Initial Financial RAG deployment

README.md

@@ -0,0 +1,235 @@
+---
+title: MiniCPM Financial RAG
+sdk: gradio
+sdk_version: 5.34.0
+python_version: "3.11"
+app_file: app.py
+pinned: false
+---
+
+
+
+# 💰 MiniCPM Financial RAG
+
+### 📊 Financial Document Intelligence Powered by Retrieval-Augmented Generation
+
+**Real-world Problem**
+
+Financial reports, insurance documents, annual reports, SEC filings, balance sheets, and investment documents often contain hundreds of pages of complex information.
+
+Finding specific financial insights manually is time-consuming and error-prone.
+
+**MiniCPM Financial RAG** enables users to upload financial PDF documents and ask questions in natural language. The system retrieves the most relevant information from the document and generates accurate, context-aware answers using MiniCPM models.
+
+---
+
+## 🎯 Example Questions
+
+- What is the company's total revenue?
+- What is the net income for this period?
+- What are the major risk factors?
+- Summarize the financial outlook.
+- What liabilities are reported?
+- What is the operating cash flow?
+
+---
+
+
+# 🤖 Models Used
+
+| Task | Model | Parameters | Purpose |
+|------|--------|------------|---------|
+| Financial Question Answering | openbmb/MiniCPM-2B-128K | 2B | Financial reasoning and answer generation |
+| Embedding Generation | openbmb/MiniCPM-Embedding-Light | Lightweight | Semantic retrieval and vector search |
+
+---
+
+# 🧠 Why MiniCPM?
+
+| Model | Benefits |
+|---------|----------|
+| MiniCPM-2B-128K | Lightweight, fast inference, long-context understanding |
+| MiniCPM-Embedding-Light | Efficient embeddings with strong retrieval performance |
+
+---
+
+# 🚀 Features
+
+| Feature | Description |
+|----------|-------------|
+| 📄 PDF Upload | Upload financial reports and PDF documents |
+| ✂️ Smart Chunking | Automatically split documents into meaningful chunks |
+| 🔎 Semantic Search | Retrieve the most relevant financial information |
+| 🧠 Financial Question Answering | Ask questions in natural language |
+| 📚 Retrieval-Augmented Generation | Generate context-grounded answers |
+| ⚡ GPU Acceleration | Fast inference using Modal GPU infrastructure |
+| 📊 Financial Analysis | Analyze revenue, expenses, assets, and liabilities |
+| 🎯 High Accuracy Retrieval | FAISS-based vector similarity search |
+
+---
+
+
+
+---
+
+# 📚 Knowledge Pipeline
+
+| Stage | Purpose |
+|--------|----------|
+| PDF Parsing | Extract text from PDF documents |
+| Text Chunking | Break large documents into manageable sections |
+| Embedding Generation | Convert text chunks into vector representations |
+| FAISS Storage | Store vectors efficiently for retrieval |
+| Similarity Search | Retrieve the most relevant document chunks |
+| LLM Generation | Generate grounded answers from retrieved context |
+
+---
+
+# ⚙️ Tech Stack
+
+| Layer | Technology |
+|--------|------------|
+| Frontend | Gradio |
+| Backend | Modal |
+| LLM | MiniCPM-2B-128K |
+| Embeddings | MiniCPM-Embedding-Light |
+| Vector Database | FAISS |
+| Framework | LangChain |
+| PDF Processing | PyPDFLoader |
+| Deep Learning | PyTorch |
+| Deployment | Hugging Face Spaces |
+
+---
+
+# 📈 Monitoring
+
+The application is continuously monitored to ensure reliability and performance.
+
+| Component | Monitoring Method |
+|------------|------------------|
+| Hugging Face Space | Build Logs & Runtime Logs |
+| Modal Backend | Endpoint Monitoring |
+| Retrieval Pipeline | Context Validation |
+| Vector Search | Similarity Search Accuracy |
+| Question Answering | Response Validation |
+| System Health | Runtime Monitoring |
+
+### Monitoring Checklist
+
+- Monitor application uptime
+- Validate retrieval quality
+- Verify answer accuracy
+- Check Modal endpoint status
+- Review Hugging Face logs
+- Monitor memory and GPU utilization
+
+---
+
+# 🌐 Deployment Architecture
+
+```text
+Hugging Face Spaces
+        │
+        ▼
+Gradio Frontend
+        │
+        ▼
+Modal Backend
+        │
+ ┌──────┴──────┐
+ ▼             ▼
+
+MiniCPM QA   FAISS Retrieval
+```
+
+---
+
+# 📂 Project Structure
+
+```text
+MiniCPM_Financial_RAG/
+
+├── backend/
+│   └── app.py
+│
+├── frontend/
+│   └── gradio_app.py
+│
+├── requirements.txt
+│
+├── README.md
+│
+└── assets/
+```
+
+---
+
+# 💻 Installation
+
+## Create Virtual Environment
+
+```bash
+python -m venv venv
+```
+
+## Activate Environment
+
+### Windows
+
+```bash
+venv\Scripts\activate
+```
+
+### Linux / Mac
+
+```bash
+source venv/bin/activate
+```
+
+## Install Dependencies
+
+```bash
+pip install -r requirements.txt
+```
+
+---
+
+# 🚀 Run Application
+
+```bash
+python app.py
+```
+
+Application URL:
+
+```text
+http://localhost:8000
+```
+
+---
+
+# 🎯 Target Users
+
+| User Type | Use Case |
+|------------|----------|
+| Financial Analysts | Analyze reports and statements |
+| Investors | Extract investment insights |
+| Accountants | Review financial data quickly |
+| Auditors | Validate financial information |
+| Researchers | Analyze large financial documents |
+| Students | Learn financial concepts interactively |
+
+---
+
+# 📊 Benefits
+
+| Benefit | Description |
+|----------|-------------|
+| Faster Analysis | Reduce manual document review time |
+| Accurate Retrieval | Retrieve the most relevant financial information |
+| Context-Aware Answers | Grounded responses from document content |
+| Scalable Architecture | Handles large financial reports efficiently |
+| Cost Effective | Uses lightweight MiniCPM models |
+
+---
+

app.py

@@ -0,0 +1,164 @@
+
+import gradio as gr
+import modal
+import requests
+
+# Modal Function
+rag = modal.Cls.from_name(
+    "minicpm-rag",
+    "RAG"
+)()
+
+
+pdf_bytes_global = None
+
+def upload_pdf(pdf):
+
+    if pdf is None:
+        return "❌ Please upload a PDF"
+
+    with open(pdf.name, "rb") as f:
+        pdf_bytes = f.read()
+
+    r = requests.post(
+        "https://gajanand1902--minicpm-rag-upload-pdf.modal.run",
+        json={"pdf_bytes": list(pdf_bytes)}
+    )
+    data = r.json()
+
+    if isinstance(data, dict):
+        return str(data)
+
+    return data
+
+
+def chat(message, history):
+    r = requests.post(
+        "https://gajanand1902--minicpm-rag-chat-api.modal.run",
+        json={"question": message}
+    )
+
+    data = r.json()
+
+    if isinstance(data, dict):
+        return data.get("answer", str(data))
+
+    return str(data)
+
+
+# Custom Theme
+theme = gr.themes.Soft(
+    primary_hue="blue",
+    secondary_hue="cyan",
+    neutral_hue="slate"
+)
+
+css = """
+.gradio-container {
+    max-width: none !important;
+    width: 100% !important;
+    margin: 0 !important;
+}
+
+.upload-card {
+    width: 100% !important;
+    max-width: none !important;
+    padding: 20px;
+    border-radius: 15px;
+    background: #f8fafc;
+    border: 1px solid #e5e7eb;
+}
+    padding: 20px;
+    border-radius: 15px;
+    background: #f8fafc;
+    border: 1px solid #e5e7eb;
+}
+
+.footer {
+    text-align:center;
+    color:gray;
+}
+
+button {
+    border-radius: 10px !important;
+}
+
+.chatbot {
+    border-radius: 15px !important;
+}
+
+.chat-section textarea {
+    background: #ffffff !important;
+    border: 2px solid #2563eb !important;
+    border-radius: 16px !important;
+    padding: 14px !important;
+    font-size: 15px !important;
+}
+
+.chat-section textarea:focus {
+    border-color: #06b6d4 !important;
+    box-shadow: 0 0 10px rgba(6,182,212,0.4) !important;
+}
+
+.chat-section textarea::placeholder {
+    color: #64748b !important;
+    opacity: 1 !important;
+    font-weight: 500;
+}
+
+"""
+
+with gr.Blocks(
+    title="📄 MiniCPM Financial RAG",
+    theme=theme,
+    css=css
+) as demo:
+    # Header
+    gr.HTML("""
+    <div style="
+        text-align:center;
+        padding:20px;
+        background:linear-gradient(90deg,#2563eb,#06b6d4);
+        color:white;
+        border-radius:15px;
+        margin-bottom:20px;"
+    >
+    </div>
+    """)
+    # Layout: left upload, right chat
+    with gr.Row():
+        # Left side (smaller header + upload)
+        with gr.Column(scale=1):
+            # Small header
+            gr.HTML("""
+            <div class="header" style="text-align:center;padding:8px;background:linear-gradient(90deg,#2563eb,#06b6d4);color:white;border-radius:12px;margin-bottom:8px;">
+                <h1 style="font-size:1.2rem;margin:0;">📄 MiniCPM Financial QA RAG</h1>
+                <p style="font-size:0.9rem;margin:0;">Upload a Financial PDF and Chat with it using AI</p>
+            </div>
+            """)
+            with gr.Group(elem_classes="upload-card"):
+                gr.Markdown("### 📚 Upload Document")
+                pdf = gr.File(label="Choose PDF", file_types=[".pdf"])
+                upload_btn = gr.Button("🚀 Process PDF", variant="primary")
+                status = gr.Textbox(label="📌 Status", interactive=False)
+                upload_btn.click(fn=upload_pdf, inputs=pdf, outputs=status)
+        # Right side (chat with scrollbar)
+        with gr.Column(scale=3):
+            gr.Markdown("### 💬 Ask Questions")
+
+            with gr.Group(elem_classes="chat-section"):
+
+                gr.ChatInterface(
+                    fn=chat,
+                    chatbot=gr.Chatbot(
+                        height=600,
+                        show_label=False
+                    ),
+                    textbox=gr.Textbox(
+                        placeholder="🤖 Ask a question about your financial report...",
+                        container=False,
+                        scale=7
+                    )
+                )
+if __name__ == "__main__":
+    demo.launch()

requirements.txt

@@ -0,0 +1,4 @@
+gradio==5.34.0
+modal
+requests
+