Update app.py

app.py

@@ -5,6 +5,7 @@ from langchain.vectorstores import FAISS
 from langchain.embeddings import HuggingFaceEmbeddings
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain.document_loaders import PyPDFLoader
+from langchain_community.llms import HuggingFaceHub
 import tempfile
 
 # Initialize global variables
@@ -15,29 +16,26 @@ retrieval_chain = None
 def process_pdf(file):
     global vectorstore, retrieval_chain
 
-    # `file` is a gradio.NamedString → use file.name to get the path
-    tmp_path = file.name  
-
-    # Load PDF
+    tmp_path = file.name
     loader = PyPDFLoader(tmp_path)
     documents = loader.load()
 
-    # Split into chunks
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
     docs = text_splitter.split_documents(documents)
 
-    # Create embeddings and FAISS vectorstore
-    embeddings = HuggingFaceEmbeddings()
+    embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
     vectorstore = FAISS.from_documents(docs, embeddings)
 
-    # Setup retrieval chain
-    retriever = vectorstore.as_retriever()
-    retriever.search_kwargs["k"] = 4
+    retriever = vectorstore.as_retriever(search_kwargs={"k": 4})
 
-    client = InferenceClient(model="deepseek-ai/DeepSeek-R1-0528")
+    # ✅ Wrap DeepSeek model properly
+    llm = HuggingFaceHub(
+        repo_id="deepseek-ai/DeepSeek-R1-0528",
+        model_kwargs={"temperature": 0.7, "max_new_tokens": 512}
+    )
 
     retrieval_chain = ConversationalRetrievalChain.from_llm(
-        llm=client,
+        llm=llm,
         retriever=retriever,
         return_source_documents=True
     )