Build ChromaDB + Tavily RAG agent with Ollama embeddings, local/web tools, create_agent routing, and CLI ingest flow.: update agent.py

agent.py

@@ -1,32 +1,28 @@
-"""
-Create a LangChain agent that chooses between local KB and web search.
-"""
-
-from typing import List, Dict
-
 from langchain.agents import create_agent
-from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
-from langchain.schema.document import Document
+from langchain_ollama import ChatOllama
 
-# Import tools
 from tools import search_local_kb, web_search
 
+OLLAMA_BASE_URL = "http://127.0.0.1:11434"
+LLM_MODEL = "llama3"
+
 SYSTEM_PROMPT = """
-You are an assistant that can answer questions using either a local knowledge base or the web. Use the tool `search_local_kb` when the question is about content already in your documents. Use `web_search` for up‑to‑date facts.
-When you provide an answer, include the source: either "chromadb" or "tavily".
+You are a RAG assistant that must choose the best source before answering.
+
+Rules:
+- Use search_local_kb for questions about local notes, internal documents, course materials, or any topic that may already exist in the local knowledge base.
+- Use web_search for current events, recent news, live facts, or questions that clearly require the internet.
+- Do not call both tools unless the first one clearly failed to provide enough information.
+- Every final answer must end with a separate line in the exact format: "Источник: chromadb" or "Источник: tavily".
+- Answer in Russian.
 """
 
-# Prompt template with tool messages
-prompt = ChatPromptTemplate.from_messages([
-    ("system", SYSTEM_PROMPT),
-    MessagesPlaceholder("history"),
-    ("human", "{input}"),
-])
-
-# Create agent harness
 agent = create_agent(
-    model="ollama:llama3",
+    model=ChatOllama(
+        model=LLM_MODEL,
+        base_url=OLLAMA_BASE_URL,
+        temperature=0,
+    ),
     tools=[search_local_kb, web_search],
     system_prompt=SYSTEM_PROMPT,
-    prompt_template=prompt,
 )