Update app.py

app.py

@@ -10,14 +10,11 @@ from langchain.memory import ConversationBufferMemory
 from langchain.document_loaders import PyPDFLoader
 from langchain.document_loaders import TextLoader
 from langchain.document_loaders import Docx2txtLoader
-from transformers import AutoTokenizer, AutoModelForCausalLM
 from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
 import os
 from dotenv import load_dotenv
 import tempfile
 
-import torch
-
 
 load_dotenv()
 
@@ -59,25 +56,18 @@ def display_chat_history(chain):
                 message(st.session_state["past"][i], is_user=True, key=str(i) + '_user', avatar_style="thumbs")
                 message(st.session_state["generated"][i], key=str(i), avatar_style="fun-emoji")
 
-
-
-
-
-
-os.environ['HuggingFaceHub_API_Token']= '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'
-tokenizer = AutoTokenizer.from_pretrained("NousResearch/Nous-Hermes-llama-2-7b")
 def create_conversational_chain(vector_store):
     load_dotenv()
     # Create llm
-    llm = CTransformers(streaming=True,
-                        model = AutoModelForCausalLM.from_pretrained("NousResearch/Nous-Hermes-llama-2-7b", device_map='auto',torch_dtype=torch.float16,load_in_4bit=True), 
-                        callbacks=[StreamingStdOutCallbackHandler()],
-                        model_type="llama", config={'max_new_tokens': 500, 'temperature': 0.01})
-    # llm = Replicate(
-    #     streaming = True,
-    #     model = "NousResearch/Llama-2-7b-hf", 
-    #     callbacks=[StreamingStdOutCallbackHandler()],
-    #     input = {"temperature": 0.01, "max_length" :500,"top_p":1})
+    #llm = CTransformers(model="llama-2-7b-chat.ggmlv3.q4_0.bin",
+                        #streaming=True, 
+                        #callbacks=[StreamingStdOutCallbackHandler()],
+                        #model_type="llama", config={'max_new_tokens': 500, 'temperature': 0.01})
+    llm = Replicate(
+        streaming = True,
+        model = "replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781", 
+        callbacks=[StreamingStdOutCallbackHandler()],
+        input = {"temperature": 0.01, "max_length" :500,"top_p":1})
     memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
 
     chain = ConversationalRetrievalChain.from_llm(llm=llm, chain_type='stuff',
@@ -89,7 +79,7 @@ def main():
     load_dotenv()
     # Initialize session state
     initialize_session_state()
-    st.title("Multi-Docs ChatBot using llama-2-7b :books:")
+    st.title("Multi-Docs ChatBot using llama-2-70b :books:")
     # Initialize Streamlit
     st.sidebar.title("Document Processing")
     uploaded_files = st.sidebar.file_uploader("Upload files", accept_multiple_files=True)
@@ -123,7 +113,7 @@ def main():
                                            model_kwargs={'device': 'cpu'})
 
         # Create vector store
-        vector_store = FAISS.from_documents(text_chunks,embeddings)
+        vector_store = FAISS.from_documents(text_chunks, embedding=embeddings)
 
         # Create the chain object
         chain = create_conversational_chain(vector_store)