updates to work with ANTHROPIC

agent.py

@@ -30,11 +30,14 @@ prompt = """
         $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. 
+    Generate a coherent response 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.
+    Your response should be comprehensive and include all relevant information from the search results. Do not omit any relevant information.
+    If multiple trials are mentioned in the search results, include all relevant trials in your response, and highlight the various trials included.
     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."}
+    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."}
 ]
 """
 
@@ -54,71 +57,48 @@ def create_assistant_tools(cfg):
         Responds to an user question about a particular result, based on the publications.
         """,
         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
+                "cutoff": 0.1
             },
             {
                 "type": "mmr",
-                "diversity_bias": 0.2,
-                "limit": 50
+                "diversity_bias": 0.1,
+                "limit": 100
             }
         ],
-        n_sentences_before = 2, n_sentences_after = 2, lambda_val = 0.005,
-        summary_num_results = 15,
+        n_sentences_before = 3, n_sentences_after = 3, lambda_val = 0.005,
+        summary_num_results = 25,
         vectara_summarizer = summarizer,
         include_citations = True,
-        vectara_prompt_text=prompt,
+        vectara_prompt_text = prompt,
         save_history = True,
-        verbose=False
+        verbose = True
     )
 
-    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]
+            [ask_publications]
     )
 
 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. 
+    - You are an expert in clinical trial and statistical data analysis 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.
+    - If asked about clinical trial, cover all relevant trials in your response (avoid aggregating results across trials, unless specifically asked to do so).
     - 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.
+      If the initial query lacks comprehensive data, try to call ask_publications with a different or refined query until you retrieve all necessary numerical details.
+      You can try multiple times. You can include additional information about the context of the query (like clinical trial name) to get more relevant results.
+    - If you are missing information about a specific trial, or some data item, call the ask_publication tool with a specific query to retrieve the missing information.
+    - If ask_publications returns citations or references, include them in your response.
     - 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.
+    2) Your responses must include contextual information like sample size (n) 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.

app.py

@@ -1,10 +1,13 @@
 import streamlit as st
+import torch
 from st_app import launch_bot
 import uuid
 
 import nest_asyncio
 import asyncio
 
+torch.classes.__path__ = []
+
 # Setup for HTTP API Calls to Amplitude Analytics
 if 'device_id' not in st.session_state:
     st.session_state.device_id = str(uuid.uuid4())
@@ -12,7 +15,11 @@ if 'device_id' not in st.session_state:
 if "feedback_key" not in st.session_state:
     st.session_state.feedback_key = 0
 
+async def main():
+    await launch_bot()
+
 if __name__ == "__main__":
    st.set_page_config(page_title="Menarini Assistant", layout="wide")
+
    nest_asyncio.apply()
-   asyncio.run(launch_bot())
+   asyncio.run(main())

requirements.txt

@@ -1,9 +1,8 @@
 omegaconf==2.3.0
 python-dotenv==1.0.1
-streamlit==1.41.1
-streamlit_pills==0.3.0
+streamlit==1.43.2
 streamlit_feedback==0.1.3
 uuid==1.30
 langdetect==1.0.9
 langcodes==3.4.0
-vectara-agentic==0.2.1
+vectara-agentic==0.2.8

st_app.py

@@ -1,4 +1,3 @@
-from PIL import Image
 import sys
 import re