Update app.py

app.py

@@ -1,11 +1,10 @@
 import gradio as gr
 import bs4
+from langchain.embeddings.huggingface import HuggingFaceBgeEmbeddings
+from langchain.document_loaders import WebBaseLoader, PyPDFDirectoryLoader
+from langchain.vectorstores import FAISS
 from langchain.text_splitter import RecursiveCharacterTextSplitter
-from langchain_community.document_loaders import WebBaseLoader
-from langchain_community.vectorstores import FAISS
-#from langchain_community.vectorstores import Chroma
-from langchain_community.embeddings import HuggingFaceBgeEmbeddings
-#from langchain_community.embeddings import OllamaEmbeddings
+from transformers import pipeline
 
 # Function to load, split, and retrieve documents from a URL
 def load_and_retrieve_docs(url):
@@ -22,24 +21,9 @@ def load_and_retrieve_docs(url):
     vectorstore = FAISS.from_documents(documents=splits, embedding=embeddings)
     return vectorstore.as_retriever()
 
-# Function to initialize vector embedding with FAISS vector store
-def vector_embedding():
-    if "vectors" not in st.session_state:
-        st.session_state.embeddings = HuggingFaceBgeEmbeddings(model_name="BAAI/bge-small-en-v1.5",
-                                                               model_kwargs={'device':'cpu'},
-                                                               encode_kwargs={'normalize_embeddings':True})
-        st.session_state.loader = PyPDFDirectoryLoader("./Data_Science")  # Data Ingestion
-        st.session_state.docs = st.session_state.loader.load()  # Document Loading
-        st.session_state.text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)  # Chunk Creation
-        st.session_state.final_documents = st.session_state.text_splitter.split_documents(st.session_state.docs[:20])  # Splitting
-        st.session_state.vectors = FAISS.from_documents(st.session_state.final_documents, st.session_state.embeddings)  # Vector HuggingFace embeddings
-        st.write("Vector Store DB Is Ready")
-    else:
-        st.write("Vectors already initialized.")
-
-# Function to format documents
+# Function to format documents into a context string
 def format_docs(docs):
-    return "\n\n".join(doc.page_content for doc in docs)
+    return "\n\n".join([doc['content'] for doc in docs])
 
 # Function that defines the RAG chain
 def rag_chain(url, question):
@@ -49,7 +33,7 @@ def rag_chain(url, question):
     formatted_prompt = f"Question: {question}\n\nContext: {formatted_context}"
     
     # Using HuggingFace transformers for generating response
-    chat_pipeline = pipeline('text-generation', model='Llama3-8b-8192')  # Use the appropriate model here
+    chat_pipeline = pipeline('text-generation', model='gpt-3.5-turbo')  # Use the appropriate model here
     response = chat_pipeline(formatted_prompt, max_length=512, num_return_sequences=1)
     
     return response[0]['generated_text']
@@ -64,4 +48,4 @@ iface = gr.Interface(
 )
 
 # Launch the app
-iface.launch()
+iface.launch()