Integration · Databases
AI agents for Zilliz Cloud (Milvus)
Search, query, read, insert, upsert and delete entities in Zilliz Cloud or Milvus collections through the RESTful API v2: vector similarity search with scalar filters, filter-only queries, and collection details.
- Actions
- 8
- Read
- 5
- Write
- 3
Actions
What your agents can do in Zilliz Cloud (Milvus)
Search, query, read, insert, upsert and delete entities in Zilliz Cloud or Milvus collections through the RESTful API v2: vector similarity search with scalar filters, filter-only queries, and collection details. Free and Serverless clusters answer on port 443; Dedicated clusters on AWS and Azure use ports 19530 to 19550, which this connection cannot reach.
Read 5
Look things up. Nothing changes.
List collections
Lists the collection names in the database, as data.
Describe a collection
Returns one collection's details, as data: fields (each with name, type, primaryKey, autoId and params such as a vector's dim), indexes (each vector field's metricType), enableDynamicField, load.
Search by vector
Finds the entities closest to one or more query vectors, as data: each with distance, the primary key and the output_fields asked for.
Query by filter
Reads the entities that match a scalar filter, with no vector, as data: each with the output_fields asked for.
Get entities by ID
Reads entities by primary key, as data: each with the output_fields asked for (all fields when empty).
Write 3
Create, change or send.
Insert entities
Inserts up to 1,000 entities, as data.insertCount and data.insertIds.
Upsert entities
Writes up to 1,000 entities, replacing those whose primary key already exists and inserting the rest, as data.upsertCount and data.upsertIds.
Delete entitiesDeletes data
Permanently deletes every entity that matches a filter, a Milvus expression like id in [1, 2, 3] or status == "archived".
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 Zilliz Cloud (Milvus) account.
What you enter
- API key or user:password
Settings
- Cluster endpoint
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 Zilliz Cloud (Milvus) data
Ask a question in plain words. The agent can list collections, describe a collection or search by vector in Zilliz Cloud (Milvus), then answers with what it found.
- 02
Let an agent update Zilliz Cloud (Milvus)
Have the agent insert entities or upsert entities in Zilliz Cloud (Milvus) 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 Zilliz Cloud (Milvus) and Slack: it can list collections in Zilliz Cloud (Milvus) 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.
- Pinecone8 actionsSearch, 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.
FAQ
Zilliz Cloud (Milvus) and MyDeepAgents
Can MyDeepAgents connect to Zilliz Cloud (Milvus)?
Yes. The Zilliz Cloud (Milvus) connector has 8 actions: 5 read and 3 make changes. Your agents can call them as tools, and your workflows can run them as steps.
How do I connect Zilliz Cloud (Milvus)?
Paste an API key from your Zilliz Cloud (Milvus) account. You'll need: API key or user:password. The connection also asks for: Cluster endpoint. 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 Zilliz Cloud (Milvus) without asking?
Only if you let it. Each of the 3 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 Zilliz Cloud (Milvus) in workflows as well as agents?
Yes. Every Zilliz Cloud (Milvus) action also works as a step in a workflow, and the same connection serves your agents and your workflows.
Early access
Put Zilliz Cloud (Milvus) to work
Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.