Ecosystem
LLM Integrations
- Overview
- OpenAI
- Anthropic
- Google Gemini
- Google Vertex AI
- Azure
- Bedrock
- AWS SageMaker
- Ollama
- More
- Bring Your Own LLM
Cloud Platforms
Guardrails
Plugins
Agents
AI Apps
Libraries
Tracing Providers
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, allowing you to use virtual keys and observability features.
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.
Copy
Ask AI
npm install --save portkey-ai
Copy
Ask AI
npm install --save portkey-ai
Copy
Ask AI
pip install portkey-ai
2. Initialize Portkey with a Virtual Key
To use Milvus with Portkey, get your Milvus API key from here, then add it to Portkey to create your Milvus virtual key.
Copy
Ask AI
import Portkey from 'portkey-ai'
const portkey = new Portkey({
apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
virtualKey: "VIRTUAL_KEY" // Your Milvus Virtual Key
})
Copy
Ask AI
import Portkey from 'portkey-ai'
const portkey = new Portkey({
apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
virtualKey: "VIRTUAL_KEY" // Your Milvus Virtual Key
})
Copy
Ask AI
from portkey_ai import Portkey
portkey = Portkey(
api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
virtual_key="VIRTUAL_KEY" # Replace with your virtual key for Milvus
)
Copy
Ask AI
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
)
)
Copy
Ask AI
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
Copy
Ask AI
from portkey_ai import Portkey
portkey = Portkey(
api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
virtual_key="MILVUS_VIRTUAL_KEY",
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)
Copy
Ask AI
from portkey_ai import Portkey
portkey = Portkey(
api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
virtual_key="MILVUS_VIRTUAL_KEY",
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)
Copy
Ask AI
import Portkey from 'portkey-ai';
// Initialize the Portkey client
const portkey = new Portkey({
apiKey: "PORTKEY_API_KEY", // Replace with your Portkey API key
virtualKey: "MILVUS_VIRTUAL_KEY", // Add your Milvus's virtual key
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)
Copy
Ask AI
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({
virtualKey: "MILVUS_VIRTUAL_KEY",
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)
Copy
Ask AI
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)
Copy
Ask AI
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-virtual-key: MILVUS_VIRTUAL_KEY' \
--header 'x-portkey-api-key: PORTKEY_API_KEY'
Was this page helpful?
Assistant
Responses are generated using AI and may contain mistakes.