Keivan

What an agent can do with the ml-pipes corpus

trained-by-humans/ml-pipes: Build composable ML pipelines that are explicit, traceable, and optimizable

• Look up how ml-pipes implements composable, computer-vision, inference, with answers cited to file and line.
• Reuse a worked example: the commit “Move inspection previews to renderer and expand list items” (5 files · Python).
• Answer from ml-pipes's real Python source instead of memory (AI, prompts and agents).

• Where does ml-pipes handle “Move inspection previews to renderer and expand list items”?
• How does ml-pipes implement composable?
• What does packages/core do in ml-pipes?

Search the GitHub repository trained-by-humans/ml-pipes with XERJ (https://hub.xerj.org/corpus/trained-by-humans--ml-pipes).
Run these in a shell, in order, and check each result before the next:
1. xerj --help  (success: it prints usage). If xerj is missing: curl -fsSL https://xerj.org/get | sh
2. git clone https://github.com/trained-by-humans/ml-pipes ml-pipes && git -C ml-pipes checkout 29682ab3d4aa5800ebdfa297ad89907f97a0e527
3. Start a local node and leave it running: xerj --insecure --data-dir ./xerj-data
4. xerj autoindex ./ml-pipes --url http://127.0.0.1:9200 --prefix ml-pipes --progress plain
5. xerj autoindex map --url http://127.0.0.1:9200
Then answer my question from the indexed files and cite the ax_path of every hit. Query syntax: https://xerj.org/llms.txt
Licence: Apache-2.0. Keep the copyright notice and credit the authors.

corpus trained-by-humans--ml-pipes · AI, prompts and agents
Related corpora: adalflow, opennyai-legal-nlp, aawhan0/ModelDock, HAITHM-ALAKHALI/virtual_mouse
AI search and retrieval with XERJ · Case study: reference coding for agents