mcpField
P
pinecone-assistant

pinecone-assistant

github.com/pinecone-ioDocuments16274 installsUpdated 6w ago
Repository

About pinecone-assistant

A skill for operating Pinecone Assistant, a managed RAG service, through scripts and natural-language requests. It covers assistant creation, document upload and sync, chat, context retrieval, and listing assistants.

Key features

  1. 01Create assistants with configuration
  2. 02Upload and incrementally sync files
  3. 03Ask questions through chat
  4. 04Retrieve context snippets
  5. 05List assistants and files

Use cases

  1. 01Creating an assistant for documentation
  2. 02Uploading or refreshing a document collection
  3. 03Asking questions and retrieving relevant context

Install

Copy the command and run it in a terminal.

$npx skills add https://github.com/pinecone-io/skills --skill pinecone-assistant

After installing, type/pinecone-assistantin Claude Code to confirm it loaded.

Bundled files

References and scripts installed along with SKILL.md.

references/
chat.md
context.md
create.md
list.md
sync.md
upload.md
scripts/
chat.py
context.py
create.py
list.py
sync.py
upload.py

Details

From the project README

Pinecone Assistant

Pinecone Assistant is a fully managed RAG service. Upload documents, ask questions, get cited answers. No embedding pipelines or infrastructure required.

All scripts are in scripts/ relative to this skill directory. Run with: uv run scripts/script_name.py [arguments]

<<clarify_style>>

Operations

What to doScriptKey args
Create an assistantscripts/create.py--name --instructions --region
Upload filesscripts/upload.py--assistant --source --patterns
Sync files (incremental)scripts/sync.py--assistant --source --delete-missing --dry-run
Chat / ask a questionscripts/chat.py--assistant --message
Get context snippetsscripts/context.py--assistant --query --top-k
List assistantsscripts/list.py--files --json

For full workflow details on any operation, read the relevant file in references/.

Natural Language Recognition

Proactively handle these patterns without requiring explicit commands:

Create: "create an assistant", "make an assistant called X", "set up an assistant for my docs" → See references/create.md

Upload: "upload my docs", "add files to my assistant", "index my documentation" → See references/upload.md

Sync: "sync my docs", "update my assistant", "keep assistant in sync", "refresh from ./docs" → See references/sync.md

Chat: "ask my assistant about X", "what does my assistant know about X", "chat with X" → See references/chat.md

Context: "search my assistant for X", "find context about X" → See references/context.md

List: "show my assistants", "what assistants do I have" → Run uv run scripts/list.py

Conversation Memory

Track the last assistant used within the conversation:

  • When a user creates or first uses an assistant, remember its name
  • If user says "my assistant", "it", or "the assistant" → use the last one
  • Briefly confirm which assistant you're using: "Asking docs-bot..."
  • If ambiguous and multiple exist → ask the user to clarify

Multi-Step Requests

Handle chained requests naturally. Example:

"Create an assistant called docs-bot, upload my ./docs folder, and ask what the main features are"

  1. uv run scripts/create.py --name docs-bot
  2. uv run scripts/upload.py --assistant docs-bot --source ./docs
  3. uv run scripts/chat.py --assistant docs-bot --message "what are the main features?"

Prerequisites

Comments

Markdown supported