Skip to Content
TensorPass
Reference@tensorpass/aiconnect

Chat, tool and generation types

The messages, content parts, tools, JSON Schema, generation options, tool choice and response format that @tensorpass/aiconnect exchanges with AI Wallet, with their types generated from the source.

Part of the @tensorpass/aiconnect reference. The tables are generated from the package's TypeScript source each time the docs are built. Open a row to see its full type.

Chat types

The chat format the site and the wallet share. The wallet translates it to each provider's own format and back. ChatMessage is a union of four messages, one per role:

Prop

Type

SystemMessage

Prop

Type

UserMessage

Prop

Type

content is a string, or a list of parts when the message carries images.

AssistantMessage

Prop

Type

ToolMessage

Prop

Type

A ToolMessage answers the ToolCall whose id it carries in toolCallId.

ToolCall

Prop

Type

ContentPart

A union of two parts, one per type:

Prop

Type

TextPart

Prop

Type

ImagePart

Prop

Type

url is a data: URL, or an https URL for the providers that fetch images themselves.

const messages: ChatMessage[] = [
  { role: 'system', content: 'You recommend books from this site\'s catalog.' },
  { role: 'user', content: 'A calm book for tonight' },
  { role: 'assistant', content: '', toolCalls: [{ id: 'call_1', name: 'search_books', arguments: { mood: 'calm' } }] },
  { role: 'tool', toolCallId: 'call_1', name: 'search_books', content: '[{"title":"Piranesi"}]' },
];

const cover: ContentPart[] = [
  { type: 'text', text: 'Which book has this cover?' },
  { type: 'image', url: 'https://example.com/covers/piranesi.jpg' },
];
messages.push({ role: 'user', content: cover });

Tool types

The tools a site offers. Any object that implements ToolSource can feed runConversation and useAiChat.

ToolDefinition

Prop

Type

ToolSource

Prop

Type

JsonSchema

The type of inputSchema, a JSON Schema object:

Prop

Type

const empty: JsonSchema = { type: 'object', properties: {} };

const clock: ToolSource = {
  listTools: async () => [{
    name: 'current_time',
    description: 'The current time of the visitor\'s computer, in UTC, as an ISO 8601 string.',
    inputSchema: empty,
  }],
  callTool: async () => new Date().toISOString(),
};

GenerationOptions

What the site asks of the answer, in ChatRequest.options.

Prop

Type

maxTokens, temperature, topP and stop are hints: the account's connector leaves out those its provider refuses. toolChoice and responseFormat always reach the provider.

GenerationHint

The names of the hints, each with the type of its option:

Prop

Type

ToolChoice

Whether the model may answer in text, must call a tool, or must call the named one. A tool choice is one of these strings:

Prop

Type

Or an object that names the tool:

Prop

Type

ResponseFormat

An answer in JSON, held to schema when one is given. strict asks the providers that offer it to refuse any schema they cannot enforce exactly.

Prop

Type

const { message, finishReason } = await state.session.chat({
  messages: [{ role: 'user', content: 'Three calm books, as JSON.' }],
  options: {
    maxTokens: 400,
    toolChoice: 'none',
    responseFormat: {
      type: 'json',
      name: 'books',
      schema: { type: 'object', properties: { titles: { type: 'array', items: { type: 'string' } } } },
    },
  },
});
const { titles } = JSON.parse(message.content) as { titles: string[] };

// The hints a ChatGPT plan account refuses, which its connector leaves out of every call.
const refusedByChatGpt: GenerationHint[] = ['maxTokens', 'temperature', 'topP'];

On this page