Update app.py

initial commit

app.py

@@ -1,11 +1,31 @@
 import gradio as gr
 from huggingface_hub import InferenceClient
+from langchain.chains import RetrievalQA
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.vectorstores import FAISS
+from langchain.llms import HuggingFaceHub
+from langchain.prompts import PromptTemplate
+from langchain.chains import ConversationalRetrievalChain
 
-"""
-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
-"""
+# Load the HuggingFace language model and embeddings
 client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
 
+# Initialize the embeddings model for document retrieval
+embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-mpnet-base-v2")
+
+# Set up FAISS as the vector store for document retrieval
+# (Replace 'documents' with your actual document list or corpus)
+texts = ["Document 1", "Document 2", "Document 3"]
+vector_store = FAISS.from_texts(texts, embeddings)
+
+# Initialize the LangChain RAG system
+retriever = vector_store.as_retriever()
+
+# Set up ConversationalRetrievalChain using LangChain's tools
+rag_chain = ConversationalRetrievalChain.from_llm(
+    HuggingFaceHub(repo_id="HuggingFaceH4/zephyr-7b-beta"),
+    retriever=retriever
+)
 
 def respond(
     message,
@@ -15,49 +35,33 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
-
+    # Combine history with the user message
+    conversation_history = [{"role": "system", "content": system_message}]
+    
     for val in history:
         if val[0]:
-            messages.append({"role": "user", "content": val[0]})
+            conversation_history.append({"role": "user", "content": val[0]})
         if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    messages.append({"role": "user", "content": message})
+            conversation_history.append({"role": "assistant", "content": val[1]})
 
-    response = ""
+    conversation_history.append({"role": "user", "content": message})
 
-    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
+    # Retrieve documents using the retriever
+    response = rag_chain({"question": message, "chat_history": history})
 
-        response += token
-        yield response
+    # Format and return the response
+    return response['answer']
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Gradio interface setup
 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(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+        gr.Slider(minimum=0.1, maximum=1.0, value=0.95, step=0.05, label="Top-p (nucleus sampling)"),
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()