invera SDK

Stream complete text and tool-call fragments with word-level input and output attributions. The SDK handles Engine discovery, tokenizer parity, chat-template rendering, raw NDJSON transport, token-to-word aggregation, claim evidence, and pre-execution tool-call assessment.

Start here

• Install the SDK and stream your first completion
• Add evidence to text responses
• Validate and gate tool calls
• Understand attribution and evidence

TypeScript

import { InveraClient } from "@layerwise/invera-sdk";

const client = new InveraClient({
  baseUrl: process.env.INVERA_BASE_URL!,
});

for await (const chunk of client.chat.completions.stream({
  messages: [{ role: "user", content: "What is attention attribution?" }],
  maxTokens: 256,
})) {
  console.log(chunk.content, chunk.input_attributions);
}

Python

from invera_sdk import ChatMessage, CompletionRequest, InveraClient

client = InveraClient("https://host.example/api/invera-engine/v1")
for chunk in client.chat.completions.stream(
    CompletionRequest(
        messages=[ChatMessage("user", "What is attention attribution?")],
        max_tokens=256,
    )
):
    print(chunk.content, chunk.input_attributions)

Compatibility

• SDK version: 0.3.2
• Supported Engine Contract range: >=1.0.0 <2.0.0
• Developed by: layerwise (Layerwise GmbH)

Released SDK versions are available from the version selector in the navigation bar.