Skip to content

Commit acce46b

Browse files
smongiarsmongiar
committed
Adding docling-serve example
1 parent 64ee484 commit acce46b

13 files changed

Lines changed: 328 additions & 1 deletion

File tree

‎README.adoc‎

Lines changed: 3 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -27,7 +27,7 @@ readme's instructions.
2727
=== Examples
2828

2929
// examples: START
30-
Number of Examples: 68 (0 deprecated)
30+
Number of Examples: 69 (0 deprecated)
3131

3232
[width="100%",cols="4,2,4",options="header"]
3333
|===
@@ -89,6 +89,8 @@ Number of Examples: 68 (0 deprecated)
8989

9090
| link:multi-datasource-2pc/readme.adoc[Multi Datasource 2pc] (multi-datasource-2pc) | Database | An example showing how to work with Camel and Spring Boot using multiple pooled datasources with two-phase commit
9191

92+
| link:docling/readme.adoc[Docling] (docling) | Document Processing | An example showing how to convert documents to Markdown using Camel Docling component and Spring Boot
93+
9294
| link:load-balancer-eip/README.adoc[Load Balancer Eip] (load-balancer-eip) | EIP | An example showing Load Balancer EIP with Camel and Spring Boot
9395

9496
| link:platform-http-proxy/README.adoc[Platform Http Proxy] (platform-http-proxy) | EIP | An example showing Camel reverse proxy with platform HTTP

‎docling/.gitignore‎

Lines changed: 11 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,11 @@
1+
target/
2+
src/main/resources/documents/*
3+
!src/main/resources/documents/.gitkeep
4+
!src/main/resources/documents/extract/
5+
src/main/resources/documents/extract/*
6+
!src/main/resources/documents/extract/.gitkeep
7+
src/main/resources/output/*
8+
!src/main/resources/output/.gitkeep
9+
!src/main/resources/output/metadata/
10+
src/main/resources/output/metadata/*
11+
!src/main/resources/output/metadata/.gitkeep

‎docling/pom.xml‎

Lines changed: 112 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,112 @@
1+
<?xml version="1.0" encoding="UTF-8"?>
2+
<!--
3+
4+
Licensed to the Apache Software Foundation (ASF) under one or more
5+
contributor license agreements. See the NOTICE file distributed with
6+
this work for additional information regarding copyright ownership.
7+
The ASF licenses this file to You under the Apache License, Version 2.0
8+
(the "License"); you may not use this file except in compliance with
9+
the License. You may obtain a copy of the License at
10+
11+
http://www.apache.org/licenses/LICENSE-2.0
12+
13+
Unless required by applicable law or agreed to in writing, software
14+
distributed under the License is distributed on an "AS IS" BASIS,
15+
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
16+
See the License for the specific language governing permissions and
17+
limitations under the License.
18+
19+
-->
20+
<project xmlns="http://maven.apache.org/POM/4.0.0"
21+
xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
22+
xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
23+
24+
<modelVersion>4.0.0</modelVersion>
25+
<parent>
26+
<groupId>org.apache.camel.springboot.example</groupId>
27+
<artifactId>examples</artifactId>
28+
<version>4.18.0-SNAPSHOT</version>
29+
</parent>
30+
31+
<artifactId>camel-example-spring-boot-docling</artifactId>
32+
<name>Camel SB Examples :: Docling</name>
33+
<description>An example showing how to convert documents to Markdown using Camel Docling component and Spring Boot</description>
34+
35+
<properties>
36+
<category>Document Processing</category>
37+
<project.build.sourceEncoding>UTF-8</project.build.sourceEncoding>
38+
<project.reporting.outputEncoding>UTF-8</project.reporting.outputEncoding>
39+
</properties>
40+
41+
<dependencyManagement>
42+
<dependencies>
43+
<!-- Spring Boot BOM -->
44+
<dependency>
45+
<groupId>org.springframework.boot</groupId>
46+
<artifactId>spring-boot-dependencies</artifactId>
47+
<version>${spring-boot-version}</version>
48+
<type>pom</type>
49+
<scope>import</scope>
50+
</dependency>
51+
<!-- Camel BOM -->
52+
<dependency>
53+
<groupId>org.apache.camel.springboot</groupId>
54+
<artifactId>camel-spring-boot-bom</artifactId>
55+
<version>${project.version}</version>
56+
<type>pom</type>
57+
<scope>import</scope>
58+
</dependency>
59+
</dependencies>
60+
</dependencyManagement>
61+
62+
<dependencies>
63+
<!-- Spring Boot -->
64+
<dependency>
65+
<groupId>org.springframework.boot</groupId>
66+
<artifactId>spring-boot-starter</artifactId>
67+
</dependency>
68+
69+
<!-- Camel -->
70+
<dependency>
71+
<groupId>org.apache.camel.springboot</groupId>
72+
<artifactId>camel-spring-boot-starter</artifactId>
73+
</dependency>
74+
<dependency>
75+
<groupId>org.apache.camel.springboot</groupId>
76+
<artifactId>camel-docling-starter</artifactId>
77+
</dependency>
78+
<dependency>
79+
<groupId>org.apache.camel.springboot</groupId>
80+
<artifactId>camel-file-starter</artifactId>
81+
</dependency>
82+
83+
<!-- test -->
84+
<dependency>
85+
<groupId>org.springframework.boot</groupId>
86+
<artifactId>spring-boot-starter-test</artifactId>
87+
<scope>test</scope>
88+
</dependency>
89+
<dependency>
90+
<groupId>org.apache.camel</groupId>
91+
<artifactId>camel-test-spring-junit5</artifactId>
92+
<scope>test</scope>
93+
</dependency>
94+
</dependencies>
95+
96+
<build>
97+
<plugins>
98+
<plugin>
99+
<groupId>org.springframework.boot</groupId>
100+
<artifactId>spring-boot-maven-plugin</artifactId>
101+
<version>${spring-boot-version}</version>
102+
<executions>
103+
<execution>
104+
<goals>
105+
<goal>repackage</goal>
106+
</goals>
107+
</execution>
108+
</executions>
109+
</plugin>
110+
</plugins>
111+
</build>
112+
</project>

‎docling/readme.adoc‎

Lines changed: 108 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,108 @@
1+
== Camel Example Spring Boot and Docling
2+
3+
This example shows how to work with Apache Camel and the Docling component using Spring Boot to convert documents to Markdown format.
4+
5+
The example demonstrates document conversion from various formats (PDF, DOCX, PPTX, HTML, MD) to Markdown using the Docling service.
6+
7+
=== Features
8+
9+
* Document to Markdown Conversion - Automatically converts PDF, DOCX, PPTX, HTML, and MD files to Markdown format
10+
* Metadata Extraction - Optional route to extract structured data as JSON from documents
11+
* File-based Processing - Watch directories for new files and process them automatically
12+
* Java DSL Routes - Routes defined using Camel Java DSL
13+
14+
=== Prerequisites
15+
16+
Before running this example, you need:
17+
18+
1. A running Docling-Serve instance at http://0.0.0.0:5001
19+
20+
----
21+
docker run -p 5001:5001 -e DOCLING_SERVE_ENABLE_UI=1 ghcr.io/docling-project/docling-serve:latest
22+
----
23+
24+
=== How to run
25+
26+
You can run this example using:
27+
28+
----
29+
mvn spring-boot:run
30+
----
31+
32+
=== Usage
33+
34+
==== Converting Documents to Markdown
35+
36+
1. Start the application
37+
2. Place any PDF, DOCX, PPTX, HTML, or MD file in the `src/main/resources/documents/` directory
38+
3. The application will:
39+
- Detect the new file
40+
- Convert it to Markdown using Docling
41+
- Save the converted file to `src/main/resources/output/` directory with `.md` extension
42+
- Delete the original file from `src/main/resources/documents/`
43+
44+
==== Extracting Structured Metadata
45+
46+
1. Place documents in `src/main/resources/documents/extract/`
47+
2. The application will:
48+
- Extract structured data from the document
49+
- Save the metadata as JSON to `src/main/resources/output/metadata/`
50+
51+
=== Project Structure
52+
53+
----
54+
docling/
55+
└── src/
56+
└── main/
57+
├── java/
58+
│ └── org/apache/camel/example/springboot/docling/
59+
│ ├── DoclingServeApplication.java
60+
│ └── DoclingServeRoute.java
61+
└── resources/
62+
├── application.properties
63+
├── documents/ # Input directory - place documents here
64+
│ └── extract/ # Optional: place documents here for metadata extraction
65+
└── output/ # Output directory for converted Markdown files
66+
└── metadata/ # Output directory for extracted metadata JSON files
67+
----
68+
69+
=== Configuration
70+
71+
Edit `src/main/resources/application.properties` to configure:
72+
73+
* `docling.serve.url` - URL of the Docling service
74+
* `documents.directory` - Input directory for documents to convert (default: src/main/resources/documents)
75+
* `output.directory` - Output directory for converted files (default: src/main/resources/output)
76+
77+
=== Routes
78+
79+
The application includes two routes defined in `src/main/java/org/apache/camel/example/springboot/docling/DoclingServeRoute.java`:
80+
81+
==== document-to-markdown-converter
82+
83+
* Watches: `src/main/resources/documents/` directory
84+
* Accepts: PDF, DOCX, PPTX, HTML, MD files
85+
* Action: Converts to Markdown
86+
* Output: `src/main/resources/output/{filename}.md`
87+
88+
==== document-metadata-extractor
89+
90+
* Watches: `src/main/resources/documents/extract/` directory
91+
* Accepts: PDF, DOCX, PPTX files
92+
* Action: Extracts structured data as JSON
93+
* Output: `src/main/resources/output/metadata/{filename}.json`
94+
95+
=== Using Camel components
96+
97+
Apache Camel provides 200+ components which you can use to integrate and route messages between many systems
98+
and data formats. To use any of these Camel components, add the component as a dependency to your project.
99+
100+
=== Help and contributions
101+
102+
If you hit any problem using Camel or have some feedback, then please
103+
https://camel.apache.org/support.html[let us know].
104+
105+
We also love contributors, so
106+
https://camel.apache.org/contributing.html[get involved] :-)
107+
108+
The Camel riders!

‎docling/src/main/java/org/apache/camel/example/springboot/docling/DoclingServeApplication.java‎

Lines changed: 28 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,28 @@
1+
/*
2+
* Licensed to the Apache Software Foundation (ASF) under one or more
3+
* contributor license agreements. See the NOTICE file distributed with
4+
* this work for additional information regarding copyright ownership.
5+
* The ASF licenses this file to You under the Apache License, Version 2.0
6+
* (the "License"); you may not use this file except in compliance with
7+
* the License. You may obtain a copy of the License at
8+
*
9+
* http://www.apache.org/licenses/LICENSE-2.0
10+
*
11+
* Unless required by applicable law or agreed to in writing, software
12+
* distributed under the License is distributed on an "AS IS" BASIS,
13+
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14+
* See the License for the specific language governing permissions and
15+
* limitations under the License.
16+
*/
17+
package org.apache.camel.example.springboot.docling;
18+
19+
import org.springframework.boot.SpringApplication;
20+
import org.springframework.boot.autoconfigure.SpringBootApplication;
21+
22+
@SpringBootApplication
23+
public class DoclingServeApplication {
24+
25+
public static void main(String[] args) {
26+
SpringApplication.run(DoclingServeApplication.class, args);
27+
}
28+
}

‎docling/src/main/java/org/apache/camel/example/springboot/docling/DoclingServeRoute.java‎

Lines changed: 46 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,46 @@
1+
/*
2+
* Licensed to the Apache Software Foundation (ASF) under one or more
3+
* contributor license agreements. See the NOTICE file distributed with
4+
* this work for additional information regarding copyright ownership.
5+
* The ASF licenses this file to You under the Apache License, Version 2.0
6+
* (the "License"); you may not use this file except in compliance with
7+
* the License. You may obtain a copy of the License at
8+
*
9+
* http://www.apache.org/licenses/LICENSE-2.0
10+
*
11+
* Unless required by applicable law or agreed to in writing, software
12+
* distributed under the License is distributed on an "AS IS" BASIS,
13+
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14+
* See the License for the specific language governing permissions and
15+
* limitations under the License.
16+
*/
17+
package org.apache.camel.example.springboot.docling;
18+
19+
import org.apache.camel.builder.RouteBuilder;
20+
import org.springframework.stereotype.Component;
21+
22+
@Component
23+
public class DoclingServeRoute extends RouteBuilder {
24+
25+
@Override
26+
public void configure() throws Exception {
27+
28+
from("file:{{documents.directory}}?delete=true&include=.*\\.(pdf|docx|pptx|html|md)$")
29+
.routeId("document-to-markdown-converter")
30+
.log("Processing document: ${header.CamelFileName}")
31+
.to("docling:CONVERT_TO_MARKDOWN?useDoclingServe=true&doclingServeUrl={{docling.serve.url}}&contentInBody=true")
32+
.log("Document converted to Markdown: ${header.CamelFileName}")
33+
.setHeader("CamelFileName", simple("${file:name.noext}.md"))
34+
.to("file:{{output.directory}}")
35+
.log("Saved converted document to: {{output.directory}}/${header.CamelFileName}");
36+
37+
from("file:{{documents.directory}}/extract?delete=true&include=.*\\.(pdf|docx|pptx)$")
38+
.routeId("document-metadata-extractor")
39+
.log("Extracting metadata from: ${header.CamelFileName}")
40+
.to("docling:EXTRACT_STRUCTURED_DATA?useDoclingServe=true&doclingServeUrl={{docling.serve.url}}&outputFormat=json&contentInBody=true")
41+
.log("Metadata extracted from: ${header.CamelFileName}")
42+
.setHeader("CamelFileName", simple("${file:name.noext}.json"))
43+
.to("file:{{output.directory}}/metadata")
44+
.log("Saved metadata to: {{output.directory}}/metadata/${header.CamelFileName}");
45+
}
46+
}

‎docling/src/main/resources/application.properties‎

Lines changed: 19 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,19 @@
1+
# Application Configuration
2+
camel.main.name=DoclingServe
3+
spring.application.name=camel-docling-serve
4+
5+
# Directory Configuration
6+
documents.directory=src/main/resources/documents
7+
output.directory=src/main/resources/output
8+
9+
# Docling Service Configuration
10+
docling.serve.url=http://0.0.0.0:5001
11+
12+
# Camel Route Configuration
13+
camel.main.run-controller=true
14+
15+
# Logging Configuration
16+
#logging.level.org.apache.camel=INFO
17+
#logging.level.org.springframework = INFO
18+
#logging.level.org.apache.camel.spring.boot = INFO
19+
#logging.level.org.apache.camel.example.springboot.docling=DEBUG

‎docling/src/main/resources/documents/.gitkeep‎

Whitespace-only changes.

‎docling/src/main/resources/documents/extract/.gitkeep‎

Whitespace-only changes.

‎docling/src/main/resources/output/.gitkeep‎

Whitespace-only changes.

0 commit comments

Comments
 (0)