When selecting the llamaParse provider option from omni-parser API, the file processing will redirect to the LlamaParse service for file processing; you need an API Key to use the service.
The following parameters are available:
| Parameter |
Description |
| apiKey |
Required. Obtain it from the LlamaParse site following the steps in Generate a New API Key |
| resultType |
Output format. Options:
- markdown (default)
- text |
| fastMode |
Parsing speed option:
- true: Bypass reconstruction, significantly accelerating parsing
- false (default): Standard parsing speed |
| targetPages |
Comma-separated list of pages to extract. Default: all pages (numbered from 0) |
| language |
Document language. Default: en. For multiple languages, repeat this parameter for each language. See Set language for other options. |
| maxTimeout |
Maximum timeout to wait for document to be parsed, defaults to 2000 seconds. |
| autoMode |
Indicates that LlamaParse will take the best strategy to extract information from the document. This will imply higher charges; false (default). |
| extractCharts |
Will extract/tag charts from the document; false (default). |
| high_res_ocr |
Will do higher resolution extraction from document however being more expensive; false (default). |
The following shows how to use the provider options:
- Text format, fastest option for the first two pages:
curl -X POST "$BASE_URL/v1/omni-parser/process" \
-H 'Authorization: Bearer $GEAI_APITOKEN' \
-F 'apiKey="$LLAMA_PARSE_API_KEY"' \
-F 'provider="llamaParse"' \
-F 'targetPages="0,1"' \
-F 'file=@"/C:/temp/SampleFile.pdf"' \
-F 'resultType="text"' \
-F 'fastMode="true"' \
-F 'maxTimeout="60"'
- First page in markdown format using high resolution:
curl -X POST "$BASE_URL/v1/omni-parser/process" \
-H 'Authorization: Bearer $GEAI_APITOKEN' \
-F 'apiKey="$LLAMA_PARSE_API_KEY"' \
-F 'provider="llamaParse"' \
-F 'targetPages="0"' \
-F 'file=@"/C:/temp/SampleFile.pdf"' \
-F 'resultType="markdown"' \
-F 'fastMode="false"' \
-F 'highResOcr="true"'
- Complete PDF file in markdown format:
curl -X POST "$BASE_URL/v1/omni-parser/process" \
-H 'Authorization: Bearer $GEAI_APITOKEN' \
-F 'apiKey="$LLAMA_PARSE_API_KEY"' \
-F 'provider="llamaParse"' \
-F 'file=@"/C:/temp/SampleFile.pdf"' \
-F 'resultType="markdown"' \
-F 'fastMode="false"' \
-F 'extractCharts="true"'
If no apiKey is configured the following error appears:
{
"error": {
"id": 8027,
"description": "Illegal header value b'Bearer '"
}
}
Since version 2025-09.