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

# Exa

> Use Exa as the default web search provider in FIM One agents — neural, fast, deep-reasoning, and instant modes with sensible defaults.

[Exa](https://exa.ai) is integrated as a first-class web search backend in FIM One. Agents get access to the full Exa search surface — `auto` (Exa's recommended default), `neural`, `fast`, `deep-lite`, `deep`, `deep-reasoning`, and `instant` — plus structured content retrieval (highlights, text, summaries) and rich filtering (categories, include/exclude domains, date ranges, and max-age windows). Sensible defaults ship out of the box, so downstream developers get Exa best practices without manual tuning.

## Why Exa in FIM One

* **Neural search for agent reasoning** — Exa's embedding-native search returns semantically relevant results, not just keyword matches. This matters for research agents that reason over web content.
* **Deep-reasoning mode for hard queries** — single-call multi-hop reasoning over the open web, without the agent orchestrating sub-queries itself.
* **Built-in content extraction** — highlights + text + optional summaries arrive with the search call, eliminating a second round-trip to fetch and clean page content.
* **Tight domain / recency controls** — includes/excludes domain lists (up to 1200 entries), ISO-8601 date windows, and `maxAgeHours` for time-sensitive workflows.

## Quick start

### 1. Get an Exa API key

Sign up at [exa.ai](https://exa.ai) and grab your API key from the dashboard.

### 2. Set the key in FIM One

Add to your `.env`:

```bash theme={null}
EXA_API_KEY=your_key_here
```

That's it. If `WEB_SEARCH_PROVIDER` is unset, FIM One auto-selects Exa when `EXA_API_KEY` is present.

To make Exa explicit:

```bash theme={null}
WEB_SEARCH_PROVIDER=exa
EXA_API_KEY=your_key_here
```

### 3. Use it from any agent

Web search is exposed to agents as a built-in tool — no extra wiring needed. Agents with `web_search` enabled will automatically route through Exa.

## Configuration

All Exa-specific knobs have sensible defaults. Override any of them via environment variables:

| Variable                   | Default | Description                                                                                |
| -------------------------- | ------- | ------------------------------------------------------------------------------------------ |
| `EXA_API_KEY`              | —       | **Required.** Your Exa API key.                                                            |
| `EXA_SEARCH_TYPE`          | `auto`  | One of `auto`, `neural`, `fast`, `deep-lite`, `deep`, `deep-reasoning`, `instant`.         |
| `EXA_CATEGORY`             | —       | One of `company`, `research paper`, `news`, `personal site`, `financial report`, `people`. |
| `EXA_INCLUDE_DOMAINS`      | —       | Comma-separated allowlist (max 1200 entries).                                              |
| `EXA_EXCLUDE_DOMAINS`      | —       | Comma-separated blocklist (max 1200 entries).                                              |
| `EXA_START_PUBLISHED_DATE` | —       | ISO-8601, e.g. `2025-01-01`.                                                               |
| `EXA_END_PUBLISHED_DATE`   | —       | ISO-8601.                                                                                  |
| `EXA_MAX_AGE_HOURS`        | —       | Only return pages indexed in the last N hours.                                             |
| `EXA_INCLUDE_HIGHLIGHTS`   | `true`  | Pull highlight snippets from results.                                                      |
| `EXA_TEXT_MAX_CHARS`       | `800`   | Cap on text/snippet length per result.                                                     |
| `EXA_SUMMARY_QUERY`        | —       | Optional custom summary prompt per result.                                                 |

### How snippets are assembled

FIM One cascades through Exa's content fields to produce a useful snippet on every result, regardless of which content types the API populated:

1. `highlights` (joined with `…`) — preferred when present
2. `text` — falls back to extracted article text, truncated to `EXA_TEXT_MAX_CHARS`
3. `summary` — used when both above are empty

This guarantees downstream agents always have a non-empty snippet to reason over, even for results where Exa couldn't extract highlights.

### Preset: news monitoring

```bash theme={null}
EXA_SEARCH_TYPE=fast
EXA_CATEGORY=news
EXA_MAX_AGE_HOURS=24
EXA_TEXT_MAX_CHARS=1200
```

### Preset: research paper retrieval

```bash theme={null}
EXA_SEARCH_TYPE=neural
EXA_CATEGORY=research paper
EXA_INCLUDE_HIGHLIGHTS=true
EXA_TEXT_MAX_CHARS=2000
```

### Preset: deep-reasoning agent

```bash theme={null}
EXA_SEARCH_TYPE=deep-reasoning
EXA_TEXT_MAX_CHARS=1500
EXA_SUMMARY_QUERY=What is the key finding and its supporting evidence?
```

## Attribution

Every Exa request from FIM One carries an `x-exa-integration: fim-one` header so Exa can attribute API usage back to this integration in maintainer dashboards. This is used only for integration-level attribution — no end-user identification or tracking.

## Source

The Exa connector lives at [`src/fim_one/core/web/search/exa.py`](https://github.com/fim-ai/fim-one/blob/master/src/fim_one/core/web/search/exa.py) and follows the same `BaseWebSearch` protocol as Jina, Tavily, and Brave — switching providers is a single env-var change.

## Links

* [Exa homepage](https://exa.ai) · [Exa API reference](https://exa.ai/docs/reference/search)
* [FIM One quickstart](/quickstart) · [Environment variables reference](/configuration/environment-variables)