Generative AI Course in Delhi: LLMs, RAG, Vector Databases and AI Agents

# Production Retrieval-Augmented Generation (RAG) Architecture
from langchain_community.document_loaders import PyPDFLoader
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_community.embeddings import HuggingFaceEmbeddings
from langchain_community.vectorstores import Chroma
from langchain_core.prompts import ChatPromptTemplate
from langchain_core.runnables import RunnablePassthrough
from langchain_core.output_parsers import StrOutputParser

# 1. Document Ingestion & Chunking
loader = PyPDFLoader("data/datadrix_enterprise_policy.pdf")
docs = loader.load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=600, chunk_overlap=100)
chunks = text_splitter.split_documents(docs)

# 2. Vector Embedding & Local ChromaDB Storage
embedding_model = HuggingFaceEmbeddings(model_name="all-MiniLM-L6-v2")
vector_db = Chroma.from_documents(chunks, embedding_model, persist_directory="./chroma_db")
retriever = vector_db.as_retriever(search_kwargs={"k": 3})

# 3. Contextual RAG Prompt
rag_prompt = ChatPromptTemplate.from_template("""
You are an expert AI Assistant at Datadrix. Answer the user question based strictly on the provided context.
Context:
{context}

Question: {question}
Answer concisely with professional technical accuracy:
""")

# 4. End-to-End RAG Chain Execution
def format_docs(docs):
    return "

".join(doc.page_content for doc in docs)

rag_chain = (
    {"context": retriever | format_docs, "question": RunnablePassthrough()}
    | rag_prompt
    | StrOutputParser()
)