oscerd opened a new pull request, #25048:
URL: https://github.com/apache/camel/pull/25048
## Summary
Adds a new MCP tool `camel_ai_pipeline_scaffold` that generates runnable
YAML DSL Camel routes for AI document-processing pipelines.
- **4 pipeline types**: summarization, extraction, RAG (with ingestion +
query routes), classification (with choice router)
- **3 document processors**: Docling (open-source), Textract (AWS-managed),
combined (both)
- **3 source types**: local file, S3 bucket, HTTP URL
- **Configurable**: Bedrock model ID and AWS region
- **Output**: YAML DSL route + matching `application.properties` template +
pipeline description
### Example usage
An MCP client can call:
```json
{"tool": "camel_ai_pipeline_scaffold", "arguments": {
"pipelineType": "summarization",
"documentProcessor": "docling",
"documentSource": "s3",
"modelId": "us.anthropic.claude-sonnet-4-20250514-v1:0"
}}
```
And receive a complete YAML route with Docling text extraction piped into
Bedrock converse.
## Test plan
- [x] 15 new tests covering all pipeline types, processors, sources, and
edge cases
- [x] All 317 existing MCP server tests pass (no regressions)
_Claude Code on behalf of oscerd_
🤖 Generated with [Claude Code](https://claude.com/claude-code)
--
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]
