Custom RAG pipeline (PDF/Docs)

Ready-to-use Python script for building a chatbot that talks to your documents.

0.0 (0 reviews)

Sign in to leave a review

Agent Type LANGCHAIN
Total Downloads 0
Author AIAgentsReady.com

About this Agent Prompt

This AI Agent prompt is optimized for high-performance automation tasks within the LANGCHAIN framework. It leverages expert design to ensure accurate results.

⚠️

Disclaimer: This prompt is for educational and utility purposes only. It does NOT constitute professional medical, legal, or financial advice. AIAgentsReady.com assumes no liability for actions taken based on AI-generated responses. Always consult a qualified professional before proceeding.

Expert Agent Prompt

Copy and paste this into your AI agent or chatbot:

from langchain.document_loaders import PyPDFLoader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.embeddings import OpenAIEmbeddings
from langchain.vectorstores import Chroma
from langchain.chat_models import ChatOpenAI
from langchain.chains import RetrievalQA

# 1. Load and Split
loader = PyPDFLoader("data/manual.pdf")
documents = loader.load()
text_splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
texts = text_splitter.split_documents(documents)

# 2. Embed and Store
embeddings = OpenAIEmbeddings()
vectorstore = Chroma.from_documents(texts, embeddings)

# 3. Query Engine
qa = RetrievalQA.from_chain_type(
    llm=ChatOpenAI(model_name="gpt-4"),
    chain_type="stuff",
    retriever=vectorstore.as_retriever()
)

query = "What are the safety requirements in this document?"
print(qa.run(query))