> ## Documentation Index
> Fetch the complete documentation index at: https://docs.nimbusbci.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Streaming Inference Configuration

> Configure cross-SDK chunk size, temporal aggregation, and streaming decision patterns for low-latency BCI inference.

# Streaming Inference Configuration

This page is the cross-SDK configuration overview for streaming inference. It explains the shared concepts: when to stream, how to choose chunk sizes, and how to aggregate chunk predictions.

<Note>
  For implementation-specific APIs, use the SDK pages:

  * **Python**: [Python Streaming Inference](/python-sdk/streaming-inference) documents `StreamingSession` and `StreamingSessionSTS`.
  * **Julia**: [Julia Streaming Inference](/julia-sdk/streaming-inference) documents `init_streaming`, `process_chunk`, and `finalize_trial`.
</Note>

## Streaming vs Batch

Use **batch inference** when full trials are already available and you are doing offline evaluation, model validation, or analytics.

Use **streaming inference** when feature chunks arrive over time and the application needs low-latency updates before a complete trial has finished.

```text theme={null}
EEG stream -> preprocessing -> feature chunks -> streaming session -> chunk posteriors -> final decision
```

## Core Configuration

Every streaming setup needs:

* `sampling_rate`: acquisition rate in Hz.
* `chunk_size`: number of samples per chunk.
* `paradigm`: task type such as motor imagery, P300, or SSVEP.
* `feature_type`: feature representation such as CSP, bandpower, or ERP amplitude.
* `n_features`: feature count per chunk.
* `n_classes`: number of output classes.
* `temporal_aggregation`: how to reduce feature time structure when required.

## Chunk Size Guidelines

| Chunk duration | Typical use                                  | Trade-off                              |
| -------------- | -------------------------------------------- | -------------------------------------- |
| 0.25-0.5s      | Fast feedback, games, exploratory interfaces | Lower latency, less evidence per chunk |
| 0.5-1.0s       | Most real-time BCI systems                   | Balanced responsiveness and confidence |
| 1.0-2.0s       | Medical or high-stakes decisions             | Higher confidence, slower feedback     |

Start with 0.5-1.0s chunks for motor imagery and adjust based on confidence, latency, and user experience.

## Aggregation Methods

Streaming produces one posterior per chunk. Trial-level decisions combine those chunk posteriors.

| Method           | Use when                                               |
| ---------------- | ------------------------------------------------------ |
| `weighted_vote`  | You want confidence-weighted decisions across chunks   |
| `posterior_mean` | You want smooth posterior averaging across chunks      |
| `max_confidence` | You trust the single most confident chunk              |
| `unanimous`      | You need conservative decisions only when chunks agree |

<Tip>
  Use `weighted_vote` as the default. Switch to `posterior_mean` when you want smoother probabilities, or `max_confidence` when the task has short high-signal windows.
</Tip>

## Quality Gates

Streaming systems should monitor:

* confidence (`max posterior probability`)
* entropy (`prediction uncertainty`)
* class balance over recent trials
* rejection rate
* per-chunk and per-trial latency

For Python rejection and quality APIs, see [Python SDK API Reference](/python-sdk/api-reference). For end-to-end real-time setup, see [Real-Time BCI Setup](/inference-configuration/real-time-setup).

## Next Read

<CardGroup cols={2}>
  <Card title="Python Streaming Inference" icon="activity" href="/python-sdk/streaming-inference">
    Python `StreamingSession` examples and STS state handling.
  </Card>

  <Card title="Julia Streaming Inference" icon="rss" href="/julia-sdk/streaming-inference">
    Julia streaming API for local chunk processing.
  </Card>

  <Card title="Real-Time BCI Setup" icon="settings" href="/inference-configuration/real-time-setup">
    Hardware, LSL, BrainFlow, and acquisition-loop guidance.
  </Card>

  <Card title="Batch Processing" icon="list" href="/inference-configuration/batch-processing">
    Offline trial processing and diagnostics.
  </Card>
</CardGroup>