CAMEL-22433 - Create a Camel Docling component
Signed-off-by: Andrea Cosentino <ancosen@gmail.com>
diff --git a/components/camel-ai/camel-docling/src/main/docs/docling-component.adoc b/components/camel-ai/camel-docling/src/main/docs/docling-component.adoc
index 6f5b8e2..4933131 100644
--- a/components/camel-ai/camel-docling/src/main/docs/docling-component.adoc
+++ b/components/camel-ai/camel-docling/src/main/docs/docling-component.adoc
@@ -111,6 +111,10 @@
=== Basic document conversion to Markdown
+[tabs]
+====
+Java::
++
[source,java]
----
from("file:///data/documents?include=.*\\.pdf")
@@ -118,8 +122,29 @@
.to("file:///data/output");
----
+YAML::
++
+[source,yaml]
+----
+- route:
+ from:
+ uri: "file:///data/documents"
+ parameters:
+ include: ".*\\.pdf"
+ steps:
+ - to:
+ uri: "docling:CONVERT_TO_MARKDOWN"
+ - to:
+ uri: "file:///data/output"
+----
+====
+
=== Convert to HTML with content in body
+[tabs]
+====
+Java::
++
[source,java]
----
from("file:///data/documents?include=.*\\.pdf")
@@ -130,8 +155,31 @@
});
----
+YAML::
++
+[source,yaml]
+----
+- route:
+ from:
+ uri: "file:///data/documents"
+ parameters:
+ include: ".*\\.pdf"
+ steps:
+ - to:
+ uri: "docling:CONVERT_TO_HTML"
+ parameters:
+ contentInBody: true
+ - process:
+ ref: "htmlProcessor"
+----
+====
+
=== Extract structured data from documents
+[tabs]
+====
+Java::
++
[source,java]
----
from("file:///data/documents?include=.*\\.pdf")
@@ -142,8 +190,32 @@
});
----
+YAML::
++
+[source,yaml]
+----
+- route:
+ from:
+ uri: "file:///data/documents"
+ parameters:
+ include: ".*\\.pdf"
+ steps:
+ - to:
+ uri: "docling:EXTRACT_STRUCTURED_DATA"
+ parameters:
+ outputFormat: "json"
+ contentInBody: true
+ - process:
+ ref: "jsonDataProcessor"
+----
+====
+
=== Convert with OCR disabled
+[tabs]
+====
+Java::
++
[source,java]
----
from("file:///data/documents?include=.*\\.pdf")
@@ -151,8 +223,31 @@
.to("file:///data/output");
----
+YAML::
++
+[source,yaml]
+----
+- route:
+ from:
+ uri: "file:///data/documents"
+ parameters:
+ include: ".*\\.pdf"
+ steps:
+ - to:
+ uri: "docling:CONVERT_TO_MARKDOWN"
+ parameters:
+ enableOCR: false
+ - to:
+ uri: "file:///data/output"
+----
+====
+
=== Using headers to control processing
+[tabs]
+====
+Java::
++
[source,java]
----
from("file:///data/documents?include=.*\\.pdf")
@@ -163,8 +258,38 @@
.to("file:///data/output");
----
+YAML::
++
+[source,yaml]
+----
+- route:
+ from:
+ uri: "file:///data/documents"
+ parameters:
+ include: ".*\\.pdf"
+ steps:
+ - setHeader:
+ name: "CamelDoclingOperation"
+ constant: "CONVERT_TO_HTML"
+ - setHeader:
+ name: "CamelDoclingEnableOCR"
+ constant: true
+ - setHeader:
+ name: "CamelDoclingOCRLanguage"
+ constant: "es"
+ - to:
+ uri: "docling:CONVERT_TO_MARKDOWN" # Operation will be overridden by header
+ - to:
+ uri: "file:///data/output"
+----
+====
+
=== Processing with custom arguments
+[tabs]
+====
+Java::
++
[source,java]
----
from("file:///data/documents?include=.*\\.pdf")
@@ -176,8 +301,35 @@
.to("file:///data/output");
----
+YAML::
++
+[source,yaml]
+----
+- route:
+ from:
+ uri: "file:///data/documents"
+ parameters:
+ include: ".*\\.pdf"
+ steps:
+ - setHeader:
+ name: "CamelDoclingCustomArguments"
+ expression:
+ method:
+ ref: "customArgsBean"
+ method: "createCustomArgs"
+ - to:
+ uri: "docling:CONVERT_TO_MARKDOWN"
+ - to:
+ uri: "file:///data/output"
+----
+====
+
=== Content in body vs file path output
+[tabs]
+====
+Java::
++
[source,java]
----
// Get content directly in body (file is automatically deleted)
@@ -197,6 +349,96 @@
});
----
+YAML::
++
+[source,yaml]
+----
+# Get content directly in body (file is automatically deleted)
+- route:
+ from:
+ uri: "file:///data/documents"
+ parameters:
+ include: ".*\\.pdf"
+ steps:
+ - to:
+ uri: "docling:CONVERT_TO_MARKDOWN"
+ parameters:
+ contentInBody: true
+ - process:
+ ref: "contentProcessor"
+
+# Get file path (file is preserved)
+- route:
+ from:
+ uri: "file:///data/documents"
+ parameters:
+ include: ".*\\.pdf"
+ steps:
+ - to:
+ uri: "docling:CONVERT_TO_MARKDOWN"
+ parameters:
+ contentInBody: false
+ - process:
+ ref: "filePathProcessor"
+----
+====
+
+=== Processor Bean Examples
+
+When using YAML DSL, the processor references used in the examples above would be implemented as Spring beans:
+
+[source,java]
+----
+@Component("htmlProcessor")
+public class HtmlProcessor implements Processor {
+ @Override
+ public void process(Exchange exchange) throws Exception {
+ String htmlContent = exchange.getIn().getBody(String.class);
+ // Process the HTML content
+ log.info("Processing HTML content of length: {}", htmlContent.length());
+ }
+}
+
+@Component("jsonDataProcessor")
+public class JsonDataProcessor implements Processor {
+ @Override
+ public void process(Exchange exchange) throws Exception {
+ String jsonData = exchange.getIn().getBody(String.class);
+ // Process the structured JSON data
+ log.info("Processing JSON data: {}", jsonData);
+ }
+}
+
+@Component("contentProcessor")
+public class ContentProcessor implements Processor {
+ private static final Logger log = LoggerFactory.getLogger(ContentProcessor.class);
+
+ @Override
+ public void process(Exchange exchange) throws Exception {
+ String markdownContent = exchange.getIn().getBody(String.class);
+ log.info("Converted content: {}", markdownContent);
+ }
+}
+
+@Component("filePathProcessor")
+public class FilePathProcessor implements Processor {
+ private static final Logger log = LoggerFactory.getLogger(FilePathProcessor.class);
+
+ @Override
+ public void process(Exchange exchange) throws Exception {
+ String outputFilePath = exchange.getIn().getBody(String.class);
+ log.info("Output file saved at: {}", outputFilePath);
+ }
+}
+
+@Component("customArgsBean")
+public class CustomArgsBean {
+ public List<String> createCustomArgs() {
+ return Arrays.asList("--verbose", "--preserve-tables");
+ }
+}
+----
+
== Error Handling
The component handles various error scenarios:
