Integration · Databases
AI agents for Pinecone
Search, add, read and delete vectors in a Pinecone index: similarity search by vector or by a stored record's ID, text search on indexes with integrated embedding, index statistics and the list of indexes in the project.
- Actions
- 8
- Read
- 6
- Write
- 2
Actions
What your agents can do in Pinecone
Search, add, read and delete vectors in a Pinecone index: similarity search by vector or by a stored record's ID, text search on indexes with integrated embedding, index statistics and the list of indexes in the project. One connection works with one index (its host); the key reaches every index in its project.
Read 6
Look things up. Nothing changes.
List indexes
Lists the indexes in the key's project, as indexes: each with its name, host (the address a connection uses), status (ready, state), deployment, deletion_protection and tags.
Get index statistics
Returns the connected index's statistics: totalVectorCount, dimension, metric, vectorType and namespaces (each namespace's vectorCount).
Search by vector
Finds the vectors most similar to a query, as matches (most similar first), each with id, score and, when asked, metadata and values.
Search by text
Searches with plain text on an index that embeds text itself (an index created with integrated embedding), as result.hits: each with _id, _score and fields.
Get vectors by ID
Reads up to 1,000 vectors by ID, as vectors: an object keyed by ID, each with id, values and metadata.
List vector IDs
Lists vector IDs in a namespace, up to 100 a page, in sorted order, as vectors (each an id).
Write 2
Create, change or send.
Add or replace vectors
Writes up to 1,000 vectors, as upsertedCount.
Delete vectorsDeletes data
Permanently deletes vectors from one namespace: the listed ids (up to 1,000), or every vector matching a metadata filter like {"doc_id".
A person can approve first
Any write action can be set to wait for a person's approval before it runs, so an agent asks before it changes anything. Actions that delete data ask first by default.
Connection
How it connects
Connect it once in the console, then give it to the agents and workflows that need it.
Paste an API key from your Pinecone account.
What you enter
- API key
Settings
- Index host
Kept safe
- Credentials are stored encrypted with your organization's own keys.
- They are opened only by the process that makes the call, at the moment it runs, and never go into a prompt or the browser.
- Calls go only to the tool's own servers.
Ideas
Ideas to start with
Starting points made only from the actions above. Mix them with any other tool your agents can use.
- 01
Ask about your Pinecone data
Ask a question in plain words. The agent can list indexes, get index statistics or search by vector in Pinecone, then answers with what it found.
- 02
Let an agent update Pinecone
Have the agent add or replace vectors or delete vectors in Pinecone as part of a larger task. Turn on approval and a person signs off on each change first.
- 03
Share what it finds in Slack
Give one agent Pinecone and Slack: it can list indexes in Pinecone and post a summary to a Slack channel in the same run.
Works well with
More Databases tools
- PostgreSQL5 actionsRead and query a PostgreSQL database directly: Amazon RDS and Aurora, Google Cloud SQL, Azure, Neon, Supabase, or your own server with a public address.
- MySQL5 actionsRead and query a MySQL database directly: Amazon RDS and Aurora MySQL, Google Cloud SQL, Azure, PlanetScale, or your own server with a public address.
- MongoDB7 actionsRead and query a MongoDB database directly: MongoDB Atlas (mongodb+srv) or your own server with a public address.
- BigQuery5 actionsRun SQL on BigQuery, browse datasets, tables and their columns, and stream rows into a table, in a Google Cloud project, signed in with the person's own Google account.
- Snowflake9 actionsRun read-only SQL in Snowflake and page through the results, and list databases, schemas, tables, columns and warehouses, through the SQL API with a programmatic access token or a key pair.
- Amazon DynamoDB8 actionsRead and write items in Amazon DynamoDB tables: get, put, update and delete an item by its key, query by partition key or an index, scan with a filter, and list and describe tables, signed with an AWS access key.
FAQ
Pinecone and MyDeepAgents
Can MyDeepAgents connect to Pinecone?
Yes. The Pinecone connector has 8 actions: 6 read and 2 make changes. Your agents can call them as tools, and your workflows can run them as steps.
How do I connect Pinecone?
Paste an API key from your Pinecone account. You'll need: API key. The connection also asks for: Index host. Credentials are stored encrypted with your organization's own keys and are opened only at the moment of a call.
Can an agent change data in Pinecone without asking?
Only if you let it. Each of the 2 actions that change data can be set to wait for a person's approval before it runs, and the one that deletes data asks first by default.
Can I use Pinecone in workflows as well as agents?
Yes. Every Pinecone action also works as a step in a workflow, and the same connection serves your agents and your workflows.
Early access
Put Pinecone to work
Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.