gnodet commented on code in PR #25273:
URL: https://github.com/apache/camel/pull/25273#discussion_r3914845454
##########
components/camel-ai/camel-langchain4j-embeddingstore/src/main/java/org/apache/camel/component/langchain4j/embeddingstore/LangChain4jEmbeddingStoreProducer.java:
##########
@@ -109,63 +110,150 @@ public void process(Exchange exchange) throws Exception {
}
/**
- * Adds an embedding to the store with optional text segment.
+ * Adds embeddings to the store with optional text segments and
caller-supplied IDs.
*
* <p>
- * Expects the following headers:
+ * Supports both single and batch operations:
+ * </p>
+ *
+ * <p>
+ * <b>Single operation</b> - when the {@code
CamelLangChain4jEmbeddingsEmbedding} header contains a single
+ * {@link Embedding}:
* </p>
* <ul>
- * <li>{@code CamelLangchain4jEmbeddingEmbedding} - The embedding vector
(required)</li>
- * <li>{@code CamelLangchain4jEmbeddingTextSegment} - Associated text
segment (optional)</li>
+ * <li>With caller-supplied ID header ({@code
CamelLangchain4jEmbeddingStoreEmbeddingId}): calls
+ * {@code add(id, embedding)}</li>
+ * <li>With text segment header: calls {@code add(embedding,
textSegment)}</li>
+ * <li>Without text segment: calls {@code add(embedding)}</li>
* </ul>
*
* <p>
- * Returns the generated embedding ID in the message body.
+ * <b>Batch operation</b> - when the {@code
CamelLangChain4jEmbeddingsEmbeddings} header contains a
+ * {@code List<Embedding>}:
* </p>
+ * <ul>
+ * <li>With IDs header ({@code
CamelLangchain4jEmbeddingStoreEmbeddingIds}) and text segments body: calls
+ * {@code addAll(ids, embeddings, textSegments)}</li>
+ * <li>With text segments body: calls {@code addAll(embeddings,
textSegments)}</li>
+ * <li>Without text segments: calls {@code addAll(embeddings)}</li>
+ * </ul>
*
* @param exchange the Camel exchange containing the embedding data
* @throws Exception if the add operation fails
*/
+ @SuppressWarnings("unchecked")
private void add(Exchange exchange) throws Exception {
final Message in = exchange.getMessage();
+ EmbeddingStore<TextSegment> store =
getEndpoint().getConfiguration().getEmbeddingStore();
+
+ // Check for batch embeddings header first
+ List<Embedding> embeddings =
in.getHeader(LangChain4jEmbeddingsHeaders.EMBEDDINGS, List.class);
+ if (embeddings != null) {
+ addBatch(in, store, embeddings);
+ return;
+ }
+ // Single embedding path
if (in.getHeader(LangChain4jEmbeddingsHeaders.EMBEDDING) == null) {
throw new NoSuchHeaderException(
"The embedding is a required header for ADD operations",
exchange,
LangChain4jEmbeddingsHeaders.EMBEDDING);
}
Embedding embedding =
in.getHeader(LangChain4jEmbeddingsHeaders.EMBEDDING, Embedding.class);
+
+ // Check for caller-supplied ID
+ String callerId =
in.getHeader(LangChain4jEmbeddingStoreHeaders.EMBEDDING_ID, String.class);
String id;
- if (in.getHeader(LangChain4jEmbeddingsHeaders.TEXT_SEGMENT) != null) {
+ if (callerId != null) {
+ store.add(callerId, embedding);
+ id = callerId;
+ } else if (in.getHeader(LangChain4jEmbeddingsHeaders.TEXT_SEGMENT) !=
null) {
TextSegment text =
in.getHeader(LangChain4jEmbeddingsHeaders.TEXT_SEGMENT, TextSegment.class);
- id =
getEndpoint().getConfiguration().getEmbeddingStore().add(embedding, text);
+ id = store.add(embedding, text);
} else {
- id =
getEndpoint().getConfiguration().getEmbeddingStore().add(embedding);
+ id = store.add(embedding);
}
- Message out = exchange.getMessage();
- out.setBody(id);
+ in.setBody(id);
+ }
+
+ @SuppressWarnings("unchecked")
+ private void addBatch(Message in, EmbeddingStore<TextSegment> store,
List<Embedding> embeddings) {
+ List<String> callerIds =
in.getHeader(LangChain4jEmbeddingStoreHeaders.EMBEDDING_IDS, List.class);
+ Object body = in.getBody();
+ List<TextSegment> textSegments = null;
+
+ if (body instanceof List && !((List<?>) body).isEmpty() && ((List<?>)
body).get(0) instanceof TextSegment) {
+ textSegments = (List<TextSegment>) body;
+ }
+
+ List<String> ids;
+ if (callerIds != null && textSegments != null) {
+ store.addAll(callerIds, embeddings, textSegments);
+ ids = callerIds;
+ } else if (callerIds != null) {
+ // No addAll(ids, embeddings) overload in langchain4j, so loop
with add(id, embedding)
+ for (int i = 0; i < embeddings.size(); i++) {
Review Comment:
_Claude Code on behalf of gnodet_
Fixed in 83b9dc9. Added explicit size validation before the loop and before
`addAll(callerIds, embeddings, textSegments)`. Throws
`IllegalArgumentException` with clear message showing both sizes. Added a
dedicated test (`addBatchSizeMismatchThrows`) that verifies the error on
mismatched sizes.
##########
components/camel-ai/camel-langchain4j-embeddings/src/main/java/org/apache/camel/component/langchain4j/embeddings/LangChain4jEmbeddingsProducer.java:
##########
@@ -55,4 +69,30 @@ public void process(Exchange exchange) throws Exception {
message.setHeader(LangChain4jEmbeddingsHeaders.TEXT_SEGMENT, in);
message.setHeader(LangChain4jEmbeddingsHeaders.EMBEDDING,
result.content());
}
+
+ private void processBatch(Exchange exchange, EmbeddingModel model, Message
message, List<Object> bodyList)
+ throws Exception {
+ // Convert each element to TextSegment using the type converter
+ List<TextSegment> segments = new ArrayList<>(bodyList.size());
+ for (Object item : bodyList) {
+ TextSegment segment =
exchange.getContext().getTypeConverter().mandatoryConvertTo(TextSegment.class,
item);
+ segments.add(segment);
+ }
+
+ final Response<List<Embedding>> result = model.embedAll(segments);
+
+ if (result.finishReason() != null) {
+ message.setHeader(LangChain4jEmbeddingsHeaders.FINISH_REASON,
result.finishReason());
+ }
+
+ if (result.tokenUsage() != null) {
+ message.setHeader(LangChain4jEmbeddingsHeaders.INPUT_TOKEN_COUNT,
result.tokenUsage().inputTokenCount());
+ message.setHeader(LangChain4jEmbeddingsHeaders.OUTPUT_TOKEN_COUNT,
result.tokenUsage().outputTokenCount());
+ message.setHeader(LangChain4jEmbeddingsHeaders.TOTAL_TOKEN_COUNT,
result.tokenUsage().totalTokenCount());
+ }
+
+ List<Embedding> embeddings = result.content();
+ message.setHeader(LangChain4jEmbeddingsHeaders.EMBEDDINGS, embeddings);
+ message.setBody(embeddings);
Review Comment:
_Claude Code on behalf of gnodet_
Fixed in 83b9dc9. The batch path now preserves text segments via a new
`TEXT_SEGMENTS` header (`CamelLangChain4jEmbeddingsTextSegments`), added to
both `CamelLangchain4jAttributes` in `core/camel-api` and
`LangChain4jEmbeddingsHeaders`. The embedding store producer reads text
segments from this header first, falling back to the body. This ensures the
embed→store pipeline preserves text segments automatically.
Added a test (`addBatchEmbeddingsWithTextSegmentsHeader`) verifying this
header-based path.
##########
components/camel-ai/camel-langchain4j-embeddingstore/src/main/java/org/apache/camel/component/langchain4j/embeddingstore/LangChain4jEmbeddingStoreProducer.java:
##########
@@ -109,63 +110,150 @@ public void process(Exchange exchange) throws Exception {
}
/**
- * Adds an embedding to the store with optional text segment.
+ * Adds embeddings to the store with optional text segments and
caller-supplied IDs.
*
* <p>
- * Expects the following headers:
+ * Supports both single and batch operations:
+ * </p>
+ *
+ * <p>
+ * <b>Single operation</b> - when the {@code
CamelLangChain4jEmbeddingsEmbedding} header contains a single
+ * {@link Embedding}:
* </p>
* <ul>
- * <li>{@code CamelLangchain4jEmbeddingEmbedding} - The embedding vector
(required)</li>
- * <li>{@code CamelLangchain4jEmbeddingTextSegment} - Associated text
segment (optional)</li>
+ * <li>With caller-supplied ID header ({@code
CamelLangchain4jEmbeddingStoreEmbeddingId}): calls
+ * {@code add(id, embedding)}</li>
+ * <li>With text segment header: calls {@code add(embedding,
textSegment)}</li>
+ * <li>Without text segment: calls {@code add(embedding)}</li>
* </ul>
*
* <p>
- * Returns the generated embedding ID in the message body.
+ * <b>Batch operation</b> - when the {@code
CamelLangChain4jEmbeddingsEmbeddings} header contains a
+ * {@code List<Embedding>}:
* </p>
+ * <ul>
+ * <li>With IDs header ({@code
CamelLangchain4jEmbeddingStoreEmbeddingIds}) and text segments body: calls
+ * {@code addAll(ids, embeddings, textSegments)}</li>
+ * <li>With text segments body: calls {@code addAll(embeddings,
textSegments)}</li>
+ * <li>Without text segments: calls {@code addAll(embeddings)}</li>
+ * </ul>
*
* @param exchange the Camel exchange containing the embedding data
* @throws Exception if the add operation fails
*/
+ @SuppressWarnings("unchecked")
private void add(Exchange exchange) throws Exception {
final Message in = exchange.getMessage();
+ EmbeddingStore<TextSegment> store =
getEndpoint().getConfiguration().getEmbeddingStore();
+
+ // Check for batch embeddings header first
+ List<Embedding> embeddings =
in.getHeader(LangChain4jEmbeddingsHeaders.EMBEDDINGS, List.class);
+ if (embeddings != null) {
+ addBatch(in, store, embeddings);
+ return;
+ }
+ // Single embedding path
if (in.getHeader(LangChain4jEmbeddingsHeaders.EMBEDDING) == null) {
throw new NoSuchHeaderException(
"The embedding is a required header for ADD operations",
exchange,
LangChain4jEmbeddingsHeaders.EMBEDDING);
}
Embedding embedding =
in.getHeader(LangChain4jEmbeddingsHeaders.EMBEDDING, Embedding.class);
+
+ // Check for caller-supplied ID
+ String callerId =
in.getHeader(LangChain4jEmbeddingStoreHeaders.EMBEDDING_ID, String.class);
String id;
- if (in.getHeader(LangChain4jEmbeddingsHeaders.TEXT_SEGMENT) != null) {
+ if (callerId != null) {
+ store.add(callerId, embedding);
+ id = callerId;
+ } else if (in.getHeader(LangChain4jEmbeddingsHeaders.TEXT_SEGMENT) !=
null) {
TextSegment text =
in.getHeader(LangChain4jEmbeddingsHeaders.TEXT_SEGMENT, TextSegment.class);
- id =
getEndpoint().getConfiguration().getEmbeddingStore().add(embedding, text);
+ id = store.add(embedding, text);
} else {
- id =
getEndpoint().getConfiguration().getEmbeddingStore().add(embedding);
+ id = store.add(embedding);
}
- Message out = exchange.getMessage();
- out.setBody(id);
+ in.setBody(id);
+ }
+
+ @SuppressWarnings("unchecked")
+ private void addBatch(Message in, EmbeddingStore<TextSegment> store,
List<Embedding> embeddings) {
+ List<String> callerIds =
in.getHeader(LangChain4jEmbeddingStoreHeaders.EMBEDDING_IDS, List.class);
+ Object body = in.getBody();
+ List<TextSegment> textSegments = null;
+
+ if (body instanceof List && !((List<?>) body).isEmpty() && ((List<?>)
body).get(0) instanceof TextSegment) {
+ textSegments = (List<TextSegment>) body;
+ }
+
+ List<String> ids;
+ if (callerIds != null && textSegments != null) {
+ store.addAll(callerIds, embeddings, textSegments);
+ ids = callerIds;
+ } else if (callerIds != null) {
+ // No addAll(ids, embeddings) overload in langchain4j, so loop
with add(id, embedding)
+ for (int i = 0; i < embeddings.size(); i++) {
+ store.add(callerIds.get(i), embeddings.get(i));
+ }
+ ids = callerIds;
+ } else if (textSegments != null) {
+ ids = store.addAll(embeddings, textSegments);
+ } else {
+ ids = store.addAll(embeddings);
+ }
+
+ in.setBody(ids);
}
/**
- * Removes an embedding from the store by its ID.
+ * Removes embeddings from the store. Supports multiple removal strategies:
*
- * <p>
- * Expects the embedding ID as the message body (String).
- * </p>
+ * <ul>
+ * <li><b>By filter</b>: when the {@code
CamelLangchain4jEmbeddingStoreFilter} header is set, removes all embeddings
+ * matching the filter via {@code removeAll(Filter)}</li>
+ * <li><b>By ID list</b>: when the body is a {@code Collection<String>},
removes all specified embeddings via
+ * {@code removeAll(Collection)}</li>
+ * <li><b>By single ID</b>: when the body is a single {@code String},
removes that embedding via
+ * {@code remove(id)}</li>
+ * </ul>
*
- * @param exchange the Camel exchange containing the embedding ID to
remove
+ * @param exchange the Camel exchange containing removal parameters
* @throws Exception if the remove operation fails
*/
+ @SuppressWarnings("unchecked")
private void remove(Exchange exchange) throws Exception {
final Message in = exchange.getMessage();
- String id = in.getBody(String.class);
+ EmbeddingStore<TextSegment> store =
getEndpoint().getConfiguration().getEmbeddingStore();
- getEndpoint().getConfiguration().getEmbeddingStore().remove(id);
+ // Check for filter-based removal first
+ Filter filter = in.getHeader(LangChain4jEmbeddingStoreHeaders.FILTER,
Filter.class);
+ if (filter != null) {
+ store.removeAll(filter);
+ return;
+ }
- Message out = exchange.getMessage();
+ Object body = in.getBody();
+
+ // Batch removal by collection of IDs
+ if (body instanceof Collection) {
+ Collection<String> ids = (Collection<String>) body;
+ store.removeAll(ids);
+ return;
+ }
+
+ // Single ID removal
+ String id = in.getBody(String.class);
+ if (id != null && !id.isEmpty()) {
+ store.remove(id);
+ return;
+ }
+
+ throw new IllegalArgumentException(
Review Comment:
_Claude Code on behalf of gnodet_
Fixed in 83b9dc9. Added entries in `camel-4x-upgrade-guide-4_22.adoc` for
both:
- `camel-langchain4j-embeddings`: documents batch embedding, `EMBEDDINGS`
and `TEXT_SEGMENTS` headers
- `camel-langchain4j-embeddingstore`: documents batch ADD, caller-supplied
IDs, batch/filter REMOVE, and the REMOVE behavior change (null body now throws
`IllegalArgumentException` instead of opaque langchain4j error)
##########
components/camel-ai/camel-langchain4j-embeddingstore/src/main/java/org/apache/camel/component/langchain4j/embeddingstore/LangChain4jEmbeddingStoreProducer.java:
##########
@@ -109,63 +110,150 @@ public void process(Exchange exchange) throws Exception {
}
/**
- * Adds an embedding to the store with optional text segment.
+ * Adds embeddings to the store with optional text segments and
caller-supplied IDs.
*
* <p>
- * Expects the following headers:
+ * Supports both single and batch operations:
+ * </p>
+ *
+ * <p>
+ * <b>Single operation</b> - when the {@code
CamelLangChain4jEmbeddingsEmbedding} header contains a single
+ * {@link Embedding}:
* </p>
* <ul>
- * <li>{@code CamelLangchain4jEmbeddingEmbedding} - The embedding vector
(required)</li>
- * <li>{@code CamelLangchain4jEmbeddingTextSegment} - Associated text
segment (optional)</li>
+ * <li>With caller-supplied ID header ({@code
CamelLangchain4jEmbeddingStoreEmbeddingId}): calls
+ * {@code add(id, embedding)}</li>
+ * <li>With text segment header: calls {@code add(embedding,
textSegment)}</li>
+ * <li>Without text segment: calls {@code add(embedding)}</li>
* </ul>
*
* <p>
- * Returns the generated embedding ID in the message body.
+ * <b>Batch operation</b> - when the {@code
CamelLangChain4jEmbeddingsEmbeddings} header contains a
+ * {@code List<Embedding>}:
* </p>
+ * <ul>
+ * <li>With IDs header ({@code
CamelLangchain4jEmbeddingStoreEmbeddingIds}) and text segments body: calls
+ * {@code addAll(ids, embeddings, textSegments)}</li>
+ * <li>With text segments body: calls {@code addAll(embeddings,
textSegments)}</li>
+ * <li>Without text segments: calls {@code addAll(embeddings)}</li>
+ * </ul>
*
* @param exchange the Camel exchange containing the embedding data
* @throws Exception if the add operation fails
*/
+ @SuppressWarnings("unchecked")
private void add(Exchange exchange) throws Exception {
final Message in = exchange.getMessage();
+ EmbeddingStore<TextSegment> store =
getEndpoint().getConfiguration().getEmbeddingStore();
+
+ // Check for batch embeddings header first
+ List<Embedding> embeddings =
in.getHeader(LangChain4jEmbeddingsHeaders.EMBEDDINGS, List.class);
+ if (embeddings != null) {
+ addBatch(in, store, embeddings);
+ return;
+ }
+ // Single embedding path
if (in.getHeader(LangChain4jEmbeddingsHeaders.EMBEDDING) == null) {
throw new NoSuchHeaderException(
"The embedding is a required header for ADD operations",
exchange,
LangChain4jEmbeddingsHeaders.EMBEDDING);
}
Embedding embedding =
in.getHeader(LangChain4jEmbeddingsHeaders.EMBEDDING, Embedding.class);
+
+ // Check for caller-supplied ID
+ String callerId =
in.getHeader(LangChain4jEmbeddingStoreHeaders.EMBEDDING_ID, String.class);
String id;
- if (in.getHeader(LangChain4jEmbeddingsHeaders.TEXT_SEGMENT) != null) {
+ if (callerId != null) {
+ store.add(callerId, embedding);
Review Comment:
_Claude Code on behalf of gnodet_
Fixed in 83b9dc9. When `callerId` is set and a `TEXT_SEGMENT` header is also
present, the code now uses `store.addAll(List.of(callerId), List.of(embedding),
List.of(textSegment))` to preserve both the caller ID and text segment. Added a
dedicated test (`addWithCallerSuppliedIdAndTextSegment`) verifying that
`addAll` with IDs is called in this case.
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
