Create app.py

app.py

@@ -0,0 +1,113 @@
+import os
+import gdown
+import gradio as gr
+from openai import OpenAI
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain_huggingface import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
+
+# --- CONFIGURATION ---
+FILE_ID = "1jmHwcjA-gLIUTIKkXfQ36ucJI_VPdULS"
+PDF_PATH = "finance_data.pdf"
+GDRIVE_URL = f'https://drive.google.com/uc?id={FILE_ID}'
+
+# Use environment variable for security on Hugging Face
+GROQ_API_KEY = os.environ.get("GROQ_API_KEY")
+
+# --- INITIALIZATION ---
+def initialize_system():
+    if not os.path.exists(PDF_PATH):
+        gdown.download(GDRIVE_URL, PDF_PATH, quiet=False)
+    
+    loader = PyPDFLoader(PDF_PATH)
+    docs = loader.load()
+    
+    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=150)
+    chunks = splitter.split_documents(docs)
+    
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    return FAISS.from_documents(chunks, embeddings)
+
+# Global Vector DB
+vector_db = initialize_system()
+
+def process_query(user_query):
+    if not GROQ_API_KEY:
+        return "Error: GROQ_API_KEY not found in Environment Variables.", ""
+    
+    if not user_query.strip():
+        return "Please enter a valid question.", ""
+
+    try:
+        # Retrieval
+        search_results = vector_db.similarity_search(user_query, k=3)
+        context = "\n\n".join([res.page_content for res in search_results])
+        
+        # Groq Client
+        client = OpenAI(api_key=GROQ_API_KEY, base_url="https://api.groq.com/openai/v1")
+        
+        # Generation
+        prompt = f"Context: {context}\n\nQuestion: {user_query}\n\nAnswer using context only:"
+        response = client.responses.create(model="openai/gpt-oss-20b", input=prompt)
+        
+        return response.output_text, context
+    except Exception as e:
+        return f"System Error: {str(e)}", ""
+
+# --- CUSTOM PINK THEME ---
+pink_theme = gr.themes.Soft(
+    primary_hue="pink",
+    secondary_hue="rose",
+    neutral_hue="slate",
+    font=[gr.themes.GoogleFont("Poppins"), "ui-sans-serif", "system-ui", "sans-serif"],
+).set(
+    button_primary_background_fill="*primary_500",
+    button_primary_background_fill_hover="*primary_600",
+    button_primary_text_color="white",
+    body_background_fill="*neutral_50",
+)
+
+# --- GRADIO UI ---
+with gr.Blocks(theme=pink_theme, title="Muhammad Bilal Finance RAG") as demo:
+    gr.Markdown(
+        """
+        # <span style='color:#e91e63;'>📊 Muhammad Bilal Finance RAG App</span>
+        ### Analyzing financial documents with precision and style.
+        """
+    )
+    
+    with gr.Row():
+        with gr.Column(scale=2):
+            query_input = gr.Textbox(
+                label="Your Question", 
+                placeholder="Ask about revenue, assets, or liabilities...",
+                lines=2
+            )
+            analyze_btn = gr.Button("✨ Analyze Document", variant="primary")
+        
+        with gr.Column(scale=3):
+            answer_output = gr.Textbox(
+                label="AI Financial Insights", 
+                placeholder="Analysis will appear here...",
+                lines=10,
+                interactive=False
+            )
+            
+    with gr.Accordion("🔍 View Retrieved Source Data", open=False):
+        context_output = gr.Markdown()
+
+    analyze_btn.click(
+        fn=process_query, 
+        inputs=[query_input], 
+        outputs=[answer_output, context_output]
+    )
+
+    gr.Markdown(
+        """
+        <center>Developed by **Muhammad Bilal** | Powered by FAISS & Groq</center>
+        """
+    )
+
+if __name__ == "__main__":
+    demo.launch()