# Build an Application to Generate Text Embeddings with Gemini on Vertex AI (Solution)

## Challenge scenario

**Scenario:** You are a data scientist working on a natural language processing (NLP) project that involves embedding text data using a pre-trained language model. Your goal is to generate vector embeddings for given text phrases to use them in a downstream machine learning task, such as text classification or semantic search.

You need to write a Python script that loads a pre-trained text embedding model, computes embeddings for a given sentence, and prints out the length of the resulting embedding vector for analysis.:

**Task:** Develop a Python function named `text_embedding(prompt)`. This function should invoke the `text-embedding-005` model using the supplied `prompt`, generate the response.

**Follow these steps to interact with the Generative AI APIs using Vertex AI Python SDK.**

1. Click **File > New File** to open a new file within the Code Editor.
    
2. Write the Python code to use Google's Vertex AI SDK to interact with the pre-trained Text Generation AI model.
    
3. Create and save the python file.
    
4. Execute the Python file by invoking the below command by replacing the **FILE\_NAME** inside the terminal within the Code Editor pane to view the output.
    

```apache
/usr/bin/python3 /FILE_NAME.py
```

Click **Check my progress** to verify the objective.

Send text embedding requests to Gen AI and receive a response

---

## Solution of Lab

%[https://youtu.be/07JPsu8kBLI] 

```python
import vertexai
from vertexai.language_models import TextEmbeddingModel

def text_embedding(prompt):
    vertexai.init(project="YOUR_PROJECT_ID", location="us-central1")
    model = TextEmbeddingModel.from_pretrained("text-embedding-005")
    embeddings = model.get_embeddings([prompt])
    vector = embeddings[0].values
    print(f"Length of embedding vector: {len(vector)}")
    return vector

if __name__ == "__main__":
    sample_text = "Natural language processing enables computers to understand human language."
    print(f"Processing text: '{sample_text}'")
    text_embedding(sample_text)
```

![](https://cdn.hashnode.com/res/hashnode/image/upload/v1769484588637/edfa4834-759c-4dd9-a2b1-95e0359c18e1.png align="center")

![](https://cdn.hashnode.com/res/hashnode/image/upload/v1769484592059/33a9f986-73e9-4f1c-8632-8fdbdf501243.png align="center")

```apache
/usr/bin/python3 /main.py
```