Update app.py

app.py

@@ -1,96 +1,75 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+
+from langchain_community.vectorstores import FAISS
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_community.embeddings import HuggingFaceEmbeddings
 from langchain.chains import ConversationalRetrievalChain
-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
-vectorstore = None
+from langchain_huggingface import HuggingFaceEndpoint
+
 retrieval_chain = None
+chat_history = []
 
 
-def process_pdf(file):
-    global vectorstore, retrieval_chain
+def process_pdf(file, hf_token):
+    global retrieval_chain
 
-    tmp_path = file.name
-    loader = PyPDFLoader(tmp_path)
+    # Load and split PDF
+    loader = PyPDFLoader(file.name)
     documents = loader.load()
 
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
-    docs = text_splitter.split_documents(documents)
-
+    # Embed with sentence transformers
     embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2")
-    vectorstore = FAISS.from_documents(docs, embeddings)
-
-    retriever = vectorstore.as_retriever(search_kwargs={"k": 4})
+    vectorstore = FAISS.from_documents(documents, embeddings)
 
-    # ✅ Wrap DeepSeek model properly
-    llm = HuggingFaceHub(
+    # Use HuggingFaceEndpoint instead of HuggingFaceHub
+    llm = HuggingFaceEndpoint(
         repo_id="deepseek-ai/DeepSeek-R1-0528",
-        model_kwargs={"temperature": 0.7, "max_new_tokens": 512}
+        huggingfacehub_api_token=hf_token,
+        task="text-generation",
     )
 
     retrieval_chain = ConversationalRetrievalChain.from_llm(
         llm=llm,
-        retriever=retriever,
-        return_source_documents=True
+        retriever=vectorstore.as_retriever()
     )
 
     return "PDF processed. You can now ask questions!"
 
 
-def respond(
-    message,
-    history: list[dict[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-    hf_token: gr.OAuthToken,
-):
-    global retrieval_chain
+def respond(message, history: list[dict[str, str]], hf_token: gr.OAuthToken):
+    global retrieval_chain, chat_history
 
     if retrieval_chain is None:
         return "Please upload a PDF first."
 
-    # Reformat history for LangChain
-    chat_history = [(h["content"], h.get("response", "")) for h in history if h["role"] == "user"]
-
-    result = retrieval_chain({"question": message, "chat_history": chat_history})
-
-    return result["answer"]
+    # Use invoke() instead of deprecated __call__
+    result = retrieval_chain.invoke({
+        "question": message,
+        "chat_history": chat_history
+    })
 
+    answer = result["answer"]
+    chat_history.append((message, answer))
+    return answer
 
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
-        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
-        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
-        gr.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
 
 with gr.Blocks() as demo:
     with gr.Sidebar():
-        gr.LoginButton()
+        hf_login = gr.LoginButton()
         pdf_upload = gr.File(label="Upload PDF", file_types=[".pdf"])
-        status = gr.Textbox(label="Status", interactive=False)
-        pdf_upload.upload(process_pdf, inputs=pdf_upload, outputs=status)
+        status_box = gr.Textbox(label="Status", interactive=False)
 
-    chatbot.render()
+    chatbot = gr.ChatInterface(
+        respond,
+        type="messages"
+    )
 
+    pdf_upload.upload(
+        fn=lambda file, token: process_pdf(file, token.token),
+        inputs=[pdf_upload, hf_login],
+        outputs=[status_box]
+    )
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()