Update app.py

app.py

@@ -8,13 +8,16 @@ from langchain.vectorstores import FAISS
 from langchain_google_genai import ChatGoogleGenerativeAI
 from langchain.chains.question_answering import load_qa_chain
 from langchain.prompts import PromptTemplate
+from langdetect import detect
 from dotenv import load_dotenv
 from google.api_core.exceptions import GoogleAPIError, InvalidArgument
 
 # Load environment variables
 load_dotenv()
-api_key = os.getenv("GOOGLE_API_KEY")
-genai.configure(api_key=api_key)
+genai.configure(api_key=os.getenv("GOOGLE_API_KEY"))
+# Mock configuration for PersianLLaMA (replace with actual configuration)
+persian_api_key = os.getenv("PERSIAN_LLAMA_API_KEY")
+# persianllama.configure(api_key=persian_api_key)
 
 # Function to read all PDF files and return text
 def get_pdf_text(pdf_docs):
@@ -32,18 +35,23 @@ def get_text_chunks(text):
     chunks = splitter.split_text(text)
     return chunks  # list of strings
 
-# Function to get embeddings for each chunk and save to vector store
-def get_vector_store(chunks):
+# Function to get embeddings for each chunk and save to vector store (language-specific)
+def get_vector_store(chunks, language):
     try:
-        embeddings = GoogleGenerativeAIEmbeddings(
-            model="models/embedding-001")  # type: ignore
+        if language == 'fa':
+            embeddings = PersianLLaMAEmbeddings(
+                model="persianllama-embedding")  # Mock PersianLLaMA embeddings
+        else:
+            embeddings = GoogleGenerativeAIEmbeddings(
+                model="models/embedding-001")  # Gemini embeddings
+
         vector_store = FAISS.from_texts(chunks, embedding=embeddings)
         vector_store.save_local("faiss_index")
     except (GoogleAPIError, InvalidArgument):
         raise RuntimeError("Error processing embeddings. Please try again in a minute.")
 
-# Function to get conversational chain
-def get_conversational_chain():
+# Function to get conversational chain (language-specific)
+def get_conversational_chain(language):
     prompt_template = """
     Answer the question as detailed as possible from the provided context. 
     If the answer is not in the provided context, just say, "answer is not available in the context".
@@ -53,9 +61,13 @@ def get_conversational_chain():
     Answer:
     """
     try:
-        model = ChatGoogleGenerativeAI(model="gemini-pro",
-                                       client=genai,
-                                       temperature=0.3)
+        if language == 'fa':
+            model = PersianLLaMAChat(model="persianllama-chat")  # Mock PersianLLaMA chat
+        else:
+            model = ChatGoogleGenerativeAI(model="gemini-pro",
+                                           client=genai,
+                                           temperature=0.3)
+            
         prompt = PromptTemplate(template=prompt_template,
                                 input_variables=["context", "question"])
         chain = load_qa_chain(llm=model, chain_type="stuff", prompt=prompt)
@@ -68,14 +80,19 @@ def clear_chat_history():
     st.session_state.messages = [
         {"role": "assistant", "content": "Upload some PDFs and ask me a question"}]
 
-# Function to handle user input
-def user_input(user_question):
+# Function to handle user input (language-specific)
+def user_input(user_question, language):
     try:
-        embeddings = GoogleGenerativeAIEmbeddings(
-            model="models/embedding-001")  # type: ignore
+        if language == 'fa':
+            embeddings = PersianLLaMAEmbeddings(
+                model="persianllama-embedding")  # Mock PersianLLaMA embeddings
+        else:
+            embeddings = GoogleGenerativeAIEmbeddings(
+                model="models/embedding-001")  # Gemini embeddings
+
         new_db = FAISS.load_local("faiss_index", embeddings, allow_dangerous_deserialization=True)
         docs = new_db.similarity_search(user_question, k=4)
-        chain = get_conversational_chain()
+        chain = get_conversational_chain(language)
         response = chain(
             {"input_documents": docs, "question": user_question}, return_only_outputs=True)
         return response
@@ -85,7 +102,8 @@ def user_input(user_question):
 # Main function to run the Streamlit app
 def main():
     st.set_page_config(
-        page_title="A ChatBot for Standards ...",
+        page_title="Gemini PDF Chatbot",
+        page_icon="🤖",
         layout="wide",
         initial_sidebar_state="expanded"
     )
@@ -142,48 +160,6 @@ def main():
                 try:
                     with st.spinner("Processing..."):
                         raw_text = get_pdf_text(pdf_docs)
+                        language = detect(raw_text)
                         text_chunks = get_text_chunks(raw_text)
-                        get_vector_store(text_chunks)
-                        st.success("Processing completed!")
-                except RuntimeError as e:
-                    st.error(str(e))
-            else:
-                st.error("Please upload at least one PDF file.")
-
-    # Main content area for displaying chat messages
-    st.title("Gemini PDF Chatbot")
-    st.write("Welcome to the Gemini PDF Chatbot! Upload your PDFs and ask questions.")
-    st.sidebar.button('Clear Chat History', on_click=clear_chat_history)
-
-    # Initialize chat history
-    if "messages" not in st.session_state:
-        st.session_state.messages = [
-            {"role": "assistant", "content": "Upload some PDFs and ask me a question"}]
-
-    # Display chat messages
-    for message in st.session_state.messages:
-        with st.chat_message(message["role"]):
-            st.write(message["content"])
-
-    # Chat input
-    if prompt := st.chat_input():
-        st.session_state.messages.append({"role": "user", "content": prompt})
-        with st.chat_message("user"):
-            st.write(prompt)
-
-        # Generate bot response
-        if st.session_state.messages[-1]["role"] != "assistant":
-            try:
-                with st.chat_message("assistant"):
-                    with st.spinner("Thinking..."):
-                        response = user_input(prompt)
-                        if response:
-                            full_response = ''.join(response['output_text'])
-                            st.write(full_response)
-                            message = {"role": "assistant", "content": full_response}
-                            st.session_state.messages.append(message)
-            except RuntimeError as e:
-                st.error(str(e))
-
-if __name__ == "__main__":
-    main()
+                        get_vector_store(text_chunks, language