Update rag_tools.py

rag_tools.py

@@ -1,54 +1,36 @@
-"""
-Tools for the RAG agent: local semantic search and web search via Tavily.
+"""Tool definitions for the RAG agent.
+
+Provides two tools:
+- search_local_kb: semantic search over the local ChromaDB vector store.
+- web_search: web search via Tavily.
 """
 
-from typing import List
+from typing import List, Dict
 
 from langchain.tools import tool
 from langchain_ollama import ChatOllama
-from langchain_chroma import Chroma
 from langchain_tavily import TavilySearchResults
 
-# Local semantic search tool
-@tool("search_local_kb")
-def search_local_kb(query: str, top_k: int = 3) -> str:
-    """Search the local ChromaDB knowledge base.
+# Local search tool will be created dynamically in agent.py because it needs the vectorstore.
 
-    Parameters
-    ----------
-    query: str
-        The user's query.
-    top_k: int, optional
-        Number of top results to return.
-
-    Returns
-    -------
-    str
-        Concatenated content of the top results.
-    """
-    # Load the vector store (persisted)
-    vectorstore = Chroma(persist_directory="./chroma_db", embedding_function=ChatOllama(model="nomic-embed-text"))
-    retriever = vectorstore.as_retriever(search_kwargs={"k": top_k})
-    docs = retriever.invoke(query)
-    # docs is a list of Document objects
-    return "\n\n---\n\n".join([doc.page_content for doc in docs])
-
-# Web search tool via Tavily
-@tool("web_search")
+@tool
 def web_search(query: str) -> str:
-    """Perform a web search using Tavily.
+    """Search the web using Tavily and return a short summary.
 
     Parameters
     ----------
     query: str
-        The user's query.
+        The search query.
 
     Returns
     -------
     str
-        Summarized search results.
+        A concise answer with a source tag.
     """
-    tavily = TavilySearchResults(api_key="${TAVILY_API_KEY}")
+    tavily = TavilySearchResults(max_results=3, api_key=None)  # API key is taken from env
     results = tavily.run(query)
-    # results is a list of dicts with keys: title, url, content
-    return "\n\n---\n\n".join([f"{r['title']}\n{r['url']}\n{r.get('content', '')}" for r in results])
+    # Build a simple summary from the results
+    summary = "\n".join([f"{idx+1}. {r['title']}: {r['content'][:200]}" for idx, r in enumerate(results)])
+    return f"[Web Search]\n{summary}\nSource: tavily"
+
+# The local search tool will be defined in agent.py where the vectorstore is available.