# Pinecone

> Manages vector embeddings with Pinecone for semantic search, recommendation, and RAG pipelines.

- Skill: `ssrjkk/pinecone` (Agent Skill, multi-file: 2 files)
- Install (CLI): `npx skillmds@latest add ssrjkk/pinecone`
- Raw SKILL.md: https://api.skillmd.com/api/skills/ssrjkk/pinecone/raw
- Safety review: pending (external: skill-scanner PASS, skillspector PASS)
- Works with: Claude Code, Claude.ai, OpenAI Codex
- Category: AI & ML
- Author: ssrjkk (https://skillmd.com/u/ssrjkk)
- Updated: 2026-08-19
- Page: https://skillmd.com/skills/ssrjkk/pinecone

---

# Pinecone
> Managed vector database for semantic search and RAG.
## Quick Start
```python
from pinecone import Pinecone, ServerlessSpec
pc = Pinecone(api_key="YOUR_API_KEY")
pc.create_index(name="my-index", dimension=384, metric="cosine", spec=ServerlessSpec(cloud="aws", region="us-east-1"))
```
## Indexing & Query
```python
index = pc.Index("my-index")
index.upsert(vectors=[{"id": "doc1", "values": [0.1, 0.2], "metadata": {"text": "Document 1"}}])
results = index.query(vector=query_embedding, top_k=5, include_metadata=True)
```
## When to Use
- Semantic search; RAG vector storage; Recommendation systems
## Validation
1. Index creation succeeds; 2. Upsert operations complete; 3. Query returns relevant results