initial

README.md

@@ -1,5 +1,5 @@
 ---
-title: Finance assistant
+title: UCSF Ortho Demo
 emoji: 🐨
 colorFrom: indigo
 colorTo: indigo
@@ -7,7 +7,7 @@ sdk: docker
 app_port: 8501
 pinned: false
 license: apache-2.0
-short_description: Finance chatbot using vectara-agentic
+short_description: Ask questions about UCSF Orthopedics
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

agent.py

@@ -1,154 +1,38 @@
 import os
-import pandas as pd
-import requests
-from pydantic import Field, BaseModel
-
+from typing import Optional
 from omegaconf import OmegaConf
 
 from vectara_agentic.agent import Agent
-from vectara_agentic.tools import ToolsFactory, VectaraToolFactory
 
 from dotenv import load_dotenv
 load_dotenv(override=True)
 
-
-tickers = {
-    "C": "Citigroup",
-    "COF": "Capital One",
-    "JPM": "JPMorgan Chase",
-    "AAPL": "Apple Computer", 
-    "GOOG": "Google", 
-    "AMZN": "Amazon",
-    "SNOW": "Snowflake",
-    "TEAM": "Atlassian",
-    "TSLA": "Tesla",
-    "NVDA": "Nvidia",
-    "MSFT": "Microsoft",
-    "AMD": "Advanced Micro Devices",
-    "INTC": "Intel",
-    "NFLX": "Netflix",
-    "STT": "State Street",
-    "BK": "Bank of New York Mellon",
-}
-years = range(2015, 2025)
 initial_prompt = "How can I help you today?"
 
-def create_assistant_tools(cfg):
-
-    def get_company_info() -> list[str]:
-        """
-        Returns a dictionary of companies you can query about. Always check this before using any other tool.
-        The output is a dictionary of valid ticker symbols mapped to company names.
-        You can use this to identify the companies you can query about, and their ticker information.
-        """
-        return tickers
-
-    def get_valid_years() -> list[str]:
-        """
-        Returns a list of the years for which financial reports are available.
-        Always check this before using any other tool.
-        """
-        return years
-
-    # Tool to get the income statement for a given company and year using the FMP API
-    def fmp_income_statement(
-        ticker: str = Field(description="the ticker symbol of the company."),
-        year: int = Field(description="the year for which to get the income statement."),
-    ) -> str:
-        """
-        Get the income statement for a given company and year using the FMP (https://financialmodelingprep.com) API.
-        Returns a dictionary with the income statement data. All data is in USD, but you can convert it to more compact form like K, M, B.
-        """
-        fmp_api_key = os.environ.get("FMP_API_KEY", None)
-        if fmp_api_key is None:
-            return "FMP_API_KEY environment variable not set. This tool does not work."
-        url = f"https://financialmodelingprep.com/api/v3/income-statement/{ticker}?apikey={fmp_api_key}"
-        response = requests.get(url)
-        if response.status_code == 200:
-            data = response.json()
-            income_statement = pd.DataFrame(data)
-            if len(income_statement) == 0 or "date" not in income_statement.columns:
-                return "No data found for the given ticker symbol."
-            income_statement["date"] = pd.to_datetime(income_statement["date"])
-            income_statement_specific_year = income_statement[
-                income_statement["date"].dt.year == int(year)
-            ]
-            values_dict = income_statement_specific_year.to_dict(orient="records")[0]
-            return f"Financial results: {', '.join([f'{key}={value}' for key, value in values_dict.items() if key not in ['date', 'cik', 'link', 'finalLink']])}"
-        
-        return f"FMP API returned error {response.status_code}. This tool does not work."
-
-    class QueryTranscriptsArgs(BaseModel):
-        query: str = Field(..., description="The user query, always in the form of a question", examples=["what are the risks reported?", "who are the competitors?"])
-        year: int | str = Field(..., description=f"The year this query relates to. An integer between {min(years)} and {max(years)} or a string specifying a condition on the year (example: '>2020').")
-        ticker: str = Field(..., description=f"The company ticker this query relates to. Must be a valid ticket symbol from the list {list(tickers.keys())}.")
-
-    vec_factory = VectaraToolFactory(vectara_api_key=cfg.api_key,
-                                     vectara_customer_id=cfg.customer_id,
-                                     vectara_corpus_id=cfg.corpus_id)
-    summarizer = 'vectara-experimental-summary-ext-2023-12-11-med-omni'
-    ask_transcripts = vec_factory.create_rag_tool(
-        tool_name = "ask_transcripts",
-        tool_description = """
-        Given a company name and year, responds to a user question about the company, based on analyst call transcripts about the company's financial reports for that year.
-        You can ask this tool any question about the company including risks, opportunities, financial performance, competitors and more.
-        """,
-        tool_args_schema = QueryTranscriptsArgs,
-        reranker = "multilingual_reranker_v1", rerank_k = 100,
-        n_sentences_before = 2, n_sentences_after = 2, lambda_val = 0.005,
-        summary_num_results = 10,
-        vectara_summarizer = summarizer,
-        include_citations = True,
-    )
-
-    tools_factory = ToolsFactory()
-    return (
-            [tools_factory.create_tool(tool) for tool in
-                [
-                    get_company_info,
-                    get_valid_years,
-                    fmp_income_statement,
-                ]
-            ] +
-            tools_factory.financial_tools() +
-            [ask_transcripts]
-    )
 
 def initialize_agent(_cfg, agent_progress_callback=None):
-    financial_bot_instructions = """
-    - You are a helpful financial assistant, with expertise in financial reporting, in conversation with a user. 
-    - Use the ask_transcripts tool to answer most questions about the company's financial performance, risks, opportunities, strategy, competitors, and more.
-    - responses from ask_transcripts are summarized. You don't need to further summarize them.
-    - Respond in a compact format by using appropriate units of measure (e.g., K for thousands, M for millions, B for billions). 
-      Do not report the same number twice (e.g. $100K and 100,000 USD).
-    - Always use the 'income_statement' tool to obtain accurate financial data like revenues, expenses, net income, and other financial metrics 
-      for a specific company, for any the year 2020 or later.
-    - Use the 'fmp_income_statement' tool (with the company ticker and year) to obtain financial data for any year before 2020.
-    - Always check the 'get_company_info' and 'get_valid_years' tools to validate company and year are valid.
-    - Do not include URLs unless they are provided in the output of a tool you use.
-    - When querying a tool for a numeric value or KPI, use a concise and non-ambiguous description of what you are looking for. 
-    - If you calculate a metric, make sure you have all the necessary information to complete the calculation. Don't guess.
-    """
-
-    agent = Agent(
-        tools=create_assistant_tools(_cfg),
-        topic="Financial data, annual reports and 10-K filings",
-        custom_instructions=financial_bot_instructions,
-        agent_progress_callback=agent_progress_callback,
+    agent = Agent.from_corpus(
+        vectara_customer_id=_cfg.customer_id,
+        vectara_corpus_id=_cfg.corpus_id,
+        vectara_api_key=_cfg.api_key,
+        tool_name="ask_ucsf_ortho",
+        data_description="UCSF Orthopedic Website",
+        assistant_specialty="UCSF Orthopedic department",
+        vectara_summarizer="vectara-summary-ext-24-05-med-omni",
+        vectara_reranker="multilingual_reranker_v1",
     )
     agent.report()
     return agent
 
 
 def get_agent_config() -> OmegaConf:
-    companies = ", ".join(tickers.values())
     cfg = OmegaConf.create({
         'customer_id': str(os.environ['VECTARA_CUSTOMER_ID']),
         'corpus_id': str(os.environ['VECTARA_CORPUS_ID']),
         'api_key': str(os.environ['VECTARA_API_KEY']),
         'examples': os.environ.get('QUERY_EXAMPLES', None),
-        'demo_name': "finance-chat",
-        'demo_welcome': "Financial Assistant demo.",
-        'demo_description': f"This assistant can help you with any questions about the financials of several companies:\n\n **{companies}**.\n"
+        'demo_name': "UCSF Ortho Demo",
+        'demo_welcome': "",
+        'demo_description': "This assistant can help you with any questions about UCSF Orthopedic department."
     })
     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="Financial Assistant", layout="wide")
+   st.set_page_config(page_title="UCSF Ortho Assistant", layout="wide")
    nest_asyncio.apply()
    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==0.1.22
+vectara-agentic==0.1.24

st_app.py

@@ -91,12 +91,12 @@ async def launch_bot():
             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"
-        )
+        # 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()
@@ -132,8 +132,8 @@ 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)
+            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)