llms-generative-ai

name	llms-generative-ai
description	LLMs, prompt engineering, RAG systems, LangChain, and AI application development
sasmp_version	1.3.0
bonded_agent	06-ml-ai-engineer
bond_type	PRIMARY_BOND
skill_version	2.0.0
last_updated	2025-01
complexity	advanced
estimated_mastery_hours	180
prerequisites	["python-programming","machine-learning"]
unlocks	["deep-learning","mlops"]

LLMs & Generative AI

Production-grade LLM applications with prompt engineering, RAG systems, and modern AI development patterns.

Quick Start

# Production RAG System with LangChain (2024-2025)
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_community.vectorstores import Chroma
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_core.output_parsers import StrOutputParser

# Initialize components
llm = ChatOpenAI(model="gpt-4-turbo-preview", temperature=0)
embeddings = OpenAIEmbeddings(model="text-embedding-3-small")

# Document processing
text_splitter = RecursiveCharacterTextSplitter(
    chunk_size=1000,
    chunk_overlap=200,
    separators=["\n\n", "\n", ". ", " ", ""]
)

documents = text_splitter.split_documents(raw_documents)

# Vector store
vectorstore = Chroma.from_documents(
    documents=documents,
    embedding=embeddings,
    persist_directory="./chroma_db"
)
retriever = vectorstore.as_retriever(
    search_type="mmr",  # Maximum Marginal Relevance
    search_kwargs={"k": 5, "fetch_k": 10}
)

# RAG chain
template = """Answer the question based only on the following context:

Context: {context}

Question: {question}

Answer thoughtfully and cite specific parts of the context."""

prompt = ChatPromptTemplate.from_template(template)

rag_chain = (
    {: retriever, : RunnablePassthrough()}
    | prompt
    | llm
    | StrOutputParser()
)


response = rag_chain.invoke()
(response)