Merge branch 'main' of https://huggingface.co/spaces/louiecerv/problem_solving_ai_tutor

app.py

@@ -3,7 +3,23 @@ import os
 import google.generativeai as genai
 import json
 from PIL import Image
+import re
+import json
+import tempfile
 
+# Define constants
+TEXT_PROMPT = """Use the provided document. Read the list of quadratic equations. 
+Return your response as a JSON list. Do not include any extra text, explanations, or backslashes.
+
+Example JSON output:
+[
+  "x^2 - 5x + 6 = 0",
+  "2x^2 + 3x - 1 = 0",
+  "x^2 - 9 = 0",
+  "3x^2 - 2x + 4 = 0",
+  "x^2 + 8x + 15 = 0"
+]
+"""
 
 MODEL_ID = "gemini-2.0-flash-exp"  
 try:
@@ -17,17 +33,17 @@ except Exception as e:
 model = genai.GenerativeModel(MODEL_ID)
 chat = model.start_chat()
 
-def get_local_pdf_path():
+def get_local_file_path(img_file="problem1.png"):
     """
     Returns the path to the local PDF file.
     """
     try:
-        pdf_path = os.path.join("problems", "problems.pdf")
-        if not os.path.exists(pdf_path):
-            raise FileNotFoundError(f"{pdf_path} does not exist.")
-        return pdf_path
+        file_path = os.path.join("problems", img_file)
+        if not os.path.exists(file_path):
+            raise FileNotFoundError(f"{file_path} does not exist.")
+        return file_path
     except Exception as e:
-        st.error(f"Failed to find the local PDF: {e}")
+        st.error(f"Failed to find the local file: {e}")
         st.stop()  # Stop if the file is not found
 
 # Initialize conversation history in Streamlit session state
@@ -36,35 +52,62 @@ if "conversation_history" not in st.session_state:
 if "uploaded_file_part" not in st.session_state:  # Store the file *part*
     st.session_state.uploaded_file_part = None
 if "uploaded_pdf_path" not in st.session_state:
-    st.session_state.uploaded_pdf_path = get_local_pdf_path()
+    st.session_state.uploaded_pdf_path = get_local_file_path()
 
-def multimodal_prompt(pdf_path, text_prompt):
+def multimodal_prompt(pdf_path, text_prompt, file_type="PDF"):
     """
     Sends a multimodal prompt to Gemini, handling file uploads efficiently.
     Args:
-        pdf_path: The path to the PDF file.
+        pdf_path: The path to the file (PDF or image).
         text_prompt: The text prompt for the model.
+        file_type: "PDF" or "image" to specify the file type.
     Returns:
         The model's response as a string, or an error message.
     """
     try:
-        if st.session_state.uploaded_file_part is None:  # First time, upload
-            pdf_part = genai.upload_file(pdf_path, mime_type="application/pdf")
-            st.session_state.uploaded_file_part = pdf_part
-            prompt = [text_prompt, pdf_part]  # First turn includes the actual file
-        else:  # Subsequent turns, reference the file
-            prompt = [text_prompt, st.session_state.uploaded_file_part]  # Subsequent turns include the file reference
+        if file_type == "PDF":
+            mime_type = "application/pdf"
+        elif file_type == "image":
+            import mimetypes
+            mime_type, _ = mimetypes.guess_type(pdf_path)
+            if mime_type is None:
+              return "Could not determine MIME type for image. Please check the file path or type."
+        else:
+            return "Invalid file_type. Must be 'PDF' or 'image'."
+
+        pdf_part = genai.upload_file(pdf_path, mime_type=mime_type)
+        prompt = [text_prompt, pdf_part]  # First turn includes the actual file
 
         response = chat.send_message(prompt)
 
         # Update conversation history
-        st.session_state.conversation_history.append({"role": "user", "content": text_prompt, "has_pdf": True})
+        st.session_state.conversation_history.append({"role": "user", "content": text_prompt, "has_file": True})
         st.session_state.conversation_history.append({"role": "assistant", "content": response.text})
         return response.text
 
     except Exception as e:
         return f"An error occurred: {e}"
 
+def get_equation(response):
+    # Remove the ```json and ``` and extra spaces.
+    try:
+        json_string = response.replace('```json', '').replace('```', '').strip()
+
+        # Parse the JSON string into a Python list.
+        problems_list = json.loads(json_string)
+
+        # return the first item found
+        return problems_list[0] 
+
+    except json.JSONDecodeError:
+        st.error("Invalid JSON format in the response.")
+        return None
+    except Exception as e:
+        st.error(f"An unexpected error occurred: {e}")
+        return None
+
+if "problem_step" not in st.session_state:
+    st.session_state.problem_step = 0   
 
 # --- Main Page ---
 st.title("📚❓Problem Solving Tutor")
@@ -73,79 +116,66 @@ about = """
 Replace this placeholder with the actual text.
 """
 
-
-import re
-import json
-
-# Define constants
-TEXT_PROMPT = """Use the provided document. Read the list of 5 quadratic equations. 
-Return your response as a JSON list. Do not include any extra text, explanations, or backslashes.
-
-Example JSON output:
-[
-  "x^2 - 5x + 6 = 0",
-  "2x^2 + 3x - 1 = 0",
-  "x^2 - 9 = 0",
-  "3x^2 - 2x + 4 = 0",
-  "x^2 + 8x + 15 = 0"
-]
-"""
-
-# Define a function to extract equations from the AI response
-def extract_equations(response):
-    try:
-        if isinstance(response, str):
-            response = response.strip().replace("\n", "").replace("\r", "")
-            if response.lower().startswith("json"):
-                response = response[4:].strip()
-            if response.startswith("[") and response.endswith("]"):
-                return json.loads(response)
-            else:
-                st.error("Error: AI response is not in expected JSON list format.")
-                return []
-        elif isinstance(response, list):
-            return response
-        else:
-            st.error("Error: Unexpected response format from AI.")
-            return []
-    except json.JSONDecodeError:
-        st.error("Error: Failed to parse AI response as a list.")
-        return []
-
-# Define a function to extract quadratic equations from the problems
-def extract_quadratic_equations(problems):
-    equations = []
-    for problem in problems:
-        match = re.search(r'([0-9x\^\+\-\=\s]+)', problem)
-        if match:
-            equations.append(match.group(1).strip())
-        else:
-            st.warning(f"Could not extract equation from: '{problem}'")
-    return equations
-
-# Main code
-with st.spinner("AI is thinking..."):
+with st.spinner("Loading the problem..."):
     if st.session_state.get("uploaded_pdf_path") is None:
-        st.session_state.uploaded_pdf_path = get_local_pdf_path()
+        st.session_state.uploaded_pdf_path = get_local_file_path("problem1.png")
 
     filepath = st.session_state.uploaded_pdf_path
-    response = multimodal_prompt(filepath, TEXT_PROMPT)
-
-# Debugging: Print response
-st.write("Raw AI Response:", response)
-
-# Extract equations
-problems = extract_equations(response)
-if problems:
-    equations = extract_quadratic_equations(problems)
-    st.write("Extracted Equations:")
-    for equation in equations:
-        st.write(equation)
-else:
-    st.error("Error: No valid equations extracted.")
-
-except Exception as e:
-    st.error(f"An unexpected error occurred: {e}")
+    response = multimodal_prompt(filepath, TEXT_PROMPT, file_type="image")
+
+# --- Display the image ---
+st.image(filepath, caption="Problem Image", use_container_width=True)
+
+equation = get_equation(response)
+st.write(f"**Equation:** {equation}")   
+
+problem_step = st.session_state.problem_step
+if problem_step == 0:
+    #Show instructions to submit the answer
+    st.write("Please write down your answer in a piece of paper.  Take a picture of the paper and submit it in the next step.")
+    st.write("Click the button below to proceed.")
+    img_file_buffer = st.camera_input("Take a picture of your answer.")
+
+    if img_file_buffer is not None:
+        # process the answer
+        st.write("Processing your answer...")
+
+       # Save the image to a temporary file
+        with tempfile.NamedTemporaryFile(delete=False, suffix=".jpg") as temp_file:
+            temp_file.write(img_file_buffer.read())
+            image_path = temp_file.name
+            st.write("Image saved to:", image_path) 
+
+            # create the text prompt
+            text_prompt = """Use the provided image. The image shows, 
+            my answer to the problem. If the image is not clear ask for another image and do not perform 
+            any of the following instructions. If the image is clear, evaluate the answer as either 
+            correct or incorrect. If the answer is incorrect, do not provide the correct answer. 
+            Provide feedback how can the student improve their answer.
+            If the answer is correct, provide feedback that the answer is correct and discuss the solution.
+            If the student used the factoring method, ask the student to try again and next time use the 
+            quadratic formula method. The goal is to solve the problem using the quadratic formula method do not
+            ask the student to use the factoring method.
+            """
+
+            if st.button("Ask Tutor for Feedback"):
+                if text_prompt:
+                    with st.spinner("AI is thinking..."):
+                        response = multimodal_prompt(image_path, text_prompt, file_type="image")
+                        st.markdown(response)
+
+                        if st.button("Next"):
+                            # Evaluate the response
+                            if "Correct" in response:
+                                st.write("Correct! 🎉")
+                                st.session_state.problem_step = 1
+                            else:
+                                st.write("Incorrect. 😞")
+                                st.session_state.problem_step = 0
+                        
+
+    else:
+        st.write("Please take a picture of your answer.")
 
 
 st.markdown("Visit our Hugging Face Space!")