jina colbert v2
An open multi-vector model that matches a query to documents token by token. jinaai/jina-colbert-v2
- Accuracy
0.452
8 retrieval sets, mean nDCG@10
- Time per request
Not timed one request at a time
- Serverless price
Call it
from sie_sdk import SIEClientclient = SIEClient("http://localhost:8080")query = "queryrefund duplicate subscription"passages = [ "passage 1We reimburse accidental double payments on any recurring membership.",]q = client.encode( "modeljinaai/jina-colbert-v2", [{"text": query}], output_types=["multivector"], is_query=True,)[0]["multivector"]docs = client.encode( "modeljinaai/jina-colbert-v2", [{"text": passage} for passage in passages], output_types=["multivector"], is_query=False,)print(q)print(docs)import { SIEClient } from '@superlinked/sie-sdk';
const client = new SIEClient('http://localhost:8080');
const query = "refund duplicate subscription";
const passages = [
"We reimburse accidental double payments on any recurring membership.",
];
const model = 'jinaai/jina-colbert-v2';
const [q] = await client.encode(model, [{ text: query }], {
outputTypes: ['multivector'], isQuery: true,
});
const docs = await client.encode(model, passages.map((text) => ({ text })), {
outputTypes: ['multivector'], isQuery: false,
});
console.log({ query: q, documents: docs });# Encode the question as a query, then the passages as documents; rank by MaxSim.
curl http://localhost:8080/v1/encode/jinaai%2Fjina-colbert-v2 \
-H "Content-Type: application/json" \
-d "{\"items\":[{\"text\":\"refund duplicate subscription\"}],\"params\":{\"output_types\":[\"multivector\"],\"options\":{\"is_query\":true}}}"
curl http://localhost:8080/v1/encode/jinaai%2Fjina-colbert-v2 \
-H "Content-Type: application/json" \
-d "{\"items\":[{\"text\":\"We reimburse accidental double payments on any recurring membership.\"}],\"params\":{\"output_types\":[\"multivector\"],\"options\":{\"is_query\":false}}}"Build the "Multi-vector" capability into my app using the Superlinked Inference Engine (SIE).
Context
- SIE is an OpenAI-style inference API. Python SDK: `from sie_sdk import SIEClient`; TypeScript: `@superlinked/sie-sdk`.
- Base URL: http://localhost:8080, my own SIE server, which takes no API key.
- Model: jinaai/jina-colbert-v2 (SIE primitive: /encode). Keep the model id configurable.
Task
- Input: a query string plus a list of candidate documents.
- Behaviour: return the query and passage token vectors from the native encode calls
- Send two POST requests to http://localhost:8080/v1/encode/jinaai%2Fjina-colbert-v2. Encode one query item {text: query} with params {output_types: ["multivector"], options: {is_query: true}}, then all candidate passages in one batch of {text: passage} items with params {output_types: ["multivector"], options: {is_query: false}}. Do not call the API per candidate. Read the returned per-token vectors from items[i].multivector.values. Return the native token vectors without adding application scoring or ranking. In Python, use SIEClient.encode(..., output_types=["multivector"], is_query=True) for the query and encode(..., output_types=["multivector"], is_query=False) for the passage batch; read each decoded ["multivector"] array. In TypeScript, use client.encode with outputTypes: ["multivector"] and isQuery: true for the query, then isQuery: false for the passage batch; the SDK decodes the native token vectors.
Deliverables
- A typed client wrapper, an application-level function for this task, error handling for timeouts/empty input, and unit tests with a stubbed client.
- Wire it into my existing stack (ask me which framework if unclear) and add a short usage example.Next to the other multi-vector models
| Model | 8 retrieval sets, mean nDCG@10 | Time per request | Serverless price | Size |
|---|---|---|---|---|
| jina colbert v2 jinaai | 0.452 | Not timed | Run in your cloud | 559M |
| GTE ModernColBERT lightonai | Not measured | Not timed | $0.0332 per 1M tokens | 149M |
| mLateOn lightonai | 0.561 | Not timed | Run in your cloud | 307M |
| Reason ModernColBERT lightonai | 0.519 | Not timed | Run in your cloud | 149M |
| answerai colbert small v1 answerdotai | 0.466 | Not timed | Run in your cloud | 33M |
Measured on public datasets
| Dataset | nDCG@10 |
|---|---|
| Sci | 0.695 |
| Legal | 0.681 |
| Stack | 0.608 |
| Nano | 0.501 |
| Fi | 0.416 |
| CQADupstack | 0.405 |
| NFCorpus | 0.357 |
| Cos | 0.261 |
| SCIDOCS | 0.192 |
Facts
- Size
- 559M parameters
- License
- CC-BY-NC-4.0
- Reads
- Text, up to 8,192 tokens
- Endpoint
-
encode
- Accuracy
- Run on SIE against the public dataset named in each figure
- 8 retrieval sets
- The mean over NFCorpus, FiQA2018, SciFact, SCIDOCS, CQADupstackPhysicsRetrieval, CosQA, StackOverflowQA and LegalBenchConsumerContractsQA
- Prices
- Serverless list prices, effective 10 Nov 2026
Run jina colbert v2 in your own cloud, or start on Serverless
SIE Serverless
Task-specific models for your agents, with no GPUs to operate.
- No idle GPUs, pay for what you use
- Fits your stack: SDK, API, CLI, MCP
- Self-host the same open-source engine
- SOC 2 Type 2, US or EU data residency
no credit card required
apply for $500 more
Native Inference
Kubernetes in your own cloud, backed by our engineers.
- Terraform modules for your cloud
- Apache-2.0, same engine as Serverless
- GPU workers scale to zero between jobs
- Separate worker pools for each tenant
Deploy SIE to our AWS account with the superlinked/sie/aws Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Google Cloud project with the superlinked/sie/google Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Azure subscription with the superlinked/sie/azure Terraform module. Docs: superlinked.com/docs/deployment.Deploy SIE to our Alibaba Cloud account with the superlinked/sie/alicloud Terraform module. Docs: superlinked.com/docs/deployment. SIE Local
The open-source server on your own machine.
- Runs on your NVIDIA GPU
- One container, no cluster
- Process your data fully offline
- Same SDK and model IDs as Serverless
docker run --gpus all -p 8080:8080 ghcr.io/superlinked/sie-server:latest-cuda12-default