Create app.py

app.py

@@ -0,0 +1,106 @@
+import streamlit as st
+from streamlit_chat import message
+import tempfile
+#from langchain_community.documentloader.csv_loader import CSVLoader
+from langchain_community.document_loaders.csv_loader import CSVLoader
+from langchain_community.embeddings import HuggingFaceEmbeddings
+#from langchain_community.embeddings import HuggingFaceBgeEmbeddings
+from langchain.text_splitter import RecursiveCharacterTextSplitter
+from langchain_community.vectorstores import FAISS
+#from langchain_community.llms import CTransformers
+from langchain_community.llms.ctransformers import CTransformers
+
+from langchain.chains.conversational_retrieval.base import ConversationalRetrievalChain
+                                                            
+#from langchain.chains.conversational_retrieval.base import ConversationalRetreievalChain
+
+
+DB_FAISS_PATH = 'vectorstore/db_faiss'
+
+def load_llm():
+    # load model from hugging face repo
+    llm = CTransformers(
+        model = 'TheBloke/Llama-2-7B-Chat-GGML',
+        model_type = 'llma',
+        max_new_token = 512,
+        temperature = 0.5
+    )
+    return llm
+
+st.title("Chat with CSV using Llma 2")
+st.markdown("<h1 style='text-align: center; color: blue;'>Chat with your PDF 📄 </h1>", unsafe_allow_html=True)
+st.markdown("<h3 style='text-align: center; color: grey;'>Built by <a href='https://github.com/DrKareemKAmal'>MindSparks ❤️ </a></h3>", unsafe_allow_html=True)
+
+uploaded_file = st.sidebar.file_uploader('Upload your data', type=['csv'])
+
+if uploaded_file:
+    with tempfile.NamedTemporaryFile(delete=False)as temp_file :
+        temp_file.write(uploaded_file.getvalue())
+        tempfile_path = temp_file.name
+    
+    loader = CSVLoader(file_path = tempfile_path, encoding = 'utf-8',
+                        csv_args = {'delimiter': ','} )
+    data = loader.load()
+    #st.json(data)
+
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size = 500 , chunk_overlap = 20)
+    text_chunks = text_splitter.split_documents(data)
+    st.write (f"Total text chunks : {len(text_chunks)}")
+
+    embeddings = HuggingFaceEmbeddings(
+        model = 'sentence-transformers/all-MiniLM-L6-v2',
+        model_kwargs = {'device': 'cpu'}
+    )
+
+
+    db = FAISS.from_documents(text_chunks, embeddings)
+    db.save_local (DB_FAISS_PATH)
+    llm = load_llm()
+
+    chain = ConversationalRetrievalChain.from_llm(llm= llm , retriever = db.as_retriever())
+
+    def conversational_chat(query):
+        result  = chain({"quetion": query ,
+                         "chat_history": st.session_state['history']})
+        st.session_state['history'].append((query , result['answer']))
+        return result['answer']
+    
+    if 'history' not in st.session_state :
+        st.session_state['history'] = []
+
+    if 'generated' not in st.session_state :
+        st.session_state['generated'] = ['Hello, Ask me anything about ' + uploaded_file.name]
+
+    if 'past' not in st.session_state :
+        st.session_state['past'] = ['Hey !']
+
+    # Container for the chat history
+    response_container = st.container()
+    container = st.container()
+
+    with container :
+        with st.form(key = 'my_form',
+                     clear_on_submit=True):
+            user_input = st.text_input('Query:', placeholder= "Talk to youur CSV Data here ")
+            submit_button = st.from_submit_button(label = 'chat')
+
+        if submit_button and user_input :
+            output = conversational_chat(user_input)
+
+            st.session_state['past'].append(user_input)
+            st.session_state['generated'].append(output)
+
+        if st.session_state['generated'] :
+            with response_container:
+                for i in range(len(st.session_state['generated'])):
+                    message(st.session_state['past'][i], is_user = True , key=str(i) + '_user',
+                            avatar_style='big-smile')
+                    message(st.session_state['generated'][i], key = str(i), avatar_style='thumb')
+        
+
+
+
+
+
+
+