Create app.py

app.py

@@ -0,0 +1,82 @@
+import gradio as gr
+from pypdf import PdfReader
+from sentence_transformers import SentenceTransformer
+import faiss
+import numpy as np
+from transformers import pipeline
+
+# Load embedding model
+embed_model = SentenceTransformer("sentence-transformers/all-MiniLM-L6-v2")
+
+# Load QA model
+qa_model = pipeline("text-generation", model="gpt2")
+
+# Temporary in-memory storage
+documents = []
+vectors = None
+index = None
+
+def read_pdfs(pdf_files):
+    global documents, vectors, index
+
+    all_text = ""
+    documents = []
+
+    for pdf in pdf_files:
+        reader = PdfReader(pdf.name)
+        text = ""
+        for page in reader.pages:
+            text += page.extract_text() + "\n"
+        documents.append(text)
+        all_text += text + "\n"
+
+    # Split text into chunks
+    chunks = all_text.split("\n")
+
+    # Embed chunks
+    embeddings = embed_model.encode(chunks)
+    vectors = np.array(embeddings).astype("float32")
+
+    # Create FAISS Index
+    index = faiss.IndexFlatL2(vectors.shape[1])
+    index.add(vectors)
+
+    return "Documents uploaded and processed. You may now ask questions."
+
+def ask_question(query):
+    global vectors, index, documents
+
+    if index is None:
+        return "Please upload PDF documents first."
+
+    # Embed query
+    q_embed = embed_model.encode([query]).astype("float32")
+
+    # Search similar chunks
+    D, I = index.search(q_embed, k=3)
+
+    # Collect top matches
+    context = ""
+    for idx in I[0]:
+        context += documents[0][idx: idx + 500] + "\n"
+
+    # Generate answer
+    prompt = f"Context: {context}\nQuestion: {query}\nAnswer:"
+    answer = qa_model(prompt, max_length=120)[0]["generated_text"]
+
+    return answer
+
+# Gradio UI
+with gr.Blocks() as demo:
+    gr.Markdown("## PDF Chatbot")
+    pdf_input = gr.File(label="Upload multiple PDFs", file_count="multiple")
+    upload_btn = gr.Button("Process Documents")
+    status = gr.Textbox(label="Status")
+
+    question = gr.Textbox(label="Ask a question")
+    answer = gr.Textbox(label="Answer")
+
+    upload_btn.click(read_pdfs, inputs=pdf_input, outputs=status)
+    question.submit(ask_question, inputs=question, outputs=answer)
+
+demo.launch()