Update app.py

app.py

@@ -6,10 +6,7 @@ from langchain_core.messages import AIMessage, HumanMessage
 from langchain_community.document_loaders import WebBaseLoader
 from langchain.text_splitter import RecursiveCharacterTextSplitter
 from langchain_community.vectorstores import Chroma
-# from langchain_openai import OpenAIEmbeddings, ChatOpenAI
-from langchain.llms import HuggingFaceHub
 from langchain.embeddings import HuggingFaceEmbeddings
-from dotenv import load_dotenv
 from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
 from langchain.chains import create_history_aware_retriever, create_retrieval_chain
 from langchain.chains.combine_documents import create_stuff_documents_chain
@@ -32,7 +29,11 @@ def get_vectorstore_from_url(url):
     return vector_store
 
 def get_context_retriever_chain(vector_store):
-    llm = HuggingFaceHub(repo_id = "HuggingFaceH4/zephyr-7b-beta", model_kwargs = {"temperature":0.5, "max_length":512})
+    # llm = HuggingFaceHub(repo_id = "HuggingFaceH4/zephyr-7b-beta", model_kwargs = {"temperature":0.5, "max_length":512})
+    llm = HuggingFaceEndpoint(
+    repo_id="HuggingFaceH4/zephyr-7b-beta",
+    task="text-generation",
+    max_new_tokens=512)
     retriever = vector_store.as_retriever()
     
     prompt = ChatPromptTemplate.from_messages([
@@ -46,8 +47,11 @@ def get_context_retriever_chain(vector_store):
     return retriever_chain
     
 def get_conversational_rag_chain(retriever_chain): 
-    llm = HuggingFaceHub(repo_id = "HuggingFaceH4/zephyr-7b-beta", model_kwargs = {"temperature":0.5, "max_length":512})
-    
+    # llm = HuggingFaceHub(repo_id = "HuggingFaceH4/zephyr-7b-beta", model_kwargs = {"temperature":0.5, "max_length":512})
+    llm = HuggingFaceEndpoint(
+    repo_id="HuggingFaceH4/zephyr-7b-beta",
+    task="text-generation",
+    max_new_tokens=512)
     prompt = ChatPromptTemplate.from_messages([
       ("system", "Answer the user's questions based on the below context:\n\n{context}"),
       MessagesPlaceholder(variable_name="chat_history"),
@@ -100,14 +104,10 @@ else:
        
 
     # conversation
-    first = 0
-    for i, message in enumerate(st.session_state.chat_history):
-        if first < 3:
-            first += 1
-        else:
-            if isinstance(message, AIMessage):
-                with st.chat_message("AI"):
-                    st.write(message.content)
-            elif isinstance(message, HumanMessage):
-                with st.chat_message("Human"):
-                    st.write(message.content)
+    for message in st.session_state.chat_history:
+        if isinstance(message, AIMessage):
+            with st.chat_message("AI"):
+                st.write(message.content)
+        elif isinstance(message, HumanMessage):
+            with st.chat_message("Human"):
+                st.write(message.content)