Create app.py

app.py

@@ -0,0 +1,45 @@
+import gradio as gr
+from langchain.document_loaders import PyPDFLoader
+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 HuggingFacePipeline
+from transformers import pipeline
+import tempfile
+
+def qa_from_pdf(pdf_file, question):
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp_file:
+        tmp_file.write(pdf_file.read())
+        tmp_path = tmp_file.name
+
+    loader = PyPDFLoader(tmp_path)
+    pages = loader.load()
+
+    splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
+    documents = splitter.split_documents(pages)
+
+    embedding_model = HuggingFaceEmbeddings(model_name='sentence-transformers/all-MiniLM-L6-v2')
+    db = FAISS.from_documents(documents, embedding_model)
+
+    hf_pipeline = pipeline('text-generation', model='tiiuae/falcon-rw-1b', max_length=512)
+    llm = HuggingFacePipeline(pipeline=hf_pipeline)
+
+    qa_chain = RetrievalQA.from_chain_type(llm=llm, retriever=db.as_retriever())
+
+    answer = qa_chain.run(question)
+    return answer
+
+iface = gr.Interface(
+    fn=qa_from_pdf,
+    inputs=[
+        gr.File(label="PDF Dosyası Yükle", file_types=[".pdf"]),
+        gr.Textbox(label="Sorunuzu yazın")
+    ],
+    outputs="text",
+    title="📄 RAG Demo: PDF üzerinden Soru-Cevap",
+    description="Bir PDF yükleyin ve ona sorular sorun. Falcon-RW-1B ile çalışır."
+)
+
+if __name__ == "__main__":
+    iface.launch()