Integration · Databases
AI agents for OpenSearch
Search, count, read, add, change and delete documents in an OpenSearch cluster.
- Actions
- 8
- Read
- 5
- Write
- 3
Actions
What your agents can do in OpenSearch
Search, count, read, add, change and delete documents in an OpenSearch cluster (an Amazon OpenSearch Service domain or your own), and list its indexes and their field mappings, signing in as a user of the Security plugin (fine-grained access control). That user's roles decide what it can reach.
Read 5
Look things up. Nothing changes.
List indexes
Lists the indexes (and data stream backing indexes) whose names match pattern, sorted by name, as result.
Get index fields
Returns the field mappings of an index (or several, with a pattern like logs-*), keyed by index name.
Search documents
Runs a search with the Query DSL and returns hits.total (with relation: eq is exact, gte a lower bound), hits.hits.
Count documents
Counts the documents that match a Query DSL query (every document when empty), as count.
Get a document
Reads one document by its ID: _source is the document, with _index, _id, _version, _seq_no and found.
Write 3
Create, change or send.
Add or replace a document
Stores document under id in an index: a new document is created (result: created), and an existing one with that ID is replaced whole (result: updated).
Update a document
Merges fields into an existing document by ID: the named fields are set (objects merge, lists and values are replaced) and the rest are kept.
Delete a documentDeletes data
Permanently deletes one document by ID; result is deleted.
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.
Enter the API credentials from your OpenSearch account.
What you enter
- Username
- Password
Settings
- Domain 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 OpenSearch data
Ask a question in plain words. The agent can list indexes, get index fields or search documents in OpenSearch, then answers with what it found.
- 02
Let an agent update OpenSearch
Have the agent add or replace a document or update a document in OpenSearch 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 OpenSearch and Slack: it can list indexes in OpenSearch 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
OpenSearch and MyDeepAgents
Can MyDeepAgents connect to OpenSearch?
Yes. The OpenSearch 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 OpenSearch?
Enter the API credentials from your OpenSearch account. You'll need: Username and Password. The connection also asks for: Domain 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 OpenSearch 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 OpenSearch in workflows as well as agents?
Yes. Every OpenSearch action also works as a step in a workflow, and the same connection serves your agents and your workflows.
Early access
Put OpenSearch to work
Connect it in a few minutes, give an agent the actions it needs, and decide which changes wait for a person.