Create app.py

app.py

@@ -0,0 +1,129 @@
+import gradio as gr
+import groq
+import os
+import tempfile
+import uuid
+from dotenv import load_dotenv
+from langchain_community.document_loaders import PyPDFLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.vectorstores import FAISS
+from langchain.embeddings import HuggingFaceEmbeddings
+
+load_dotenv()
+client = groq.Client(api_key=os.getenv("GROQ_FINANCE_API_KEY"))
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+
+FAISS_INDEX_DIR = "faiss_indexes_finance"
+if not os.path.exists(FAISS_INDEX_DIR):
+    os.makedirs(FAISS_INDEX_DIR)
+
+user_vectorstores = {}
+
+custom_css = """
+:root {
+    --primary-green: #10B981;
+    --dark-green: #047857;
+    --light-green: #D1FAE5;
+    --medium-grey: #6B7280;
+    --light-grey: #F3F4F6;
+    --white: #FFFFFF;
+    --border-grey: #E5E7EB;
+}
+body { background-color: var(--light-grey); font-family: 'Inter', sans-serif; }
+.container { max-width: 900px !important; margin: 0 auto !important; }
+.header { background-color: var(--white); border-bottom: 2px solid var(--border-grey); padding: 15px 0; margin-bottom: 20px; border-radius: 12px 12px 0 0; box-shadow: 0 2px 4px rgba(0,0,0,0.05); }
+.header-title { color: var(--dark-green); font-size: 1.5rem; font-weight: 700; text-align: center; }
+.header-subtitle { color: var(--medium-grey); font-size: 0.9rem; text-align: center; margin-top: 5px; }
+.chat-container { border-radius: 12px !important; box-shadow: 0 4px 6px rgba(0,0,0,0.1) !important; background-color: var(--white) !important; border: 1px solid var(--border-grey) !important; }
+.message-user { background-color: var(--primary-green) !important; color: var(--white) !important; border-radius: 18px 18px 4px 18px !important; padding: 12px 16px !important; margin-left: auto !important; max-width: 80% !important; }
+.message-bot { background-color: var(--light-grey) !important; color: var(--medium-grey) !important; border-radius: 18px 18px 18px 4px !important; padding: 12px 16px !important; margin-right: auto !important; max-width: 80% !important; }
+.input-area { background-color: var(--white) !important; border-top: 1px solid var(--border-grey) !important; padding: 12px !important; border-radius: 0 0 12px 12px !important; }
+.input-box { border: 1px solid var(--border-grey) !important; border-radius: 24px !important; padding: 12px 16px !important; box-shadow: 0 2px 4px rgba(0,0,0,0.05) !important; }
+.send-btn { background-color: var(--primary-green) !important; border-radius: 24px !important; color: var(--white) !important; padding: 10px 20px !important; font-weight: 500 !important; }
+.clear-btn { background-color: var(--light-grey) !important; border: 1px solid var(--border-grey) !important; border-radius: 24px !important; color: var(--medium-grey) !important; padding: 8px 16px !important; font-weight: 500 !important; }
+"""
+
+def process_pdf(pdf_file):
+    if pdf_file is None:
+        return None, "No file uploaded"
+    try:
+        session_id = str(uuid.uuid4())
+        with tempfile.NamedTemporaryFile(suffix='.pdf', delete=False) as temp_file:
+            temp_file.write(pdf_file)
+            pdf_path = temp_file.name
+        loader = PyPDFLoader(pdf_path)
+        documents = loader.load()
+        text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
+        texts = text_splitter.split_documents(documents)
+        vectorstore = FAISS.from_documents(texts, embeddings)
+        index_path = os.path.join(FAISS_INDEX_DIR, session_id)
+        vectorstore.save_local(index_path)
+        user_vectorstores[session_id] = vectorstore
+        os.unlink(pdf_path)
+        return session_id, f"✅ Successfully processed {len(texts)} text chunks from your PDF"
+    except Exception as e:
+        if 'pdf_path' in locals() and os.path.exists(pdf_path):
+            os.unlink(pdf_path)
+        return None, f"Error processing PDF: {str(e)}"
+
+def generate_response(message, session_id, model_name, history):
+    if not message:
+        return history
+    try:
+        context = ""
+        if session_id and session_id in user_vectorstores:
+            vectorstore = user_vectorstores[session_id]
+            docs = vectorstore.similarity_search(message, k=3)
+            if docs:
+                context = "\n\nRelevant information from uploaded PDF:\n" + "\n".join(f"- {doc.page_content}" for doc in docs)
+        system_prompt = "You are a financial analyst adept at summarizing reports and extracting key metrics."
+        if context:
+            system_prompt += " Use the following context to answer the question if relevant: " + context
+        completion = client.chat.completions.create(
+            model=model_name,
+            messages=[
+                {"role": "system", "content": system_prompt},
+                {"role": "user", "content": message}
+            ],
+            temperature=0.7,
+            max_tokens=1024
+        )
+        response = completion.choices[0].message.content
+        history.append((message, response))
+        return history
+    except Exception as e:
+        history.append((message, f"Error generating response: {str(e)}"))
+        return history
+
+with gr.Blocks(css=custom_css, theme=gr.themes.Soft()) as demo:
+    current_session_id = gr.State(None)
+    gr.HTML("""
+    <div class="header">
+        <div class="header-title">Financial Report Summarizer</div>
+        <div class="header-subtitle">Summarize financial data with Groq's LLM API</div>
+    </div>
+    """)
+    with gr.Row():
+        with gr.Column(scale=1):
+            pdf_file = gr.File(label="Upload PDF Document", file_types=[".pdf"], type="binary")
+            upload_button = gr.Button("Process PDF", variant="primary")
+            pdf_status = gr.Markdown("No PDF uploaded yet")
+            model_dropdown = gr.Dropdown(
+                choices=["llama3-70b-8192", "llama3-8b-8192", "mixtral-8x7b-32768", "gemma-7b-it"],
+                value="llama3-70b-8192",
+                label="Select Groq Model"
+            )
+        with gr.Column(scale=2):
+            chatbot = gr.Chatbot(height=500, bubble_full_width=False, show_copy_button=True, elem_classes="chat-container")
+            with gr.Row():
+                msg = gr.Textbox(show_label=False, placeholder="Ask about your financial report...", scale=5)
+                send_btn = gr.Button("Send", scale=1)
+            clear_btn = gr.Button("Clear Conversation")
+    
+    upload_button.click(process_pdf, inputs=[pdf_file], outputs=[current_session_id, pdf_status])
+    msg.submit(generate_response, inputs=[msg, current_session_id, model_dropdown, chatbot], outputs=[chatbot]).then(lambda: "", None, [msg])
+    send_btn.click(generate_response, inputs=[msg, current_session_id, model_dropdown, chatbot], outputs=[chatbot]).then(lambda: "", None, [msg])
+    clear_btn.click(lambda: ([], None, "No PDF uploaded yet"), None, [chatbot, current_session_id, pdf_status])
+
+if __name__ == "__main__":
+    demo.launch()