multiAI Summary Pending
rag-pipeline
Details on the Retrieval Augmented Generation pipeline, Ingestion, and Vector Search.
231 stars
Installation
Claude Code / Cursor / Codex
$curl -o ~/.claude/skills/rag-pipeline/SKILL.md --create-dirs "https://raw.githubusercontent.com/aiskillstore/marketplace/main/skills/abdulsamad94/rag-pipeline/SKILL.md"
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/rag-pipeline/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How rag-pipeline Compares
| Feature / Agent | rag-pipeline | Standard Approach |
|---|---|---|
| Platform Support | multi | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Details on the Retrieval Augmented Generation pipeline, Ingestion, and Vector Search.
Which AI agents support this skill?
This skill is compatible with multi.
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# RAG Pipeline Logic
## Ingestion
- **Script**: `backend/ingest.py`
- **Process**:
1. Scans `docs/`.
2. Cleans MDX (removes frontmatter/imports).
3. Chunks text (1000 chars, 100 overlap).
4. Embeds using `models/text-embedding-004`.
5. Upserts to Qdrant collection `physical_ai_book`.
- **Run**: `python backend/ingest.py`
## Vector Search (Qdrant)
- **Client**: `qdrant-client`
- **Collection**: `physical_ai_book`
- **Vector Size**: 768 (Gecko-004)
- **Similarity**: Cosine
## Prompt Engineering
- **File**: `backend/utils/helpers.py`.
- **RAG Prompt**: Constructs a prompt containing retrieved context chunks.
- **Personalization**: `backend/personalization.py` creates system instructions based on `software_background` and `hardware_background` of the user.
## Agentic Flow
We use a custom `Agent` class (`backend/agents.py`) that wraps the LLM calls, allowing for future expansion into multi-agent workflows.