Upload 2 files

app.py

@@ -0,0 +1,103 @@
+import streamlit as st
+from langchain_community.document_loaders import PyPDFLoader, TextLoader
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.llms import HuggingFacePipeline
+from langchain.chains import RetrievalQA
+
+from transformers import pipeline
+
+# -------------------------------
+# Load Documents
+# -------------------------------
+def load_documents(uploaded_files):
+    documents = []
+    for file in uploaded_files:
+        with open(file.name, "wb") as f:
+            f.write(file.getbuffer())
+
+        if file.name.endswith(".pdf"):
+            loader = PyPDFLoader(file.name)
+        else:
+            loader = TextLoader(file.name)
+
+        documents.extend(loader.load())
+    return documents
+
+
+# -------------------------------
+# Split Documents
+# -------------------------------
+def split_documents(documents):
+    splitter = RecursiveCharacterTextSplitter(
+        chunk_size=500,
+        chunk_overlap=50
+    )
+    return splitter.split_documents(documents)
+
+
+# -------------------------------
+# Create Vector Store
+# -------------------------------
+def create_vectorstore(chunks):
+    embeddings = HuggingFaceEmbeddings(
+        model_name="sentence-transformers/all-MiniLM-L6-v2"
+    )
+    return FAISS.from_documents(chunks, embeddings)
+
+
+# -------------------------------
+# Load Local LLM (FREE)
+# -------------------------------
+def load_llm():
+    pipe = pipeline(
+        "text-generation",
+        model="google/flan-t5-base",
+        max_length=512
+    )
+    return HuggingFacePipeline(pipeline=pipe)
+
+
+# -------------------------------
+# Build QA Chain
+# -------------------------------
+def build_qa(vectorstore):
+    llm = load_llm()
+    retriever = vectorstore.as_retriever()
+
+    qa = RetrievalQA.from_chain_type(
+        llm=llm,
+        retriever=retriever,
+        return_source_documents=False
+    )
+    return qa
+
+
+# -------------------------------
+# Streamlit UI
+# -------------------------------
+st.set_page_config(page_title="RAG Chatbot", layout="wide")
+st.title("📄 Chat with Your Documents (RAG)")
+
+uploaded_files = st.file_uploader(
+    "Upload PDF or TXT files",
+    accept_multiple_files=True
+)
+
+if uploaded_files:
+    with st.spinner("Processing documents..."):
+        docs = load_documents(uploaded_files)
+        chunks = split_documents(docs)
+        vectorstore = create_vectorstore(chunks)
+        qa_chain = build_qa(vectorstore)
+
+    st.success("Documents ready!")
+
+    query = st.text_input("Ask a question from your documents")
+
+    if query:
+        with st.spinner("Generating answer..."):
+            result = qa_chain.run(query)
+            st.write("### Answer:")
+            st.write(result)

requirements.txt

@@ -0,0 +1,9 @@
+streamlit==1.35.0
+langchain==0.2.15
+langchain-community==0.2.15
+langchain-text-splitters==0.2.2
+faiss-cpu==1.8.0
+sentence-transformers==2.7.0
+transformers==4.41.2
+pypdf==4.2.0
+torch==2.3.0