Update app.py

app.py

@@ -3,18 +3,30 @@ 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_openai import OpenAIEmbeddings, ChatOpenAI
 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
-from dotenv import load_dotenv
+from langchain_community.embeddings import HuggingFaceBgeEmbeddings
+from langchain_community.llms import CTransformers
+from ctransformers import AutoModelForCausalLM
+# from dotenv import load_dotenv
 
-load_dotenv()
+# load_dotenv()
 
 def get_response(user_input):
     return "I dont know"
 
 def get_vector_store_from_url(url):
+    model_name = "BAAI/bge-large-en"
+    model_kwargs = {'device': 'cpu'}
+    encode_kwargs = {'normalize_embeddings': False}
+    embeddings = HuggingFaceBgeEmbeddings(
+        model_name=model_name,
+        model_kwargs=model_kwargs,
+        encode_kwargs=encode_kwargs
+    )
+    
     loader = WebBaseLoader(url)
     document = loader.load()
     
@@ -23,13 +35,24 @@ def get_vector_store_from_url(url):
     document_chunks = text_splitter.split_documents(document)
     
     # create a vectorstore from the chunks
-    vector_store = Chroma.from_documents(document_chunks, OpenAIEmbeddings())
+    # vector_store = Chroma.from_documents(document_chunks, OpenAIEmbeddings())
+    vector_store = Chroma.from_documents(document_chunks, embeddings)
 
     return vector_store
     
 
 def get_context_retriever_chain(vector_store):
-    llm = ChatOpenAI()
+    # llm = ChatOpenAI()
+    llm = CTransformers(
+                    # model = "TheBloke/Mistral-7B-Instruct-v0.2-GGUF",
+                    model= "TheBloke/Llama-2-7B-Chat-GGUF",
+                    model_file = "llama-2-7b-chat.Q3_K_S.gguf",
+                    model_type="llama",
+                    max_new_tokens = 300,
+                    temperature = 0.3,
+                    lib="avx2", # for CPU
+                    )
+
     
     retriever = vector_store.as_retriever()