Build image search and query with natural language with vision model CLIP

In this project, we will build image search and query it with natural language. You can search for “a cute animal” or “a red car”, and the system returns visually relevant results — no manual tagging needed.

We are going to use multi-modal embedding model CLIP to understand and directly embed the image; and build a vector index for efficient retrieval. We are going use CocoIndex to build the indexing flow. It supports long running flow and only process changed files - we can keep adding new files to the folder and it will be indexed within a minute.

We are constantly improving, and more features and examples are coming soon. If this tutorial is helpful, we would appreciate a star ⭐ at GitHub to help us grow.

🚀 The entire project end to end is open sourced here.

Technologies

CLIP ViT-L/14

CLIP ViT-L/14 is a powerful vision-language model that can understand both images and texts. It's trained to align visual and textual representations in a shared embedding space, making it perfect for our image search use case.

In our project, we use CLIP to:

1. Generate embeddings of the images directly
2. Convert natural language search queries into the same embedding space
3. Enable semantic search by comparing query embeddings with caption embeddings

Alternative: CLIP ViT-B/32 is a smaller model that is faster to run. While it may have slightly lower accuracy compared to ViT-L/14, it offers better performance and lower resource requirements, making it suitable for applications where speed and efficiency are priorities.

CocoIndex

CocoIndex is an ultra performant open-source data transformation framework, with support for multi-modality data pipelines and incremental processing. With CocoIndex, you can easily build a production grade data pipeline for AI with ~100 lines of code, that handles data freshness out of the box.

Qdrant

Qdrant is a high performance vector database. We use it to store and query the embeddings.

FastAPI

FastAPI is a modern, fast (high-performance), web framework for building APIs with Python 3.7+ based on standard Python type hints. We use it to build the web API for the image search.

Prerequisites

• Install Postgres. CocoIndex uses Postgres to keep track of data lineage for incremental processing.
• Install Qdrant.

Define Indexing Flow

Flow Design

The flow diagram illustrates how we'll process our codebase:

1. Read image files from the local filesystem
2. Use CLIP to understand and embed the image
3. Store the embeddings in a vector database for retrieval

1. Ingest the images.

@cocoindex.flow_def(name="ImageObjectEmbedding")
def image_object_embedding_flow(flow_builder: cocoindex.FlowBuilder, data_scope: cocoindex.DataScope):
    data_scope["images"] = flow_builder.add_source(
        cocoindex.sources.LocalFile(path="img", included_patterns=["*.jpg", "*.jpeg", "*.png"], binary=True),
        refresh_interval=datetime.timedelta(minutes=1)  # Poll for changes every 1 minute
    )
    img_embeddings = data_scope.add_collector()

flow_builder.add_source will create a table with sub fields (filename, content), we can refer to the documentation for more details.

2. Process each image and collect the information.

2.1 Embed the image with CLIP

@functools.cache
def get_clip_model() -> tuple[CLIPModel, CLIPProcessor]:
    model = CLIPModel.from_pretrained(CLIP_MODEL_NAME)
    processor = CLIPProcessor.from_pretrained(CLIP_MODEL_NAME)
    return model, processor

The @functools.cache decorator caches the results of a function call. In this case, it ensures that we only load the CLIP model and processor once.

@cocoindex.op.function(cache=True, behavior_version=1, gpu=True)
def embed_image(img_bytes: bytes) -> cocoindex.Vector[cocoindex.Float32, Literal[384]]:
    """
    Convert image to embedding using CLIP model.
    """
    model, processor = get_clip_model()
    image = Image.open(io.BytesIO(img_bytes)).convert("RGB")
    inputs = processor(images=image, return_tensors="pt")
    with torch.no_grad():
        features = model.get_image_features(**inputs)
    return features[0].tolist()

embed_image is a custom function that uses the CLIP model to convert an image into a vector embedding. It accepts image data in bytes format and returns a list of floating-point numbers representing the image's embedding.

The function supports caching through the cache parameter. When enabled, the executor will store the function's results for reuse during reprocessing, which is particularly useful for computationally intensive operations. For more information about custom function parameters, refer to the documentation.

Then we are going to process each image and collect the information.

with data_scope["images"].row() as img:
    img["embedding"] = img["content"].transform(embed_image)
    img_embeddings.collect(
        id=cocoindex.GeneratedField.UUID,
        filename=img["filename"],
        embedding=img["embedding"],
    )

2.3 Collect the embeddings

Export the embeddings to a table in Qdrant.

img_embeddings.export(
    "img_embeddings",
    cocoindex.storages.Qdrant(
        collection_name="image_search",
        grpc_url=QDRANT_GRPC_URL,
    ),
    primary_key_fields=["id"],
    setup_by_user=True,
)

3. Query the index

Embed the query with CLIP, which maps both text and images into the same embedding space, allowing for cross-modal similarity search.

def embed_query(text: str) -> list[float]:
    model, processor = get_clip_model()
    inputs = processor(text=[text], return_tensors="pt", padding=True)
    with torch.no_grad():
        features = model.get_text_features(**inputs)
    return features[0].tolist()

Defines a FastAPI endpoint /search that performs semantic image search.

@app.get("/search")
def search(q: str = Query(..., description="Search query"), limit: int = Query(5, description="Number of results")):
    # Get the embedding for the query
    query_embedding = embed_query(q)
    
    # Search in Qdrant
    search_results = app.state.qdrant_client.search(
        collection_name="image_search",
        query_vector=("embedding", query_embedding),
        limit=limit
    )
    

This searches the Qdrant vector database for similar embeddings. Returns the top limit results

# Format results
out = []
for result in search_results:
    out.append({
        "filename": result.payload["filename"],
        "score": result.score
    })
return {"results": out}

This endpoint enables semantic image search where users can find images by describing them in natural language, rather than using exact keyword matches.

Application

Fast API

app = FastAPI()
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_credentials=True,
    allow_methods=["*"],
    allow_headers=["*"],
)
# Serve images from the 'img' directory at /img
app.mount("/img", StaticFiles(directory="img"), name="img")

FastAPI application setup with CORS middleware and static file serving The app is configured to:

• Allow cross-origin requests from any origin
• Serve static image files from the 'img' directory
• Handle API endpoints for image search functionality

@app.on_event("startup")
def startup_event():
    load_dotenv()
    cocoindex.init()
    # Initialize Qdrant client
    app.state.qdrant_client = QdrantClient(
        url=QDRANT_GRPC_URL,
        prefer_grpc=True
    )
    app.state.live_updater = cocoindex.FlowLiveUpdater(image_object_embedding_flow)
    app.state.live_updater.start()

The startup event handler initializes the application when it first starts up. Here's what each part does:

1. load_dotenv(): Loads environment variables from a .env file, which is useful for configuration like API keys and URLs

2. cocoindex.init(): Initializes the CocoIndex framework, setting up necessary components and configurations

3. Qdrant Client Setup:

   • Creates a new QdrantClient instance
   • Configures it to use the gRPC URL specified in environment variables
   • Enables gRPC preference for better performance
   • Stores the client in the FastAPI app state for access across requests

4. Live Updater Setup:

   • Creates a FlowLiveUpdater instance for the image_object_embedding_flow
   • This enables real-time updates to the image search index
   • Starts the live updater to begin monitoring for changes

This initialization ensures that all necessary components are properly configured and running when the application starts.

Frontend

you can check the frontend code here. We intentionally kept it simple and minimalistic to focus on the image search functionality.

Time to have fun!

• Create a collection in Qdrant

  curl -X PUT 'http://localhost:6333/collections/image_search' \
  -H 'Content-Type: application/json' \
  -d '{
      "vectors": {
      "embedding": {
          "size": 768,
          "distance": "Cosine"
      }
      }
  }'

• Setup indexing flow

  cocoindex setup main.py

  It is setup with a live updater, so you can add new files to the folder and it will be indexed within a minute.

• Run backend

  uvicorn main:app --reload --host 0.0.0.0 --port 8000

• Run frontend

  cd frontend
  npm install
  npm run dev

Go to http://localhost:5174 to search.

Now add another image in the img folder, for example, this cute squirrel, or any picture you like. Wait a minute for the new image to be processed and indexed.

If you want to monitor the indexing progress, you can view it in CocoInsight cocoindex server -ci main.py .

It's fascinating to see how modern open-source data stack has simplified building real-time image search systems. What once required a dedicated team of engineers and complex infrastructure can now be built with just a few key components: a powerful vision-language model, a vector database, and an indexing framework. This democratization of advanced search capabilities enables developers to create sophisticated image search applications in a fraction of the time and with significantly less complexity than before.

Acknowledgement

This image search project is largely contributed by @par4m - Param Arora ❤️. He is currently a open source developer at Google Summer of Code.

Support us

We are constantly improving, and more features and examples are coming soon. If this end to end project is helpful, we would appreciate a star ⭐ at GitHub to help us grow.

Thanks for reading!