Class JambaRequest

Inheritance
object
JambaRequest
Inherited Members
Namespace: Glitch9.AIDevKit.AI21Labs
Assembly: Glitch9.AIDevKit.Provider.AI21.dll
Syntax
public sealed class JambaRequest

Properties

| Edit this page View Source

Documents

Optional. The document parameter accepts a list of objects, each containing multiple fields.

Declaration
[JsonProperty("documents")]
public AI21LabsDocument[] Documents { get; set; }
Property Value
Type Description
AI21LabsDocument[]
| Edit this page View Source

MaxTokens

Optional. The maximum number of tokens the model can generate in its response. For Jamba models, the maximum allowed value is 4096 tokens.

Declaration
[JsonProperty("max_tokens")]
public int? MaxTokens { get; set; }
Property Value
Type Description
int?
| Edit this page View Source

Messages

Required. A list of messages representing the conversation history.

Declaration
[JsonProperty("messages")]
public Message[] Messages { get; set; }
Property Value
Type Description
Message[]
| Edit this page View Source

Model

Required. The name of the model to use. You can call our model without specifying a version by using: jamba-large, jamba-mini

Declaration
[JsonProperty("model")]
public string Model { get; set; }
Property Value
Type Description
string
| Edit this page View Source

N

Optional. How many chat responses to generate. Default: 1, Range: 1–16. Notes:

  • If n > 1, setting temperature = 0 will fail.
  • n must be 1 when stream = True
Declaration
[JsonProperty("n")]
public int? N { get; set; }
Property Value
Type Description
int?
| Edit this page View Source

RawRequest

Declaration
[JsonIgnore]
public IGenerativeRequest RawRequest { get; set; }
Property Value
Type Description
IGenerativeRequest
| Edit this page View Source

ResponseFormat

Optional. An object defining the output format required from the model. Setting it to { "type": "json_object" } activates JSON mode.

Declaration
[JsonProperty("response_format")]
public ResponseFormat ResponseFormat { get; set; }
Property Value
Type Description
ResponseFormat
| Edit this page View Source

Stop

Optional. End the message when the model generates one of these strings. The stop sequence is not included in the generated message.

Declaration
[JsonProperty("stop")]
public string[] Stop { get; set; }
Property Value
Type Description
string[]
| Edit this page View Source

Stream

Optional. Stream results one token at a time using server-sent events. Useful for long results to avoid long wait times. If True, n must be 1. Must be False if using tools.

Declaration
[JsonProperty("stream")]
public bool? Stream { get; set; }
Property Value
Type Description
bool?
| Edit this page View Source

Temperature

Optional. Controls the variety of responses provided; a higher value results in more diverse answers. Default: 0.4, Range: 0.0–1.0

Declaration
[JsonProperty("temperature")]
public float? Temperature { get; set; }
Property Value
Type Description
float?
| Edit this page View Source

Tools

Optional. A list of tools that the model can use when generating a response. Currently, only function type tools are supported.

Declaration
[JsonProperty("tools")]
public ToolEnvelope[] Tools { get; set; }
Property Value
Type Description
ToolEnvelope[]
| Edit this page View Source

TopP

Declaration
[JsonProperty("top_p")]
public float? TopP { get; set; }
Property Value
Type Description
float?

Extension Methods