Update app.py

app.py

@@ -8,16 +8,14 @@ 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
+from langdetect import detect
 
 # Load environment variables
 load_dotenv()
-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)
+api_key = os.getenv("GOOGLE_API_KEY")
+genai.configure(api_key=api_key)
 
 # Function to read all PDF files and return text
 def get_pdf_text(pdf_docs):
@@ -30,28 +28,25 @@ def get_pdf_text(pdf_docs):
 
 # Function to split text into chunks
 def get_text_chunks(text):
-    splitter = RecursiveCharacterTextSplitter(
-        chunk_size=10000, chunk_overlap=1000)
+    splitter = RecursiveCharacterTextSplitter(chunk_size=10000, chunk_overlap=1000)
     chunks = splitter.split_text(text)
     return chunks  # list of strings
 
-# Function to get embeddings for each chunk and save to vector store (language-specific)
-def get_vector_store(chunks, language):
-    try:
-        if language == 'fa':
-            embeddings = PersianLLaMAEmbeddings(
-                model="persianllama-embedding")  # Mock PersianLLaMA embeddings
-        else:
-            embeddings = GoogleGenerativeAIEmbeddings(
-                model="models/embedding-001")  # Gemini embeddings
+# Function to detect the language of the text
+def detect_language(text):
+    return detect(text)
 
+# Function to get embeddings for each chunk and save to vector store
+def get_vector_store(chunks, model_name):
+    try:
+        embeddings = GoogleGenerativeAIEmbeddings(model=model_name)  # type: ignore
         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 (language-specific)
-def get_conversational_chain(language):
+# Function to get conversational chain
+def get_conversational_chain(model_name):
     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".
@@ -61,15 +56,8 @@ def get_conversational_chain(language):
     Answer:
     """
     try:
-        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"])
+        model = ChatGoogleGenerativeAI(model=model_name, 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)
         return chain
     except (GoogleAPIError, InvalidArgument):
@@ -80,21 +68,16 @@ def clear_chat_history():
     st.session_state.messages = [
         {"role": "assistant", "content": "Upload some PDFs and ask me a question"}]
 
-# Function to handle user input (language-specific)
-def user_input(user_question, language):
+# Function to handle user input
+def user_input(user_question):
     try:
-        if language == 'fa':
-            embeddings = PersianLLaMAEmbeddings(
-                model="persianllama-embedding")  # Mock PersianLLaMA embeddings
-        else:
-            embeddings = GoogleGenerativeAIEmbeddings(
-                model="models/embedding-001")  # Gemini embeddings
-
+        embeddings = GoogleGenerativeAIEmbeddings(model="models/embedding-001")  # type: ignore
         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(language)
-        response = chain(
-            {"input_documents": docs, "question": user_question}, return_only_outputs=True)
+        language = detect_language(' '.join([doc.page_content for doc in docs]))
+        model_name = "farsi-model" if language == "fa" else "gemini-pro"
+        chain = get_conversational_chain(model_name)
+        response = chain({"input_documents": docs, "question": user_question}, return_only_outputs=True)
         return response
     except (GoogleAPIError, InvalidArgument):
         raise RuntimeError("Error processing request. Please try again in a minute.")
@@ -153,13 +136,56 @@ def main():
     # Sidebar for uploading PDF files
     with st.sidebar:
         st.title("Menu")
-        pdf_docs = st.file_uploader(
-            "Upload your PDF files", accept_multiple_files=True)
+        pdf_docs = st.file_uploader("Upload your PDF files", accept_multiple_files=True)
         if st.button("Submit & Process", key="submit_button"):
             if pdf_docs:
                 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, language
+                        language = detect_language(raw_text)
+                        model_name = "farsi-model" if language == "fa" else "gemini-pro"
+                        get_vector_store(text_chunks, model_name)
+                        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()