This is an automated email from the ASF dual-hosted git repository.
fmariani pushed a commit to branch main
in repository https://gitbox.apache.org/repos/asf/camel-website.git
The following commit(s) were added to refs/heads/main by this push:
new e781c100 Making Apache Camel Documentation Accessible to LLMs blogpost
e781c100 is described below
commit e781c1000d3c4b375c85fdeea99302873d10899c
Author: Croway <[email protected]>
AuthorDate: Wed Nov 12 11:22:42 2025 +0100
Making Apache Camel Documentation Accessible to LLMs blogpost
---
.../2025/11/camel-website-llmstxt/featured.png | Bin 0 -> 243818 bytes
.../blog/2025/11/camel-website-llmstxt/index.md | 119 +++++++++++++++++++++
2 files changed, 119 insertions(+)
diff --git a/content/blog/2025/11/camel-website-llmstxt/featured.png
b/content/blog/2025/11/camel-website-llmstxt/featured.png
new file mode 100644
index 00000000..a9a95d3b
Binary files /dev/null and
b/content/blog/2025/11/camel-website-llmstxt/featured.png differ
diff --git a/content/blog/2025/11/camel-website-llmstxt/index.md
b/content/blog/2025/11/camel-website-llmstxt/index.md
new file mode 100644
index 00000000..11b47937
--- /dev/null
+++ b/content/blog/2025/11/camel-website-llmstxt/index.md
@@ -0,0 +1,119 @@
+---
+title: "Making Apache Camel Documentation Accessible to LLMs"
+date: 2025-11-12
+draft: false
+authors: [ croway ]
+categories: [ "Tooling" ]
+preview: "How we implemented llms.txt to make Apache Camel documentation
easily accessible to AI coding agents and LLM training"
+---
+
+The Apache Camel website now generates markdown versions of all documentation
pages following the [llms.txt specification](https://llmstxt.org/). This makes
our documentation easily accessible to Large Language Models (LLMs) and AI
coding assistants.
+
+## What is llms.txt?
+
+The llms.txt specification is a standardized format that helps LLMs discover
and consume website content efficiently. Similar to how `robots.txt` guides web
crawlers and `sitemap.xml` helps search engines, `llms.txt` provides a
structured entry point for AI systems to understand and access documentation.
+
+The Apache Camel website now exposes [/llms.txt](/llms.txt) which provides:
+
+- An overview of Apache Camel and its documentation structure
+- Instructions for accessing markdown versions of pages
+- Information about key documentation sections (components, languages,
patterns, user guides)
+- A count of available markdown pages (5,355+ pages)
+- Direct links to important documentation areas
+
+This standardized file makes it easy for LLM training pipelines and AI coding
assistants to discover and consume Apache Camel documentation efficiently.
+
+## Why This Matters
+
+Making Apache Camel documentation LLM-friendly brings two significant benefits:
+
+### 1. Better AI Training Data
+
+When LLMs are trained or updated, they can easily crawl and index Apache Camel
documentation through the standardized llms.txt format. This ensures that AI
models have access to accurate, well-structured information about Apache Camel.
+
+### 2. Enhanced Developer Experience with AI Coding Agents
+
+Modern coding assistants like Claude Code, Cursor, GitHub Copilot, and Gemini
CLI can now directly access Apache Camel documentation in a format optimized
for their consumption. This means:
+
+- More accurate code suggestions for Apache Camel integrations
+- Better understanding of component configurations and patterns
+- Improved troubleshooting and debugging assistance
+- Up-to-date knowledge of the latest Camel features and versions
+
+## Using the Markdown Documentation
+
+### Example: AI Assistant Using llms.txt
+
+Here's a real example of an AI coding assistant using the llms.txt endpoint to
answer Apache Camel questions:
+
+**User:** Reply to Apache Camel-related questions using the llms.txt
`https://camel.apache.org/llms.txt` follow links and redirect.
+What is the latest Camel release? And the latest Camel Quarkus?
+
+**Assistant:**
+> I'll fetch the Apache Camel llms.txt file and follow any links to find the
latest release information.
+>
+> Fetch(`https://camel.apache.org/llms.txt`)
+>
+> Let me follow the releases page link to get the specific version numbers:
+>
+> Fetch(`https://camel.apache.org/releases/index.md`)
+>
+> Fetch(`https://camel.apache.org/camel-quarkus/next/index.md`)
+>
+> Based on the Apache Camel documentation:
+>
+> **Latest Apache Camel Release:** 4.16.0 (released 2025-11-05)
+>
+> **Latest Camel Quarkus:** 3.27.x (compatible with Camel 4.14.2 and Quarkus
3.27.0)
+>
+> Note that the Camel Quarkus version (3.27.x) is currently tracking Camel
4.14.2, which is a few versions behind the latest Camel core release (4.16.0).
This is typical as Camel Quarkus needs to maintain compatibility with both
Apache Camel and Quarkus frameworks.
+
+This demonstrates how AI assistants can autonomously navigate the llms.txt
file, follow links to relevant documentation, and provide accurate, up-to-date
information about Apache Camel releases.
+
+### Accessing Markdown Documentation
+
+For any HTML page on the Apache Camel website, a markdown version is available
by appending `.md` to the URL:
+
+- **HTML**:
`https://camel.apache.org/components/4.10.x/languages/simple-language.html`
+- **Markdown**:
`https://camel.apache.org/components/4.10.x/languages/simple-language.html.md`
+
+## Try It Yourself
+
+Visit [/llms.txt](/llms.txt) to see the implementation in action. You can
access markdown versions of any documentation page by appending `.md` to the
URL.
+
+When using AI coding assistants like Claude Code, Cursor, or GitHub Copilot,
they can now provide more accurate and up-to-date information about Apache
Camel by accessing these markdown pages directly.
+
+## Implementation Details
+
+The implementation integrates into the existing build pipeline:
+
+### Build Pipeline Integration
+
+The markdown generation runs automatically during the website build process:
+
+1. **Antora** generates HTML documentation from AsciiDoc sources
+2. **Hugo** builds the website structure
+3. **Gulp task** converts HTML to markdown
+4. Generated markdown files are deployed alongside HTML pages
+
+### Content Extraction and Cleaning
+
+The conversion process focuses on extracting only the essential documentation
content:
+
+- Removes navigation elements, headers, and footers
+- Extracts the main article content using semantic HTML selectors
+- Converts tables, code blocks, and formatting to GitHub Flavored Markdown
+- Preserves document structure and hierarchy
+
+## Results and Impact
+
+The implementation generates:
+
+- **5,355+ markdown pages** automatically during each build
+- **Coverage** of components, languages, data formats, and user guides
+- **Clean, structured content** optimized for LLM consumption
+- **No manual maintenance required** - fully automated with the build pipeline
+
+## Conclusion
+
+By implementing the llms.txt specification, we've made Apache Camel
documentation more accessible to both AI training pipelines and
developer-facing coding assistants. This automated solution requires no manual
maintenance while providing structured, clean documentation in a format
optimized for LLM consumption.
\ No newline at end of file
