pip install langchain
pip install boto3

import boto3
from langchain.llms.bedrock import Bedrock

bedrock_client = boto3.client("bedrock-runtime")

# Start with the query
prompt = "For medical research trial consent forms to sign, what are the top 5 questions can be asked?"

claude_llm = Bedrock(
    model_id="anthropic.claude-v2:1",
    model_kwargs={"temperature": 0, "top_k": 10, "max_tokens_to_sample": 3000},
    client=bedrock_client,
)

# Provide the prompt to the LLM to generate an answer to the query without any additional context provided
response = claude_llm(prompt)
questions = [
    item.split(".")[1].strip() for item in response.strip().split("nn")[1:-1]
]
questions
>>> answer:
'What is the purpose of the study? Make sure you understand the goals of the research and what the study procedures will entail',
'What are the risks and potential benefits? The form should explain all foreseeable risks, side effects, or discomforts you might experience from participating',
'What will participation involve? Get details on what tests, medications, lifestyle changes, or procedures you will go through, how much time it will take, and how long the study will last',
'Are there any costs or payments? Ask if you will be responsible for any costs related to the study or get paid for participating',
'How will my privacy be protected? The form should explain how your personal health information will be kept confidential before, during, and after the trial'

bedrock_agent_client = boto3.client("bedrock-agent-runtime")

kb_id = "<YOUR_KNOWLEDGE_BASE_ID>"

def retrieveAndGenerate(
    input: str,
    kbId: str,
    region: str = "us-east-1",
    sessionId: str = None,
    model_id: str = "anthropic.claude-v2:1",
):
    model_arn = f"arn:aws:bedrock:{region}::foundation-model/{model_id}"

    if sessionId:
        return bedrock_agent_client.retrieve_and_generate(
            input={"text": input},
            retrieveAndGenerateConfiguration={
                "type": "KNOWLEDGE_BASE",
                "knowledgeBaseConfiguration": {
                    "knowledgeBaseId": kbId,
                    "modelArn": model_arn,
                },
            },
            sessionId=sessionId,
        )

    else:
        return bedrock_agent_client.retrieve_and_generate(
            input={"text": input},
            retrieveAndGenerateConfiguration={
                "type": "KNOWLEDGE_BASE",
                "knowledgeBaseConfiguration": {
                    "knowledgeBaseId": kbId,
                    "modelArn": model_arn,
                },
            },
        )

response = retrieveAndGenerate(
    "What are the potential risks and benefits of participating?", kb_id
)

generated_text = response["output"]["text"]
>>> "The potential risks include side effects from the study medication lithium such as nausea, loose stools, thirst, urination changes, shakiness, headaches, sweating, fatigue, decreased concentration, and skin rash. There is also a risk of lithium interaction with other medications. For women, there is a risk of birth defects if lithium is taken during pregnancy. There are no guaranteed benefits, but possible benefits include new information that could help the participant from the interviews and tests conducted during the study."

response["citations"]

>>> [
    {
        "generatedResponsePart": {
            "textResponsePart": {
                "text": " The potential risks include side effects from the study...",
                "span": {"start": 0, "end": 361},
            }
        },
        "retrievedReferences": [
            {
                "content": {
                    "text": "590 ICF#2 Page 7 of 19 The primary risks and discomforts of participation…"
                },
                "location": {"type": "S3", "s3Location": {"uri": "s3://XXXX/XXXX.pdf"}},
            },
            {
                "content": {
                    "text": "N/A CSP 590 ICF#2 Page 10 of 19 Risks associated with suddenly stopping study medications..."
                },
                "location": {"type": "S3", "s3Location": {"uri": "s3://XXXX/XXXX.pdf"}},
            },
        ],
    },
    {
        "generatedResponsePart": {
            "textResponsePart": {
                "text": " There are no guaranteed benefits, but possible benefits include...",
                "span": {"start": 363, "end": 531},
            }
        },
        "retrievedReferences": [
            {
                "content": {
                    "text": "research, not usual clinical care. After these are done we ask..."
                },
                "location": {"type": "S3", "s3Location": {"uri": "s3://XXXX/XXXX.pdf"}},
            }
        ],
    },
]

retrieveAndGenerate("elaborate more on the first side effect", kb_id, sessionId=None)["output"]["text"]
>>> "The search results do not provide additional details about the mild nausea side effect that would allow me to elaborate further on it."

retrieveAndGenerate("elaborate more on the first side effect", kb_id, sessionId=response["sessionId"])["output"]["text"]
>>> "The search results provide details that nausea from taking lithium is usually mild and goes away after days or weeks for most people. Specifically, up to 75% of people may experience mild nausea when first starting lithium, but this goes away in 90-99% of people who continue taking it."

def retrieve(query: str, kbId: str, numberOfResults: int = 5):
    return bedrock_agent_client.retrieve(
        retrievalQuery={"text": query},
        knowledgeBaseId=kbId,
        retrievalConfiguration={
            "vectorSearchConfiguration": {"numberOfResults": numberOfResults}
        },
    )

query = "What is the purpose of the medical research study?"
response = retrieve(query, kb_id, 3)
retrievalResults = response["retrievalResults"]
>>> [
    {
        "content": {"text": "You will not be charged for any procedures that..."},
        "location": {"type": "S3", "s3Location": {"uri": "s3://XXXXX/XXXX.pdf"}},
        "score": 0.6552521,
    },
    {
        "content": {"text": "and possible benefits of the study. You have been..."},
        "location": {"type": "S3", "s3Location": {"uri": "s3://XXXX/XXXX.pdf"}},
        "score": 0.6581577,
    },
    ...,
]

def get_contexts(retrievalResults):
    contexts = []
    for retrievedResult in retrievalResults:
        contexts.append(retrievedResult["content"]["text"])
    return " ".join(contexts)

contexts = get_contexts(retrievalResults)

from langchain.prompts import PromptTemplate

PROMPT_TEMPLATE = """
Human: You are an AI system working on medical trial research, and provides answers to questions 
by using fact based and statistical information when possible.
Use the following pieces of information to provide a concise answer to the question enclosed in <question> tags.
If you don't know the answer, just say that you don't know, don't try to make up an answer.

<context>
{context_str}
</context>

<question>
{query_str}
</question>

The response should be specific and use statistics or numbers when possible.

Assistant:"""

claude_prompt = PromptTemplate(
    template=PROMPT_TEMPLATE, input_variables=["context_str", "query_str"]
)

prompt = claude_prompt.format(context_str=contexts, query_str=query)
response = claude_llm(prompt)
>>> "Based on the context provided, the purpose of this medical research study is to evaluate the efficacy of lithium compared to a placebo in preventing suicide over a 1 year period. Specifically, participants will be randomly assigned to receive either lithium or a placebo pill for 1 year, with their doctors and the participants themselves not knowing which treatment they receive (double-blind). Blood lithium levels will be monitored and doses adjusted over the first 6-8 visits, then participants will be followed monthly for 1 year to assess outcomes."

from langchain.retrievers.bedrock import AmazonKnowledgeBasesRetriever

retriever = AmazonKnowledgeBasesRetriever(
    knowledge_base_id=kb_id,
    retrieval_config={"vectorSearchConfiguration": {"numberOfResults": 4}},
)

from langchain.chains import RetrievalQA

qa = RetrievalQA.from_chain_type(
    llm=claude_llm,
    chain_type="stuff",
    retriever=retriever,
    return_source_documents=True,
    chain_type_kwargs={"prompt": claude_prompt},
)

[qa(q)["result"] for q in questions]