LangChain Chains, Agents and Tools

from langchain.llms import OpenAI
from langchain.prompts import PromptTemplate
from langchain.chains import LLMChain

# 1. Define LLM
llm = OpenAI(model="gpt-3.5-turbo", temperature=0.7)

# 2. Define prompt template
prompt = PromptTemplate(
    input_variables=["topic"],
    template="Explain {topic} in simple words."
)

# 3. Create chain
chain = LLMChain(llm=llm, prompt=prompt)

# 4. Run chain
result = chain.invoke({"topic": "Microservices"})
print(result["text"])

from langchain.chains import RetrievalQA
from langchain.vectorstores import FAISS
from langchain.embeddings import OpenAIEmbeddings
from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.llms import OpenAI

# Load and split document
loader = PyPDFLoader("data/tech_document.pdf")
docs = loader.load()
splitter = RecursiveCharacterTextSplitter(chunk_size=1000,
    chunk_overlap=200)
chunks = splitter.split_documents(docs)

# Create vector store
embeddings = OpenAIEmbeddings()
vectorstore = FAISS.from_documents(chunks, embeddings)
retriever = vectorstore.as_retriever()

# Create RetrievalQA chain
qa_chain = RetrievalQA.from_chain_type(llm=OpenAI(),
    chain_type="stuff", retriever=retriever)

result = qa_chain.invoke({"query": "What is the main topic of this document?"})
print(result["result"])

from langchain.agents import initialize_agent, Tool
from langchain.tools import DuckDuckGoSearchRun
from langchain.llms import OpenAI

# Define tools
search = DuckDuckGoSearchRun()
tools = [
    Tool(
        name="Search",
        func=search.run,
        description="Useful for searching information on the internet"
    )
]

# Create agent
llm = OpenAI(model="gpt-3.5-turbo", temperature=0.7)
agent = initialize_agent(tools, llm, agent="zero-shot-react-description",
                         verbose=True)

# Run agent
response = agent.invoke({"input": "Find latest news about AU Small Finance Bank"})
print(response["output"])