update to v0.1.16

.gitignore

@@ -11,6 +11,7 @@ core/__pycache__/
 *.so
 
 # Distribution / packaging
+*.db
 .Python
 build/
 develop-eggs/
@@ -140,4 +141,4 @@ dmypy.json
 project.yaml
 
 .idea/
-ev_database.db
+ev_database.db

agent.py

@@ -4,7 +4,7 @@ from pydantic import Field, BaseModel
 from omegaconf import OmegaConf
 
 from llama_index.core.utilities.sql_wrapper import SQLDatabase
-from sqlalchemy import create_engine, text
+from sqlalchemy import create_engine
 
 from dotenv import load_dotenv
 load_dotenv(override=True)
@@ -22,7 +22,6 @@ def create_assistant_tools(cfg):
                                         vectara_corpus_id=cfg.corpus_ids)
     
     summarizer = 'vectara-experimental-summary-ext-2023-12-11-med-omni'
-
     ask_complaints = vec_factory.create_rag_tool(
         tool_name = "ask_complaints",
         tool_description = """
@@ -32,9 +31,9 @@ def create_assistant_tools(cfg):
         tool_args_schema = QueryCFPBComplaints,
         reranker = "multilingual_reranker_v1", rerank_k = 100, 
         n_sentences_before = 2, n_sentences_after = 2, lambda_val = 0.005,
-        summary_num_results = 5,
+        summary_num_results = 15,
         vectara_summarizer = summarizer,
-        include_citations = False,
+        include_citations = True,
     )
 
     tools_factory = ToolsFactory()
@@ -53,17 +52,12 @@ def create_assistant_tools(cfg):
 
 def initialize_agent(_cfg, update_func=None):
     cfpb_complaints_bot_instructions = """
-    - You are a helpful research assistant, with expertise in complaints from the Consumer Financial Protection Bureau, in conversation with a user.
+    - You are a helpful research assistant, 
+      with expertise in finance and complaints from the CFPB (Consumer Financial Protection Bureau), 
+      in conversation with a user.
     - For a query with multiple sub-questions, break down the query into the sub-questions, 
       and make separate calls to the ask_complaints tool to answer each sub-question,
       then combine the answers to provide a complete response.
-    - If you do not find an answer from one of the tools, try to use the other tools to answer the query.
-    - Before answering any user query, use cfpb_describe_tables to understand schema of each table, and use get_sample_data 
-      to get sample data from each table in the database, so that you can understand NULL and unique values for each column.
-    - Use the database tools (cfpb_load_data, cfpb_describe_tables and cfpb_list_tables) to answer analytical queries.
-    - IMPORTANT: When using database_tools, always call the ev_load_sample_data tool with the table you want to query
-      to understand the table structure, column naming, and values in the table. Never call the cfpb_load_data tool for a query until you have called cfpb_load_sample_data.
-    - When providing links, try to put the name of the website or source of information for the displayed text. Don't just say 'Source'.
     - Never discuss politics, and always respond politely.
     """
 

app.py

@@ -1,166 +1,14 @@
-from PIL import Image
-import sys
 import os
-import uuid
 
 import streamlit as st
-from streamlit_pills import pills
-from streamlit_feedback import streamlit_feedback
+from st_app import launch_bot
 
 import nest_asyncio
 import asyncio
 
-from utils import thumbs_feedback, escape_dollars_outside_latex, send_amplitude_data
-
 import sqlite3
 from datasets import load_dataset
 
-from vectara_agentic.agent import AgentStatusType
-from agent import initialize_agent, get_agent_config
-
-
-initial_prompt = "How can I help you today?"
-
-# Setup for HTTP API Calls to Amplitude Analytics
-if 'device_id' not in st.session_state:
-    st.session_state.device_id = str(uuid.uuid4())
-
-
-if "feedback_key" not in st.session_state:
-        st.session_state.feedback_key = 0
-
-def toggle_logs():
-    st.session_state.show_logs = not st.session_state.show_logs
-
-def show_example_questions():        
-    if len(st.session_state.example_messages) > 0 and st.session_state.first_turn:            
-        selected_example = pills("Queries to Try:", st.session_state.example_messages, index=None)
-        if selected_example:
-            st.session_state.ex_prompt = selected_example
-            st.session_state.first_turn = False
-            return True
-    return False
-
-def update_func(status_type: AgentStatusType, msg: str):
-    if status_type != AgentStatusType.AGENT_UPDATE:
-        output = f"{status_type.value} - {msg}"
-        st.session_state.log_messages.append(output)
-
-async def launch_bot():
-    def reset():
-        st.session_state.messages = [{"role": "assistant", "content": initial_prompt, "avatar": "🦖"}]
-        st.session_state.thinking_message = "Agent at work..."
-        st.session_state.log_messages = []
-        st.session_state.prompt = None
-        st.session_state.ex_prompt = None
-        st.session_state.first_turn = True
-        st.session_state.show_logs = False
-        if 'agent' not in st.session_state:
-            st.session_state.agent = initialize_agent(cfg, update_func=update_func)
-
-    if 'cfg' not in st.session_state:
-        cfg = get_agent_config()
-        st.session_state.cfg = cfg
-        st.session_state.ex_prompt = None
-        example_messages = [example.strip() for example in cfg.examples.split(";")] if cfg.examples else []
-        st.session_state.example_messages = [em for em in example_messages if len(em)>0]
-        reset()
-
-    cfg = st.session_state.cfg
-
-    # left side content
-    with st.sidebar:
-        image = Image.open('Vectara-logo.png')
-        st.image(image, width=175)
-        st.markdown(f"## {cfg['demo_welcome']}")
-        st.markdown(f"{cfg['demo_description']}")
-
-        st.markdown("\n\n")
-        bc1, _ = st.columns([1, 1])
-        with bc1:
-            if st.button('Start Over'):
-                reset()
-                st.rerun()
-
-        st.divider()
-        st.markdown(
-            "## How this works?\n"
-            "This app was built with [Vectara](https://vectara.com).\n\n"
-            "It demonstrates the use of Agentic RAG functionality with Vectara"
-        )
-
-    if "messages" not in st.session_state.keys():
-        reset()
-
-    # Display chat messages
-    for message in st.session_state.messages:
-        with st.chat_message(message["role"], avatar=message["avatar"]):
-            st.write(message["content"])
-
-    example_container = st.empty()
-    with example_container:
-        if show_example_questions():
-            example_container.empty()
-            st.session_state.first_turn = False
-            st.rerun()
-
-    # User-provided prompt
-    if st.session_state.ex_prompt:
-        prompt = st.session_state.ex_prompt
-    else:
-        prompt = st.chat_input()
-    if prompt:
-        st.session_state.messages.append({"role": "user", "content": prompt, "avatar": '🧑‍💻'})
-        st.session_state.prompt = prompt  # Save the prompt in session state
-        st.session_state.log_messages = []
-        st.session_state.show_logs = False
-        with st.chat_message("user", avatar='🧑‍💻'):
-            print(f"Starting new question: {prompt}\n")
-            st.write(prompt)
-        st.session_state.ex_prompt = None
-        
-    # Generate a new response if last message is not from assistant
-    if st.session_state.prompt:
-        with st.chat_message("assistant", avatar='🤖'):
-            with st.spinner(st.session_state.thinking_message):
-                res = st.session_state.agent.chat(st.session_state.prompt)
-                res = escape_dollars_outside_latex(res)
-            message = {"role": "assistant", "content": res, "avatar": '🤖'}
-            st.session_state.messages.append(message)
-            st.markdown(res)
-
-        send_amplitude_data(
-            user_query=st.session_state.messages[-2]["content"], 
-            bot_response=st.session_state.messages[-1]["content"],
-            demo_name=cfg['demo_name']
-        )
-
-        st.session_state.ex_prompt = None
-        st.session_state.prompt = None
-        st.session_state.first_turn = False
-        st.rerun()
-
-    # Record user feedback
-    if (st.session_state.messages[-1]["role"] == "assistant") & (st.session_state.messages[-1]["content"] != initial_prompt):
-        streamlit_feedback(
-            feedback_type="thumbs", on_submit = thumbs_feedback, key = st.session_state.feedback_key,
-            kwargs = {"user_query": st.session_state.messages[-2]["content"],
-                      "bot_response": st.session_state.messages[-1]["content"],
-                      "demo_name": cfg["demo_name"]}
-        )
-        
-    log_placeholder = st.empty()
-    with log_placeholder.container():
-        if st.session_state.show_logs:
-            st.button("Hide Logs", on_click=toggle_logs)
-            for msg in st.session_state.log_messages:
-                st.text(msg)
-        else:
-            if len(st.session_state.log_messages) > 0:
-                st.button("Show Logs", on_click=toggle_logs)
-
-    sys.stdout.flush()
-
 def setup_db():
     db_path = 'cfpb_database.db'
     conn = sqlite3.connect(db_path)

requirements.txt

@@ -7,4 +7,4 @@ langdetect==1.0.9
 langcodes==3.4.0
 datasets==2.19.2
 uuid==1.30
-vectara-agentic==0.1.15
+vectara-agentic==0.1.16

st_app.py

@@ -0,0 +1,169 @@
+from PIL import Image
+import sys
+import uuid
+
+import streamlit as st
+from streamlit_pills import pills
+from streamlit_feedback import streamlit_feedback
+
+from utils import thumbs_feedback, escape_dollars_outside_latex, send_amplitude_data
+
+from vectara_agentic.agent import AgentStatusType
+from agent import initialize_agent, get_agent_config
+
+initial_prompt = "How can I help you today?"
+
+# Setup for HTTP API Calls to Amplitude Analytics
+if 'device_id' not in st.session_state:
+    st.session_state.device_id = str(uuid.uuid4())
+
+
+if "feedback_key" not in st.session_state:
+        st.session_state.feedback_key = 0
+
+def toggle_logs():
+    st.session_state.show_logs = not st.session_state.show_logs
+
+def show_example_questions():        
+    if len(st.session_state.example_messages) > 0 and st.session_state.first_turn:            
+        selected_example = pills("Queries to Try:", st.session_state.example_messages, index=None)
+        if selected_example:
+            st.session_state.ex_prompt = selected_example
+            st.session_state.first_turn = False
+            return True
+    return False
+
+def update_func(status_type: AgentStatusType, msg: str):
+    if status_type != AgentStatusType.AGENT_UPDATE:
+        output = f"{status_type.value} - {msg}"
+        st.session_state.log_messages.append(output)
+
+async def launch_bot():
+    def reset():
+        st.session_state.messages = [{"role": "assistant", "content": initial_prompt, "avatar": "🦖"}]
+        st.session_state.thinking_message = "Agent at work..."
+        st.session_state.log_messages = []
+        st.session_state.prompt = None
+        st.session_state.ex_prompt = None
+        st.session_state.first_turn = True
+        st.session_state.logs_enabled = False
+        st.session_state.show_logs = False
+        if 'agent' not in st.session_state:
+            st.session_state.agent = initialize_agent(cfg, update_func=update_func)
+        else:
+            st.session_state.agent.clear_memory()
+
+    if 'cfg' not in st.session_state:
+        cfg = get_agent_config()
+        st.session_state.cfg = cfg
+        st.session_state.ex_prompt = None
+        example_messages = [example.strip() for example in cfg.examples.split(";")] if cfg.examples else []
+        st.session_state.example_messages = [em for em in example_messages if len(em)>0]
+        reset()
+
+    cfg = st.session_state.cfg
+
+    # left side content
+    with st.sidebar:
+        image = Image.open('Vectara-logo.png')
+        st.image(image, width=175)
+        st.markdown(f"## {cfg['demo_welcome']}")
+        st.markdown(f"{cfg['demo_description']}")
+
+        st.markdown("\n\n")
+        bc1, bc2 = st.columns([1, 1])
+        with bc1:
+            if st.button('Start Over'):
+                reset()
+                st.rerun()
+        with bc2:  # Updated button for enabling/disabling logs
+            if st.session_state.logs_enabled:
+                if st.button('Disable Logs', key='disable_logs'):
+                    st.session_state.logs_enabled = False
+                    st.rerun()
+            else:
+                if st.button('Enable Logs', key='enable_logs'):
+                    st.session_state.logs_enabled = True
+                    st.rerun()
+
+        st.divider()
+        st.markdown(
+            "## How this works?\n"
+            "This app was built with [Vectara](https://vectara.com).\n\n"
+            "It demonstrates the use of Agentic RAG functionality with Vectara"
+        )
+
+    if "messages" not in st.session_state.keys():
+        reset()
+
+    # Display chat messages
+    for message in st.session_state.messages:
+        with st.chat_message(message["role"], avatar=message["avatar"]):
+            st.write(message["content"])
+
+    example_container = st.empty()
+    with example_container:
+        if show_example_questions():
+            example_container.empty()
+            st.session_state.first_turn = False
+            st.rerun()
+
+    # User-provided prompt
+    if st.session_state.ex_prompt:
+        prompt = st.session_state.ex_prompt
+    else:
+        prompt = st.chat_input()
+    if prompt:
+        st.session_state.messages.append({"role": "user", "content": prompt, "avatar": '🧑‍💻'})
+        st.session_state.prompt = prompt  # Save the prompt in session state
+        st.session_state.log_messages = []
+        st.session_state.show_logs = False
+        with st.chat_message("user", avatar='🧑‍💻'):
+            print(f"Starting new question: {prompt}\n")
+            st.write(prompt)
+        st.session_state.ex_prompt = None
+        
+    # Generate a new response if last message is not from assistant
+    if st.session_state.prompt:
+        with st.chat_message("assistant", avatar='🤖'):
+            with st.spinner(st.session_state.thinking_message):
+                res = st.session_state.agent.chat(st.session_state.prompt)
+                res = escape_dollars_outside_latex(res)
+            message = {"role": "assistant", "content": res, "avatar": '🤖'}
+            st.session_state.messages.append(message)
+            st.markdown(res)
+
+        send_amplitude_data(
+            user_query=st.session_state.messages[-2]["content"], 
+            bot_response=st.session_state.messages[-1]["content"],
+            demo_name=cfg['demo_name']
+        )
+
+        st.session_state.ex_prompt = None
+        st.session_state.prompt = None
+        st.session_state.first_turn = False
+        st.rerun()
+
+    # Record user feedback
+    if (st.session_state.messages[-1]["role"] == "assistant") & (st.session_state.messages[-1]["content"] != initial_prompt):
+        if st.session_state.show_logs and st.session_state.logs_enabled:  # Only show logs if enabled
+            streamlit_feedback(
+                feedback_type="thumbs", on_submit=thumbs_feedback, key=st.session_state.feedback_key,
+                kwargs={"user_query": st.session_state.messages[-2]["content"],
+                        "bot_response": st.session_state.messages[-1]["content"],
+                        "demo_name": cfg["demo_name"]}
+            )
+
+    log_placeholder = st.empty()
+    with log_placeholder.container():
+        if st.session_state.logs_enabled:  # Show logs button only if log toggle is enabled
+            if st.session_state.show_logs:
+                st.button("Hide Logs", on_click=toggle_logs)
+                for msg in st.session_state.log_messages:
+                    st.text(msg)
+            else:
+                if len(st.session_state.log_messages) > 0:
+                    st.button("Show Logs", on_click=toggle_logs)
+
+
+    sys.stdout.flush()