Langchain Architecture

from langchain.chains import RetrievalQA
from langchain.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import Chroma
from langchain.embeddings import OpenAIEmbeddings

# Load and process documents
loader = TextLoader('documents.txt')
documents = loader.load()

text_splitter = CharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
texts = text_splitter.split_documents(documents)

# Create vector store
embeddings = OpenAIEmbeddings()
vectorstore = Chroma.from_documents(texts, embeddings)

# Create retrieval chain
qa_chain = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type="stuff",
    retriever=vectorstore.as_retriever(),
    return_source_documents=True
)

# Query
result = qa_chain({"query": "What is the main topic?"})

from langchain.agents import Tool, AgentExecutor
from langchain.agents.react.base import ReActDocstoreAgent
from langchain.tools import tool

@tool
def search_database(query: str) -> str:
    """Search internal database for information."""
    # Your database search logic
    return f"Results for: {query}"

@tool
def send_email(recipient: str, content: str) -> str:
    """Send an email to specified recipient."""
    # Email sending logic
    return f"Email sent to {recipient}"

tools = [search_database, send_email]

agent = initialize_agent(
    tools,
    llm,
    agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
    verbose=True
)

from langchain.chains import LLMChain, SequentialChain
from langchain.prompts import PromptTemplate

# Step 1: Extract key information
extract_prompt = PromptTemplate(
    input_variables=["text"],
    template="Extract key entities from: {text}\n\nEntities:"
)
extract_chain = LLMChain(llm=llm, prompt=extract_prompt, output_key="entities")

# Step 2: Analyze entities
analyze_prompt = PromptTemplate(
    input_variables=["entities"],
    template="Analyze these entities: {entities}\n\nAnalysis:"
)
analyze_chain = LLMChain(llm=llm, prompt=analyze_prompt, output_key="analysis")

# Step 3: Generate summary
summary_prompt = PromptTemplate(
    input_variables=["entities", "analysis"],
    template="Summarize:\nEntities: {entities}\nAnalysis: {analysis}\n\nSummary:"
)
summary_chain = LLMChain(llm=llm, prompt=summary_prompt, output_key="summary")

# Combine into sequential chain
overall_chain = SequentialChain(
    chains=[extract_chain, analyze_chain, summary_chain],
    input_variables=["text"],
    output_variables=["entities", "analysis", "summary"],
    verbose=True
)

# 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)

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()])

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']

from langchain.cache import InMemoryCache
import langchain

langchain.llm_cache = InMemoryCache()

# 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))

from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler

llm = OpenAI(streaming=True, callbacks=[StreamingStdOutCallbackHandler()])