Design LLM applications using the LangChain framework with agents, memory, and tool integration patterns. Use when building LangChain applications, implementing AI agents, or creating complex LLM workflows.
# For short conversations (< 10 messages)
from langchain.memory import ConversationBufferMemory
memory = ConversationBufferMemory()
# For long conversations (summarize old messages)
from langchain.memory import ConversationSummaryMemory
memory = ConversationSummaryMemory(llm=llm)
# For sliding window (last N messages)
from langchain.memory import ConversationBufferWindowMemory
memory = ConversationBufferWindowMemory(k=5)
# For entity tracking
from langchain.memory import ConversationEntityMemory
memory = ConversationEntityMemory(llm=llm)
# For semantic retrieval of relevant history
from langchain.memory import VectorStoreRetrieverMemory
memory = VectorStoreRetrieverMemory(retriever=retriever)
Callback System
Custom Callback Handler
from langchain.callbacks.base import BaseCallbackHandler
class CustomCallbackHandler(BaseCallbackHandler):
def on_llm_start(self, serialized, prompts, **kwargs):
print(f"LLM started with prompts: {prompts}")
def on_llm_end(self, response, **kwargs):
print(f"LLM ended with response: {response}")
def on_llm_error(self, error, **kwargs):
print(f"LLM error: {error}")
def on_chain_start(self, serialized, inputs, **kwargs):
print(f"Chain started with inputs: {inputs}")
def on_agent_action(self, action, **kwargs):
print(f"Agent taking action: {action}")
# Use callback
agent.run("query", callbacks=[CustomCallbackHandler()])
Testing Strategies
import pytest
from unittest.mock import Mock
def test_agent_tool_selection():
# Mock LLM to return specific tool selection
mock_llm = Mock()
mock_llm.predict.return_value = "Action: search_database\nAction Input: test query"
agent = initialize_agent(tools, mock_llm, agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION)
result = agent.run("test query")
# Verify correct tool was selected
assert "search_database" in str(mock_llm.predict.call_args)
def test_memory_persistence():
memory = ConversationBufferMemory()
memory.save_context({"input": "Hi"}, {"output": "Hello!"})
assert "Hi" in memory.load_memory_variables({})['history']
assert "Hello!" in memory.load_memory_variables({})['history']
Performance Optimization
1. Caching
from langchain.cache import InMemoryCache
import langchain
langchain.llm_cache = InMemoryCache()
2. Batch Processing
# Process multiple documents in parallel
from langchain.document_loaders import DirectoryLoader
from concurrent.futures import ThreadPoolExecutor
loader = DirectoryLoader('./docs')
docs = loader.load()
def process_doc(doc):
return text_splitter.split_documents([doc])
with ThreadPoolExecutor(max_workers=4) as executor:
split_docs = list(executor.map(process_doc, docs))
3. Streaming Responses
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
llm = OpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()])
Resources
references/agents.md: Deep dive on agent architectures