# instructor-xl

Source: https://zilliz.com/ai-models/instructor-xl
Published: 2024-08-12T22:48:47.205Z

## Model attributes

| Attribute | Value |
| --- | --- |
| Provider | HKU NLP |
| Task | Embedding |
| Modality | Text |
| Similarity metric | Cosine |
| License | Apache 2.0 |
| Dimensions | 768 |
| Max input tokens | 512 |
| Price | Free |

## Introduction to the Instructor Model Family

The **Instructor model by NKU NLP** is a text embedding model fine-tuned with instructions. It creates task-specific embeddings (for classification, retrieval, clustering, text evaluation, etc.) across various domains (like science and finance) by just providing task instructions—no extra fine-tuning is needed. It has set state-of-the-art results on 70 embedding tasks!

![Figure How the Instructor Model works](https://assets.zilliz.com/Figure_How_the_Instructor_Model_works_2b174dc8aa.png)

Figure: How the Instructor Model works (image by NKU NLP) 

The Instructor model comes in three variations: **[instructor-base](instructor-base), [instructor-xl](https://zilliz.com/ai-models/instructor-xl), and [instructor-large](https://zilliz.com/ai-models/instructor-large).** Each version offers different levels of performance and scalability to suit various embedding needs.


## Introduction to instructor-xl

**instructor-xl** is the largest variation of the Instructor model family, which is optimized for performance and balancing accuracy and efficiency in large-scale natural language processing (NLP) applications. 

It can generate task-specific and domain-tailored text embeddings by providing natural language instruction without further fine-tuning. It is ideal for any tasks (e.g., classification, retrieval, clustering, text evaluation, etc.) and domains (e.g., science, finance, etc.). 

### Comparing instructor-base, instructor-xl, and instructor-large: 

| Feature             | [instructor-base](https://zilliz.com/ai-models/instructor-base) | [instructor-large](https://zilliz.com/ai-models/instructor-large) | [instructor-xl](https://zilliz.com/ai-models/instructor-xl) |
| ------------------- | --------------- | ---------------- | ------------- |
| Parameter Size      | 86 million      | 335 million      | 1.5 billion   |
| Embedding Dimension | 768             | 768              | 768          |
| Avg. MTEB Score     | 55.9            | 58.4             | 58.8          |


## How to create vector embeddings with the instructor-xl model

We recommend using the `InstructorEmbedding` Library to create vector embeddings.  

Once the vector embeddings are generated, they can be stored in [Zilliz Cloud](https://zilliz.com/cloud) (a fully managed vector database service powered by Milvus) and used for [semantic similarity search](https://zilliz.com/glossary/semantic-search). Here are four key steps:

1. [**Sign up**](https://cloud.zilliz.com/signup) for a Zilliz Cloud account for free.
2. **[Set up a serverless cluster](https://docs.zilliz.com/docs/create-cluster#set-up-a-free-cluster)** and obtain the [Public Endpoint and API Key](https://docs.zilliz.com/docs/on-zilliz-cloud-console#free-cluster-details).
3. **Create a vector collection** and insert your vector embeddings.
4. **Run a semantic search** on the stored embeddings.

### Generate vector embeddings via InstructorEmbedding Library and insert them into Zilliz Cloud for semantic search


```
from InstructorEmbedding import INSTRUCTOR
from pymilvus import MilvusClient

model = INSTRUCTOR('hkunlp/instructor-XL')

docs = [["Represent the Wikipedia document for retrieval: ", "Artificial intelligence was founded as an academic discipline in 1956."],
        ["Represent the Wikipedia document for retrieval: ", "Alan Turing was the first person to conduct substantial research in AI."],
        ["Represent the Wikipedia document for retrieval: ", "Born in Maida Vale, London, Turing was raised in southern England."]]
# Generate embeddings for documents
docs_embeddings = model.encode(docs, normalize_embeddings=True)

queries = [["Represent the Wikipedia question for retrieving supporting documents: ", "When was artificial intelligence founded"],
           ["Represent the Wikipedia question for retrieving supporting documents: ", "Where was Alan Turing born?"]]
# Generate embeddings for queries
query_embeddings = model.encode(queries, normalize_embeddings=True)

# Connect to Zilliz Cloud with Public Endpoint and API Key
client = MilvusClient(
    uri=ZILLIZ_PUBLIC_ENDPOINT,
    token=ZILLIZ_API_KEY)

COLLECTION = "documents"
if client.has_collection(collection_name=COLLECTION):
    client.drop_collection(collection_name=COLLECTION)
client.create_collection(
    collection_name=COLLECTION,
    dimension=768,
    auto_id=True)

for doc, embedding in zip(docs, docs_embeddings):
    client.insert(COLLECTION, {"text": doc, "vector": embedding})
    
results = client.search(
    collection_name=COLLECTION,
    data=query_embeddings,
    consistency_level="Strong", 
    output_fields=["text"])
```