Milvus

Milvus is an open-source vector database built for GenAI applications. It is built to be performant and scale to tens of billions of vectors with minimal performance loss.

Portkey provides a proxy to Milvus - you can log your Milvus requests and manage auth for Qdrant clusters on Portkey.

Portkey SDK Integration with Milvus

Portkey provides a consistent API to interact with models from various providers. To integrate Milvus with Portkey:

1. Install the Portkey SDK

Add the Portkey SDK to your application to interact with Milvus through Portkey’s gateway.

npm install --save portkey-ai

2. Create a New Integration

To use Milvus with Portkey, get your Milvus API key and create a new Milvus integration on Portkey.

import Portkey from 'portkey-ai'

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
    provider:"@PROVIDER" // Your Milvus provider slug
})

import Portkey from 'portkey-ai'

const portkey = new Portkey({
    apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
    provider:"@PROVIDER" // Your Milvus provider slug
})

from portkey_ai import Portkey

portkey = Portkey(
    api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
    provider="@PROVIDER"   # Replace with your Milvus provider slug
)

from openai import OpenAI

from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

client = OpenAI(
    api_key="MILVUS_API_KEY",
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        api_key="PORTKEY_API_KEY",
        provider="milvus",
        custom_host="MILVUS_HOST" # Replace with your Milvus host example: https://in03-34d7b37f7ee12c7.serverless.gcp-us-west1.cloud.zilliz.com
    )
)

import OpenAI from "openai";

import { PORTKEY_GATEWAY_URL, createHeaders } from "portkey-ai";

const client = new OpenAI({
  apiKey: "MILVUS_API_KEY",
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    provider: "milvus",
    apiKey: "PORTKEY_API_KEY",
    customHost: "MILVUS_HOST" // Replace with your Milvus host example: https://in03-34d7b37f7ee12c7.serverless.gcp-us-west1.cloud.zilliz.com
  }),
});

3. Use the Portkey SDK to interact with Milvus

from portkey_ai import Portkey

portkey = Portkey(
    api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
    provider="@MILVUS_PROVIDER",
    custom_host="MILVUS_HOST" # Replace with your Milvus host example: https://in03-34d7b37f7ee12c7.serverless.gcp-us-west1.cloud.zilliz.com
)

response = portkey.post(
    url="v2/vectordb/collections/list", # Replace with the endpoint you want to call
)

print(response)

from portkey_ai import Portkey

portkey = Portkey(
    api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
    provider="@MILVUS_PROVIDER",
    custom_host="MILVUS_HOST" # Replace with your Milvus host example: https://in03-34d7b37f7ee12c7.serverless.gcp-us-west1.cloud.zilliz.com
)

response = portkey.post(
    url="v2/vectordb/collections/list", # Replace with the endpoint you want to call
)

print(response)

import Portkey from 'portkey-ai';

// Initialize the Portkey client
const portkey = new Portkey({
  apiKey: "PORTKEY_API_KEY", // Replace with your Portkey API key
  provider:"@MILVUS_PROVIDER", // Add your Milvus provider slug
  customHost="MILVUS_HOST" // Replace with your Milvus host example: https://in03-34d7b37f7ee12c7.serverless.gcp-us-west1.cloud.zilliz.com
});

response = portkey.post(
    url="v2/vectordb/collections/list", # Replace with the endpoint you want to call
)

print(response)

import OpenAI from 'openai'; // We're using the v4 SDK
import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai'

const openai = new OpenAI({
  apiKey: 'MILVUS_API_KEY', // defaults to process.env["OPENAI_API_KEY"],
  baseURL: PORTKEY_GATEWAY_URL,
  defaultHeaders: createHeaders({
    provider:"@MILVUS_PROVIDER",
    apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
    customHost: "MILVUS_HOST" // Replace with your Milvus host example: https://in03-34d7b37f7ee12c7.serverless.gcp-us-west1.cloud.zilliz.com
  })
});

response = openai.post(
    url="v2/vectordb/collections/list", # Replace with the endpoint you want to call
)

print(response)

from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders

openai = OpenAI(
    api_key='MILVUS_API_KEY',
    base_url=PORTKEY_GATEWAY_URL,
    default_headers=createHeaders(
        provider="milvus",
        api_key="PORTKEY_API_KEY",
        custom_host="MILVUS_HOST" # Replace with your Milvus host example: https://in03-34d7b37f7ee12c7.serverless.gcp-us-west1.cloud.zilliz.com
    )
)

response = openai.post(
    url="v2/vectordb/collections/list", # Replace with the endpoint you want to call
)

print(response)

curl --location --request POST 'https://api.portkey.ai/v1/v2/vectordb/collections/list' \
--header 'x-portkey-custom-host: https://in03-34d7b37f7de12c7.serverless.gcp-us-west1.cloud.zilliz.com' \
--header 'x-portkey-provider: MILVUS_PROVIDER' \
--header 'x-portkey-api-key: PORTKEY_API_KEY'

Exa Online Search Qdrant

On this page

Portkey SDK Integration with Milvus
1. Install the Portkey SDK
2. Create a New Integration
3. Use the Portkey SDK to interact with Milvus

Ecosystem

LLM Integrations

Cloud Platforms

Guardrails

Plugins

Vector Databases

Agents

AI Apps

Libraries

Tracing Providers

Portkey SDK Integration with Milvus

1. Install the Portkey SDK

2. Create a New Integration

3. Use the Portkey SDK to interact with Milvus

Ecosystem

LLM Integrations

Cloud Platforms

Guardrails

Plugins

Vector Databases

Agents

AI Apps

Libraries

Tracing Providers

​Portkey SDK Integration with Milvus

​1. Install the Portkey SDK

​2. Create a New Integration

​3. Use the Portkey SDK to interact with Milvus

Portkey SDK Integration with Milvus

1. Install the Portkey SDK

2. Create a New Integration

3. Use the Portkey SDK to interact with Milvus