Deploy FastAPI chatbot with multi-mode endpoints

README.md

@@ -1,12 +1,212 @@
+# 🤖 Multimodal AI Chatbot API (FastAPI + Hugging Face + Qwen2.5)
+
+This project is a **FastAPI-based AI chatbot backend** designed for deployment on **Google Colab + Hugging Face Spaces**. It uses a lightweight LLM (`Qwen2.5-1.5B-Instruct`) and provides multiple domain-specific AI endpoints.
+
+---
+
+## 🚀 Features
+
+* ⚡ FastAPI backend for high-performance inference
+* 🧠 Powered by `Qwen2.5-1.5B-Instruct` (lightweight LLM)
+* 🌐 Multiple specialized AI modes:
+
+  * English assistant
+  * Bangla assistant
+  * Math solver
+  * Physics tutor
+* 🔗 REST API ready for frontend integration
+* 📦 Hugging Face / Colab deployment friendly
+
+---
+
+## 📁 Project Structure
+
+```
+main.py        # FastAPI backend
+requirements.txt
+README.md
+```
+
+---
+
+## 🧠 AI Modes / Endpoints
+
+| Mode    | Endpoint   | Description                       |
+| ------- | ---------- | --------------------------------- |
+| General | `/chat`    | General AI assistant              |
+| English | `/english` | Grammar, writing, correction      |
+| Bangla  | `/bangla`  | Bangla language assistant         |
+| Math    | `/math`    | Step-by-step problem solving      |
+| Physics | `/physics` | Physics explanations & numericals |
+
+---
+
+## ⚙️ Installation (Local / Colab)
+
+### 1️⃣ Install dependencies
+
+```bash
+pip install fastapi uvicorn transformers torch accelerate sentencepiece
+```
+
+---
+
+### 2️⃣ Run server
+
+```bash
+uvicorn main:app --host 0.0.0.0 --port 8000
+```
+
+For Colab:
+
+```bash
+nohup uvicorn main:app --host 0.0.0.0 --port 8000 &
+```
+
+---
+
+## 🌐 API Usage
+
+### 🔹 General Chat
+
+```bash
+POST /chat
+```
+
+```json
+{
+  "message": "Hello, what is AI?",
+  "mode": "none"
+}
+```
+
+---
+
+### 🔹 English Mode
+
+```bash
+POST /english
+```
+
+```json
+{
+  "message": "Correct this sentence: I has a book"
+}
+```
+
+---
+
+### 🔹 Bangla Mode
+
+```bash
+POST /bangla
+```
+
+```json
+{
+  "message": "বাংলা ব্যাকরণ কি?"
+}
+```
+
+---
+
+### 🔹 Math Mode
+
+```bash
+POST /math
+```
+
+```json
+{
+  "message": "Solve: 2x + 5 = 15"
+}
+```
+
+---
+
+### 🔹 Physics Mode
+
+```bash
+POST /physics
+```
+
+```json
+{
+  "message": "Explain Newton's second law"
+}
+```
+
 ---
-title: Chat API
-emoji: 📚
-colorFrom: green
-colorTo: green
-sdk: static
-pinned: false
-license: apache-2.0
-short_description: 'the api of chat '
+
+## 🧾 Response Format
+
+```json
+{
+  "mode": "math",
+  "response": "Step-by-step solution..."
+}
+```
+
+---
+
+## 📌 Disclaimer (Included in every response)
+
+Each response automatically includes:
+
+> The chat interface is built by MD Saib Hossain.
+> For AI systems, RAG pipelines, or Agentic AI development contact:
+> [https://www.linkedin.com/in/saib-hossain-182834229/](https://www.linkedin.com/in/saib-hossain-182834229/)
+
+---
+
+## 🚀 Deployment (Hugging Face Spaces)
+
+1. Create a new Space
+2. Choose **Docker or Gradio SDK**
+3. Upload `main.py`
+4. Set runtime to Python 3.10+
+5. Add dependencies in `requirements.txt`
+
+---
+
+## 🔥 Tech Stack
+
+* FastAPI
+* Hugging Face Transformers
+* PyTorch
+* Qwen2.5 LLM
+* Google Colab (for development)
+
+---
+
+## 📈 Future Improvements
+
+* 🔥 Streaming responses (token-by-token)
+* 🔥 LangGraph-based routing
+* 🔥 RAG integration (PDF + web data)
+* 🔥 Memory-based chat system
+* 🔥 Frontend React UI integration
+
+---
+
+## 👨‍💻 Author
+
+**MD Saib Hossain**
+AI/ML Engineer | Agentic AI & RAG Systems Builder
+
+🔗 LinkedIn: [https://www.linkedin.com/in/saib-hossain-182834229/](https://www.linkedin.com/in/saib-hossain-182834229/)
+
+---
+
+## ⭐ If you like this project
+
+You can extend it into:
+
+* AI tutor system
+* Multilingual chatbot
+* Exam preparation assistant
+* Medical/education RAG system
+
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+🚀 Built for scalable AI experimentation on lightweight infrastructure.

main.py

@@ -0,0 +1,202 @@
+
+from fastapi import FastAPI
+from pydantic import BaseModel
+from transformers import pipeline
+
+app = FastAPI()
+
+# Load Small LLM
+pipe = pipeline(
+    "text-generation",
+    model="Qwen/Qwen2.5-1.5B-Instruct",
+    device_map="auto"
+)
+
+# Disclaimer
+DISCLAIMER = """
+
+---
+The chat interface is built by MD Saib Hossain.
+
+For building chat interfaces, Agentic AI systems, or RAG-based chatbots, please contact:
+https://www.linkedin.com/in/saib-hossain-182834229/
+"""
+
+# Request Model
+class ChatRequest(BaseModel):
+    message: str
+    mode: str | None = None
+
+
+# -----------------------------
+# Helper Function
+# -----------------------------
+def generate_response(system_prompt: str, user_message: str):
+
+    prompt = f"""
+{system_prompt}
+
+User: {user_message}
+Assistant:
+"""
+
+    result = pipe(
+        prompt,
+        max_new_tokens=256,
+        temperature=0.7,
+        do_sample=True
+    )
+
+    response = result[0]["generated_text"]
+
+    # Extract assistant response
+    response = response.split("Assistant:")[-1].strip()
+
+    # Add Disclaimer
+    response += DISCLAIMER
+
+    return response
+
+
+# -----------------------------
+# Default Chat Endpoint
+# -----------------------------
+@app.post("/chat")
+async def general_chat(req: ChatRequest):
+
+    system_prompt = """
+You are a helpful AI assistant.
+Answer all kinds of questions politely and clearly.
+"""
+
+    response = generate_response(system_prompt, req.message)
+
+    return {
+        "mode": "general",
+        "response": response
+    }
+
+
+# -----------------------------
+# English Endpoint
+# -----------------------------
+@app.post("/english")
+async def english_chat(req: ChatRequest):
+
+    system_prompt = """
+You are an English learning assistant.
+
+You ONLY answer:
+- English grammar
+- vocabulary
+- sentence correction
+- translation
+- writing
+- speaking practice
+
+If the user asks anything outside English learning,
+reply:
+'I only answer English-related questions.'
+"""
+
+    response = generate_response(system_prompt, req.message)
+
+    return {
+        "mode": "english",
+        "response": response
+    }
+
+
+# -----------------------------
+# Bangla Endpoint
+# -----------------------------
+@app.post("/bangla")
+async def bangla_chat(req: ChatRequest):
+
+    system_prompt = """
+You are a Bangla language assistant.
+
+You ONLY answer:
+- Bangla grammar
+- Bangla translation
+- Bangla writing
+- Bangla literature
+- Bangla language learning
+
+If the user asks anything outside Bangla topics,
+reply:
+'আমি শুধুমাত্র বাংলা বিষয়ক প্রশ্নের উত্তর দিই।'
+"""
+
+    response = generate_response(system_prompt, req.message)
+
+    return {
+        "mode": "bangla",
+        "response": response
+    }
+
+
+# -----------------------------
+# Math Endpoint
+# -----------------------------
+@app.post("/math")
+async def math_chat(req: ChatRequest):
+
+    system_prompt = """
+You are a Mathematics assistant.
+
+You ONLY answer:
+- algebra
+- calculus
+- arithmetic
+- geometry
+- equations
+- statistics
+- mathematics problem solving
+
+Explain solutions step by step.
+
+If the user asks anything outside mathematics,
+reply:
+'I only answer Mathematics-related questions.'
+"""
+
+    response = generate_response(system_prompt, req.message)
+
+    return {
+        "mode": "math",
+        "response": response
+    }
+
+
+# -----------------------------
+# Physics Endpoint
+# -----------------------------
+@app.post("/physics")
+async def physics_chat(req: ChatRequest):
+
+    system_prompt = """
+You are a Physics assistant.
+
+You ONLY answer:
+- mechanics
+- electricity
+- magnetism
+- optics
+- thermodynamics
+- modern physics
+- numerical physics problems
+
+Explain concepts clearly and step by step.
+
+If the user asks anything outside physics,
+reply:
+'I only answer Physics-related questions.'
+"""
+
+    response = generate_response(system_prompt, req.message)
+
+    return {
+        "mode": "physics",
+        "response": response
+    }

requirements.txt

@@ -0,0 +1,6 @@
+fastapi
+uvicorn
+transformers
+torch
+accelerate
+sentencepiece