updates

README.md

@@ -1,13 +1,13 @@
 ---
-title: Clinical Trials Assistant
-emoji: 👨‍⚕️
+title: Cona Assistant
+emoji: 🐨
 colorFrom: indigo
 colorTo: indigo
 sdk: docker
 app_port: 8501
 pinned: false
 license: apache-2.0
-short_description: Clinical Trial assistant using vectara-agentic
+short_description: Ask questions about Cona Services
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

agent.py

@@ -1,137 +1,68 @@
-import pandas as pd
-import requests
+import os
+from typing import Optional
+import json
 from pydantic import Field, BaseModel
-
 from omegaconf import OmegaConf
+import requests
 
 from vectara_agentic.agent import Agent
-from vectara_agentic.tools import ToolsFactory, VectaraToolFactory
+from vectara_agentic.tools import VectaraToolFactory, ToolsFactory
 
-initial_prompt = "How can I help you today?"
+from dotenv import load_dotenv
+load_dotenv(override=True)
 
-prompt = """
-[
-  {"role": "system", "content": "You are an AI assistant that forms a coherent answer to a user query based on search results that are provided to you." },
-  {"role": "user", "content": " 
-    [INSTRUCTIONS]
-    If the search results are irrelevant to the question respond with *** I do not have enough information to answer this question.***
-    Search results may include tables in a markdown format. When answering a question using a table be careful about which rows and columns contain the answer and include all relevant information from the relevant rows and columns that the query is asking about.
-    Do not base your response on information or knowledge that is not in the search results.
-    Make sure your response is answering the query asked. If the query is related to an entity (such as a person or place), make sure you use search results related to that entity.
-    Consider that each search result is a partial segment from a bigger text, and may be incomplete.
-    Your output should always be in a single language - the $vectaraLangName language. Check spelling and grammar for the $vectaraLangName language.
-    Search results for the query *** $vectaraQuery***, are listed below, some are text, some MAY be tables in markdown format.
-    #foreach ($qResult in $vectaraQueryResultsDeduped)
-      [$esc.java($foreach.index + 1)]
-      #if($qResult.hasTable())
-        Table Title: $qResult.getTable().title() || Table Description: $qResult.getTable().description() || Table Data:
-        $qResult.getTable().markdown()
-      #else
-        $qResult.getText()
-      #end
-    #end
-    Generate a coherent response (but no more than $vectaraOutChars characters) to the query *** $vectaraQuery *** using information and facts in the search results provided. 
-    Give a slight preference to search results that appear earlier in the list.
-    Include statistical and numerical evidence to support and contextualize your response.
-    Only cite relevant search results in your answer following these specific instructions: $vectaraCitationInstructions
-    If the search results are irrelevant to the query, respond with ***I do not have enough information to answer this question.***. Respond always in the $vectaraLangName language, and only in that language."}
-]
-"""
+initial_prompt = "How can I help you today?"
 
 def create_assistant_tools(cfg):
 
+    class QueryCona(BaseModel):
+        query: str = Field(description="The user query.")
 
-    class QueryPublicationsArgs(BaseModel):
-        query: str = Field(..., description="The user query, always in the form of a question", 
-                           examples=["what are the risks reported?", "which drug was use on the and how big was the population?"])        
-        
-    vec_factory = VectaraToolFactory(vectara_api_key=cfg.api_key,
-                                     vectara_corpus_key=cfg.corpus_key)
+    vec_factory = VectaraToolFactory(
+        vectara_api_key=cfg.api_key,
+        vectara_corpus_key=cfg.corpus_key
+    )
+    
     summarizer = 'vectara-summary-table-md-query-ext-jan-2025-gpt-4o'
-    ask_publications = vec_factory.create_rag_tool(
-        tool_name = "ask_publications",
+    ask_ti = vec_factory.create_rag_tool(
+        tool_name = "ask_cona",
         tool_description = """
-        Responds to an user question about a particular result, based on the publications.
+        Given a user query, 
+        returns a response to a user question about bottling companies.
         """,
-        tool_args_schema = QueryPublicationsArgs,
-#        reranker = "multilingual_reranker_v1", rerank_k = 100,
-        reranker = "chain", rerank_k = 100, 
-        rerank_chain = [
-            {
-                "type": "multilingual_reranker_v1",
-#                "cutoff": 0.2
-            },
-            {
-                "type": "mmr",
-                "diversity_bias": 0.2,
-                "limit": 50
-            }
-        ],
-        n_sentences_before = 2, n_sentences_after = 2, lambda_val = 0.005,
-        summary_num_results = 15,
+        tool_args_schema = QueryCona,
+        reranker = "slingshot", rerank_k = 100, 
+        n_sentences_before = 2, n_sentences_after = 2, lambda_val = 0.01,
         vectara_summarizer = summarizer,
+        summary_num_results = 20,
         include_citations = True,
-        vectara_prompt_text=prompt,
-        save_history = True,
-        verbose=False
-    )
-
-    search_publications = vec_factory.create_search_tool(
-        tool_name = "search_publications",
-        tool_description = """
-        Returns matching publications to a user query.
-        """,
-        tool_args_schema = QueryPublicationsArgs,
-        reranker = "chain", rerank_k = 100, 
-        rerank_chain = [
-            {
-                "type": "multilingual_reranker_v1",
-#                "cutoff": 0.2
-            },
-            {
-                "type": "mmr",
-                "diversity_bias": 0.2,
-                "limit": 50
-            }
-        ],
-#        reranker = "multilingual_reranker_v1", rerank_k = 100,
-        n_sentences_before = 2, n_sentences_after = 2, lambda_val = 0.005,
-        save_history = True,
-        verbose=True
-    )
-
-
-    tools_factory = ToolsFactory()
-    return (
-            tools_factory.standard_tools() +
-            [ask_publications, search_publications]
+        verbose = True
     )
+    return [ask_ti] + ToolsFactory().guardrail_tools()
 
 def initialize_agent(_cfg, agent_progress_callback=None):
-    menarini_bot_instructions = """
-    - You are an expert statistician and clinical trial data analyst with extensive experience in designing, analyzing, and interpreting clinical research data.
-    - Your responses should be technically rigorous, data-driven, and written for an audience familiar with advanced statistical methodologies, regulatory standards, and the nuances of clinical trial design. 
-    - Call the ask_publications tool to retreive information to answer the user query.
-      If the initial query lacks comprehensive data, continue to query ask_publications with refined search parameters until you retrieve all necessary numerical details
-    - Call the search_publications tool to retreive a list of publications that may contain the information needed to answer the user query.
-      The results include the document_id of each publication, and metadata.
-    - When responding to queries:
-    1) Use precise statistical terminology (e.g., randomization, blinding, intention-to-treat, type I/II error, p-values, confidence intervals, Bayesian methods, etc.) 
-       and reference common methodologies or guidelines where applicable (e.g., CONSORT, FDA, EMA).
-    2) Your responses must include contextual information such as sample size and population characteristics. This nuance is crucial in clinical trial analysis.
-       When considering or reporting sample sizes, consider participants who were eligible for the study, those who were randomized, and those who completed the study.
-       If it's unclear which one is being referred to, clarify this in your response or ask the user for clarification.
-    3) Provide clear explanations of statistical concepts, including assumptions, potential biases, and limitations in the context of clinical trial data.
-    4) Ensure that your analysis is evidence-based and reflects current best practices in the field of clinical research and data analysis.
-    5) Before finalizing your answer, review the analysis to ensure that all relevant data has been incorporated and that your conclusions are well-supported by the evidence.
-    6) Provide sources and citations for all data and statistical information included in your responses, as provided in the response from the tools.
+    bot_instructions = """
+    - You are a helpful assistant, with expertise in products from coca cola and other bottling companies.
+    - Use the ask_coma tool to answer most questions about any products related to coca cola.
     """
 
     agent = Agent(
         tools=create_assistant_tools(_cfg),
-        topic="Drug trials publications",
-        custom_instructions=menarini_bot_instructions,
+        topic="Cona services and coca cola",
+        custom_instructions=bot_instructions,
         agent_progress_callback=agent_progress_callback,
     )
     agent.report()
-    return agent
+    return agent
+
+
+def get_agent_config() -> OmegaConf:
+    cfg = OmegaConf.create({
+        'corpus_key': str(os.environ['VECTARA_CORPUS_KEY']),
+        'api_key': str(os.environ['VECTARA_API_KEY']),
+        'examples': os.environ.get('QUERY_EXAMPLES', None),
+        'demo_name': "Cona Demo",
+        'demo_welcome': "Cona Assistant.",
+        'demo_description': "This assistant can help you with any questions about Cona Serices."
+    })
+    return cfg

app.py

@@ -13,6 +13,6 @@ if "feedback_key" not in st.session_state:
     st.session_state.feedback_key = 0
 
 if __name__ == "__main__":
-   st.set_page_config(page_title="Menarini Assistant", layout="wide")
+   st.set_page_config(page_title="Cona Assistant", layout="wide")
    nest_asyncio.apply()
-   asyncio.run(launch_bot())
+   asyncio.run(launch_bot())

requirements.txt

@@ -6,4 +6,4 @@ streamlit_feedback==0.1.3
 uuid==1.30
 langdetect==1.0.9
 langcodes==3.4.0
-vectara-agentic==0.2.1
+vectara-agentic==0.2.1

st_app.py

@@ -3,13 +3,24 @@ import sys
 import re
 
 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
-from config import get_agent_config
+from agent import initialize_agent, get_agent_config
 
 initial_prompt = "How can I help you today?"
 
+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 format_log_msg(log_msg: str):
     max_log_msg_size = 500
@@ -57,19 +68,50 @@ async def launch_bot():
         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
-    print(f'Configuration: {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:
+            if st.button('Show Logs'):
+                show_modal()
+
+        # 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:
-        print(f'Message: {message}')
         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:
@@ -90,17 +132,33 @@ async def launch_bot():
     if st.session_state.prompt:
         with st.chat_message("assistant", avatar='🤖'):
             st.session_state.status = st.status('Processing...', expanded=False)
-            res = st.session_state.agent.chat(st.session_state.prompt)
-            #res = escape_dollars_outside_latex(res)
-            res = str(res)
+            response = st.session_state.agent.chat(st.session_state.prompt)
+            res = escape_dollars_outside_latex(response.response)
             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()
 
-    sys.stdout.flush()
+    # Record user feedback
+    if (st.session_state.messages[-1]["role"] == "assistant") & (st.session_state.messages[-1]["content"] != initial_prompt):
+        if "feedback_key" not in st.session_state:
+            st.session_state.feedback_key = 0
+        streamlit_feedback(
+            feedback_type="thumbs", on_submit=thumbs_feedback, key=str(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"]}
+            )
+
+
+    sys.stdout.flush()