First commit to see interfaz

src/streamlit_app.py

@@ -4,37 +4,15 @@ import pandas as pd
 import streamlit as st
 
 """
-# Welcome to Streamlit!
+# Bienvenido a tu Tutor IA
 
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+Este ChatBot está diseñado para ayudarte a aprender y practicar tus habilidades en matemáticas y física.
+Puedes hacer preguntas, resolver problemas y recibir explicaciones detalladas sobre diversos temas.
 
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
+## !Empecemos!
 
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
+"""
 
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
+st.title("Bienvenido a tu Tutor IA. ¡Espero que hoy estés lleno de curiosidad y ganas de aprender!.")
 
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
 
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))

src/utils.py

@@ -0,0 +1,39 @@
+from transformers import pipeline
+from langchain_huggingface import HuggingFacePipeline
+from langchain.prompts import PromptTemplate
+from transformers.utils.logging import set_verbosity_error
+
+## setup the model
+set_verbosity_error()
+
+# Use Phi-2 for math solving
+math_pipeline = pipeline(
+    "text-generation",
+    model="microsoft/phi-2", # hjskhan/gemma-2b-fine-tuned-math
+    device=0,
+    max_new_tokens=256,  # 💡 increase for full explanation
+    temperature=0.7,
+    do_sample=True
+)
+
+math_solver = HuggingFacePipeline(pipeline=math_pipeline)
+
+# QA model (same as before)
+qa_pipeline = pipeline("question-answering", model="bert-large-uncased-whole-word-masking-finetuned-squad", device=-1)
+
+# Prompt to force step-by-step reasoning
+math_template = PromptTemplate.from_template(
+    "You are a math and physics tutor with great didactic methods. Solve the following problem step-by-step and explain clearly:\n\n{problem}\n\nSolution:"
+)
+
+# Chain definition
+math_chain = math_template | math_solver
+
+def ask_math_problem(problem):
+    """
+    Function to ask a math problem and get the solution.
+    """
+    # Generate the answer
+    solution = math_chain.invoke({"problem": problem})
+
+    return solution