conversation:

In[12]:=12
✖
https://wolfram.com/xid/05fczwzf6u-ob9hvy
Out[12]=12
Wolfram Research (2025), ChatSubmit, Wolfram Language function, https://reference.wolfram.com/language/ref/ChatSubmit.html.
✖
Wolfram Research (2025), ChatSubmit, Wolfram Language function, https://reference.wolfram.com/language/ref/ChatSubmit.html.

Text

Wolfram Research (2025), ChatSubmit, Wolfram Language function, https://reference.wolfram.com/language/ref/ChatSubmit.html.

✖
Wolfram Research (2025), ChatSubmit, Wolfram Language function, https://reference.wolfram.com/language/ref/ChatSubmit.html.

CMS

Wolfram Language. 2025. "ChatSubmit." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/ChatSubmit.html.

✖
Wolfram Language. 2025. "ChatSubmit." Wolfram Language & System Documentation Center. Wolfram Research. https://reference.wolfram.com/language/ref/ChatSubmit.html.

APA

Wolfram Language. (2025). ChatSubmit. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/ChatSubmit.html

✖
Wolfram Language. (2025). ChatSubmit. Wolfram Language & System Documentation Center. Retrieved from https://reference.wolfram.com/language/ref/ChatSubmit.html

BibTeX

@misc{reference.wolfram_2025_chatsubmit, author="Wolfram Research", title="{ChatSubmit}", year="2025", howpublished="\url{https://reference.wolfram.com/language/ref/ChatSubmit.html}", note=[Accessed: 19-March-2025 ]}

✖
@misc{reference.wolfram_2025_chatsubmit, author="Wolfram Research", title="{ChatSubmit}", year="2025", howpublished="\url{https://reference.wolfram.com/language/ref/ChatSubmit.html}", note=[Accessed: 19-March-2025 ]}

BibLaTeX

@online{reference.wolfram_2025_chatsubmit, organization={Wolfram Research}, title={ChatSubmit}, year={2025}, url={https://reference.wolfram.com/language/ref/ChatSubmit.html}, note=[Accessed: 19-March-2025 ]}

✖
@online{reference.wolfram_2025_chatsubmit, organization={Wolfram Research}, title={ChatSubmit}, year={2025}, url={https://reference.wolfram.com/language/ref/ChatSubmit.html}, note=[Accessed: 19-March-2025 ]}