Package org.apache.tika.inference

Class OpenAIEmbeddingFilter

java.lang.Object

org.apache.tika.metadata.filter.MetadataFilter

org.apache.tika.inference.AbstractEmbeddingFilter

org.apache.tika.inference.OpenAIEmbeddingFilter

All Implemented Interfaces:

Closeable, Serializable, AutoCloseable, SelfConfiguring

Direct Known Subclasses:

JinaEmbeddingFilter

@Deprecated
public class OpenAIEmbeddingFilter
extends AbstractEmbeddingFilter

Deprecated.

since 4.1.0, removed in 4.2.0; see AbstractEmbeddingFilter.

Metadata filter that calls an OpenAI-compatible /v1/embeddings endpoint to produce vectors for each text chunk.

Works with OpenAI, vLLM, Ollama, sentence-transformers servers, and any endpoint that implements the OpenAI Embeddings API.

Configuration key: "openai-embedding-filter"

Since:

Apache Tika 4.0

See Also:

• Serialized Form

Constructor Summary

Constructors

Constructor	Description
OpenAIEmbeddingFilter()	Deprecated.
OpenAIEmbeddingFilter(InferenceConfig config)	Deprecated.

Method Summary

Modifier and Type	Method	Description
void	close()	Deprecated. Releases any resources held by this filter (e.g.
protected void	embed(List<Chunk> chunks, InferenceConfig config, ParseContext parseContext)	Deprecated. Call the embeddings endpoint to fill in vectors on each chunk.
String	getApiKeyHeaderName()	Deprecated.
String	getApiKeyPrefix()	Deprecated.
protected String	getComponentName()	Deprecated. The @TikaComponent name this filter's per-request JSON config is keyed by in parse-context (e.g.
String	getEmbeddingsPath()	Deprecated.
void	setApiKeyHeaderName(String apiKeyHeaderName)	Deprecated. Set the HTTP header name for API key authentication.
void	setApiKeyPrefix(String apiKeyPrefix)	Deprecated. Set the prefix prepended to the API key in the auth header.
void	setEmbeddingsPath(String embeddingsPath)	Deprecated. Set the URL path for embeddings requests.

Methods inherited from class org.apache.tika.inference.AbstractEmbeddingFilter

doFilter, getApiKey, getBaseUrl, getContentField, getDefaultConfig, getMaxBatchSize, getMaxChunkChars, getMaxChunks, getModel, getOutputField, getOverlapChars, getTimeoutMillis, isClearContentAfterChunking, isSkipEmbedding, setApiKey, setBaseUrl, setClearContentAfterChunking, setContentField, setMaxBatchSize, setMaxChunkChars, setMaxChunks, setModel, setOutputField, setOverlapChars, setSkipEmbedding, setTimeoutMillis

Methods inherited from class org.apache.tika.metadata.filter.MetadataFilter

filter, filter

Methods inherited from class java.lang.Object

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

Constructor Details

OpenAIEmbeddingFilter

public OpenAIEmbeddingFilter()

Deprecated.

OpenAIEmbeddingFilter

public OpenAIEmbeddingFilter(InferenceConfig config)

Deprecated.

Method Details

getComponentName

protected String getComponentName()

Deprecated.

Description copied from class: AbstractEmbeddingFilter

The @TikaComponent name this filter's per-request JSON config is keyed by in parse-context (e.g. {"openai-embedding-filter": {...}}).

Specified by:

getComponentName in class AbstractEmbeddingFilter

close

public void close()
           throws IOException

Deprecated.

Description copied from class: MetadataFilter

Releases any resources held by this filter (e.g. HTTP connection pools, thread pools). The default implementation is a no-op; filters that hold long-lived resources should override this.

Callers that control the filter lifecycle (e.g. PipesServer, try-with-resources blocks) should call this when the filter is no longer needed.

Specified by:

close in interface AutoCloseable

Specified by:

close in interface Closeable

Overrides:

close in class MetadataFilter

Throws:

IOException

embed

protected void embed(List<Chunk> chunks,
 InferenceConfig config,
 ParseContext parseContext)
              throws IOException,
TikaException

Deprecated.

Description copied from class: AbstractEmbeddingFilter

Call the embeddings endpoint to fill in vectors on each chunk. Implementations should set Chunk.setVector(float[]) on each chunk in the list.

Specified by:

embed in class AbstractEmbeddingFilter

Parameters:

chunks - the text chunks to embed

config - the resolved config for this call

parseContext - the task's ParseContext -- pass to TikaHttpClient calls to bound the request by the task's remaining budget and checkpoint while waiting

Throws:

IOException - on HTTP errors

TikaException - on API-level errors

getEmbeddingsPath

public String getEmbeddingsPath()

Deprecated.

setEmbeddingsPath

public void setEmbeddingsPath(String embeddingsPath)

Deprecated.

Set the URL path for embeddings requests. Default is /v1/embeddings. For Azure OpenAI, use /openai/deployments/{deployment}/embeddings?api-version=2024-02-01.

getApiKeyHeaderName

public String getApiKeyHeaderName()

Deprecated.

setApiKeyHeaderName

public void setApiKeyHeaderName(String apiKeyHeaderName)

Deprecated.

Set the HTTP header name for API key authentication. Default is Authorization. For Azure OpenAI, set to api-key.

getApiKeyPrefix

public String getApiKeyPrefix()

Deprecated.

setApiKeyPrefix

public void setApiKeyPrefix(String apiKeyPrefix)

Deprecated.

Set the prefix prepended to the API key in the auth header. Default is "Bearer " (with trailing space). For Azure OpenAI, set to "" (empty string).