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

# Set up Recall

> Ask questions about scoped clipboard history and check source citations.

Recall retrieves supporting clips from your selected history scope and uses a generation model to answer. It does not automatically read every file, application, or uncaptured content. Answers can be wrong.

<h2 id="setup">
  Prepare Recall
</h2>

1. Connect Ollama and enable generation under **Intelligence → Models → Local Text Generation** using [Local AI setup](/local-ai#generation-models).
2. Optionally [enable Meaning Search](/meaning-search) for semantic retrieval. Recall uses available enabled retrieval sources; embeddings and generation have separate roles.
3. Select the relevant history scope and filters.
4. Type a question in search and use **Recall**, or the displayed shortcut. When generation is unavailable, the setup action opens Intelligence.

<h2 id="first-answer">
  Try an answer with evidence
</h2>

Copy these harmless notes separately:

```text theme={null}
Team outing: meet at Kissa Mori on Thursday at 2 pm.
```

```text theme={null}
Kissa Mori confirmed six seats upstairs for our Thursday gathering.
```

Ask **What time is the Kissa Mori meeting, and how many seats are available?** The place name gives exact retrieval a starting point. Open the answer's numbered citations and check the source text.

The goal is a supported answer, not an exact wording or retrieval order. If no evidence appears, confirm the notes are captured and included in the selected scope.

<h2 id="sources">
  Check and narrow sources
</h2>

Open citation buttons to inspect excerpts and original clips. Select sources and **Use only these clips** for a focused follow-up, or deliberately choose **Search all history** to widen scope.

Detected secret clips are excluded from Recall evidence. There is no Recall override for that exclusion. Never use real secrets in setup exercises. Citations help inspection; they do not guarantee correct interpretation.

<h2 id="recovery">
  Understand incomplete results
</h2>

* **No evidence:** check scope, filters, captured text, and enabled sources. Try an exact name before a broad question.
* **Incomplete or reduced context:** review sources and ask something narrower. Not all retrieved text necessarily fits generation context.
* **Generation unavailable:** check Ollama, model installation, and enablement.
* **Incorrect answer:** compare sources, refine the question, or evaluate another model. Larger models do not guarantee accuracy.
* **Expired session:** ask again. Conversations are temporary and expire after inactivity.

<h2 id="controls">
  Stop and reuse deliberately
</h2>

Cancel an active answer when needed. Review before **Copy answer** or **Copy with sources**. Prompts and answers do not become canonical clip metadata. Disable Local Text Generation in Models to stop it.

See [model resources](/local-ai#resources) and [Troubleshooting](/troubleshooting).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.