Tuesday, November 28, 2023
HomeAIUse Amazon SageMaker Studio to construct a RAG query answering resolution with...

Use Amazon SageMaker Studio to construct a RAG query answering resolution with Llama 2, LangChain, and Pinecone for quick experimentation

Retrieval Augmented Era (RAG) permits you to present a big language mannequin (LLM) with entry to knowledge from exterior information sources corresponding to repositories, databases, and APIs with out the necessity to fine-tune it. When utilizing generative AI for query answering, RAG allows LLMs to reply questions with probably the most related, up-to-date info and optionally cite their knowledge sources for verification.

A typical RAG resolution for information retrieval from paperwork makes use of an embeddings mannequin to transform the information from the information sources to embeddings and shops these embeddings in a vector database. When a person asks a query, it searches the vector database and retrieves paperwork which might be most just like the person’s question. Subsequent, it combines the retrieved paperwork and the person’s question in an augmented immediate that’s despatched to the LLM for textual content technology. There are two fashions on this implementation: the embeddings mannequin and the LLM that generates the ultimate response.

On this submit, we show methods to use Amazon SageMaker Studio to construct a RAG query answering resolution.

Utilizing notebooks for RAG-based query answering

Implementing RAG sometimes entails experimenting with varied embedding fashions, vector databases, textual content technology fashions, and prompts, whereas additionally debugging your code till you obtain a useful prototype. Amazon SageMaker gives managed Jupyter notebooks geared up with GPU situations, enabling you to quickly experiment throughout this preliminary part with out spinning up extra infrastructure. There are two choices for utilizing notebooks in SageMaker. The primary possibility is quick launch notebooks obtainable by way of SageMaker Studio. In SageMaker Studio, the built-in growth atmosphere (IDE) purpose-built for ML, you may launch notebooks that run on totally different occasion varieties and with totally different configurations, collaborate with colleagues, and entry extra purpose-built options for machine studying (ML). The second possibility is utilizing a SageMaker pocket book occasion, which is a completely managed ML compute occasion working the Jupyter Pocket book app.

On this submit, we current a RAG resolution that augments the mannequin’s information with extra knowledge from exterior information sources to supply extra correct responses particular to a customized area. We use a single SageMaker Studio pocket book working on an ml.g5.2xlarge occasion (1 A10G GPU) and Llama 2 7b chat hf, the fine-tuned model of Llama 2 7b, which is optimized for dialog use instances from Hugging Face Hub. We use two AWS Media & Leisure Weblog posts because the pattern exterior knowledge, which we convert into embeddings with the BAAI/bge-small-en-v1.5 embeddings. We retailer the embeddings in Pinecone, a vector-based database that gives high-performance search and similarity matching. We additionally focus on methods to transition from experimenting within the pocket book to deploying your fashions to SageMaker endpoints for real-time inference if you full your prototyping. The identical strategy can be utilized with totally different fashions and vector databases.

Resolution overview

The next diagram illustrates the answer structure.

Implementing the answer consists of two high-level steps: creating the answer utilizing SageMaker Studio notebooks, and deploying the fashions for inference.

Develop the answer utilizing SageMaker Studio notebooks

Full the next steps to begin creating the answer:

  1. Load the Llama-2 7b chat mannequin from Hugging Face Hub within the pocket book.
  2. Create a PromptTemplate with LangChain and use it to create prompts in your use case.
  3. For 1–2 instance prompts, add related static textual content from exterior paperwork as immediate context and assess if the standard of the responses improves.
  4. Assuming that the standard improves, implement the RAG query answering workflow:
    • Collect the exterior paperwork that may assist the mannequin higher reply the questions in your use case.
    • Load the BGE embeddings mannequin and use it to generate embeddings of those paperwork.
    • Retailer these embeddings in a Pinecone index.
    • When a person asks a query, carry out a similarity search in Pinecone and add the content material from probably the most related paperwork to the immediate’s context.

Deploy the fashions to SageMaker for inference at scale

Once you hit your efficiency targets, you may deploy the fashions to SageMaker for use by generative AI functions:

  1. Deploy the Llama-2 7b chat mannequin to a SageMaker real-time endpoint.
  2. Deploy the BAAI/bge-small-en-v1.5 embeddings mannequin to a SageMaker real-time endpoint.
  3. Use the deployed fashions in your query answering generative AI functions.

Within the following sections, we stroll you thru the steps of implementing this resolution in SageMaker Studio notebooks.


To comply with the steps on this submit, you want to have an AWS account and an AWS Identification and Entry Administration (IAM) position with permissions to create and entry the answer assets. In case you are new to AWS, see Create a standalone AWS account.

To make use of SageMaker Studio notebooks in your AWS account, you want a SageMaker area with a person profile that has permissions to launch the SageMaker Studio app. In case you are new to SageMaker Studio, the Fast Studio setup is the quickest option to get began. With a single click on, SageMaker provisions the SageMaker area with default presets, together with establishing the person profile, IAM position, IAM authentication, and public web entry. The pocket book for this submit assumes an ml.g5.2xlarge occasion sort. To evaluate or improve your quota, open the AWS Service Quotas console, select AWS Providers within the navigation pane, select Amazon SageMaker, and seek advice from the worth for Studio KernelGateway apps working on ml.g5.2xlarge situations.

After confirming your quota restrict, you want to full the dependencies to make use of Llama 2 7b chat.

Llama 2 7b chat is offered below the Llama 2 license. To entry Llama 2 on Hugging Face, you want to full a couple of steps first:

  1. Create a Hugging Face account when you don’t have one already.
  2. Full the shape “Request entry to the following model of Llama” on the Meta web site.
  3. Request entry to Llama 2 7b chat on Hugging Face.

After you’ve got been granted entry, you may create a brand new entry token to entry fashions. To create an entry token, navigate to the Settings web page on the Hugging Face web site.

You could have an account with Pinecone to make use of it as a vector database. Pinecone is offered on AWS by way of the AWS Market. The Pinecone web site additionally gives the choice to create a free account that comes with permissions to create a single index, which is adequate for the needs of this submit. To retrieve your Pinecone keys, open the Pinecone console and select API Keys.

Arrange the pocket book and atmosphere

To comply with the code on this submit, open SageMaker Studio and clone the next GitHub repository. Subsequent, open the pocket book studio-local-gen-ai/rag/RAG-with-Llama-2-on-Studio.ipynb and select the PyTorch 2.0.0 Python 3.10 GPU Optimized picture, Python 3 kernel, and ml.g5.2xlarge because the occasion sort. If that is your first time utilizing SageMaker Studio notebooks, seek advice from Create or Open an Amazon SageMaker Studio Pocket book.

To arrange the event atmosphere, you want to set up the required Python libraries, as demonstrated within the following code:

%%writefile necessities.txt
speed up==0.21.0
!pip set up -U -r necessities.txt

Load the pre-trained mannequin and tokenizer

After you’ve got imported the required libraries, you may load the Llama-2 7b chat mannequin together with its corresponding tokenizers from Hugging Face. These loaded mannequin artifacts are saved within the native listing inside SageMaker Studio. This allows you to swiftly reload them into reminiscence every time you want to resume your work at a distinct time.

import torch

from transformers import (
import transformers

tg_model_id = "meta-llama/Llama-2-7b-chat-hf" #the mannequin id in Hugging Face
tg_model_path = f"./tg_model/{tg_model_id}" #the native listing the place the mannequin shall be saved

tg_model = AutoModelForCausalLM.from_pretrained(tg_model_id, token=hf_access_token,do_sample=True, use_safetensors=True, device_map="auto", torch_dtype=torch.float16
tg_tokenizer = AutoTokenizer.from_pretrained(tg_model_id, token=hf_access_token)

tg_model.save_pretrained(save_directory=tg_model_path, from_pt=True)
tg_tokenizer.save_pretrained(save_directory=tg_model_path, from_pt=True)

Ask a query that requires up-to-date info

Now you can begin utilizing the mannequin and ask questions. Llama-2 chat fashions anticipate the immediate to stick to the next format:

<s>[INST] <<SYS>>
{{ user_message }} [/INST]

You should utilize the PromptTemplate from LangChain to create a recipe primarily based on the immediate format, in an effort to simply create prompts going ahead:

from langchain import PromptTemplate

template = """<s>[INST] <<SYS>>nYou are an assistant for question-answering duties. You're useful and pleasant. Use the next items of retrieved context to reply the question. If you do not know the reply, you simply say I do not know. Use three sentences most and hold the reply concise.
{query} [/INST]
prompt_template = PromptTemplate( template=template, input_variables=['context','question'] )

Let’s ask the mannequin a query that wants latest info from 2023. You should utilize LangChain and particularly the LLMChain sort of chain and go as parameters the LLM, the immediate template you created earlier, and the query:

query = "When can I go to the AWS M&E Buyer Expertise Middle in New York Metropolis?"

tg_tokenizer.add_special_tokens( {"pad_token": "[PAD]"} )
tg_tokenizer.padding_side = "left"

tg_pipe = transformers.pipeline(activity='text-generation', mannequin=tg_model, tokenizer=tg_tokenizer, num_return_sequences=1, eos_token_id=tg_tokenizer.eos_token_id, pad_token_id=tg_tokenizer.eos_token_id, max_new_tokens=400, temperature=0.7)

from langchain.chains import LLMChain
from langchain.llms import HuggingFacePipeline

llm=HuggingFacePipeline(pipeline=tg_pipe, model_kwargs={'temperature':0.7})
llm_chain = LLMChain(llm=llm, immediate=prompt_template)
no_context_response = llm_chain.predict(context="", query=query)

We get the next generated reply:

Thanks for reaching out! The AWS M&E Buyer Expertise Middle in New York Metropolis is presently closed for visits because of the COVID-19 pandemic. Nevertheless, you may examine their official web site or social media accounts for any updates on when the middle will reopen. Within the meantime, you may discover their digital excursions and assets obtainable on-line.

Enhance the reply by including context to the immediate

The reply we generated will not be totally true. Let’s see if we will enhance it by offering some context. You possibly can add an extract from the submit AWS broadcasts new M&E Buyer Expertise Middle in New York, which incorporates updates on the subject from 2023:

context = """Media and leisure (M&E) prospects proceed to face challenges in creating extra content material, extra rapidly, and distributing it to extra endpoints than ever earlier than of their quest to thrill viewers globally. Amazon Net Providers (AWS), together with AWS Companions, have showcased the speedy evolution of M&E options for years at business occasions just like the Nationwide Affiliation of Broadcasters (NAB) Present and the Worldwide Broadcast Conference (IBC). Till now, AWS for M&E know-how demonstrations have been accessible on this means just some weeks out of the 12 months. Clients are extra engaged than ever earlier than; they wish to have greater high quality conversations relating to person expertise and media tooling. These conversations are finest supported by having an interconnected resolution structure for reference. Scheduling a go to of the M&E Buyer Expertise Middle shall be obtainable beginning November thirteenth, please ship an e-mail to AWS-MediaEnt-CXC@amazon.com."""

Use the LLMChain once more and go the previous textual content as context:

context_response = llm_chain.predict(context=context, query=query)

The brand new response solutions the query with up-to-date info:

You possibly can go to the AWS M&E Buyer Expertise Middle in New York Metropolis ranging from November thirteenth. Please ship an e-mail to AWS-MediaEnt-CXC@amazon.com to schedule a go to.

We’ve confirmed that by including the precise context, the mannequin’s efficiency is improved. Now you may focus your efforts on discovering and including the precise context for the query requested. In different phrases, implement RAG.

Implement RAG query answering with BGE embeddings and Pinecone

At this juncture, you have to determine on the sources of knowledge to boost the mannequin’s information. These sources could possibly be inner webpages or paperwork inside your group, or publicly obtainable knowledge sources. For the needs of this submit and for the sake of simplicity, we now have chosen two AWS Weblog posts printed in 2023:

These posts are already obtainable as PDF paperwork within the knowledge mission listing in SageMaker Studio for fast entry. To divide the paperwork into manageable chunks, you may make use of the RecursiveCharacterTextSplitter methodology from LangChain:

from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.document_loaders import PyPDFDirectoryLoader

loader = PyPDFDirectoryLoader("./knowledge/")

paperwork = loader.load()

docs = text_splitter.split_documents(paperwork)

Subsequent, use the BGE embeddings mannequin bge-small-en created by the Beijing Academy of Synthetic Intelligence (BAAI) that’s obtainable on Hugging Face to generate the embeddings of those chunks. Obtain and save the mannequin within the native listing in Studio. We use fp32 in order that it may run on the occasion’s CPU.

em_model_name = "BAAI/bge-small-en"
em_model_path = f"./em-model"

from transformers import AutoModel
# Load mannequin from HuggingFace Hub
em_model = AutoModel.from_pretrained(em_model_name,torch_dtype=torch.float32)
em_tokenizer = AutoTokenizer.from_pretrained(em_model_name,machine="cuda")

# save mannequin to disk

Use the next code to create an embedding_generator perform, which takes the doc chunks as enter and generates the embeddings utilizing the BGE mannequin:

# Tokenize sentences
def tokenize_text(_input, machine):
    return em_tokenizer(

# Run embedding activity as a perform with mannequin and textual content sentences as enter
def embedding_generator(_input, normalize=True):
    # Compute token embeddings
    with torch.no_grad():
        embedded_output = em_model(
        sentence_embeddings = embedded_output[0][:, 0]
        # normalize embeddings
        if normalize:
            sentence_embeddings = torch.nn.useful.normalize(
    return sentence_embeddings[0, :].tolist()
sample_sentence_embedding = embedding_generator(docs[0].page_content)
print(f"Embedding dimension of the doc --->", len(sample_sentence_embedding))

On this submit, we show a RAG workflow utilizing Pinecone, a managed, cloud-native vector database that additionally gives an API for similarity search. You’re free to rewrite the next code to make use of your most well-liked vector database.

We initialize a Pinecone python consumer and create a brand new vector search index utilizing the embedding mannequin’s output size. We use LangChain’s built-in Pinecone class to ingest the embeddings we created within the earlier step. It wants three parameters: the paperwork to ingest, the embeddings generator perform, and the title of the Pinecone index.

import pinecone
    api_key = os.environ["PINECONE_API_KEY"],
    atmosphere = os.environ["PINECONE_ENV"]
#examine if index already exists, if not we create it
index_name = "rag-index"
if index_name not in pinecone.list_indexes():
        dimension=len(sample_sentence_embedding), ## 384 for bge-small-en 

#insert the embeddings
from langchain.vectorstores import Pinecone
vector_store = Pinecone.from_documents(

With the Llama-2 7B chat mannequin loaded into reminiscence and the embeddings built-in into the Pinecone index, now you can mix these components to boost Llama 2’s responses for our question-answering use case. To realize this, you may make use of the LangChain RetrievalQA, which augments the preliminary immediate with probably the most related paperwork from the vector retailer. By setting return_source_documents=True, you acquire visibility into the precise paperwork used to generate the reply as a part of the response, permitting you to confirm the accuracy of the reply.

from langchain.chains import RetrievalQA
import textwrap

#helper methodology to enhance the readability of the response
def print_response(llm_response):
    temp = [textwrap.fill(line, width=100) for line in llm_response['result'].cut up('n')]
    response="n".be part of(temp)
    print(f"{llm_response['query']}n n{response}'n n Supply Paperwork:")
    for supply in llm_response["source_documents"]:

llm_qa_chain = RetrievalQA.from_chain_type(
    llm=llm, #the Llama-2 7b chat mannequin
    retriever=vector_store.as_retriever(search_kwargs={"okay": 2}), # carry out similarity search in Pinecone
    return_source_documents=True, #present the paperwork that have been used to reply the query
    chain_type_kwargs={"immediate": prompt_template}

We get the next reply:

Q: When can I go to the AWS M&E Buyer Expertise Middle in New York Metropolis?

A: I’m blissful to assist! In accordance with the context, the AWS M&E Buyer Expertise Middle in New York Metropolis shall be obtainable for visits beginning on November thirteenth. You possibly can ship an e-mail to AWS-MediaEnt-CXC@amazon.com to schedule a go to.’

Supply Paperwork:

{‘web page’: 4.0, ‘supply’: ‘knowledge/AWS broadcasts new M&E Buyer Expertise Middle in New York Metropolis _ AWS for M&E Weblog.pdf’}

{‘web page’: 2.0, ‘supply’: ‘knowledge/AWS broadcasts new M&E Buyer Expertise Middle in New York Metropolis _ AWS for M&E Weblog.pdf’}

Let’s attempt a distinct query:

question2=" What number of awards have AWS Media Providers gained in 2023?"

We get the next reply:

Q: What number of awards have AWS Media Providers gained in 2023?

A: In accordance with the weblog submit, AWS Media Providers have gained 5 business awards in 2023.’

Supply Paperwork:

{‘web page’: 0.0, ‘supply’: ‘knowledge/AWS Media Providers awarded business accolades _ AWS for M&E Weblog.pdf’}

{‘web page’: 1.0, ‘supply’: ‘knowledge/AWS Media Providers awarded business accolades _ AWS for M&E Weblog.pdf’}

After you’ve got established a adequate stage of confidence, you may deploy the fashions to SageMaker endpoints for real-time inference. These endpoints are absolutely managed and provide help for auto scaling.

SageMaker gives giant mannequin inference utilizing Giant Mannequin Inference containers (LMIs), which we will make the most of to deploy our fashions. These containers come geared up with pre-installed open supply libraries like DeepSpeed, facilitating the implementation of performance-enhancing methods corresponding to tensor parallelism throughout inference. Moreover, they use DJLServing as a pre-built built-in mannequin server. DJLServing is a high-performance, common model-serving resolution that gives help for dynamic batching and employee auto scaling, thereby growing throughput.

In our strategy, we use the SageMaker LMI with DJLServing and DeepSpeed Inference to deploy the Llama-2-chat 7b and BGE fashions to SageMaker endpoints working on ml.g5.2xlarge situations, enabling real-time inference. If you wish to comply with these steps your self, seek advice from the accompanying pocket book for detailed directions.

You’ll require two ml.g5.2xlarge situations for deployment. To evaluate or improve your quota, open the AWS Service Quotas console, select AWS Providers within the navigation pane, select Amazon SageMaker, and seek advice from the worth for ml.g5.2xlarge for endpoint utilization.

The next steps define the method of deploying customized fashions for the RAG workflow on a SageMaker endpoint:

  • Deploy the Llama-2 7b chat mannequin to a SageMaker real-time endpoint working on an ml.g5.2xlarge occasion for quick textual content technology.
  • Deploy the BAAI/bge-small-en-v1.5 embeddings mannequin to a SageMaker real-time endpoint working on an ml.g5.2xlarge occasion. Alternatively, you may deploy your individual embedding mannequin.
  • Ask a query and use the LangChain RetrievalQA to enhance the immediate with probably the most related paperwork from Pinecone, this time utilizing the mannequin deployed within the SageMaker real-time endpoint:
# convert your native LLM into SageMaker endpoint LLM
llm_sm_ep = SagemakerEndpoint(
    endpoint_name=tg_sm_model.endpoint_name, # <--- Your text-gen mannequin endpoint title
        "temperature": 0.05, 
        "max_new_tokens": 512

llm_qa_smep_chain = RetrievalQA.from_chain_type(
    llm=llm_sm_ep,  # <--- This makes use of SageMaker Endpoint mannequin for inference
    retriever=vector_store.as_retriever(search_kwargs={"okay": 2}),
    chain_type_kwargs={"immediate": prompt_template}
  • Use LangChain to confirm that the SageMaker endpoint with the embedding mannequin works as anticipated in order that it may be used for future doc ingestion:
response_model = smr_client.invoke_endpoint(
    EndpointName=em_sm_model.endpoint_name, <--- Your embedding mannequin endpoint title
        "textual content": "It is a pattern textual content"

outputs = json.hundreds(response_model["Body"].learn().decode("utf8"))['outputs']

Clear up

Full the next steps to scrub up your assets:

  • When you’ve got completed working in your SageMaker Studio pocket book, ensure you shut down the ml.g5.2xlarge occasion to keep away from any costs by selecting the cease icon. You may also arrange lifecycle configuration scripts to routinely shut down assets when they don’t seem to be used.

  • In the event you deployed the fashions to SageMaker endpoints, run the next code on the finish of the pocket book to delete the endpoints:
#delete your textual content technology endpoint
# delete your textual content embedding endpoint
  • Lastly, run the next line to delete the Pinecone index:


SageMaker notebooks present a simple option to kickstart your journey with Retrieval Augmented Era. They permit you to experiment interactively with varied fashions, configurations, and questions with out spinning up extra infrastructure. On this submit, we confirmed methods to improve the efficiency of Llama 2 7b chat in a query answering use case utilizing LangChain, the BGE embeddings mannequin, and Pinecone. To get began, launch SageMaker Studio and run the pocket book obtainable within the following GitHub repo. Please share your ideas within the feedback part!

In regards to the authors

Anastasia Tzeveleka is a Machine Studying and AI Specialist Options Architect at AWS. She works with prospects in EMEA and helps them architect machine studying options at scale utilizing AWS providers. She has labored on initiatives in several domains together with Pure Language Processing (NLP), MLOps and Low Code No Code instruments.

Pranav Murthy is an AI/ML Specialist Options Architect at AWS. He focuses on serving to prospects construct, practice, deploy and migrate machine studying (ML) workloads to SageMaker. He beforehand labored within the semiconductor business creating giant laptop imaginative and prescient (CV) and pure language processing (NLP) fashions to enhance semiconductor processes. In his free time, he enjoys taking part in chess and touring.



Please enter your comment!
Please enter your name here

- Advertisment -

Most Popular

Recent Comments