agent.pypersonalLangchainv1.0.0

LangChain: Research Assistant

Research agent with web search. Gathers info, synthesizes findings, writes reports.

Setup time: ~15 min

Model: GPT-4o

Cost: ~$0.25/day

Last updated: Mar 16, 2026

byRunbooks Communitycontributor

Template

agent.py

# Install: pip install langchain langchain-openai langchain-community google-search-results

from langchain_openai import ChatOpenAI
from langchain.agents import AgentExecutor, create_openai_tools_agent
from langchain_community.tools import DuckDuckGoSearchRun
from langchain.tools import Tool
from langchain.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain.memory import ConversationBufferMemory
import os

# --- Config ---
llm = ChatOpenAI(model="gpt-4o", temperature=0.2)

# --- Tools ---
search = DuckDuckGoSearchRun()

tools = [
    Tool(
        name="web_search",
        func=search.run,
        description="Search the web for current information. Use for facts, news, and research.",
    ),
]

# --- Agent prompt ---
prompt = ChatPromptTemplate.from_messages([
    ("system", """You are a thorough research assistant. When given a research topic:
1. Break it into sub-questions
2. Search for each sub-question
3. Synthesize findings into a clear, structured report
4. Cite your sources with URLs when possible
5. Distinguish between facts and opinions
6. Note any conflicting information you find

Be systematic. Search multiple times to get comprehensive coverage."""),
    MessagesPlaceholder(variable_name="chat_history"),
    ("human", "{input}"),
    MessagesPlaceholder(variable_name="agent_scratchpad"),
])

# --- Build agent ---
memory = ConversationBufferMemory(memory_key="chat_history", return_messages=True)
agent = create_openai_tools_agent(llm, tools, prompt)
agent_executor = AgentExecutor(
    agent=agent,
    tools=tools,
    memory=memory,
    verbose=True,
    max_iterations=10,
)

if __name__ == "__main__":
    print("Research Assistant ready. Ask me to research any topic.")
    while True:
        query = input("\nResearch: ")
        if query.lower() == "quit":
            break
        result = agent_executor.invoke({"input": query})
        print(f"\n{result['output']}")

Setup

1
Copy the agent.py content above.
2
Create a Python virtual environment and install dependencies.
3
Set your OPENAI_API_KEY environment variable.
4
Run: python agent.py

Run with LangChain

This is a Python script using LangChain. Set up a virtual environment and install dependencies.

# 1. Create a virtual environment
python -m venv venv && source venv/bin/activate

# 2. Install dependencies
pip install langchain langchain-openai langchain-community chromadb

# 3. Set your API key
export OPENAI_API_KEY="sk-..."

# 4. Save the agent.py from above and run it
python agent.py