npx claudepluginhub pinecone-io/pinecone-claude-code-plugin --plugin pineconeThis skill is limited to using the following tools:
Welcome! This skill walks you through your first Pinecone experience using the tools available to you. In this quickstart,
Provides overview of all Pinecone skills, required setup (account, API key), optional tools (CLI, MCP server, uv), and recommendations for which skill to use.
Provides setup and TypeScript examples for Upstash Vector DB: semantic search, namespaces, auto-embedding with MixBread. Use for vector search features on Vercel.
Implements vector databases with Pinecone, Weaviate, Qdrant, Milvus, pgvector for semantic search, RAG, recommendations, and similarity systems. Optimizes embeddings, indexing, and hybrid search.
Share bugs, ideas, or general feedback.
Welcome! This skill walks you through your first Pinecone experience using the tools available to you. In this quickstart, you will learn how to do a simple form of semantic search over some example data.
Before starting either path, verify the API key works by calling list-indexes via the Pinecone MCP. If it succeeds, proceed. If it fails, ask the user to set their key:
export PINECONE_API_KEY="your-key"
Then retry list-indexes to confirm.
Use AskUserQuestion to let the user choose their path:
For each step, explain to the user what will happen. An overview is here:
The prerequisite check already called list-indexes. If it succeeded, the MCP is working — proceed to Step 2.
If it failed because MCP tools were unavailable (not an auth error):
Use the MCP create-index-for-model tool to create a serverless index with integrated embeddings:
name: quickstart-skills
cloud: aws
region: us-east-1
embed:
model: llama-text-embed-v2
fieldMap:
text: chunk_text
Explain to the user what's happening:
llama-text-embed-v2)field_map tells Pinecone which field in your records contains the text to embedWait for the index to become ready before proceeding. Waiting a few seconds is sufficient.
Run the bundled upsert script to seed the index with sample records:
uv run scripts/upsert.py --index quickstart-skills
Explain to the user what's happening:
_id, a chunk_text field (the text that gets embedded), and a category fieldUse the MCP search-records tool to run the first semantic search:
index: quickstart-skills
namespace: example-namespace
query:
topK: 3
inputs:
text: "getting things done efficiently"
Display the results in a clean table: ID, score, and chunk_text.
Explain to the user what's happening:
Offer to explore further: Use AskUserQuestion to ask if they'd like to try another query:
"feeling under the weather" — should surface the health records"wildlife spotting outside" — should surface the nature recordsRun whichever query they choose and display the results the same way. If they want to try both, do both. After each result, point out which theme surfaced and why.
If they decline or are done exploring, proceed to Step 5 or offer to skip ahead to the complete script.
Use AskUserQuestion to ask if the user wants to try reranking.
If yes, use search-records again with reranking enabled:
rerank:
model: bge-reranker-v2-m3
rankFields: [chunk_text]
topN: 3
Explain: Reranking runs a second-pass model over the results to improve relevance ordering.
Congratulate the user on completing the quickstart. Use AskUserQuestion to ask if they'd like a standalone Python script that does everything in one go — create index, upsert, query, and rerank.
If yes, copy it to their working directory:
cp scripts/quickstart_complete.py ./pinecone_quickstart.py
Tell the user:
./pinecone_quickstart.pyuv run pinecone_quickstart.pyuv inline dependencies — no separate install neededrecords list to build something realGuide the user through the Pinecone Assistant workflow using the existing assistant skills:
Before anything else, use AskUserQuestion to ask if the user has files to upload. Pinecone Assistant accepts .pdf, .md, .txt, and .docx files — a single file or a folder of files both work.
If they have files: ask for the path and proceed to Step 2.
If they don't have files: use AskUserQuestion to offer two options:
./sample-docs/ so they can complete the quickstart right now. Ask what topics they'd like (or default to: a product FAQ, a short how-to guide, and a brief company overview). Write 3 files, each 150–250 words.Invoke pinecone:assistant or run:
uv run ../assistant/scripts/create.py --name my-assistant
Explain: The assistant is a fully managed RAG service — upload documents, ask questions, get cited answers.
Invoke pinecone:assistant or run:
uv run ../assistant/scripts/upload.py --assistant my-assistant --source ./your-docs
Explain: Pinecone handles chunking, embedding, and indexing automatically — no configuration needed.
Invoke pinecone:assistant or run:
uv run ../assistant/scripts/chat.py --assistant my-assistant --message "What are the main topics in these documents?"
Explain: Responses include citations with source file and page number.
pinecone:assistant to keep the assistant up to date as documents changePINECONE_API_KEY not set
export PINECONE_API_KEY="your-key"
MCP tools not available
PINECONE_API_KEY is set before the MCP server startsIndex already exists
pc index delete -n quickstart-skills via the CLIuv not installed
See the uv installation guide.