LLM revisions

app.py

@@ -32,8 +32,6 @@ from langchain.memory import ConversationBufferMemory
 from langchain.prompts import PromptTemplate
 import joblib
 import nltk
-import json
-nltk.download('averaged_perceptron_tagger')
 
 import nest_asyncio  # noqa: E402
 nest_asyncio.apply()
@@ -106,55 +104,15 @@ css = """
 """
 
 st.write(css, unsafe_allow_html=True)
-#--------------
-def load_credentials(filepath):
-    with open(filepath, 'r') as file:
-        return json.load(file)
-
-# Load credentials from 'credentials.json'
-credentials = load_credentials('chroma_db_LT1/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()
-
+st.sidebar.image('StratXcel.png', width=150)
 #------------- 
 llm=ChatGroq(groq_api_key=groq_api_key,
-             model_name="llama-3.1-70b-Versatile", temperature = 0.0, streaming=True)   
+             model_name="Llama-3.1-70b-Versatile", temperature = 0.0, streaming=True)   
+             #model_name="Llama-3.1-70b-Versatile", temperature = 0.0, streaming=True)   
+
+llm_tool=ChatGroq(groq_api_key=groq_api_key,
+             model_name="llama3-groq-70b-8192-tool-use-preview", temperature = 0.0, streaming=True)   
+             #model_name="Llama-3.1-70b-Versatile", temperature = 0.0, streaming=True)   
 #--------------
 doc_retriever_ESG = None
 doc_retriever_financials = None
@@ -166,7 +124,7 @@ def load_or_parse_data_ESG():
 
     parsingInstructionUber10k = """The provided document contain detailed information about the company's environmental, social and governance matters.
     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. 
+    Give only precide CO2 and energy consumption 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."""
 
@@ -340,15 +298,15 @@ def ESG_strategy():
 )   
 
     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_2 = qa.invoke("Does the company's main business fall under the European Union's taxonomy regulation? Answer whether the company is taxonomy compliant under European Union Taxonomy Regulation?")
+    ESG_answer_3 = qa.invoke("Describe what specific ESG transparency commitments the company has given. Give details how the company has followed 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? Has the company reached its carbod dioxide reduction objectives? Set out in a table the company's carbon footprint by location and its development or equivalent figures. List carbon dioxide emissions in relation to turnover.")
+    ESG_answer_5 = qa.invoke("Describe and set out in a table the following specific information: (i) Scope 1 CO2 emissions, (ii) Scope 2 CO2 emissions, and (iii) Scope 3 CO2 emissions of the company for 2021, 2022 and 2023. List the material changes relating to these figures.")
+    ESG_answer_6 = qa.invoke("List in a table the company's energy and renewable energy usage for each material activity. Explain the main 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?")
     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 percentage of women are represented in the (i) board, (ii) executive directors and (iii) upper management?")
+    ESG_answer_9 = qa.invoke("Set out waste management produces by the company and possible waste into the soil. Describe if the company's real estates have hazardous waste.")
+    ESG_answer_10 = qa.invoke("What percentage of women are represented in the (i) board, (ii) executive directors and (iii) upper management? Set out the measures taken to have the gender balance on the upper management of the company.")
     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 **__Gender equality:__** {ESG_answer_10} \n\n **__Anti-money laundering:__** {ESG_answer_11}"
@@ -561,7 +519,7 @@ with strategies_container:
                     Conversation history:
                     {chat_history}
 
-                    Based on the context: answer the following question: {question}.
+                    Based on the context: {context}, answer the following question: {question}.
                 """
             )
 
@@ -574,7 +532,7 @@ with strategies_container:
                     "question": RunnablePassthrough(),
                 }
                 | prompt_financials
-                | llm
+                | llm_tool
                 | StrOutputParser()
             )
 
@@ -585,59 +543,39 @@ with strategies_container:
                     "question": RunnablePassthrough(),
                 }
                 | prompt_ESG
-                | llm
+                | llm_tool
                 | 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.",
+            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 about specific 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.",
+            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 about specific 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.",
+                    name="ESG QA System",
+                    func=ESG_chain.invoke,
+                    description="Useful for answering general questions about environmental, social, and governance (ESG) matters related to the company. ",
                 ),
                 Tool(
-                    name="Validate ESG Response",
-                    func=validate_esg_response,
-                    description="Validates the response of the Vector Query Engine ESG tool.",
+                    name="Financials QA System",
+                    func=financials_chain.invoke,
+                    description="Useful for answering general questions about financial or operational information concerning the company.",
                 ),
                 Tool(
-                    name="Validate Financials Response",
-                    func=validate_financials_response,
-                    description="Validates the response of the Vector Query Engine Financials tool.",
+                    name="Search Tool",
+                    func=search.run,
+                    description="Useful when other tools do not provide the answer.",
                 ),
                 vector_query_tool_ESG,
                 vector_query_tool_financials,