Update web search tool

basic_agent.py

@@ -2,7 +2,6 @@ import os
 import re
 import asyncio
 
-from tavily import AsyncTavilyClient
 from llama_index.core.tools import FunctionTool
 from llama_index.llms.huggingface_api import HuggingFaceInferenceAPI
 from llama_index.tools.duckduckgo import DuckDuckGoSearchToolSpec
@@ -19,6 +18,11 @@ from llama_index.core.agent.workflow import (
 
 from multimodality_tools import get_image_qa_tool, get_transcription_tool, \
     get_excel_analysis_tool, get_excel_tool, get_csv_analysis_tool, get_csv_tool, _get_file, get_read_file_tool
+from web_tools import get_search_web_tool
+
+answer_specifics = ("When answering, provide ONLY the precise answer requested. " 
+                    "Do not include explanations, steps, reasoning, or additional text. Be direct and specific. "
+                    'For example, if asked "What is the capital of France?", respond simply with "Paris".')
 
 class BasicAgent:
     def __init__(self, ollama=False, langfuse=False):
@@ -42,8 +46,8 @@ class BasicAgent:
             system_prompt=(
                 "You are a general AI assistant. I will ask you a question. "
                 "Report your thoughts, delegate work to other agents if necessary, and" 
-                "finish your answer with the following template: "
-                "FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number "
+                "finish your answer with the following template:\n"
+                "FINAL ANSWER: [YOUR FINAL ANSWER]. \nYOUR FINAL ANSWER should be a number "
                 "OR as few words as possible OR a comma separated list of numbers and/or "
                 "strings. If you are asked for a number, don't use comma to write your "
                 "number neither use units such as $ or percent sign unless specified otherwise. "
@@ -75,12 +79,7 @@ class BasicAgent:
         )
 
         tool_spec = DuckDuckGoSearchToolSpec()
-        search_tool = FunctionTool.from_defaults(tool_spec.duckduckgo_full_search)
-        # In case DuckDuckGo is not good enough
-        async def search_web(query: str) -> str:
-            """Searches the web to answer questions."""
-            client = AsyncTavilyClient(api_key=os.getenv("TAVILY"))
-            return str(await client.search(query))
+        search_tool = FunctionTool.from_defaults(tool_spec.duckduckgo_full_search)    
 
         web_search_agent = FunctionAgent(
             name="WebAgent",
@@ -91,7 +90,7 @@ class BasicAgent:
                 "you communicate this clearly. Always hand off your answer to MainAgent."
             ),
             llm=llm,
-            tools=[search_web],
+            tools=[get_search_web_tool()],
             can_handoff_to=["MainAgent"],
         )
 

web_tools.py

@@ -0,0 +1,28 @@
+"""Tools to search the web and extract information."""
+import os
+
+from tavily import AsyncTavilyClient
+from llama_index.core.tools import FunctionTool
+
+async def tavily_web_tool(query: str) -> str:
+    """
+    Search the web with a given query and return the first two results.
+    If results do not return what you are looking for, rephrasing the query can help.
+    """
+    client = AsyncTavilyClient(api_key=os.getenv("TAVILY"))
+    res = await client.search(query)
+    urls = [r.get("url") for r in res.get("results", []) if "url" in r][:2]
+    page_contents = {
+        url: await client.extract(url)
+        for url in urls
+    }
+    return "\n\n".join(
+        f"RESULT {i}:\n{content}"
+        for i, content in enumerate(page_contents.values())
+    )
+
+def get_search_web_tool():
+    return FunctionTool.from_defaults(
+        fn=tavily_web_tool,
+        description="Search the web with a given query and return the first two results."
+    )