RAG

from PyPDF2 import PdfReader
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain_community.embeddings.sentence_transformer import SentenceTransformerEmbeddings
from langchain_openai import OpenAIEmbeddings
from langchain_core.documents import Document
from langchain_qdrant import QdrantVectorStore
from qdrant_client import QdrantClient
import openai
import config

def extract_text_from_pdf(pdf_file):
    pdf_text = ''
    reader = PdfReader(pdf_file)
    for page_no in range(len(reader.pages)):
        pdf_text = pdf_text + reader.pages[page_no].extract_text()
    if(len(pdf_text)==0):
        raise ValueError('No text extracted from this pdf.')
    return pdf_text

text_article = extract_text_from_pdf("Harsha_Achyuthuni_resume.pdf")
print("The first 100 chars in the resume are:\n", text_article[:100])

The first 100 chars in the resume are:
 Achyuthuni Sri Harsha
Data Scientist, Deloitte, Imperial College London, IIMB, harshaash.com
E-mail:

print("The total number of words in the document are: ", len(text_article.split()))

The total number of words in the document are:  1611

query = "How many years of experience does the candidate have?"

# Split the text based on tokens into chunks
text_splitter = RecursiveCharacterTextSplitter.from_tiktoken_encoder(
    encoding_name='cl100k_base',
    chunk_size=100, # Minimum chunk size is 100
    chunk_overlap=25 # Overlap in the chunk size is 25
)
split_texts = text_splitter.split_text(text_article)
split_texts = [Document(page_content = split_texts[i]) for i in range(len(split_texts))]
print("The total number of chunks in the document are: "+str(len(split_texts)))

The total number of chunks in the document are: 34

# Create embeddings
embeddings = OpenAIEmbeddings(api_key = config.open_api_key, model="text-embedding-3-large")

# Initialise vector database
qdrant_client = QdrantClient(
    url=config.qdrant_url, 
    api_key=config.qdrant_api_key,
)
# Delete existing collection
qdrant_client.delete_collection(collection_name="my_chat_documents")

# Store embeddings in vector db
qdrant = QdrantVectorStore.from_documents(
    split_texts,
    embeddings,
    url=config.qdrant_url, 
    api_key=config.qdrant_api_key,
    prefer_grpc=True,
    collection_name="my_chat_documents",
)

[qdrant_client.get_collections().collections[i].name for i in range(len(qdrant_client.get_collections().collections))]

['my_chat_documents']

# retrieve selected part of the website
qdrant = QdrantVectorStore.from_existing_collection(
  embedding=embeddings,
  collection_name="my_chat_documents",
  url=config.qdrant_url, api_key=config.qdrant_api_key
)
# Find closest chunks
relevant_document_chunks = qdrant.similarity_search(query=query,k=3)
context_list = [d.page_content for d in relevant_document_chunks]

print("\n-----------------------\n".join(context_list))

Summary
Harsha has 7 years of experience in Data Science and Machine learning. As a senior consultant at
Deloitte, he likes solving complex business problems using data, statistics, technology and business
understanding. He has worked on projects across the data science spectrum, including regression,
classification, deep learning, machine learning, AI, ChatGPT, reinforcement learning, optimization,
unsupervised learning and streaming machine learning.
-----------------------
Achyuthuni Sri Harsha
Data Scientist, Deloitte, Imperial College London, IIMB, harshaash.com
E-mail: achyuthuni.sri.harsha@gmail.com ✼Phone/Whatsapp: +91-9019413416
LinkedIn: sri-harsha-achyuthuni ✼Website: www.harshaash.com
Summary
Harsha has 7 years of experience in Data Science and Machine learning. As a senior consultant at
-----------------------
Solutions that he built are currently deployed at Walmart, Rolls Royce and Dr Reddys. He has also
built, presented and converted POCs across many Fortune 500 clients.
He has a masters from Imperial College London in Business Analytics and is an alumnus of IIM
Bangalore.
Technical skills
Analytics Python, R, CPLEX
Data Engineering SQL, Alteryx
Visualisation Tableau, HTML, Javascript

agumented_search_context = ". ".join(context_list)

qna_system_message = '''You will be provided with a text, and your task is to answer the question based on the text alone. 
    If you are unable to answer or doubtful, please say "I dont know"'''
qna_user_message_template = """
###Context
Here are some documents that are relevant to the question mentioned below.
{context}

###Question
{question}
"""

prompt = [
    {'role':'system', 'content': qna_system_message},
    {'role': 'user', 'content': qna_user_message_template.format(
         context=agumented_search_context,
         question=query
        )
    }
]
openai.api_key = config.open_api_key
response = openai.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=prompt,
    temperature=0
)

prediction = response.choices[0].message.content.strip()

print(prediction)

The candidate has 7 years of experience.

!wget https://huggingface.co/microsoft/Phi-3-mini-4k-instruct-gguf/resolve/main/Phi-3-mini-4k-instruct-q4.gguf

Phi-3-mini-4k-instr 100%[===================>]   2.23G  39.2MB/s    in 57s

from langchain import LlamaCpp

llm = LlamaCpp(
    model_path="Phi-3-mini-4k-instruct-q4.gguf",
    n_gpu_layers=-1,
    max_tokens=500,
    n_ctx=2048,
    seed=42,
    verbose=False
)

from langchain.embeddings.huggingface import HuggingFaceEmbeddings

# Embedding Model for converting text to numerical representations
embedding_model = HuggingFaceEmbeddings(
    model_name='BAAI/bge-small-en-v1.5'
)

from langchain.vectorstores import FAISS

# Split into a list of sentences
texts = text_article.split('\n')

# Clean up to remove empty spaces and new lines
texts = [t.strip(' \n') for t in texts]

# Create a local vector database
db = FAISS.from_texts(texts, embedding_model)

from langchain import PromptTemplate
from langchain.chains import RetrievalQA


# Create a prompt template
template = """<|user|>
Relevant information:
{context}

Provide a concise answer the following question using the relevant information provided above:
{question}<|end|>
<|assistant|>"""
prompt = PromptTemplate(
    template=template,
    input_variables=["context", "question"]
)

# RAG Pipeline
rag = RetrievalQA.from_chain_type(
    llm=llm,
    chain_type='stuff',
    retriever=db.as_retriever(),
    chain_type_kwargs={
        "prompt": prompt
    },
    verbose=True
)

rag.invoke(query)

1m> Finished chain.

{'query': 'How many years of experience does the candidate have?',
 'result': ' The candidate has 7 years of experience in Data Science and Machine learning.'}

groundedness_rater_system_message = """
You are tasked with rating AI generated answers to questions posed by users.
You will be presented a question, context used by the AI system to generate the answer and an AI generated answer to the question.
In the input, the question will begin with ###Question, the context will begin with ###Context while the AI generated answer will begin with ###Answer.

Evaluation criteria:
The task is to judge the extent to which the metric is followed by the answer.
1 - The metric is not followed at all
2 - The metric is followed only to a limited extent
3 - The metric is followed to a good extent
4 - The metric is followed mostly
5 - The metric is followed completely

Metric:
The answer should be derived only from the information presented in the context

Instructions:
1. First write down the steps that are needed to evaluate the answer as per the metric.
2. Give a step-by-step explanation if the answer adheres to the metric considering the question and context as the input.
3. Next, evaluate the extent to which the metric is followed.
4. Use the previous information to rate the answer using the evaluaton criteria and assign a score.
"""

groundedness_prompt = [
    {'role':'system', 'content': groundedness_rater_system_message},
    {'role': 'user', 'content': user_message_template.format(
        question=query,
        context=agumented_search_context,
        answer=prediction
        )
    }
]

response = openai.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=groundedness_prompt,
    temperature=0
)

print(response.choices[0].message.content)

Steps to evaluate the answer:
1. Identify the specific information in the context related to the candidate's experience.
2. Check if the answer provided matches the exact number of years of experience mentioned in the context.
3. Determine if any additional information not present in the context is included in the answer.

Explanation:
1. The context clearly states that Harsha has 7 years of experience in Data Science and Machine learning.
2. The answer provided states "The candidate has 7 years of experience," which directly matches the information given in the context.
3. The answer does not include any additional information beyond what is provided in the context.

The answer follows the metric completely by accurately stating the number of years of experience the candidate has based on the information given in the context.

### Evaluation: 5
### Score: 5

relevance_rater_system_message = """
You are tasked with rating AI generated answers to questions posed by users.
You will be presented a question, context used by the AI system to generate the answer and an AI generated answer to the question.
In the input, the question will begin with ###Question, the context will begin with ###Context while the AI generated answer will begin with ###Answer.

Evaluation criteria:
The task is to judge the extent to which the metric is followed by the answer.
1 - The metric is not followed at all
2 - The metric is followed only to a limited extent
3 - The metric is followed to a good extent
4 - The metric is followed mostly
5 - The metric is followed completely

Metric:
Relevance measures how well the answer addresses the main aspects of the question, based on the context.
Consider whether all and only the important aspects are contained in the answer when evaluating relevance.

Instructions:
1. First write down the steps that are needed to evaluate the context as per the metric.
2. Give a step-by-step explanation if the context adheres to the metric considering the question as the input.
3. Next, evaluate the extent to which the metric is followed.
4. Use the previous information to rate the context using the evaluaton criteria and assign a score.
"""

relevance_prompt = [
    {'role':'system', 'content': relevance_rater_system_message},
    {'role': 'user', 'content': user_message_template.format(
        question=query,
        context=agumented_search_context,
        answer=prediction
        )
    }
]

response = openai.chat.completions.create(
    model="gpt-3.5-turbo",
    messages=relevance_prompt,
    temperature=0
)

print(response.choices[0].message.content)

1. Identify the main aspects of the question: The main aspect of the question is to determine the number of years of experience the candidate has.

2. Look for relevant information in the context: Search for details related to the candidate's experience in the context provided.

3. Determine if the answer contains the specific number of years of experience: Check if the answer explicitly states the number of years of experience the candidate has.

4. Evaluate if the answer addresses the main aspect of the question: Assess whether the answer accurately provides the number of years of experience as requested in the question.

Explanation:
The context clearly states that Harsha has 7 years of experience in Data Science and Machine learning. The AI generated answer directly addresses the main aspect of the question by stating "The candidate has 7 years of experience." The answer is relevant as it provides the specific number of years of experience the candidate has based on the information in the context.

Therefore, the answer follows the metric of relevance completely by addressing the main aspect of the question accurately.

###Final Rating
5 - The metric is followed completely