Update app.py

app.py

@@ -1,52 +1,67 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain_community.document_loaders import PyPDFLoader
+from langchain_text_splitters import RecursiveCharacterTextSplitter
+from langchain import hub
+from langchain_core.output_parsers import StrOutputParser
+from langchain_core.runnables import RunnablePassthrough
+from langchain.chains.combine_documents import create_stuff_documents_chain
+from langchain_core.prompts import ChatPromptTemplate
+from langchain.chains import create_retrieval_chain
 
-"""
-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
-"""
+# Set up Inference Client
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+# Load the vector database
+vectorstore = FAISS.load_local("vectorstore.db")
+retriever = vectorstore.as_retriever()
+
+# Define LLM configuration
+llm = client  # Assuming the model on Hugging Face is used directly via API
+prompt_template = """
+You are an assistant for question-answering tasks.
+Answer the given questions.
+
+<context>
+{context}
+</context>
+
+Question: {input}
+"""
+
+# Function to create the prompt template
+prompt = ChatPromptTemplate.from_template(prompt_template)
+doc_chain = create_stuff_documents_chain(llm, prompt)
+chain = create_retrieval_chain(retriever, doc_chain)
 
+# Chatbot response function
 def respond(
     message,
-    history: list[tuple[str, str]],
+    history,
     system_message,
     max_tokens,
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
+    # Use the RAG model to retrieve relevant context and answer the question
+    response = chain.invoke({"input": message})
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+    # Extract the answer from the response
+    answer = response.get('answer', "Sorry, I couldn't find an answer.")
+    
+    # Add conversation to history
+    history.append((message, answer))
 
-    messages.append({"role": "user", "content": message})
+    # Return the updated history
+    return "", history
 
-    response = ""
-
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Gradio Chat Interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
+        gr.Textbox(value="You are a helpful assistant.", 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(
@@ -59,6 +74,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
     demo.launch()