Skip to main content

​
SarvamAILLM

Sarvam AI large language model (LLM).

​
Constructor

​
apiKey
string
Sarvam AI API key. Defaults to the SARVAM_API_KEY environment variable.
​
model
SarvamAILLMModel | string
Model id. Default 'sarvam-30b'.
​
temperature
number
Sampling temperature; higher is more random. Default 0.7.
​
toolChoice
string
Tool-selection strategy. Default 'auto'.
​
maxCompletionTokens
number
Maximum number of tokens to generate. Default 1024.
​
topP
number | null
Nucleus-sampling probability mass. Default null (provider default).
​
frequencyPenalty
number | null
Frequency penalty. Default null.
​
presencePenalty
number | null
Presence penalty. Default null.
​
seed
number | null
Random seed for reproducible sampling. Default null.
​
stop
string | null
Stop sequence(s). Default null.
​
user
string | null
Stable end-user identifier. Default null.
​
parallelToolCalls
boolean | null
Allow parallel tool calls. Default null (provider default).
​
responseFormat
Record<string, any> | null
Structured-output response format. Default null.
​
reasoningEffort
string
Reasoning effort hint. Default null.
​
wikiGrounding
boolean
Enable wiki grounding. Default false.

​
cancelCurrentGeneration

Cancel the in-flight generation for the current session, if any.

​
chat

Stream a completion for the given messages, yielding LLMResponse chunks.
​
returns
AsyncIterator<LLMResponse>

​
close

Release any resources held by the provider.

​
closeEmitter

Close the emitter: drop all handlers and stop emitting. Waits up to 2 seconds for in-flight async handlers to settle before returning.

​
emit

​
event
string
required

​
getRuntimeConfig

​
returns
Record<string, any>

​
listenerCount

​
event
string
required
​
returns
number

​
off

​
event
string
required
​
handler
EventHandler
required

​
on

​
event
string
required
​
handler
EventHandler
required
​
returns
EventHandler

​
once

​
event
string
required
​
handler
EventHandler
required
​
returns
EventHandler

​
removeAllListeners

​
event
string

​
SarvamAILLMModel

Supported Sarvam AI LLM model names.