Update agent.py

Updating the agent tools and factory

agent.py

@@ -1,4 +1,3 @@
-import os
 import pandas as pd
 import requests
 from pydantic import Field, BaseModel
@@ -8,92 +7,34 @@ 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):
+years = range(2015, 2025)
 
-    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
+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."
+def create_assistant_tools(cfg):
 
-    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())}.")
 
+    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_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",
+    summarizer = 'vectara-summary-ext-24-05-med-omni'
+    ask_publications = vec_factory.create_rag_tool(
+        tool_name = "ask_publications",
         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.
+        Responds to an user question about a particular result, based on the publications.
         """,
-        tool_args_schema = QueryTranscriptsArgs,
+        tool_args_schema = QueryPublicationsArgs,
         reranker = "multilingual_reranker_v1", rerank_k = 100,
         n_sentences_before = 2, n_sentences_after = 2, lambda_val = 0.005,
         summary_num_results = 10,
@@ -105,50 +46,25 @@ def create_assistant_tools(cfg):
     return (
             [tools_factory.create_tool(tool) for tool in
                 [
-                    get_company_info,
                     get_valid_years,
-                    fmp_income_statement,
                 ]
             ] +
-            tools_factory.financial_tools() +
-            [ask_transcripts]
+            tools_factory.standard_tools() +
+            [ask_publications]
     )
 
 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.
+    menarini_bot_instructions = """
+    - You are a helpful clinical trial assistant, with expertise in clinical trial test publications, in conversation with a user. 
+    - Use the ask_publications tool to answer most questions about the results of clinical trials, risks, and more.
+    - Responses from ask_publications are summarized. You don't need to further summarize them.
     """
 
     agent = Agent(
         tools=create_assistant_tools(_cfg),
-        topic="Financial data, annual reports and 10-K filings",
-        custom_instructions=financial_bot_instructions,
+        topic="Drug trials publications",
+        custom_instructions=menarini_bot_instructions,
         agent_progress_callback=agent_progress_callback,
     )
     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"
-    })
-    return cfg
+    return agent