Milvus integration for AI agents
Run similarity search, list and create collections, and insert vector entities
Connect Milvus to Langdock and use it in chat, in agents and in workflows.
5 actions
Milvus actions
Each action is one step an agent or workflow can run in Milvus.
- Create collection
Creates a new collection to store vectors and their metadata.
- Insert entity
Inserts a vector and its metadata into a collection so it can be found by later searches.
- List collections
Lists the names of all collections in the database.
- Search collection
Finds entities whose fields match a filter expression (keyword search). For a semantic nearest-match search by meaning, use Similarity search instead.
- Similarity search
Searches the collection for the entities most similar to the query, ranked by vector similarity. Use this to find the most relevant information for a query.
Setup and permissions
An action can ask for your confirmation before it runs. In an agent, each action is set to “Always allow” or “Needs approval”.