Dockerfile setup and text embeddings integrated.

Dockerfile

@@ -0,0 +1,14 @@
+FROM python:3.11-slim
+
+ARG GRADIO_SERVER_PORT=7860
+ENV GRADIO_SERVER_PORT=${GRADIO_SERVER_PORT}
+
+WORKDIR /app
+
+COPY requirements.txt /app/
+
+RUN pip install -r /app/requirements.txt
+
+COPY app.py /app/
+
+CMD ["python", "/app/app.py"]

README.md

@@ -3,11 +3,17 @@ title: Clip Embedding
 emoji: 💻
 colorFrom: pink
 colorTo: gray
-sdk: gradio
-sdk_version: 3.41.2
+sdk: docker
 app_file: app.py
 pinned: false
+app_port: 7860
 license: mit
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+
+
+```
+docker build . -t clip_embeddings
+docker run -v ./cache_dir:/app/cache -p 7860:7860 clip_embeddings
+```

app.py

@@ -3,13 +3,20 @@ import numpy as np
 from PIL import Image
 from sentence_transformers import SentenceTransformer
 
-model = SentenceTransformer('clip-ViT-B-32')
+model = SentenceTransformer('clip-ViT-B-32', cache_folder='/app/cache')
 
 
-def image_to_embedding(img: np.ndarray):
-    embedding = model.encode(sentences=[Image.fromarray(img)], batch_size=128)
+def image_to_embedding(img: np.ndarray = None, txt: str = None) -> np.ndarray:
+    if img is None and not txt:
+        return []
+    
+    if img is not None:
+        embedding = model.encode(sentences=[Image.fromarray(img)], batch_size=128)
+    else:
+        embedding = model.encode(sentences=[txt], batch_size=128)
+
     return embedding
 
 
-iface = gr.Interface(fn=image_to_embedding, inputs="image", outputs="textbox", cache_examples=True)
-iface.launch(auth=("Cdpv9i6Q", "R206pqYF"))
+demo = gr.Interface(fn=image_to_embedding, inputs=["image", "textbox"], outputs="textbox", cache_examples=True)
+demo.launch(server_name="0.0.0.0")