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

# sift extract

> Extract entities and relations from documents

## Overview

Extract entities and relations from documents using LLM-based extraction. Processes documents in a directory, chunks them, and uses configured LLM to identify entities and relationships.

## Usage

```bash theme={null}
sift extract DIRECTORY [OPTIONS]
```

## Arguments

<ParamField path="directory" type="string" required>
  Directory containing documents to process. Must be a valid directory path.
</ParamField>

## Options

### Model & Domain

<ParamField path="--model" type="string">
  LLM model to use for extraction (e.g., `openai/gpt-4o-mini`, `anthropic/claude-3-5-sonnet-20241022`). Overrides default from config.
</ParamField>

<ParamField path="--domain" type="string">
  Path to custom domain YAML file defining entity and relation types.
</ParamField>

<ParamField path="--domain-name" type="string" default="schema-free">
  Bundled domain name to use (e.g., `general`, `osint`, `academic`). Use `-d` as shorthand.
</ParamField>

### Performance & Cost

<ParamField path="--chunk-size" type="integer" default="10000">
  Characters per chunk. Larger chunks = fewer API calls and lower cost, but may reduce extraction quality for very large documents.
</ParamField>

<ParamField path="--concurrency" type="integer" default="4">
  Concurrent LLM calls per document. Use `-c` as shorthand. Higher values speed up processing but may hit rate limits.
</ParamField>

<ParamField path="--rpm" type="integer" default="40">
  Maximum requests per minute to prevent rate limit waste and throttle API calls.
</ParamField>

<ParamField path="--max-cost" type="float">
  Maximum cost budget in USD. Extraction stops when this limit is reached.
</ParamField>

### Extraction Settings

<ParamField path="--force" type="boolean" default="false">
  Re-extract all documents, ignoring cached results. Use `-f` as shorthand.
</ParamField>

<ParamField path="--extractor" type="string" choices="['kreuzberg', 'pdfplumber']">
  Extraction backend to use. `kreuzberg` supports 75+ formats, `pdfplumber` is PDF-only.
</ParamField>

<ParamField path="--ocr" type="boolean" default="false">
  Enable OCR for scanned documents and images.
</ParamField>

<ParamField path="--ocr-backend" type="string" choices="['tesseract', 'easyocr', 'paddleocr', 'gcv']">
  OCR backend to use. `gcv` = Google Cloud Vision (requires API key).
</ParamField>

<ParamField path="--ocr-language" type="string">
  OCR language code in ISO 639-3 format (e.g., `eng` for English, `fra` for French, `deu` for German).
</ParamField>

### Output

<ParamField path="--output" type="string">
  Output directory for extraction results. Use `-o` as shorthand. Defaults to value in config.
</ParamField>

<ParamField path="--verbose" type="boolean" default="false">
  Enable verbose logging with debug-level output. Use `-v` as shorthand.
</ParamField>

## Output

Extraction results are saved to `{output_dir}/extractions/` with one JSON file per document.

In schema-free mode, discovered entity and relation types are saved to `{output_dir}/discovered_domain.yaml`.

## Examples

### Basic extraction

```bash theme={null}
sift extract ./documents
```

Extracts entities from all documents in `./documents` using default settings.

### With custom domain

```bash theme={null}
sift extract ./documents --domain-name osint
```

Uses the bundled OSINT domain for specialized entity extraction.

### With OCR for scanned documents

```bash theme={null}
sift extract ./scanned_pdfs --ocr --ocr-backend tesseract --ocr-language eng
```

Enables OCR using Tesseract for English documents.

### Cost-limited extraction

```bash theme={null}
sift extract ./documents --max-cost 5.0 --model openai/gpt-4o-mini
```

Extracts with a \$5 budget using GPT-4o-mini.

### High-performance extraction

```bash theme={null}
sift extract ./documents -c 8 --chunk-size 15000 --rpm 60
```

Uses 8 concurrent workers, larger chunks, and higher rate limit.

## Output Summary

After completion, displays:

* Documents processed
* Total entities extracted
* Total relations extracted
* Total cost in USD
* Output location

## Next Steps

After extraction, run:

```bash theme={null}
sift build
```

To construct the knowledge graph from extraction results.

## See Also

* [build](/api/cli/build) - Build knowledge graph from extractions
* [domains](/api/cli/domains) - List available bundled domains