Upload 2 files

app.py

@@ -0,0 +1,134 @@
+import streamlit as st
+from streamlit_chat import message
+from langchain.chains import ConversationalRetrievalChain
+from langchain.embeddings import HuggingFaceEmbeddings
+from langchain.llms import Replicate
+from langchain.text_splitter import CharacterTextSplitter
+from langchain.vectorstores import FAISS
+from langchain.memory import ConversationBufferMemory
+from langchain.document_loaders import PyPDFLoader, TextLoader, Docx2txtLoader
+from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
+from deep_translator import GoogleTranslator
+import os
+import tempfile
+
+# Initialize session state
+def initialize_session_state():
+    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 about your file 🤖"]
+
+    if 'past' not in st.session_state:
+        st.session_state['past'] = ["Hey! 👋"]
+
+    if 'selected_languages' not in st.session_state:
+        st.session_state['selected_languages'] = []
+
+# Conversation chat function with translation
+def conversation_chat(query, chain, history, selected_languages):
+    translated_queries = [GoogleTranslator(source='auto', target=lang).translate(query) for lang in selected_languages]
+    result = chain({"question": query, "chat_history": history})
+    translated_answers = [GoogleTranslator(source='auto', target=lang).translate(result["answer"]) for lang in selected_languages]
+    history.append((query, result["answer"]))
+    return translated_answers
+
+# Display chat history
+def display_chat_history(chain, selected_languages):
+    reply_container = st.container()
+    container = st.container()
+
+    with container:
+        with st.form(key='my_form', clear_on_submit=True):
+            user_input = st.text_input("Question:", placeholder="Ask about your Documents", key='input')
+            submit_button = st.form_submit_button(label='Send')
+
+        if submit_button and user_input:
+            with st.spinner('Generating response...'):
+                output = conversation_chat(user_input, chain, st.session_state['history'], selected_languages)
+
+            st.session_state['past'].append(user_input)
+            st.session_state['generated'].extend(output)
+
+    if st.session_state['generated']:
+        with reply_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="thumbs")
+                message(st.session_state["generated"][i], key=str(i), avatar_style="bottts")
+
+# Create conversational chain
+def create_conversational_chain(vector_store):
+    replicate_api_token = "r8_47kvoIaHBIPYgBBoiGSrmoTN3cgazu71MyjHh"
+    os.environ["REPLICATE_API_TOKEN"] = replicate_api_token
+
+    llm = Replicate(
+        streaming=True,
+        model="replicate/llama-2-70b-chat:58d078176e02c219e11eb4da5a02a7830a283b14cf8f94537af893ccff5ee781",
+        callbacks=[StreamingStdOutCallbackHandler()],
+        input={"temperature": 0.01, "max_length": 500, "top_p": 1},
+        replicate_api_token=replicate_api_token
+    )
+    memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
+
+    chain = ConversationalRetrievalChain.from_llm(llm=llm, chain_type='stuff',
+                                                  retriever=vector_store.as_retriever(search_kwargs={"k": 2}),
+                                                  memory=memory)
+    return chain
+
+# Main function
+def main():
+    initialize_session_state()
+
+    # Header and Tagline
+    st.title("LANGSMITH BOT")
+    st.subheader("Your Professional Assistant for Document Insights")
+
+    # Main interface
+    st.sidebar.title("Document Processing 📂")
+    uploaded_files = st.sidebar.file_uploader("Upload files", accept_multiple_files=True)
+
+    languages = ["en", "es", "fr", "de", "it", "pt", "zh", "ja", "ko", "hi", "sa"]
+    language_labels = {
+        "en": "English", "es": "Spanish", "fr": "French", "de": "German",
+        "it": "Italian", "pt": "Portuguese", "zh": "Chinese", "ja": "Japanese",
+        "ko": "Korean", "hi": "Hindi", "sa": "Sanskrit"
+    }
+    selected_languages = st.sidebar.multiselect("Select languages for conversation", languages, format_func=lambda x: language_labels[x])
+    st.session_state['selected_languages'] = selected_languages
+
+    if uploaded_files:
+        text = []
+        for file in uploaded_files:
+            file_extension = os.path.splitext(file.name)[1]
+            with tempfile.NamedTemporaryFile(delete=False) as temp_file:
+                temp_file.write(file.read())
+                temp_file_path = temp_file.name
+
+            loader = None
+            if file_extension == ".pdf":
+                loader = PyPDFLoader(temp_file_path)
+            elif file_extension == ".docx" or file_extension == ".doc":
+                loader = Docx2txtLoader(temp_file_path)
+            elif file_extension == ".txt":
+                loader = TextLoader(temp_file_path)
+
+            if loader:
+                text.extend(loader.load())
+                os.remove(temp_file_path)
+
+        text_splitter = CharacterTextSplitter(separator="\n", chunk_size=1000, chunk_overlap=100, length_function=len)
+        text_chunks = text_splitter.split_documents(text)
+
+        embeddings = HuggingFaceEmbeddings(model_name="sentence-transformers/all-MiniLM-L6-v2",
+                                           model_kwargs={'device': 'cpu'})
+        vector_store = FAISS.from_documents(text_chunks, embedding=embeddings)
+        chain = create_conversational_chain(vector_store)
+        display_chat_history(chain, st.session_state['selected_languages'])
+
+# Add a footer
+st.markdown("---")
+st.markdown("Team Chandrama: Shine with Glory!!!! ✨🚀")
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,16 @@
+langchain
+torch
+accelerate
+sentence_transformers
+streamlit_chat
+streamlit
+faiss-cpu
+tiktoken
+ctransformers
+huggingface-hub
+pypdf
+python-dotenv
+replicate
+docx2txt
+langchain-community
+deep-translator