Push chatbot to Hugging Face Space

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -0,0 +1,2 @@
+.env
+secrets.toml

.huggingface.yml

@@ -0,0 +1,4 @@
+sdk: docker
+app_file: app.py
+port: 7860
+hardware: cpu-basic

Dockerfile

@@ -0,0 +1,21 @@
+FROM python:3.11
+
+# Create and use a non-root user (optional)
+RUN useradd -m -u 1000 user
+USER user
+ENV PATH="/home/user/.local/bin:$PATH"
+
+# Set working directory
+WORKDIR /app
+
+# Copy all project files to the container
+COPY . .
+
+# Install dependencies
+RUN pip install --no-cache-dir -r requirements.txt
+
+# Expose port
+EXPOSE 7860
+
+# Run the application
+CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860", "--workers", "3"]

README.md

@@ -0,0 +1,11 @@
+---
+title: Tutorbot
+emoji: 🧑‍🏫
+colorFrom: green
+colorTo: purple
+sdk: docker
+sdk_version: latest
+pinned: false
+license: apache-2.0
+short_description: Simple tutor chatbot
+---

app.py

@@ -0,0 +1,215 @@
+# https://binkhoale1812-tutorbot.hf.space/chat
+import os
+import time
+import uvicorn
+import tempfile
+import psutil
+import logging
+
+from fastapi import FastAPI, UploadFile, File, Form, HTTPException
+from fastapi.responses import JSONResponse
+from fastapi.middleware.cors import CORSMiddleware
+
+from google import genai
+from gradio_client import Client, handle_file
+
+# —————— Logging ——————
+logging.basicConfig(level=logging.DEBUG, format="%(asctime)s — %(name)s — %(levelname)s — %(message)s", force=True)
+logger = logging.getLogger("tutor-chatbot")
+logger.setLevel(logging.DEBUG)
+logger.info("🚀 Starting Tutor Chatbot API...")
+
+# —————— Environment ——————
+gemini_flash_api_key = os.getenv("FlashAPI")
+if not gemini_flash_api_key:
+    raise ValueError("❌ Missing Gemini Flash API key!")
+
+# —————— System Check ——————
+def check_system_resources():
+    memory = psutil.virtual_memory()
+    cpu = psutil.cpu_percent(interval=1)
+    disk = psutil.disk_usage("/")
+    logger.info(f"🔍 RAM: {memory.percent}%, CPU: {cpu}%, Disk: {disk.percent}%")
+check_system_resources()
+
+os.environ["OMP_NUM_THREADS"] = "1"
+os.environ["TOKENIZERS_PARALLELISM"] = "false"
+
+# —————— FastAPI Setup ——————
+app = FastAPI(title="Tutor Chatbot API")
+app.add_middleware(
+    CORSMiddleware,
+    allow_origins=[
+        "http://localhost:5173",
+        "http://localhost:3000",
+        "https://medical-chatbot-henna.vercel.app",
+    ],
+    allow_credentials=True,
+    allow_methods=["*"],
+    allow_headers=["*"],
+)
+
+# —————— Gemini 2.5 API Call ——————
+def gemini_flash_completion(prompt, model="gemini-2.5-flash-preview-04-17", temperature=0.7):
+    client = genai.Client(api_key=gemini_flash_api_key)
+    try:
+        response = client.models.generate_content(model=model, contents=prompt)
+        return response.text
+    except Exception as e:
+        logger.error(f"❌ Gemini error: {e}")
+        return "Error generating response from Gemini."
+
+# —————— Qwen 2.5 VL Client Setup ——————
+qwen_client = Client("prithivMLmods/Qwen2.5-VL-7B-Instruct")
+logger.info("[Qwen] Using remote API via Gradio Client")
+
+def qwen_image_summary(image_file: UploadFile, subject: str, level: str) -> str:
+    from gradio_client import Client, handle_file
+    import tempfile
+    # Read file with appropriate format
+    if image_file.content_type not in {"image/png", "image/jpeg", "image/jpg"}:
+        raise HTTPException(415, "Only PNG or JPEG images are supported")
+    # Write/read file
+    try:
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as tmp:
+            tmp.write(image_file.file.read())
+            tmp_path = tmp.name
+        logger.info(f"[Qwen] File saved at {tmp_path}, sending to /generate_image...")
+        # Prompt
+        instruction = f"""
+        You are an academic tutor.
+
+        The student has submitted an image that may contain multiple exam-style questions or study material. Your task is to:
+        1. Carefully extract **each individual question** from the image (if visible), even if they are numbered (e.g., 1., 2., 3.).
+        2. If any question contains **multiple-choice options** (e.g., a), b), c), d)), include them exactly as shown.
+        3. Preserve the original structure and wording as much as possible — DO NOT paraphrase.
+        4. Do not include commentary, analysis, or summaries — just return the extracted question(s) cleanly.
+
+        Format your output as:
+        1. Question 1 text  
+        a) option A  
+        b) option B  
+        c) option C  
+        d) option D
+
+        2. Question 2 text  
+        a) ... (if applicable)
+
+        Only include what appears in the image. Be accurate and neat.
+        """
+        # Client spec
+        client = Client("prithivMLmods/Qwen2.5-VL")
+        # Client configs
+        result = client.predict(
+            model_name="Qwen2.5-VL-7B-Instruct",
+            text=instruction,
+            image=handle_file(tmp_path),
+            max_new_tokens=1024,
+            temperature=0.6,
+            top_p=0.9,
+            top_k=50,
+            repetition_penalty=1.2,
+            api_name="/generate_image"
+        )
+        logger.info("[Qwen] ✅ Summary returned from /generate_image")
+        os.remove(tmp_path)
+        return result.strip()
+    # Error
+    except Exception as e:
+        logger.error(f"[QWEN_API_ERROR] {e}")
+        raise HTTPException(500, "❌ Qwen image analysis failed")
+
+
+# —————— Unified Chat Endpoint ——————
+@app.post("/chat")
+async def chat_endpoint(
+    query: str = Form(""),
+    subject: str = Form("general"),
+    level: str = Form("secondary"),
+    lang: str = Form("EN"),
+    image: UploadFile = File(None)
+):
+    start_time = time.time()
+    image_context = ""
+
+    # Step 1: If image is present, get transcription from Qwen
+    if image:
+        logger.info("[Router] 📸 Image uploaded — using Qwen2.5-VL for transcription")
+        try:
+            image_context = qwen_image_summary(image, subject, level)
+        except HTTPException as e:
+            return JSONResponse(status_code=e.status_code, content={"response": e.detail})
+
+    # Step 2: Build prompt for Gemini depending on presence of text and/or image
+    if query and image_context:
+        # Case: image + query
+        prompt = f"""
+            You are an academic tutor specialized in **{subject}** at **{level}** level.
+            Below is an image submitted by a student and transcribed by a vision model:
+
+            --- BEGIN IMAGE CONTEXT ---
+            {image_context}
+            --- END IMAGE CONTEXT ---
+
+            The student asked the following:
+
+            **Question:** {query}
+
+            Respond appropriately using markdown:
+            - **Bold** key ideas
+            - *Italic* for reasoning
+            - Provide examples if useful
+
+            **Response Language:** {lang}
+            """
+    elif image_context and not query:
+        # Case: image only — auto-answer based on content
+        prompt = f"""
+            You are an academic tutor specialized in **{subject}** at **{level}** level.
+            A student submitted an image with no question. Below is the vision model’s transcription:
+
+            --- BEGIN IMAGE CONTENT ---
+            {image_context}
+            --- END IMAGE CONTENT ---
+
+            Based on this image, explain its key ideas and help the student understand it.
+            Assume it's part of their study material.
+
+            Respond using markdown:
+            - **Bold** key terms
+            - *Italic* for explanations
+            - Give brief insights or examples
+
+            **Response Language:** {lang}
+            """
+    elif query and not image_context:
+        # Case: text only
+        prompt = f"""
+            You are an academic tutor specialized in **{subject}** at **{level}** level.
+
+            **Question:** {query}
+
+            Answer clearly using markdown:
+            - **Bold** key terms
+            - *Italic* for explanations
+            - Include examples if helpful
+
+            **Response Language:** {lang}
+            """
+    else:
+        # Nothing was sent
+        return JSONResponse(content={"response": "❌ Please provide either a query, an image, or both."})
+    # Step 3: Call Gemini
+    response_text = gemini_flash_completion(prompt)
+    end_time = time.time()
+    response_text += f"\n\n*(Response time: {end_time - start_time:.2f} seconds)*"
+    return JSONResponse(content={"response": response_text})
+
+# —————— Launch Server ——————
+if __name__ == "__main__":
+    logger.info("✅ Launching FastAPI server...")
+    try:
+        uvicorn.run(app, host="0.0.0.0", port=7860, log_level="debug")
+    except Exception as e:
+        logger.error(f"❌ Server startup failed: {e}")
+        exit(1)

requirements.txt

@@ -0,0 +1,14 @@
+# **Agents**
+google-genai
+huggingface_hub
+# **Environment**
+python-dotenv       # Not used in Streamlit deployment
+python-multipart
+# **Deployment**
+uvicorn
+fastapi
+psutil              # CPU/RAM logger
+# **OCR&&
+# OCR
+gradio_client
+pillow