Package org.apache.tika.parser.vlm

Class GeminiVLMParser

java.lang.Object

org.apache.tika.parser.vlm.AbstractVLMParser

org.apache.tika.parser.vlm.GeminiVLMParser

All Implemented Interfaces:

Closeable, Serializable, AutoCloseable, Initializable, SelfConfiguring, ContentEnricher, TextRecognizer, Engine, Parser

public class GeminiVLMParser
extends AbstractVLMParser

VLM parser for the Google Gemini generateContent API.

Supports both images and PDFs natively (Gemini processes PDFs with native vision, understanding layout, charts, tables, and diagrams — not just extracting text).

The API key is sent in the x-goog-api-key header, never in the URL, which error messages and logs quote.

Default base URL points to the public Gemini API; change it for Vertex AI or a proxy.

Configuration key: "gemini-vlm-parser"

Since:

Apache Tika 4.0

See Also:

• Serialized Form

Nested Class Summary

Nested classes/interfaces inherited from class org.apache.tika.parser.vlm.AbstractVLMParser

AbstractVLMParser.HttpCall

Field Summary

Fields inherited from class org.apache.tika.parser.vlm.AbstractVLMParser

VLM_COMPLETION_TOKENS, VLM_IMAGE_PIXELS, VLM_META, VLM_MODEL, VLM_PROMPT_TOKENS, VLM_SKIPPED_REASON

Constructor Summary

Constructors

Constructor	Description
GeminiVLMParser()
GeminiVLMParser(JsonConfig jsonConfig)
GeminiVLMParser(VLMOCRConfig config)

Method Summary

Modifier and Type	Method	Description
protected AbstractVLMParser.HttpCall	buildHttpCall(VLMOCRConfig config, String base64Data, String mimeType)	Build a fully formed AbstractVLMParser.HttpCall for the target API.
protected String	configKey()
protected String	extractResponseText(String responseBody, Metadata metadata)	Parse the API response body and extract the model's text output.
protected Map<String,String>	getHealthCheckHeaders(VLMOCRConfig config)
protected String	getHealthCheckUrl(VLMOCRConfig config)
protected Set<MediaType>	getSupportedMediaTypes()

Methods inherited from class org.apache.tika.parser.vlm.AbstractVLMParser

close, getApiKey, getBaseUrl, getConfig, getDefaultConfig, getMaxFileSizeToOcr, getMaxTokens, getMinFileSizeToOcr, getModel, getPrompt, getSupportedTypes, getTemperature, getTimeoutMillis, initialize, isInlineContent, isServerAvailable, isSkipOcr, parse, parsesDocuments, recognizesText, setApiKey, setBaseUrl, setInlineContent, setMaxFileSizeToOcr, setMaxRetries, setMaxTokens, setMinFileSizeToOcr, setModel, setPrompt, setSkipOcr, setTemperature, setTimeoutMillis, stripTrailingSlash

Methods inherited from class java.lang.Object

clone, equals, finalize, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait

Constructor Details

GeminiVLMParser

public GeminiVLMParser()

GeminiVLMParser

public GeminiVLMParser(VLMOCRConfig config)

GeminiVLMParser

public GeminiVLMParser(JsonConfig jsonConfig)

Method Details

buildHttpCall

protected AbstractVLMParser.HttpCall buildHttpCall(VLMOCRConfig config,
 String base64Data,
 String mimeType)

Description copied from class: AbstractVLMParser

Build a fully formed AbstractVLMParser.HttpCall for the target API.

Specified by:

buildHttpCall in class AbstractVLMParser

Parameters:

config - resolved config for this parse

base64Data - base64-encoded version of the file bytes

mimeType - the MIME type of the input (e.g. image/png)

Returns:

a ready-to-execute AbstractVLMParser.HttpCall

extractResponseText

protected String extractResponseText(String responseBody,
 Metadata metadata)
                              throws TikaException

Description copied from class: AbstractVLMParser

Parse the API response body and extract the model's text output. Implementations should also populate AbstractVLMParser.VLM_PROMPT_TOKENS and AbstractVLMParser.VLM_COMPLETION_TOKENS in metadata when the information is available.

Specified by:

extractResponseText in class AbstractVLMParser

Parameters:

responseBody - raw JSON response body

metadata - metadata to enrich with token counts

Returns:

the extracted text content

Throws:

TikaException

getSupportedMediaTypes

protected Set<MediaType> getSupportedMediaTypes()

Specified by:

getSupportedMediaTypes in class AbstractVLMParser

Returns:

the set of media types this parser handles (images, PDFs, etc.)

configKey

protected String configKey()

Specified by:

configKey in class AbstractVLMParser

Returns:

the JSON config key for ParseContextConfig lookup (e.g. "openai-vlm-parser", "gemini-vlm-parser")

getHealthCheckUrl

protected String getHealthCheckUrl(VLMOCRConfig config)

Specified by:

getHealthCheckUrl in class AbstractVLMParser

Returns:

an optional health-check URL to probe at init time, or null to skip the probe

getHealthCheckHeaders

protected Map<String,String> getHealthCheckHeaders(VLMOCRConfig config)

Overrides:

getHealthCheckHeaders in class AbstractVLMParser

Returns:

the headers for the health-check probe; Bearer auth by default