LLM - LLMBuilder

LLM.LLMBuilder

Construct a multi-modal LLM agent from a purpose, prompt, functions and streams.

Example

 const price = new SourceBuilder("price")
   .value({ value: 5 });

 const message = new SourceBuilder("message",)
   .writeable(AssistantInputStateType);

 const sales = new SourceBuilder("sales")
   .writeable(DictType(
     StringType,
     StructType({
       date: DateTimeType,
       item: StringType,
       qty: IntegerType,
       inventory: IntegerType,
       price: FloatType,
       amount: FloatType,
     }))
   )

 const model = new SourceBuilder("model",)
   .value({ value: variant('gpt-3.5-turbo-1106', null), type: LLMModelType });
 
 const assistant = new LLMBuilder("assistant")
   .input({ name: "sales", stream: sales.outputStream() })
   .input({ name: "message", stream: message.outputStream() })
   .input({ name: "model", stream: model.outputStream() })
   .input({ name: "price", stream: price.outputStream() })
   .assistant({
       api_key: "...",
       purpose: "You are a business analyst assistant",
       prompt: (inputs) => inputs.message,
       model: (inputs) => inputs.model,
   })
   .write(
       "change_price",
       "Change the value of the price.",
       price.outputStream(),
   )

Type parameters

Name	Type
Inputs	extends Record =

LLM

assistant

▸ assistant(args):

LLMAssistantBuilder<Inputs, , , VariantType<{ message: LLMMessage } & >>

Construct an Agent that produces any EastType

Stream, based on a purpose, requests and other streams.

Parameters

Name	Type	Description
args	Object	-
args.api_key	string | (inputs: Inputs) => EastFunction	the OpenAI api key
args.model?	OpenAiModel | (inputs: Inputs) => EastFunction	the open ai model to use
args.prompt?	string | (inputs: Inputs) => EastFunction<Nullable>	the assistant state, a message or thread
args.purpose?	string | (inputs: Inputs) => EastFunction	the purpose of the assistant

Returns

LLMAssistantBuilder<Inputs, , , VariantType<{ message: LLMMessage } & >>

a new

LLMAssistantBuilder

Example

 const price = new SourceBuilder("price")
   .value({ value: 5 });

 const message = new SourceBuilder("message",)
   .writeable(AssistantInputStateType);

 const sales = new SourceBuilder("sales")
   .writeable(DictType(
     StringType,
     StructType({
       date: DateTimeType,
       item: StringType,
       qty: IntegerType,
       inventory: IntegerType,
       price: FloatType,
       amount: FloatType,
     }))
   )

 const model = new SourceBuilder("model",)
   .value({ value: variant('gpt-3.5-turbo-1106', null), type: LLMModelType });
 
 const assistant = new LLMBuilder("assistant")
   .input({ name: "sales", stream: sales.outputStream() })
   .input({ name: "message", stream: message.outputStream() })
   .input({ name: "model", stream: model.outputStream() })
   .input({ name: "price", stream: price.outputStream() })
   .assistant({
       api_key: "...",
       purpose: "You are a business analyst assistant",
       prompt: (inputs) => inputs.message,
       model: (inputs) => inputs.model,
   })
   .write(
       "change_price",
       "Change the value of the price.",
       price.outputStream(),
   )

---

input

▸ input(config):

LLMBuilder<Inputs & { [K in string]: Variable }>

Add an additional named input

Stream to the LLMBuilder.

Type parameters

Name	Type
Name	extends string
I	extends EastType

Parameters

Name	Type	Description
config	Object	the input stream and the resulting variable name
config.name	Name extends "input" | keyof Inputs ? never : Name	The name of the input. *
config.stream	Stream	The Stream to input. *

Returns

LLMBuilder<Inputs & { [K in string]: Variable }>

a new

LLMBuilder

Example

 // use a stream that is a collection of pdf documents per customer
 const price = new SourceBuilder("price")
   .value({ value: 5 });

 const message = new SourceBuilder("message",)
   .writeable(AssistantInputStateType);

 const model = new SourceBuilder("model",)
   .value({ value: variant('gpt-3.5-turbo-1106', null), type: LLMModelType });
 
 const assistant = new LLMBuilder("assistant")
   .input({ name: "message", stream: message.outputStream() })
   .input({ name: "model", stream: model.outputStream() })
   .input({ name: "price", stream: price.outputStream() })
   .assistant({
       api_key: "...",
       purpose: "You are a business analyst assistant",
       prompt: (inputs) => inputs.message,
       model: (inputs) => inputs.model,
   })
   .input({ name: "price", stream: price.outputStream() })
   .write(
       "change_price",
       "Change the value of the price.",
       price.outputStream(),
   )

Other

constructor

• new LLMBuilder(name, module?, inputs?, input_streams?):

LLMBuilder

Construct a multi-modal LLM agent from a purpose, prompt, functions and streams.

Type parameters

Name	Type
Inputs	extends Record =

Parameters

Name	Type
name	string
module?	ModulePath | ModuleBuilder
inputs	Inputs
input_streams	Record

Returns

LLMBuilder

Example

 const price = new SourceBuilder("price")
   .value({ value: 5 });

 const message = new SourceBuilder("message",)
   .writeable(AssistantInputStateType);

 const sales = new SourceBuilder("sales")
   .writeable(DictType(
     StringType,
     StructType({
       date: DateTimeType,
       item: StringType,
       qty: IntegerType,
       inventory: IntegerType,
       price: FloatType,
       amount: FloatType,
     }))
   )

 const model = new SourceBuilder("model",)
   .value({ value: variant('gpt-3.5-turbo-1106', null), type: LLMModelType });
 
 const assistant = new LLMBuilder("assistant")
   .input({ name: "sales", stream: sales.outputStream() })
   .input({ name: "message", stream: message.outputStream() })
   .input({ name: "model", stream: model.outputStream() })
   .input({ name: "price", stream: price.outputStream() })
   .assistant({
       api_key: "...",
       purpose: "You are a business analyst assistant",
       prompt: (inputs) => inputs.message,
       model: (inputs) => inputs.model,
   })
   .write(
       "change_price",
       "Change the value of the price.",
       price.outputStream(),
   )