rag-in-erp
Skill1 starsChanged 2 months agoNo licenceView on GitHub
Explains how retrieval-augmented generation is actually built inside a Frappe/ERPNext bench in the rfq_intelligence app: hybrid BM25 (frappe's FTS5 SQLiteSearch) + dense retrieval (MariaDB native VECTOR columns and VEC_DISTANCE_COSINE), fused with reciprocal rank fusion, with the LLM used only to pick from a retrieved shortlist. Use this skill whenever a task involves semantic search, embeddings, a vector store, a knowledge base, "chat with my data", item/party matching, document-to-master matching, RRF, BM25 vs embeddings, chunking, or an LLM choosing among ERP records — and before adding any vector database, Chroma/FAISS/pgvector dependency, or writing a new retrieval or LLM-selection path in a Frappe app. Reach for it before designing retrieval so the infrastructure, quota discipline and hallucination guardrails match what already works here.
In this repository4 other files it gives its agents.
The file
We split this skill into the rules it gives an agent
6 rules. About 0 are common, 4 are distinctive, and 2 are very specific to this project.
≈0
Common · estimate
Many files like this have a rule of this kind.
≈4
Distinctive · estimate
This author's own choices. Worth a look.
2
Very specific
Tied to their project's names, files or tools. Probably skip.
No licence file, so all rights are reserved — read it at the source. We count its rules but don't quote them. Read them on GitHub.
≈ “Common” is an estimate: at least 1 in 5 of the 350,495 skill files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.
Does it work?
Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.
No reviews yet
People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.
- It worked
- Partly
- It didn't
Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.
Your trail
Files you open will collect here, so you can find them again.
Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.
Now do this for your own.
Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.