Update app.py

app.py

@@ -7,14 +7,7 @@
 
 from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
 from langchain.llms import HuggingFaceHub
-model_name = "bn22/Mistral-7B-Instruct-v0.1-sharded"
-
-###### other models:
-# "Trelis/Llama-2-7b-chat-hf-sharded-bf16"
-# "bn22/Mistral-7B-Instruct-v0.1-sharded"
-# "HuggingFaceH4/zephyr-7b-beta"
-
-# function for loading 4-bit quantized model
+ 
 def load_model(model_name: str):
 
     model =  HuggingFaceHub(
@@ -22,23 +15,7 @@ def load_model(model_name: str):
         model_kwargs={"max_length": 1048, "temperature":0.2, "max_new_tokens":256, "top_p":0.95, "repetition_penalty":1.0},
     )
 
-    """
-    :param model_name: Name or path of the model to be loaded.
-    :return: Loaded quantized model.
-    
-    bnb_config = BitsAndBytesConfig(
-        load_in_4bit=True,
-        bnb_4bit_use_double_quant=True,
-        bnb_4bit_quant_type="nf4",
-        bnb_4bit_compute_dtype=torch.bfloat16
-    )
-
-    model = AutoModelForCausalLM.from_pretrained(
-        model_name,
-        load_in_4bit=True,
-        torch_dtype=torch.bfloat16,
-        quantization_config=bnb_config
-    )"""
+ 
     return model
 
 ##################################################
@@ -51,8 +28,7 @@ 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.embeddings import HuggingFaceBgeEmbeddings
 from langchain.vectorstores.faiss import FAISS
 
@@ -67,8 +43,8 @@ load_dotenv()
 
 from langchain_community.document_loaders import TextLoader
 
-def load_txt():
-    loader = TextLoader("./a.cv.ckaller.2024.txt")
+def load_txt(path="./a.cv.ckaller.2024.txt"):
+    loader = TextLoader(path)
     document = loader.load()
    # split the document into chunks
     text_splitter = RecursiveCharacterTextSplitter()
@@ -100,7 +76,7 @@ def load_txt():
     return vector_store
 
 
-def get_vectorstore_from_url(url):
+def get_vectorstore_from_url(url="https://huggingface.co/Chris4K"):
     # get the text in document form
     loader = WebBaseLoader(url)
     document = loader.load()
@@ -216,7 +192,7 @@ def get_response(user_input):
     
 
     #vs = get_vectorstore_from_url(user_url, all_domain)
-    vs = get_vectorstore_from_url("https://huggingface.co/Chris4K")
+    vs = get_vectorstore_from_url()
    # print("------ here 22 " )
     chat_history =[]
     retriever_chain = get_context_retriever_chain(vs)
@@ -248,6 +224,7 @@ def get_response(message, history):
     dialog = history_to_dialog_format(history)
     dialog.append({"role": "user", "content": message})
 
+    print(dialog)
       # Define the prompt as a ChatPromptValue object
     #user_input = ChatPromptValue(user_input)