Update app.py

app.py

@@ -1,19 +1,14 @@
 import gradio as gr
-from langchain.document_loaders import PyPDFLoader
+from langchain_community.document_loaders import PyPDFLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain.embeddings import HuggingFaceEmbeddings
-from langchain.vectorstores import FAISS
+from langchain_community.embeddings import HuggingFaceEmbeddings
+from langchain_community.vectorstores import FAISS
 from langchain.chains import RetrievalQA
-from langchain.llms import HuggingFacePipeline
+from langchain_community.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)
+def qa_from_pdf(pdf_path, question):
+    loader = PyPDFLoader(pdf_path)
     pages = loader.load()
 
     splitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)
@@ -23,23 +18,21 @@ def qa_from_pdf(pdf_file, question):
     db = FAISS.from_documents(documents, embedding_model)
 
     hf_pipeline = pipeline('text-generation', model='sshleifer/tiny-gpt2', max_length=100)
-
     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.File(label="PDF Dosyası Yükle", file_types=[".pdf"], type="filepath"),
         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."
+    description="Bir PDF yükleyin ve ona sorular sorun. Küçük dil modeliyle çalışan demo."
 )
 
 if __name__ == "__main__":