Update app.py

app.py

@@ -1,120 +1,79 @@
 import os
 import json
-from flask import Flask, render_template, request, jsonify, redirect, url_for
-from werkzeug.utils import secure_filename
-from huggingface_hub import InferenceClient
 import pandas as pd
-import docx
+from docx import Document
 from PyPDF2 import PdfReader
+from huggingface_hub import InferenceClient
+import gradio as gr
 
-app = Flask(__name__)
-
-# Set up file upload configurations
-UPLOAD_FOLDER = "uploads"
-app.config["UPLOAD_FOLDER"] = UPLOAD_FOLDER
-ALLOWED_EXTENSIONS = {"txt", "csv", "json", "pdf", "docx"}
-
-# Retrieve Hugging Face API key securely from environment variables
-api_key = os.getenv("APIHUGGING")
-if not api_key:
-    raise ValueError("Hugging Face API key not found. Set 'HF_API_KEY' in your Space secrets.")
+# Retrieve Hugging Face API key from environment variable (secret)
+API_KEY = os.getenv("APIHUGGING")
+if not API_KEY:
+    raise ValueError("Hugging Face API key not found. Please set the 'APIHUGGING' secret.")
 
 # Initialize Hugging Face Inference Client
-client = InferenceClient(api_key=api_key)
-
-
-# Function to check allowed file types
-def allowed_file(filename):
-    return '.' in filename and filename.rsplit('.', 1)[1].lower() in ALLOWED_EXTENSIONS
-
-
-# Function to read uploaded files and extract content
-def extract_file_content(filepath, file_type):
-    content = ""
+client = InferenceClient(api_key=API_KEY)
+
+# Function to extract text from various file types
+def extract_file_content(file_path):
+    _, file_extension = os.path.splitext(file_path.name)
+    if file_extension.lower() in [".txt"]:
+        return file_path.read().decode("utf-8")
+    elif file_extension.lower() in [".csv"]:
+        df = pd.read_csv(file_path)
+        return df.to_string(index=False)
+    elif file_extension.lower() in [".json"]:
+        data = json.load(file_path)
+        return json.dumps(data, indent=4)
+    elif file_extension.lower() in [".pdf"]:
+        reader = PdfReader(file_path)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text()
+        return text
+    elif file_extension.lower() in [".docx"]:
+        doc = Document(file_path)
+        return "\n".join([para.text for para in doc.paragraphs])
+    else:
+        return "Unsupported file type."
+
+# Function to interact with the Hugging Face model
+def get_bot_response(file, prompt):
     try:
-        if file_type == "txt":
-            with open(filepath, "r", encoding="utf-8") as file:
-                content = file.read()
-        elif file_type == "csv":
-            df = pd.read_csv(filepath)
-            content = df.to_string()
-        elif file_type == "json":
-            with open(filepath, "r", encoding="utf-8") as file:
-                content = json.dumps(json.load(file), indent=4)
-        elif file_type == "pdf":
-            reader = PdfReader(filepath)
-            content = "".join(page.extract_text() for page in reader.pages)
-        elif file_type == "docx":
-            doc = docx.Document(filepath)
-            content = "\n".join(paragraph.text for paragraph in doc.paragraphs)
-    except Exception as e:
-        raise ValueError(f"Error extracting file content: {e}")
-    return content
+        # Extract content from the uploaded file
+        file_content = extract_file_content(file)
 
+        # Prepare conversation history
+        messages = [
+            {"role": "user", "content": f"{prompt}\n\nFile Content:\n{file_content}"}
+        ]
 
-# Function to send content to Hugging Face model
-def get_bot_response(prompt):
-    try:
-        response = client.text_generation(
-            prompt=prompt,
+        # Call Hugging Face API
+        bot_response = client.chat_completions.create(
             model="Qwen/Qwen2.5-Coder-32B-Instruct",
+            messages=messages,
             max_tokens=500
         )
-        return response
-    except Exception as e:
-        return f"Error in model response: {e}"
-
-
-# Route: Home Page (File Upload Form)
-@app.route("/", methods=["GET", "POST"])
-def upload_file():
-    if request.method == "POST":
-        # Check if file is uploaded
-        if "file" not in request.files:
-            return jsonify({"error": "No file part"}), 400
-
-        file = request.files["file"]
-
-        if file.filename == "":
-            return jsonify({"error": "No selected file"}), 400
-
-        if file and allowed_file(file.filename):
-            filename = secure_filename(file.filename)
-            filepath = os.path.join(app.config["UPLOAD_FOLDER"], filename)
-            os.makedirs(app.config["UPLOAD_FOLDER"], exist_ok=True)
-            file.save(filepath)
-
-            # Extract file content
-            file_type = filename.rsplit(".", 1)[1].lower()
-            try:
-                content = extract_file_content(filepath, file_type)
-            except Exception as e:
-                return jsonify({"error": str(e)}), 500
-
-            # Send content to Hugging Face model
-            response = get_bot_response(content)
-
-            return jsonify({"response": response})
-
-        else:
-            return jsonify({"error": "File type not allowed"}), 400
-
-    return render_template("upload.html")
 
+        # Collect and return the bot's response
+        return bot_response.choices[0].message.content
+    except Exception as e:
+        return f"Error: {str(e)}"
 
-# Route: Retrieve Model Response (API Endpoint)
-@app.route("/generate", methods=["POST"])
-def generate_response():
-    data = request.get_json()
-    prompt = data.get("prompt")
+# Gradio Interface
+with gr.Blocks() as app:
+    gr.Markdown("# 📁 AI File Chat with Hugging Face 🚀")
+    gr.Markdown("Upload any file and ask the AI a question based on the file's content!")
 
-    if not prompt:
-        return jsonify({"error": "No prompt provided"}), 400
+    with gr.Row():
+        file_input = gr.File(label="Upload File")
+        prompt_input = gr.Textbox(label="Enter your question", placeholder="Ask something about the uploaded file...")
 
-    # Send prompt to Hugging Face model
-    response = get_bot_response(prompt)
-    return jsonify({"response": response})
+    output = gr.Textbox(label="AI Response")
 
+    submit_button = gr.Button("Submit")
+    submit_button.click(get_bot_response, inputs=[file_input, prompt_input], outputs=output)
 
+# Launch the Gradio app
 if __name__ == "__main__":
-    app.run(debug=True)
+    app.launch()