MongoDB

MongoDB can act as a source or destination

​

1. Pick an Embedding Model

Pick an embedding model from the options on the models page

Consult the Embedding Benchmarks scripts for a more empirical approach. Otherwise, there are KNN evaluation tools that we can help use.

​

2. Create MongoDB Cluster via MongoDB Atlas

1. Navigate to MongoDB Atlas.
2. If you don’t already have an account, create one. Otherwise, sign in.
3. Follow the prompts to create a new cluster.

​

3. Create Vector Search Index

1. In MongoDB Atlas, navigate to Atlas Search
2. Choose Create Search Index and then JSON Editor.
3. Select the collection you wish to index.
4. Enter the JSON configuration for your index. Replace "test_embedding_768" with the name of the field where your embeddings will be stored, and adjust "dimensions" to match the dimensions of your chosen embedding model from the models page.

Sample Index Configuration:

{
  "fields":[
    {
      "type": "vector",
      "path": "embedding_768",
      "numDimensions": 768,
      "similarity": "euclidean"
    }
  ]
}

​

4. Create your MongoDB Connection

​

Set MongoDB as your Source

​

Set MongoDB as your Destination

from mixpeek import Mixpeek

mixpeek = Mixpeek('API_KEY')

mixpeek.connections.create(
    alias="my-mongo-test",
    engine="mongodb",
    details={
        "host": "your_host_address",
        "database": "your_database_name",
        "username": "your_username",
        "password": "your_password"
    }
)

curl --location 'https://api.mixpeek.com/connections' \
--header 'Authorization: Bearer API_KEY' \
--header 'Content-Type: application/json' \
--data '{
    "alias": "my-mongo-test",
    "engine": "mongodb",
    "details": {
        "host": "my_hostname",
        "database": "my_database",
        "username": "my_username",
        "password": "my_password"
    }
}'