Update app.py

app.py

@@ -1,5 +1,50 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+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
+import tempfile
+
+# Initialize global variables
+vectorstore = None
+retrieval_chain = None
+
+
+def process_pdf(file):
+    global vectorstore, retrieval_chain
+
+    # Save uploaded PDF temporarily
+    with tempfile.NamedTemporaryFile(delete=False, suffix=".pdf") as tmp:
+        tmp.write(file.read())
+        tmp_path = tmp.name
+
+    # Load PDF
+    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()
+    vectorstore = FAISS.from_documents(docs, embeddings)
+
+    # Setup retrieval chain with HuggingFace inference client
+    retriever = vectorstore.as_retriever()
+    retriever.search_kwargs["k"] = 4
+
+    client = InferenceClient(model="deepseek-ai/DeepSeek-R1-0528")
+
+    retrieval_chain = ConversationalRetrievalChain.from_llm(
+        llm=client,
+        retriever=retriever,
+        return_source_documents=True
+    )
+
+    return "PDF processed. You can now ask questions!"
 
 
 def respond(
@@ -11,38 +56,19 @@ def respond(
     top_p,
     hf_token: gr.OAuthToken,
 ):
-    """
-    For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-    """
-    client = InferenceClient(token=hf_token.token, model="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
+    global retrieval_chain
 
-    messages.append({"role": "user", "content": message})
+    if retrieval_chain is None:
+        return "Please upload a PDF first."
 
-    response = ""
+    # Reformat history for LangChain
+    chat_history = [(h["content"], h.get("response", "")) for h in history if h["role"] == "user"]
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+    result = retrieval_chain({"question": message, "chat_history": chat_history})
 
-        response += token
-        yield response
+    return result["answer"]
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 chatbot = gr.ChatInterface(
     respond,
     type="messages",
@@ -63,6 +89,8 @@ chatbot = gr.ChatInterface(
 with gr.Blocks() as demo:
     with gr.Sidebar():
         gr.LoginButton()
+        pdf_upload = gr.File(label="Upload PDF", file_types=[".pdf"])
+        pdf_upload.upload(process_pdf, inputs=pdf_upload, outputs=[])
     chatbot.render()