Add application file

.gitignore

@@ -0,0 +1,2 @@
+.env
+.venv/

README.md

@@ -1,8 +1,8 @@
 ---
 title: Phospho Multimodal
-emoji: 👁
-colorFrom: indigo
-colorTo: pink
+emoji: 🧪
+colorFrom: gray
+colorTo: green
 sdk: gradio
 sdk_version: 4.29.0
 app_file: app.py

app.py

@@ -0,0 +1,94 @@
+import gradio as gr
+import base64
+import time
+import os
+from dotenv import load_dotenv
+import requests
+
+
+load_dotenv()
+
+phospho_api_key = os.environ.get("PHOSPHO_API_KEY")
+
+assert phospho_api_key, "Please set the PHOSPHO_API_KEY environment variable"
+
+
+# Image to Base 64 Converter
+def image_to_base64(image_path):
+    with open(image_path, "rb") as img:
+        encoded_string = base64.b64encode(img.read())
+    return encoded_string.decode("utf-8")
+
+
+# Function that takes User Inputs and displays it on ChatUI
+def query_message(history, txt, img):
+    if not img:
+        history += [(txt, None)]
+        return history
+    base64 = image_to_base64(img)
+    data_url = f"data:image/jpeg;base64,{base64}"
+    history += [(f"{txt} ![]({data_url})", None)]
+    return history
+
+
+# Function that takes User Inputs, generates Response and displays on Chat UI
+def llm_response(history, text, img):
+    if not img:
+        answer = f"Please provide an image, otherwise I cannot answer."
+        history += [(None, answer)]
+        return history
+
+    else:
+        url = "https://api.phospho.ai/v2/predict"
+        headers = {
+            "accept": "application/json",
+            "Authorization": f"Bearer {phospho_api_key}",
+            "Content-Type": "application/json",
+        }
+        data = {
+            "inputs": [
+                {
+                    "text": text,
+                    "image_url": image_to_base64(img),
+                    "temperature": 0.2,
+                    "top_p": 0.9,
+                    "max_new_tokens": 100,
+                }
+            ],
+            "model": "phospho-multimodal",
+        }
+
+        response = requests.post(url, json=data, headers=headers)
+
+        # Check if the response is successful
+        if response.status_code != 200:
+            history += [
+                (None, "Sorry, I couldn't process the image. Please try again.")
+            ]
+            return history
+
+        else:
+            response = response.json()
+            print(response)
+            answer = response["predictions"][0]["description"]
+            history += [(None, answer)]
+            return history
+
+
+# Interface Code
+with gr.Blocks() as app:
+    with gr.Row():
+        image_box = gr.Image(type="filepath")
+
+        chatbot = gr.Chatbot(scale=2, height=750)
+    text_box = gr.Textbox(
+        placeholder="What is your question about the image?",
+        container=False,
+    )
+
+    btn = gr.Button("Submit")
+    clicked = btn.click(query_message, [chatbot, text_box, image_box], chatbot).then(
+        llm_response, [chatbot, text_box, image_box], chatbot
+    )
+app.queue()
+app.launch(debug=True)

requirements.txt

@@ -0,0 +1,74 @@
+aiofiles==23.2.1
+altair==5.3.0
+annotated-types==0.6.0
+anyio==4.3.0
+attrs==23.2.0
+certifi==2024.2.2
+charset-normalizer==3.3.2
+click==8.1.7
+contourpy==1.2.1
+cycler==0.12.1
+dnspython==2.6.1
+email_validator==2.1.1
+fastapi==0.111.0
+fastapi-cli==0.0.3
+ffmpy==0.3.2
+filelock==3.14.0
+fonttools==4.51.0
+fsspec==2024.3.1
+gradio==4.29.0
+gradio_client==0.16.1
+h11==0.14.0
+httpcore==1.0.5
+httptools==0.6.1
+httpx==0.27.0
+huggingface-hub==0.23.0
+idna==3.7
+importlib_resources==6.4.0
+Jinja2==3.1.4
+jsonschema==4.22.0
+jsonschema-specifications==2023.12.1
+kiwisolver==1.4.5
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+matplotlib==3.8.4
+mdurl==0.1.2
+mypy==1.10.0
+mypy-extensions==1.0.0
+numpy==1.26.4
+orjson==3.10.3
+packaging==24.0
+pandas==2.2.2
+pillow==10.3.0
+pydantic==2.7.1
+pydantic_core==2.18.2
+pydub==0.25.1
+Pygments==2.18.0
+pyparsing==3.1.2
+python-dateutil==2.9.0.post0
+python-dotenv==1.0.1
+python-multipart==0.0.9
+pytz==2024.1
+PyYAML==6.0.1
+referencing==0.35.1
+requests==2.31.0
+rich==13.7.1
+rpds-py==0.18.1
+ruff==0.4.3
+semantic-version==2.10.0
+shellingham==1.5.4
+six==1.16.0
+sniffio==1.3.1
+starlette==0.37.2
+tomlkit==0.12.0
+toolz==0.12.1
+tqdm==4.66.4
+typer==0.12.3
+typing_extensions==4.11.0
+tzdata==2024.1
+ujson==5.9.0
+urllib3==2.2.1
+uvicorn==0.29.0
+uvloop==0.19.0
+watchfiles==0.21.0
+websockets==11.0.3