Switch to use EU LAW GPT in .env

.env.local

@@ -0,0 +1,11 @@
+# This file is used to store the environment variables that are used in the application
+# Please make sure to create a .env file in the root directory of the project and add the following variables
+
+# OPEN AI API KEY
+OPENAI_API_KEY=
+
+# LAW GPT MODEL URL, please look at https://huggingface.co/codimind for the model url
+LAW_GPT_MODEL_URL=
+
+# Huggingface hub api token
+HUGGINGFACEHUB_API_TOKEN=

.gitignore

@@ -0,0 +1,3 @@
+.env
+__pycache__/
+.DS_Store

app.py

@@ -48,11 +48,15 @@ def get_vector_store(text_chunks):
     return vectorstore
 
 def get_conversation_chain(vectorstore):
-    llm = ChatOpenAI(openai_api_key=os.getenv('OPENAI_API_KEY'))
-   # llm = HuggingFaceHub(repo_id="google/flan-t5-xxl", model_kwargs={"temperature":0.5, "max_length":512})
-#    llm = HuggingFaceHub(repo_id="meta-llama/Meta-Llama-3.1-8B-Instruct", model_kwargs={"temperature":0.5, "max_length":512})
-  #  llm = HuggingFaceHub(repo_id="meta-llama/Meta-Llama-3.1-8B-Instruct")
+    if not os.getenv('OPENAI_API_KEY') and not os.getenv('LAW_GPT_MODEL_URL'):
+        raise ValueError("Please provide either OPENAI_API_KEY or LAW_GPT_MODEL_URL in the .env file")
 
+    # Use LAW GPT model if LAW_GPT_MODEL_URL is provided  
+    if os.getenv('LAW_GPT_MODEL_URL'):
+        llm = HuggingFaceHub(repo_id=os.getenv('LAW_GPT_MODEL_URL'))
+    else:
+        llm = ChatOpenAI(openai_api_key=os.getenv('OPENAI_API_KEY'))
+        
     memory = ConversationBufferMemory(memory_key='chat_history', return_messages=True)
     conversation_chain = ConversationalRetrievalChain.from_llm(
         llm=llm,
@@ -76,12 +80,12 @@ def handle_user_input(user_question):
                 st.write(bot_template.replace(
                     "{{MSG}}", message.content), unsafe_allow_html=True)
     else:
-        st.write("Please upload PDFs and click process")
+        st.write("No data is loaded for RAG. Please upload a PDFs files to the data/ directory.")
 
 def main():
     load_dotenv()
 
-    st.set_page_config(page_title="Onki AI Assistant - Chat with multiple PDFs", page_icon=":books:")
+    st.set_page_config(page_title="EULawGPT - LLM model that can understand and reason about EU public domain data", page_icon=":books:")
     st.write(css, unsafe_allow_html=True)
     
     #load knowledge data PDF
@@ -97,31 +101,21 @@ def main():
     if "chat_history" not in st.session_state:
         st.session_state.chat_history = None
 
-    st.header("Chat with multiple PDFs :books:")
-    user_question = st.text_input("Ask a question about your documents:")
-
-    if user_question:
-        handle_user_input(user_question)
-    
-    with st.sidebar:
-
-        st.subheader("Your documents")
-        pdf_docs = st.file_uploader("Upload your PDFs here and click on 'Process'", accept_multiple_files=True)
-        if st.button("Process"):
-            with st.spinner("Processing"):
-                # get pdf text
-                raw_text = get_pdf_text(pdf_docs)
+    st.title("EU Law GPT")
+    st.write("EU Law GPT is a LLM model that can understand and reason about EU public domain data")
 
-                # get the text chunks
-                text_chunks = get_text_chunks(raw_text)
+    st.subheader('Popular questions:')
+    if st.button("What is happening in Equador?"):
+        handle_user_input("What is happening in Equador?")
 
-                # create vector store
-                vectorstore = get_vector_store(text_chunks)
+    if st.button("What EU will do with Ecuador crisis?"):
+        handle_user_input("What EU will do with Ecuador crisis?")
 
-                vectorstore.merge_from(vectorstore_knowledge)
+    st.subheader('Ask anything:')
+    user_question = st.text_input("Ask a question about EU Law and Parlament work")
 
-                #create conversation chain
-                st.session_state.conversation = get_conversation_chain(vectorstore)
+    if user_question:
+        handle_user_input(user_question)
 
 if __name__ == '__main__':
     main()

htmlTemplates.py

@@ -28,7 +28,8 @@ css = '''
 bot_template = '''
 <div class="chat-message bot">
     <div class="avatar">
-        <img src="https://i.ibb.co/cN0nmSj/Screenshot-2023-05-28-at-02-37-21.png" style="max-height: 78px; max-width: 78px; border-radius: 50%; object-fit: cover;">
+      <img style='display:block; width:100px;height:100px;' id='base64imageBot'
+       src='data:image/svg+xml;base64,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' />
     </div>
     <div class="message">{{MSG}}</div>
 </div>
@@ -37,8 +38,10 @@ bot_template = '''
 user_template = '''
 <div class="chat-message user">
     <div class="avatar">
-        <img src="https://i.ibb.co/rdZC7LZ/Photo-logo-1.png">
+        <img style="display: block; width: 100px; height: 100px;" id="base64imageUser"
+             src="data:image/svg+xml;base64,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" />
     </div>    
     <div class="message">{{MSG}}</div>
 </div>
+
 '''

requirements.txt

@@ -1,9 +1,8 @@
-#unstructured[pdf]
-#python-magic
 streamlit
 python-dotenv
 PyPDF2
 langchain
 langchain_openai
 langchain_community
-faiss-cpu
+faiss-cpu
+huggingface_hub