Update src/streamlit_app.py

src/streamlit_app.py

@@ -1,40 +1,47 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
-
-"""
-# Welcome to Streamlit!
-
-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).
-
-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)
-
-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)
-
-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])),
-    ))
+from langchain.document_loaders import TextLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.chains import RetrievalQA
+from langchain.llms import HuggingFaceHub
+
+@st.cache_resource
+def load_vector_store():
+    # Load and chunk the document
+    loader = TextLoader("data/sample.txt")  # Make sure this file exists
+    documents = loader.load()
+
+    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=50)
+    chunks = splitter.split_documents(documents)
+
+    # Create embeddings and vector store
+    embedding_model = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
+    db = FAISS.from_documents(chunks, embedding_model)
+    return db
+
+def main():
+    st.title("📄 Ask Your Document")
+    st.write("Powered by LangChain + Hugging Face")
+
+    query = st.text_input("Enter your question:")
+    if query:
+        db = load_vector_store()
+
+        # Create RAG chain with Hugging Face model
+        qa_chain = RetrievalQA.from_chain_type(
+            llm=HuggingFaceHub(
+                repo_id="google/flan-t5-base",
+                model_kwargs={"temperature": 0.5, "max_length": 256}
+            ),
+            retriever=db.as_retriever(),
+            return_source_documents=True
+        )
+
+        result = qa_chain.run(query)
+
+        st.write("### 📌 Answer")
+        st.write(result)
+
+if __name__ == "__main__":
+    main()