Update agent.py

update model and prompt

agent.py

@@ -9,15 +9,34 @@ from vectara_agentic.tools import ToolsFactory, VectaraToolFactory
 
 initial_prompt = "How can I help you today?"
 
-years = range(2015, 2025)
-
-
-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
+prompt = """
+[
+  {"role": "system", "content": "You are a search bot 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 cobble facts together from multiple search results, instead summarize the main facts into a consistent and easy to understand response.
+    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.
+    For queries where only a short answer is required, you can give a brief response.
+    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 *** $vectaraQuery***, are listed below, some are text, some MAY be tables in the format described above.
+    #foreach ($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 *** by summarizing the search results provided. Give a slight preference to search results that appear earlier in the list.
+    Include as many statistical numerical evidence from the search results in 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."}
+]
+"""
 
 def create_assistant_tools(cfg):
 
@@ -28,7 +47,7 @@ def create_assistant_tools(cfg):
     vec_factory = VectaraToolFactory(vectara_api_key=cfg.api_key,
                                      vectara_customer_id=cfg.customer_id,
                                      vectara_corpus_id=cfg.corpus_id)
-    summarizer = 'vectara-summary-ext-24-05-med-omni'
+    summarizer = 'vectara-summary-table-md-query-ext-jan-2025-gpt-4o'
     ask_publications = vec_factory.create_rag_tool(
         tool_name = "ask_publications",
         tool_description = """
@@ -36,28 +55,26 @@ def create_assistant_tools(cfg):
         """,
         tool_args_schema = QueryPublicationsArgs,
         reranker = "multilingual_reranker_v1", rerank_k = 100,
-        n_sentences_before = 2, n_sentences_after = 2, lambda_val = 0.005,
+        n_sentences_before = 3, n_sentences_after = 3, lambda_val = 0.005,
         summary_num_results = 10,
         vectara_summarizer = summarizer,
         include_citations = True,
+        vectara_prompt_text=prompt
     )
 
     tools_factory = ToolsFactory()
     return (
-            [tools_factory.create_tool(tool) for tool in
-                [
-                    get_valid_years,
-                ]
-            ] +
             tools_factory.standard_tools() +
             [ask_publications]
     )
 
 def initialize_agent(_cfg, agent_progress_callback=None):
     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.
+    - You are a helpful clinical trial assistant, with expertise in clinical trial publications, in conversation with a user. 
+    - You always respond to the user with supporting evidence based on the data, with p-values where available.
+    - Your responses follow a standard statistical format for results of clinical trials.
+      for example: instead of "Reduced 4-component MACE by 30%" use "Reduced 4-component MACE by 30% (HR: 0.70; p=0.002)"
+    - Call the ask_publications tool as much as needed, with appropiate queries, until you have all the numerical data to respond properly to the user question.
     """
 
     agent = Agent(