Uppdated with credentials

app.py

@@ -32,6 +32,7 @@ from langchain.memory import ConversationBufferMemory
 from langchain.prompts import PromptTemplate
 import joblib
 import nltk
+import json
 
 import nest_asyncio  # noqa: E402
 nest_asyncio.apply()
@@ -49,8 +50,6 @@ groq_api_key=os.getenv('GROQ_API_KEY')
 
 st.set_page_config(layout="wide")
 
-nltk.download('averaged_perceptron_tagger')
-
 css = """
 <style>
     [data-testid="stAppViewContainer"] {
@@ -106,10 +105,55 @@ css = """
 """
 
 st.write(css, unsafe_allow_html=True)
-st.sidebar.image('lt.png', width=250)
+#--------------
+def load_credentials(filepath):
+    with open(filepath, 'r') as file:
+        return json.load(file)
+
+# Load credentials from 'credentials.json'
+credentials = load_credentials('Assets/credentials.json')
+
+# Initialize session state if not already done
+if 'logged_in' not in st.session_state:
+    st.session_state.logged_in = False
+    st.session_state.username = ''
+
+# Function to handle login
+def login(username, password):
+    if username in credentials and credentials[username] == password:
+        st.session_state.logged_in = True
+        st.session_state.username = username
+        st.rerun()  # Rerun to reflect login state
+    else:
+        st.session_state.logged_in = False
+        st.session_state.username = ''
+        st.error("Invalid username or password.")
+
+# Function to handle logout
+def logout():
+    st.session_state.logged_in = False
+    st.session_state.username = ''
+    st.rerun()  # Rerun to reflect logout state
+
+# If not logged in, show login form
+if not st.session_state.logged_in:
+    st.sidebar.write("Login")
+    username = st.sidebar.text_input('Username')
+    password = st.sidebar.text_input('Password', type='password')
+    if st.sidebar.button('Login'):
+        login(username, password)
+    # Stop the script here if the user is not logged in
+    st.stop()
+
+# If logged in, show logout button and main content
+if st.session_state.logged_in:
+    st.sidebar.write(f"Welcome, {st.session_state.username}!")
+    if st.sidebar.button('Logout'):
+        logout()
+
 #------------- 
 llm=ChatGroq(groq_api_key=groq_api_key,
-             model_name="Llama-3.1-70b-Versatile", temperature = 0.0, streaming=True)   
+             model_name="llama-3.2-90b-text-preview", temperature = 0.0, streaming=True)   
 #--------------
 doc_retriever_ESG = None
 doc_retriever_financials = None
@@ -120,7 +164,10 @@ def load_or_parse_data_ESG():
     data_file = "./data/parsed_data_ESG.pkl"
 
     parsingInstructionUber10k = """The provided document contain detailed information about the company's environmental, social and governance matters.
-    It contains several tables, figures and statistical information. You must be precise while answering the questions and never provide false numeric or statistical data."""
+    It contains several tables, figures and statistical information about CO2 emissions and energy consumption. 
+    Give only precide CO2 and energy consumotion levels inly from the context documents. 
+    You must never provide false numeric or statistical data that is not included in the context document.
+    Include tables and numeric data always when possible. Only refer to other sources if the context document refers to them or if necessary to provide additional understanding to company's own data."""
 
     parser = LlamaParse(api_key=LLAMA_PARSE_API_KEY,
                         result_type="markdown",
@@ -167,31 +214,6 @@ def load_or_parse_data_financials():
 
     return parsed_data_financials
 
-#@st.cache_data
-def load_or_parse_data_portfolio():
-    data_file = "./data/parsed_data_portfolio.pkl"
-
-    parsingInstructionUber10k = """The provided document is the ESG and sustainability report of LocalTapiola (Lähitapiola) group including the funds it manages.
-    It contains several tabless, figures and statistical information. You must be precise while answering the questions and never provide false numeric or statistical data."""
-
-    parser = LlamaParse(api_key=LLAMA_PARSE_API_KEY,
-                        result_type="markdown",
-                        parsing_instruction=parsingInstructionUber10k,
-                        max_timeout=5000,
-                        gpt4o_mode=True,
-                        )
-
-    file_extractor = {".pdf": parser}
-    reader = SimpleDirectoryReader("./ESG_Documents_Portfolio", file_extractor=file_extractor)
-    documents = reader.load_data()
-
-    print("Saving the parse results in .pkl format ..........")
-    joblib.dump(documents, data_file)
-
-    # Set the parsed data to the variable
-    parsed_data_portfolio = documents
-
-    return parsed_data_portfolio
 #--------------
 # Create vector database
 
@@ -206,42 +228,32 @@ def create_vector_database_ESG():
 
     markdown_path = "data/output_ESG.md"
     loader = UnstructuredMarkdownLoader(markdown_path)
-
-    #loader = DirectoryLoader('data/', glob="**/*.md", show_progress=True)
     documents = loader.load()
     # Split loaded documents into chunks
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=15)
+    text_splitter = RecursiveCharacterTextSplitter(chunk_size=400, chunk_overlap=30)
     docs = text_splitter.split_documents(documents)
 
     #len(docs)
     print(f"length of documents loaded: {len(documents)}")
     print(f"total number of document chunks generated :{len(docs)}")
     embed_model = HuggingFaceEmbeddings()
-    #embed_model = OpenAIEmbeddings()
-    # Create and persist a Chroma vector database from the chunked documents
-    # Set up the Chroma client in local mode
-    print('Vector DB not yet created !')
-    persist_directory = os.path.join(os.getcwd(), "chroma_db_LT")
-    if not os.path.exists(persist_directory):
-        os.makedirs(persist_directory)
 
     vs = Chroma.from_documents(
         documents=docs,
         embedding=embed_model,
-        persist_directory=persist_directory,  # Local mode with in-memory storage only
         collection_name="rag",
     )
-
     doc_retriever_ESG = vs.as_retriever()
-    
-    print('Vector DB created successfully !')
-    return doc_retriever_ESG
+
+    index = VectorStoreIndex.from_documents(llama_parse_documents)
+    query_engine = index.as_query_engine()
+
+    return doc_retriever_ESG, query_engine
 
 @st.cache_resource
 def create_vector_database_financials():
     # Call the function to either load or parse the data
     llama_parse_documents = load_or_parse_data_financials()
-    print(llama_parse_documents[0].text[:300])
 
     with open('data/output_financials.md', 'a') as f:  # Open the file in append mode ('a')
         for doc in llama_parse_documents:
@@ -249,69 +261,25 @@ def create_vector_database_financials():
 
     markdown_path = "data/output_financials.md"
     loader = UnstructuredMarkdownLoader(markdown_path)
-
-   #loader = DirectoryLoader('data/', glob="**/*.md", show_progress=True)
     documents = loader.load()
-    # Split loaded documents into chunks
     text_splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=15)
     docs = text_splitter.split_documents(documents)
 
-    #len(docs)
-    print(f"length of documents loaded: {len(documents)}")
-    print(f"total number of document chunks generated :{len(docs)}")
     embed_model = HuggingFaceEmbeddings()
-    #embed_model = OpenAIEmbeddings()
-    # Create and persist a Chroma vector database from the chunked documents
-    persist_directory = os.path.join(os.getcwd(), "chroma_db_fin")
-    if not os.path.exists(persist_directory):
-        os.makedirs(persist_directory)
 
     vs = Chroma.from_documents(
         documents=docs,
         embedding=embed_model,
-        persist_directory=persist_directory,  # Local mode with in-memory storage only
         collection_name="rag"
     )
     doc_retriever_financials = vs.as_retriever()
 
-    print('Vector DB created successfully !')
-    return doc_retriever_financials
-
-@st.cache_resource
-def create_vector_database_portfolio():
-    # Call the function to either load or parse the data
-    llama_parse_documents = load_or_parse_data_portfolio()
-    print(llama_parse_documents[0].text[:300])
-
-    with open('data/output_portfolio.md', 'a') as f:  # Open the file in append mode ('a')
-        for doc in llama_parse_documents:
-            f.write(doc.text + '\n')
-
-    markdown_path = "data/output_portfolio.md"
-    loader = UnstructuredMarkdownLoader(markdown_path)
-
-    documents = loader.load()
-    text_splitter = RecursiveCharacterTextSplitter(chunk_size=100, chunk_overlap=15)
-    docs = text_splitter.split_documents(documents)
-
-    print(f"length of documents loaded: {len(documents)}")
-    print(f"total number of document chunks generated :{len(docs)}")
-    embed_model = HuggingFaceEmbeddings()
-
-    persist_directory = os.path.join(os.getcwd(), "chroma_db_portfolio")
-    if not os.path.exists(persist_directory):
-        os.makedirs(persist_directory)
-
-    vs = Chroma.from_documents(
-        documents=docs,
-        embedding=embed_model,
-        persist_directory=persist_directory,  # Local mode with in-memory storage only
-        collection_name="rag"
-    )
-    doc_retriever_portfolio = vs.as_retriever()
+    index = VectorStoreIndex.from_documents(llama_parse_documents)
+    query_engine_financials = index.as_query_engine()
 
     print('Vector DB created successfully !')
-    return doc_retriever_portfolio
+    return doc_retriever_financials, query_engine_financials
+
 #--------------
 ESG_analysis_button_key = "ESG_strategy_button"
 portfolio_analysis_button_key = "portfolio_strategy_button"
@@ -333,7 +301,6 @@ def delete_files_and_folders(folder_path):
 
 uploaded_files_ESG = st.sidebar.file_uploader("Choose a Sustainability Report", accept_multiple_files=True, key="ESG_files")
 for uploaded_file in uploaded_files_ESG:
-    #bytes_data = uploaded_file.read()
     st.write("filename:", uploaded_file.name)
     def save_uploadedfile(uploadedfile):
      with open(os.path.join("ESG_Documents",uploadedfile.name),"wb") as f:
@@ -343,7 +310,6 @@ for uploaded_file in uploaded_files_ESG:
 
 uploaded_files_financials = st.sidebar.file_uploader("Choose an Annual Report", accept_multiple_files=True, key="financial_files")
 for uploaded_file in uploaded_files_financials:
-    #bytes_data = uploaded_file.read()
     st.write("filename:", uploaded_file.name)
     def save_uploadedfile(uploadedfile):
      with open(os.path.join("Financial_Documents",uploadedfile.name),"wb") as f:
@@ -353,7 +319,7 @@ for uploaded_file in uploaded_files_financials:
 
 #---------------
 def ESG_strategy():
-    doc_retriever_ESG = create_vector_database_ESG()
+    doc_retriever_ESG, _ = create_vector_database_ESG()
     prompt_template = """<|system|>
     You are a seasoned specialist in environmental, social and governance matters. You write expert analyses for institutional investors. Always use figures, nemerical and statistical data when possible. Output must have sub-headings in bold font and be fluent.<|end|>
     <|user|>
@@ -372,18 +338,19 @@ def ESG_strategy():
     | StrOutputParser()
 )   
 
-    ESG_answer_1 = qa.invoke("Give a summary what ESG measures the company has taken and compare these to the best practices. Has the company issues green bonds or green loans.")
-    ESG_answer_2 = qa.invoke("Do the company's main business fall under the European Union's taxonomy regulation? Is the company taxonomy compliant under European Union Taxonomy Regulation? Does the company follow the Paris Treaty's obligation to limit globabl warming to 1.5 celcius degrees? What are the measures to achieve this goal")
-    ESG_answer_3 = qa.invoke("Explain what items of ESG information the company publishes. Describe what ESG transparency commitments the company has given?")
-    ESG_answer_4 = qa.invoke("Does the company have carbon emissions reduction plan? Set out in a table the company's carbon footprint by location and its development over time. Set out carbon dioxide emissions in relation to turnover and whether the company has reached its carbod dioxide reduction objectives")
-    ESG_answer_5 = qa.invoke("Describe and give a time series table of the company's carbon dioxide emissions (Scope 1), carbon dioxide emissions from purchased energy (Scope 2) and other indirect carbon dioxide emissions (Scope 3). Set out the company's objectives and material developments relating to these figures")
-    ESG_answer_6 = qa.invoke("Set out in a table the company's energy and renewable energy usage for each activity coverning the last two or three years. Explain the energy efficiency measures taken by the company. Does the company have a plan to make its use of energy greemer?.")
+    ESG_answer_1 = qa.invoke("Give a summary what specific ESG measures the company has taken recently and compare these to the best practices.")
+    ESG_answer_2 = qa.invoke("Does the company's main business fall under the European Union's taxonomy regulation? Is the company taxonomy compliant under European Union Taxonomy Regulation?")
+    ESG_answer_3 = qa.invoke("Explain what items of ESG information the company publishes. Describe what ESG transparency commitments the company has given. Does the company follow the Paris Treaty's obligation to limit globabl warming to 1.5 celcius degrees?")
+    ESG_answer_4 = qa.invoke("Does the company have carbon emissions reduction plan and has the company reached its carbod dioxide reduction objectives? Set out in a table the company's carbon footprint by location and its development from the context. Set out carbon dioxide emissions in relation to turnover.")
+    ESG_answer_5 = qa.invoke("Describe and set out in a table the following carbon emissions figures: (i) Scope 1 CO2 emissions, (ii) Scope 2 CO2, and (iii) Scope 3 CO2 emissions. Set out the material changes relating to these figures.")
+    ESG_answer_6 = qa.invoke("Set out in a table the company's energy and renewable energy usage for each material activity coverning the available years. Explain the energy efficiency measures taken by the company.")
     ESG_answer_7 = qa.invoke("Does the company follow UN Guiding Principles on Business and Human Rights, ILO Declaration on Fundamental Principles and Rights at Work or OECD Guidelines for Multinational Enterprises that involve affected communities? Set out the measures taken to have the gender balance on the upper management of the company.")
     ESG_answer_8 = qa.invoke("List the environmental permits and certifications held by the company. Set out and explain any environmental procedures and investigations and decisions taken against the company. Answer whether the company's locations or operations are connected to areas sensitive in relation to biodiversity.")
     ESG_answer_9 = qa.invoke("Set out waste produces by the company and possible waste into the soil by real estate. Describe if the company's real estates have hazardous waste.")
-    ESG_answer_10 = qa.invoke("What policies has the company implemented to counter money laundering and corruption? What percentage of women are represented in the board, executive directors and upper management?")
+    ESG_answer_10 = qa.invoke("What percentage of women are represented in the (i) board, (ii) executive directors and (iii) upper management?")
+    ESG_answer_11 = qa.invoke("What policies has the company implemented to counter money laundering and corruption?")
 
-    ESG_output = f"**__Summary of  ESG reporting and obligations:__** {ESG_answer_1} \n\n **__Compliance with taxonomy:__** \n\n {ESG_answer_2} \n\n **__Disclosure transparency:__** \n\n {ESG_answer_3} \n\n **__Carbon footprint:__** \n\n {ESG_answer_4} \n\n **__Carbon dioxide emissions:__** \n\n {ESG_answer_5} \n\n **__Renewable energy:__** \n\n {ESG_answer_6} \n\n **__Human rights compliance:__** \n\n {ESG_answer_7} \n\n **__Management and gender balance:__** \n\n {ESG_answer_8} \n\n **__Waste and other emissions:__** {ESG_answer_9} \n\n **__Money laundering and corruption:__** {ESG_answer_10}"
+    ESG_output = f"**__Summary of  ESG reporting and obligations:__** {ESG_answer_1} \n\n **__Compliance with taxonomy:__** \n\n {ESG_answer_2} \n\n **__Disclosure transparency:__** \n\n {ESG_answer_3} \n\n **__Carbon footprint:__** \n\n {ESG_answer_4} \n\n **__Carbon dioxide emissions:__** \n\n {ESG_answer_5} \n\n **__Renewable energy:__** \n\n {ESG_answer_6} \n\n **__Human rights compliance:__** \n\n {ESG_answer_7} \n\n **__Management and gender balance:__** \n\n {ESG_answer_8} \n\n **__Waste and other emissions:__** {ESG_answer_9} \n\n **__Gender equality:__** {ESG_answer_10} \n\n **__Anti-money laundering:__** {ESG_answer_11}"
     financial_output = ESG_output
     
     with open("ESG_analysis.txt", 'w') as file:
@@ -391,68 +358,6 @@ def ESG_strategy():
     
     return financial_output
 
-def portfolio_strategy():
-    persist_directory_ESG = "chroma_db_LT"
-    embeddings = HuggingFaceEmbeddings()
-    doc_retriever_ESG = Chroma(persist_directory=persist_directory_ESG, embedding_function=embeddings).as_retriever()
-
-    doc_retriever_portfolio = create_vector_database_portfolio()
-    prompt_portfolio = PromptTemplate.from_template(
-        template="""<|system|>
-            You are a seasoned finance specialist and a specialist in environmental, social and governance matters. You write expert portofolion analyses fund management. Always use figures, numerical and statistical data when possible. Output must have sub-headings in bold font and be fluent.<|end|>
-            <|user|> Based on the {context}, write a summary of LähiTapiola's investment policy. Set out also the most important ESG and sustainability aspects of the policy.<|end|>"\
-            <|assistant|>""")
-    
-    prompt_strategy = PromptTemplate.from_template(
-        template="""<|system|>
-            You are a seasoned specialist in environmental, social and governance matters. You analyse companies' ESG matters. Always use figures, numerical and statistical data when possible. Output must have sub-headings in bold font and be fluent.<|end|>
-            <|user|> Based on the {context}, give a summary of the target company's ESG policy. Set out also the most important ESG and sustainability aspects of the policy.<|end|>"\
-            <|assistant|>""")
-    
-    prompt_analysis = PromptTemplate.from_template(
-        template="""<|system|>
-            You are a seasoned finance specialist and a specialist in environmental, social and governance matters. You write expert portofolio analyses fund management. Always use figures, numerical and statistical data when possible. Output must have sub-headings in bold font and be fluent.<|end|>
-            <|user|> Answer the {question} based on {company_ESG} and {fund_policy}.<|end|>"\
-            <|assistant|>""")
-    
-    portfolio_chain = (
-            {
-            "context": doc_retriever_portfolio,
-            #"question": RunnablePassthrough(),
-            }
-            | prompt_portfolio
-            | llm
-            | StrOutputParser()
-            )
-    strategy_chain = (
-            {
-            "context": doc_retriever_ESG,
-            #"question": RunnablePassthrough(),
-            }
-            | prompt_strategy
-            | llm
-            | StrOutputParser()
-            )
-    
-    analysis_chain = (
-        {
-            "company_ESG": strategy_chain, 
-            "fund_policy": portfolio_chain, 
-            "question": RunnablePassthrough(),
-        }
-        | prompt_analysis
-        | llm
-        | StrOutputParser()
-            )
-
-    portfolio_answer = analysis_chain.invoke("is the company's ESG such that it fits within LähiTapiola's investment policy of: {fund_policy}? Give a policy rating")
-    portfolio_output = f"**__Summary of fit with LähiTapiola's sustainability policy:__** {portfolio_answer} \n"
-    
-    with open("portfolio_analysis.txt", 'w') as file:
-        file.write(portfolio_output)
-
-    return portfolio_output
-
 #-------------
 @st.cache_data
 def generate_ESG_strategy() -> str:
@@ -460,11 +365,6 @@ def generate_ESG_strategy() -> str:
     st.session_state.results["ESG_analysis_button_key"] = ESG_output
     return ESG_output
 
-@st.cache_data
-def generate_portfolio_analysis() -> str:
-    portfolio_output = portfolio_strategy()
-    st.session_state.results["portfolio_analysis_button_key"] = portfolio_output
-    return portfolio_output
 #---------------
 #@st.cache_data
 def create_pdf():
@@ -473,8 +373,8 @@ def create_pdf():
     pdf.add_page()
     pdf.set_margins(10, 10, 10)
     pdf.set_font("Arial", size=15)
-    image = "lt.png"
-    pdf.image(image, w = 40)
+    #image = "lt.png"
+    #pdf.image(image, w = 40)
     # Add introductory lines
     #pdf.cell(0, 10,  txt="Company name", ln=1, align='C')
     pdf.cell(0, 10, txt="Structured ESG Analysis", ln=2, align='C')
@@ -517,7 +417,6 @@ def create_directory_loader(file_type, directory_path):
         loader_cls=loaders[file_type],
     )
 
-
 strategies_container = st.container()
 with strategies_container:
     mrow1_col1, mrow1_col2 = st.columns(2)
@@ -575,6 +474,19 @@ with strategies_container:
         else:
             pass
             # st.warning("No 'data' subfolder found.")
+        
+        if os.path.exists("ESG_Documents_Portfolio"):
+            # Iterate through files in the subfolder and delete them
+            for filename in os.listdir("ESG_Documents_Portfolio"):
+                file_path = os.path.join("ESG_Documents_Portfolio", filename)
+                try:
+                    if os.path.isfile(file_path):
+                        os.unlink(file_path)
+                except Exception as e:
+                    st.error(f"Error deleting {file_path}: {e}")
+        else:
+            pass
+            # st.warning("No 'data' subfolder found.")
 
         folders_to_clean = ["data", "chroma_db_portfolio", "chroma_db_LT", "chroma_db_fin"]
 
@@ -615,209 +527,180 @@ with strategies_container:
         st.divider()
 
     with mrow1_col2:
-        st.subheader("Analyze the ESG summary and LähiTapiola's investment policy")
-        st.info("This tool enables analysing the company's ESG policy with respect to the portfolio and investment policy.")
-        uploaded_files_portfolio = st.file_uploader("Choose a pdf file", accept_multiple_files=True, key="portfolio_files")
-        for uploaded_file in uploaded_files_portfolio:
-            st.write("filename:", uploaded_file.name)
-            def save_uploadedfile(uploadedfile):
-                with open(os.path.join("ESG_Documents_Portfolio",uploadedfile.name),"wb") as f:
-                    f.write(uploadedfile.getbuffer())
-                return st.success("Saved File:{} to ESG_Documents_Portfolio".format(uploadedfile.name))
-            save_uploadedfile(uploaded_file)
-        button_container3 = st.container()
-        #st.button("Portfolio Analysis")
-        if "button_states" not in st.session_state:
-            st.session_state.button_states = {
-            "portfolio_analysis_button_key": False,
-            }
-        if button_container3.button("Portfolio Analysis", key=portfolio_analysis_button_key):
-            st.session_state.button_states[portfolio_analysis_button_key] = True
-            portfolio_result_generator = generate_portfolio_analysis()
-            st.session_state.results["portfolio_analysis_output"] = portfolio_result_generator
-            st.write(portfolio_result_generator)
+        if "ESG_analysis_button_key" in st.session_state.results and st.session_state.results["ESG_analysis_button_key"]:
+            
+            doc_retriever_ESG, query_engine = create_vector_database_ESG()
+            doc_retriever_financials, query_engine_financials = create_vector_database_financials()
+            memory = ConversationBufferMemory(memory_key="chat_history", k=3, return_messages=True)
+            search = SerpAPIWrapper()
+
+            # Updated prompt templates to include chat history
+            def format_chat_history(chat_history):
+                """Format chat history as a single string for input to the chain."""
+                formatted_history = "\n".join([f"User: {entry['input']}\nAI: {entry['output']}" for entry in chat_history])
+                return formatted_history
+
+            prompt_financials = PromptTemplate.from_template(
+                template="""
+                    You are a seasoned corporate finance specialist.
+                    Use figures, numerical, and statistical data when possible. Never give false information, numbers or data.
+
+                    Conversation history:
+                    {chat_history}
+
+                    Based on the context: {context}, answer the following question: {question}.
+                """
+            )
 
-        if "portfolio_analysis_output" in st.session_state.results:
-            st.write(st.session_state.results["portfolio_analysis_output"])
+            prompt_ESG = PromptTemplate.from_template(
+                template="""
+                    You are a seasoned finance specialist and a specialist in environmental, social, and governance matters.
+                    Use figures, numerical, and statistical data when possible. Never give false information, numbers or data.
 
-        st.divider()
-        
-        with mrow1_col2:
-            if "ESG_analysis_button_key" in st.session_state.results and st.session_state.results["ESG_analysis_button_key"]:
-                doc_retriever_ESG = create_vector_database_ESG()
-                doc_retriever_financials = create_vector_database_financials()
-
-                persist_directory = os.path.join(os.getcwd(), "chroma_db_portfolio")
-                if not os.path.exists(persist_directory):
-                    os.makedirs(persist_directory)
+                    Conversation history:
+                    {chat_history}
+
+                    Based on the context: answer the following question: {question}.
+                """
+            )
+
+            # LCEL Chains with memory integration
+            financials_chain = (
+                {
+                    "context": doc_retriever_financials,
+                    # Lambda function now accepts one argument (even if unused)
+                    "chat_history": lambda _: format_chat_history(memory.load_memory_variables({})["chat_history"]),
+                    "question": RunnablePassthrough(),
+                }
+                | prompt_financials
+                | llm
+                | StrOutputParser()
+            )
+
+            ESG_chain = (
+                {
+                    "context": doc_retriever_ESG,
+                    "chat_history": lambda _: format_chat_history(memory.load_memory_variables({})["chat_history"]),
+                    "question": RunnablePassthrough(),
+                }
+                | prompt_ESG
+                | llm
+                | StrOutputParser()
+            )
+
+            # Define the tools with LCEL expressions
+            # Define the vector query engine tool
+            vector_query_tool_ESG = Tool(
+                name="Vector Query Engine ESG",
+                func=lambda query: query_engine.query(query),  # Use query_engine to query the vector database
+                description="Useful for answering questions that require ESG figures, data and statistics.",
+            )
+
+            vector_query_tool_financials = Tool(
+                name="Vector Query Engine Financials",
+                func=lambda query: query_engine_financials.query(query),  # Use query_engine to query the vector database
+                description="Useful for answering questions that require financial figures, data and statistics.",
+            )
+
+            # Create a function to validate responses
+            def validate_esg_response(query):
+                esg_response = vector_query_tool_ESG.func(query)
+                esg_validation = ESG_chain.invoke({
+                    "context": doc_retriever_ESG,
+                    "chat_history": format_chat_history(memory.load_memory_variables({})["chat_history"]),
+                    "question": esg_response
+                })
+                return esg_validation
+
+            def validate_financials_response(query):
+                financials_response = vector_query_tool_financials.func(query)
+                financials_validation = financials_chain.invoke({
+                    "context": doc_retriever_financials,
+                    "chat_history": format_chat_history(memory.load_memory_variables({})["chat_history"]),
+                    "question": financials_response
+                })
+                return financials_validation
+
+            # Update the tools list to include validation
+            tools = [
+                Tool(
+                    name="Search Tool",
+                    func=search.run,
+                    description="Useful when other tools do not provide the answer.",
+                ),
+                Tool(
+                    name="Validate ESG Response",
+                    func=validate_esg_response,
+                    description="Validates the response of the Vector Query Engine ESG tool.",
+                ),
+                Tool(
+                    name="Validate Financials Response",
+                    func=validate_financials_response,
+                    description="Validates the response of the Vector Query Engine Financials tool.",
+                ),
+                vector_query_tool_ESG,
+                vector_query_tool_financials,
+            ]
+
+            # Initialize the agent with LCEL tools and memory
+            agent = initialize_agent(
+                tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True, memory=memory, handle_parsing_errors=True)
+            def conversational_chat(query):
+                # Get the result from the agent
+                result = agent.invoke({"input": query, "chat_history": st.session_state['history']})
+                
+                # Handle different response types
+                if isinstance(result, dict):
+                    # Extract the main content if the result is a dictionary
+                    result = result.get("output", "")  # Adjust the key as needed based on your agent's output
+                elif isinstance(result, list):
+                    # If the result is a list, join it into a single string
+                    result = "\n".join(result)
+                elif not isinstance(result, str):
+                    # Convert the result to a string if it is not already one
+                    result = str(result)
+                
+                # Add the query and the result to the session state
+                st.session_state['history'].append((query, result))
+                
+                # Update memory with the conversation
+                memory.save_context({"input": query}, {"output": result})
                 
-                # Load the Chroma retriever from the persisted directory
-                embeddings = HuggingFaceEmbeddings()
-                doc_retriever_portfolio = Chroma(persist_directory=persist_directory, embedding_function=embeddings).as_retriever()
-
-                memory = ConversationBufferMemory(memory_key="chat_history", k=3, return_messages=True)
-                search = SerpAPIWrapper()
-
-                # Updated prompt templates to include chat history
-                def format_chat_history(chat_history):
-                    """Format chat history as a single string for input to the chain."""
-                    formatted_history = "\n".join([f"User: {entry['input']}\nAI: {entry['output']}" for entry in chat_history])
-                    return formatted_history
-
-                prompt_portfolio = PromptTemplate.from_template(
-                    template="""
-                        You are a seasoned finance specialist and a specialist in environmental, social, and governance matters.
-                        Use figures, numerical, and statistical data when possible.
-
-                        Conversation history:
-                        {chat_history}
-
-                        Based on the context: {context}, write a summary of LähiTapiola's investment policy. Set out also the most important ESG and sustainability aspects of the policy.
-                    """
-                )
-
-                prompt_financials = PromptTemplate.from_template(
-                    template="""
-                        You are a seasoned corporate finance specialist.
-                        Use figures, numerical, and statistical data when possible.
-
-                        Conversation history:
-                        {chat_history}
-
-                        Based on the context: {context}, answer the following question: {question}.
-                    """
-                )
-
-                prompt_ESG = PromptTemplate.from_template(
-                    template="""
-                        You are a seasoned finance specialist and a specialist in environmental, social, and governance matters.
-                        Use figures, numerical, and statistical data when possible.
-
-                        Conversation history:
-                        {chat_history}
-
-                        Based on the context: {context}, write a summary of LähiTapiola's ESG policy. Set out also the most important sustainability aspects of the policy.
-                    """
-                )
-
-                # LCEL Chains with memory integration
-                financials_chain = (
-                    {
-                        "context": doc_retriever_financials,
-                        # Lambda function now accepts one argument (even if unused)
-                        "chat_history": lambda _: format_chat_history(memory.load_memory_variables({})["chat_history"]),
-                        "question": RunnablePassthrough(),
-                    }
-                    | prompt_financials
-                    | llm
-                    | StrOutputParser()
-                )
-
-                portfolio_chain = (
-                    {
-                        "context": doc_retriever_portfolio,
-                        "chat_history": lambda _: format_chat_history(memory.load_memory_variables({})["chat_history"]),
-                        "question": RunnablePassthrough(),
-                    }
-                    | prompt_portfolio
-                    | llm
-                    | StrOutputParser()
-                )
-
-                ESG_chain = (
-                    {
-                        "context": doc_retriever_ESG,
-                        "chat_history": lambda _: format_chat_history(memory.load_memory_variables({})["chat_history"]),
-                        "question": RunnablePassthrough(),
-                    }
-                    | prompt_ESG
-                    | llm
-                    | StrOutputParser()
-                )
-
-                # Define the tools with LCEL expressions
-                tools = [
-                    Tool(
-                        name="ESG QA System",
-                        func=ESG_chain.invoke,
-                        description="Useful for answering questions about environmental, social, and governance (ESG) matters related to the target company, but not LähiTapiola.",
-                    ),
-                    Tool(
-                        name="Financials QA System",
-                        func=financials_chain.invoke,
-                        description="Useful for answering questions about financial or operational information concerning the target company, but not LähiTapiola.",
-                    ),
-                    Tool(
-                        name="Policy QA System",
-                        func=portfolio_chain.invoke,
-                        description="Useful for answering questions about LähiTapiola's ESG policy and sustainability measures.",
-                    ),
-                    Tool(
-                        name="Search Tool",
-                        func=search.run,
-                        description="Useful when other tools do not provide the answer.",
-                    ),
-                ]
-
-                # Initialize the agent with LCEL tools and memory
-                agent = initialize_agent(
-                    tools, llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION, verbose=True, memory=memory, handle_parsing_errors=True)
-                def conversational_chat(query):
-                    # Get the result from the agent
-                    result = agent.invoke({"input": query, "chat_history": st.session_state['history']})
-                    
-                    # Handle different response types
-                    if isinstance(result, dict):
-                        # Extract the main content if the result is a dictionary
-                        result = result.get("output", "")  # Adjust the key as needed based on your agent's output
-                    elif isinstance(result, list):
-                        # If the result is a list, join it into a single string
-                        result = "\n".join(result)
-                    elif not isinstance(result, str):
-                        # Convert the result to a string if it is not already one
-                        result = str(result)
-                    
-                    # Add the query and the result to the session state
-                    st.session_state['history'].append((query, result))
-                    
-                    # Update memory with the conversation
-                    memory.save_context({"input": query}, {"output": result})
-                    
-                    # Return the result
-                    return result
-
-                # Ensure session states are initialized
-                if 'history' not in st.session_state:
-                    st.session_state['history'] = []
-
-                if 'generated' not in st.session_state:
-                    st.session_state['generated'] = ["Let's discuss the ESG matters and financial matters 🤗"]
-
-                if 'past' not in st.session_state:
-                    st.session_state['past'] = ["Hey ! 👋"]
-
-                if 'input' not in st.session_state:
-                    st.session_state['input'] = ""
-
-                # Streamlit layout
-                st.subheader("Discuss the ESG and financial matters")
-                st.info("This tool is designed to enable discussion about the ESG and financial matters concerning the company and also LocalTapiola's own comprehensive sustainability policy and guidance.")
-                response_container = st.container()
-                container = st.container()
-
-                with container:
-                    with st.form(key='my_form'):
-                        user_input = st.text_input("Query:", placeholder="What would you like to know about ESG and financial matters", key='input')
-                        submit_button = st.form_submit_button(label='Send')
-                    if submit_button and user_input:
-                        output = conversational_chat(user_input)
-                        st.session_state['past'].append(user_input)
-                        st.session_state['generated'].append(output)
-                        user_input = "Query:"
-                    #st.session_state['input'] = ""
-                # Display generated responses
-                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="shapes")
-                            message(st.session_state["generated"][i], key=str(i), avatar_style="icons")
+                # Return the result
+                return result
+
+            # Ensure session states are initialized
+            if 'history' not in st.session_state:
+                st.session_state['history'] = []
+
+            if 'generated' not in st.session_state:
+                st.session_state['generated'] = ["Let's discuss the ESG matters and financial matters 🤗"]
+
+            if 'past' not in st.session_state:
+                st.session_state['past'] = ["Hey ! 👋"]
+
+            if 'input' not in st.session_state:
+                st.session_state['input'] = ""
+
+            # Streamlit layout
+            st.subheader("Discuss the ESG and financial matters")
+            st.info("This tool is designed to enable discussion about the ESG and financial matters concerning the company.")
+            response_container = st.container()
+            container = st.container()
+
+            with container:
+                with st.form(key='my_form'):
+                    user_input = st.text_input("Query:", placeholder="What would you like to know about ESG and financial matters", key='input')
+                    submit_button = st.form_submit_button(label='Send')
+                if submit_button and user_input:
+                    output = conversational_chat(user_input)
+                    st.session_state['past'].append(user_input)
+                    st.session_state['generated'].append(output)
+                    user_input = "Query:"
+                #st.session_state['input'] = ""
+            # Display generated responses
+            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="shapes")
+                        message(st.session_state["generated"][i], key=str(i), avatar_style="icons")