> ## Documentation Index
> Fetch the complete documentation index at: https://portkey-docs-feature-comparison-update.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.
# Jina AI
> Use Jina AI's embedding and reranker models through Portkey.
## Quick Start
Get started with Jina AI in under 2 minutes:
```python Python icon="python" theme={null}
from portkey_ai import Portkey
# 1. Install: pip install portkey-ai
# 2. Add @jina provider in model catalog
# 3. Use it:
portkey = Portkey(api_key="PORTKEY_API_KEY")
response = portkey.chat.completions.create(
model="@jina/jina-embeddings-v2-base-en",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
```
```js Javascript icon="square-js" theme={null}
import Portkey from 'portkey-ai'
// 1. Install: npm install portkey-ai
// 2. Add @jina provider in model catalog
// 3. Use it:
const portkey = new Portkey({
apiKey: "PORTKEY_API_KEY"
})
const response = await portkey.chat.completions.create({
model: "@jina/jina-embeddings-v2-base-en",
messages: [{ role: "user", content: "Hello!" }]
})
console.log(response.choices[0].message.content)
```
```python OpenAI Py icon="python" theme={null}
from openai import OpenAI
from portkey_ai import PORTKEY_GATEWAY_URL
# 1. Install: pip install openai portkey-ai
# 2. Add @jina provider in model catalog
# 3. Use it:
client = OpenAI(
api_key="PORTKEY_API_KEY", # Portkey API key
base_url=PORTKEY_GATEWAY_URL
)
response = client.chat.completions.create(
model="@jina/jina-embeddings-v2-base-en",
messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)
```
```js OpenAI JS icon="square-js" theme={null}
import OpenAI from "openai"
import { PORTKEY_GATEWAY_URL } from "portkey-ai"
// 1. Install: npm install openai portkey-ai
// 2. Add @jina provider in model catalog
// 3. Use it:
const client = new OpenAI({
apiKey: "PORTKEY_API_KEY", // Portkey API key
baseURL: PORTKEY_GATEWAY_URL
})
const response = await client.chat.completions.create({
model: "@jina/jina-embeddings-v2-base-en",
messages: [{ role: "user", content: "Hello!" }]
})
console.log(response.choices[0].message.content)
```
```bash cURL theme={null}
curl https://api.portkey.ai/v1/embeddings \
-H "Content-Type: application/json" \
-H "x-portkey-api-key: $PORTKEY_API_KEY" \
-H "x-portkey-provider: @jina" \
-d '{
"model": "jina-embeddings-v2-base-en",
"input": "embed this text"
}'
```
## Add Provider in Model Catalog
Before making requests, add Jina AI to your Model Catalog:
1. Go to [**Model Catalog → Add Provider**](https://app.portkey.ai/model-catalog/providers)
2. Select **Jina AI**
3. Enter your [Jina AI API key](https://jina.ai/)
4. Name your provider (e.g., `jina`)
See all setup options and detailed configuration instructions
***
## Jina AI Capabilities
### Embeddings
Generate embeddings with language-specific models:
```python Python theme={null}
from portkey_ai import Portkey
portkey = Portkey(api_key="PORTKEY_API_KEY", provider="@jina")
embeddings = portkey.embeddings.create(
model="jina-embeddings-v2-base-en",
input="embed this text"
)
print(embeddings.data[0].embedding)
```
```javascript Node.js theme={null}
import Portkey from 'portkey-ai';
const portkey = new Portkey({
apiKey: 'PORTKEY_API_KEY',
provider: '@jina'
});
const embeddings = await portkey.embeddings.create({
model: "jina-embeddings-v2-base-en",
input: "embed this text"
});
console.log(embeddings.data[0].embedding);
```
### Reranking
Rerank documents for better search results:
```bash cURL theme={null}
curl https://api.portkey.ai/v1/rerank \
-H "Content-Type: application/json" \
-H "x-portkey-api-key: $PORTKEY_API_KEY" \
-H "x-portkey-provider: @jina" \
-d '{
"model": "jina-reranker-v1-base-en",
"query": "Organic skincare products for sensitive skin",
"documents": [
"Eco-friendly kitchenware for modern homes",
"Biodegradable cleaning supplies for eco-conscious consumers",
"Organic cotton baby clothes for sensitive skin"
],
"top_n": 2
}'
```
```python Python theme={null}
from portkey_ai import Portkey
portkey = Portkey(api_key="PORTKEY_API_KEY", provider="@jina")
response = portkey.post(
"/rerank",
model="jina-reranker-v1-base-en",
query="Organic skincare products for sensitive skin",
documents=[
"Eco-friendly kitchenware for modern homes",
"Biodegradable cleaning supplies for eco-conscious consumers",
"Organic cotton baby clothes for sensitive skin"
],
top_n=2
)
print(response)
```
```javascript Node.js theme={null}
import Portkey from 'portkey-ai';
const portkey = new Portkey({
apiKey: 'PORTKEY_API_KEY',
provider: '@jina'
});
const response = await portkey.post(
"/rerank",
{
model: "jina-reranker-v1-base-en",
query: "Organic skincare products for sensitive skin",
documents: [
"Eco-friendly kitchenware for modern homes",
"Biodegradable cleaning supplies for eco-conscious consumers",
"Organic cotton baby clothes for sensitive skin"
],
top_n: 2
}
);
console.log(response);
```
***
## Supported Models
Jina AI provides embedding models in multiple languages:
| Model Family | Languages | Description |
| ----------------------- | ------------------------ | ----------------------- |
| jina-embeddings-v2-base | en, de, es, zh, and more | Multilingual embeddings |
| jina-reranker-v1-base | en, de, es, zh | Reranking models |
Check [Jina AI's model page](https://jina.ai/embeddings) for the complete list.
***
## Next Steps
Add fallbacks, load balancing, and more
Monitor and trace your Jina AI requests
Cache embeddings for faster responses
Add custom metadata to requests
For complete SDK documentation:
Complete Portkey SDK documentation