fixes

app.py

@@ -3,7 +3,7 @@ import lancedb.embeddings.imagebind
 from lancedb.embeddings import get_registry
 from lancedb.pydantic import LanceModel, Vector
 import gradio as gr
-from downloader import dowload_and_save_audio, dowload_and_save_image, base_path
+from .downloader import dowload_and_save_audio, dowload_and_save_image, base_path
 
 model = get_registry().get("imagebind").create()
 

downloader.py

@@ -1,90 +1,66 @@
-import lancedb
-import lancedb.embeddings.imagebind
-from lancedb.embeddings import get_registry
-from lancedb.pydantic import LanceModel, Vector
-import gradio as gr
-from downloader import dowload_and_save_audio, dowload_and_save_image, base_path
-
-model = get_registry().get("imagebind").create()
-
-
-class TextModel(LanceModel):
-    text: str
-    image_uri: str = model.SourceField()
-    audio_path: str
-    vector: Vector(model.ndims()) = model.VectorField()
-
-
-text_list = ["A bird", "A dragon", "A car"]
-image_paths = dowload_and_save_image()
-audio_paths = dowload_and_save_audio()
-
-# Load data
-inputs = [
-    {"text": a, "audio_path": b, "image_uri": c}
-    for a, b, c in zip(text_list, audio_paths, image_paths)
+import requests
+import os
+from pathlib import Path
+
+# URL of the raw audio file on GitHub
+audio_file_urls = [
+    "https://github.com/raghavdixit99/assets/raw/main/bird_audio.wav",
+    "https://github.com/raghavdixit99/assets/raw/main/dragon-growl-37570.wav",
+    "https://github.com/raghavdixit99/assets/raw/main/car_audio.wav",
+]
+image_urls = [
+    "https://github.com/raghavdixit99/assets/assets/34462078/abf47cc4-d979-4aaa-83be-53a2115bf318",
+    "https://github.com/raghavdixit99/assets/assets/34462078/93be928e-522b-4e37-889d-d4efd54b2112",
+    "https://github.com/raghavdixit99/assets/assets/34462078/025deaff-632a-4829-a86c-3de6e326402f",
 ]
 
-db = lancedb.connect("/tmp/lancedb")
-table = db.create_table("img_bind", schema=TextModel)
-table.add(inputs)
-
-
-def process_image(inp_img) -> str:
-    actual = (
-        table.search(inp_img, vector_column_name="vector")
-        .limit(1)
-        .to_pydantic(TextModel)[0]
-    )
-
-    return actual.text, actual.audio_path
-
-
-def process_text(inp_text) -> str:
-    actual = (
-        table.search(inp_text, vector_column_name="vector")
-        .limit(1)
-        .to_pydantic(TextModel)[0]
-    )
-
-    return actual.image_uri, actual.audio_path
-
-
-def process_audio(inp_audio) -> str:
-    actual = (
-        table.search(inp_audio, vector_column_name="vector")
-        .limit(1)
-        .to_pydantic(TextModel)[0]
-    )
-
-    return actual.image_uri, actual.text
-
-
-im_to_at = gr.Interface(
-    process_image,
-    gr.Image(type="filepath", value=image_paths[0]),
-    [gr.Text(label="Output Text"), gr.Audio(label="Output Audio")],
-    examples=image_paths,
-    allow_flagging="never",
-)
-txt_to_ia = gr.Interface(
-    process_text,
-    gr.Textbox(label="Enter a prompt:"),
-    [gr.Image(label="Output Image"), gr.Audio(label="Output Audio")],
-    allow_flagging="never",
-    examples=text_list,
-)
-a_to_it = gr.Interface(
-    process_audio,
-    gr.Audio(type="filepath", value=audio_paths[0]),
-    [gr.Image(label="Output Image"), gr.Text(label="Output Text")],
-    examples=audio_paths,
-    allow_flagging="never",
-)
-demo = gr.TabbedInterface(
-    [im_to_at, txt_to_ia, a_to_it],
-    ["Image to Text/Audio", "Text to Image/Audio", "Audio to Image/Text"],
-)
-
-if __name__ == "__main__":
-    demo.launch(share=True, allowed_paths=[f"{base_path}/test_inputs/"])
+base_path = os.path.dirname(os.path.abspath(__file__))
+
+
+# Local path where you want to save the .wav file
+def dowload_and_save_audio():
+    audio_pths = []
+    for url in audio_file_urls:
+        filename = url.split("/")[-1]
+        local_file_path = Path(f"{base_path}/test_inputs/{filename}")
+        local_file_path.parent.mkdir(parents=True, exist_ok=True)
+        # Perform the GET request
+        response = requests.get(url)
+
+        # Check if the request was successful
+        if response.status_code == 200:
+            # Write the content of the response to a local file
+            with open(local_file_path, "wb") as audio_file:
+                audio_file.write(response.content)
+                audio_pths.append(str(local_file_path))
+            print(
+                f"Audio file downloaded successfully and saved as '{local_file_path}'."
+            )
+        else:
+            print(f"Failed to download file. Status code: {response.status_code}")
+    return audio_pths
+
+
+def dowload_and_save_image():
+    image_paths = []
+    for url in image_urls:
+        filename = url.split("/")[-1]
+        local_file_path = Path(f"{base_path}/test_inputs/{filename}.jpeg")
+
+        local_file_path.parent.mkdir(parents=True, exist_ok=True)
+        # Perform the GET request
+        response = requests.get(url)
+
+        # Check if the request was successful
+        if response.status_code == 200:
+            # Write the content of the response to a local file
+            with open(local_file_path, "wb") as image_file:
+                image_file.write(response.content)
+                image_paths.append(str(local_file_path))
+            print(
+                f"Image file downloaded successfully and saved as '{local_file_path}'."
+            )
+        else:
+            print(f"Failed to download file. Status code: {response.status_code}")
+
+    return image_paths