Needle integration

import os

os.environ["NEEDLE_API_KEY"] = ""

os.environ["OPENAI_API_KEY"] = ""

from langchain_community.document_loaders.needle import NeedleLoader

collection_id = "clt_01J87M9T6B71DHZTHNXYZQRG5H"

# Initialize NeedleLoader to store documents to the collection
document_loader = NeedleLoader(
    needle_api_key=os.getenv("NEEDLE_API_KEY"),
    collection_id=collection_id,
)

files = {
    "tech-radar-30.pdf": "https://www.thoughtworks.com/content/dam/thoughtworks/documents/radar/2024/04/tr_technology_radar_vol_30_en.pdf"
}

document_loader.add_files(files=files)

# Show the documents in the collection
# collections_documents = document_loader.load()

# Show the documents in the collection
# collections_documents = document_loader.lazy_load()

import os

from langchain_classic.chains import create_retrieval_chain
from langchain_classic.chains.combine_documents import create_stuff_documents_chain
from langchain_community.retrievers.needle import NeedleRetriever
from langchain_core.prompts import ChatPromptTemplate
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(temperature=0)

# Initialize the Needle retriever (make sure your Needle API key is set as an environment variable)
retriever = NeedleRetriever(
    needle_api_key=os.getenv("NEEDLE_API_KEY"),
    collection_id="clt_01J87M9T6B71DHZTHNXYZQRG5H",
)

# Define system prompt for the assistant
system_prompt = """
    You are an assistant for question-answering tasks.
    Use the following pieces of retrieved context to answer the question.
    If you don't know, say so concisely.\n\n{context}
    """

prompt = ChatPromptTemplate.from_messages(
    [("system", system_prompt), ("human", "{input}")]
)

# Define the question-answering chain using a document chain (stuff chain) and the retriever
question_answer_chain = create_stuff_documents_chain(llm, prompt)

# Create the RAG (Retrieval-Augmented Generation) chain by combining the retriever and the question-answering chain
rag_chain = create_retrieval_chain(retriever, question_answer_chain)

# Define the input query
query = {"input": "Did RAG move to accepted?"}

response = rag_chain.invoke(query)

response

{'input': 'Did RAG move to accepted?',
 'context': [Document(metadata={}, page_content='New Moved in/out No change\n\n© Thoughtworks, Inc. All Rights Reserved. 12\n\nTechniques\n\n1. Retrieval-augmented generation (RAG)\nAdopt\n\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \na given prompt, the database is queried to retrieve relevant documents, which are then combined \nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \nreduced hallucinations. The context window — which determines the maximum size of the LLM input \n— is limited, which means that selecting the most relevant documents is crucial. We improve the \nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \na difficult problem, and one approach is to have the chunks overlap to a certain extent.'),
  Document(metadata={}, page_content='New Moved in/out No change\n\n© Thoughtworks, Inc. All Rights Reserved. 12\n\nTechniques\n\n1. Retrieval-augmented generation (RAG)\nAdopt\n\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \na given prompt, the database is queried to retrieve relevant documents, which are then combined \nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \nreduced hallucinations. The context window — which determines the maximum size of the LLM input \n— is limited, which means that selecting the most relevant documents is crucial. We improve the \nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \na difficult problem, and one approach is to have the chunks overlap to a certain extent.'),
  Document(metadata={}, page_content='New Moved in/out No change\n\n© Thoughtworks, Inc. All Rights Reserved. 12\n\nTechniques\n\n1. Retrieval-augmented generation (RAG)\nAdopt\n\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \na given prompt, the database is queried to retrieve relevant documents, which are then combined \nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \nreduced hallucinations. The context window — which determines the maximum size of the LLM input \n— is limited, which means that selecting the most relevant documents is crucial. We improve the \nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \na difficult problem, and one approach is to have the chunks overlap to a certain extent.'),
  Document(metadata={}, page_content='New Moved in/out No change\n\n© Thoughtworks, Inc. All Rights Reserved. 12\n\nTechniques\n\n1. Retrieval-augmented generation (RAG)\nAdopt\n\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \na given prompt, the database is queried to retrieve relevant documents, which are then combined \nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \nreduced hallucinations. The context window — which determines the maximum size of the LLM input \n— is limited, which means that selecting the most relevant documents is crucial. We improve the \nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \na difficult problem, and one approach is to have the chunks overlap to a certain extent.'),
  Document(metadata={}, page_content='New Moved in/out No change\n\n© Thoughtworks, Inc. All Rights Reserved. 12\n\nTechniques\n\n1. Retrieval-augmented generation (RAG)\nAdopt\n\nRetrieval-augmented generation (RAG) is the preferred pattern for our teams to improve the quality of \nresponses generated by a large language model (LLM). We’ve successfully used it in several projects, \nincluding the popular Jugalbandi AI Platform. With RAG, information about relevant and trustworthy \ndocuments — in formats like HTML and PDF — are stored in databases that supports a vector data \ntype or efficient document search, such as pgvector, Qdrant or Elasticsearch Relevance Engine. For \na given prompt, the database is queried to retrieve relevant documents, which are then combined \nwith the prompt to provide richer context to the LLM. This results in higher quality output and greatly \nreduced hallucinations. The context window — which determines the maximum size of the LLM input \n— is limited, which means that selecting the most relevant documents is crucial. We improve the \nrelevancy of the content that is added to the prompt by reranking. Similarly, the documents are usually \ntoo large to calculate an embedding, which means they must be split into smaller chunks. This is often \na difficult problem, and one approach is to have the chunks overlap to a certain extent.')],
 'answer': 'Yes, RAG has been adopted as the preferred pattern for improving the quality of responses generated by a large language model.'}