Maqboolzia/Leagalbase-Chatbot

This Python 3 environment comes with many helpful analytics libraries installed

It is defined by the kaggle/python Docker image: https://github.com/kaggle/docker-python

For example, here's several helpful packages to load

import numpy as np # linear algebra import pandas as pd # data processing, CSV file I/O (e.g. pd.read_csv)

Input data files are available in the read-only "../input/" directory

For example, running this (by clicking run or pressing Shift+Enter) will list all files under the input directory

import os for dirname, _, filenames in os.walk('/kaggle/input'): for filename in filenames: print(os.path.join(dirname, filename))

You can write up to 20GB to the current directory (/kaggle/working/) that gets preserved as output when you create a version using "Save & Run All"

You can also write temporary files to /kaggle/temp/, but they won't be saved outside of the current session

pip install --quiet PyPDF2 gradio groq langchain langchain-community langchain-huggingface sentence-transformers transformers faiss-gpu import gradio as gr from langchain.prompts import PromptTemplate from langchain_community.vectorstores import FAISS from langchain_huggingface import HuggingFaceEmbeddings from PyPDF2 import PdfReader from groq import Groq import os import json # For handling JSON data from PyPDF2 import PdfReader from langchain.embeddings import HuggingFaceEmbeddings from langchain.vectorstores import FAISS import gradio as gr

Load JSON file instead of PDF

pdf_path = "/kaggle/input/ai-assignment/pdf_data.json" # Updated path try: with open(pdf_path, "r") as f: data = json.load(f)

# Handle different possible structures of the JSON file
if isinstance(data, list):
    # Assuming the text data is in the first element of the list
    document_text = data[0].get("text", "") if isinstance(data[0], dict) else ""
elif isinstance(data, dict):
    document_text = data.get("text", "")
else:
    raise ValueError("Unexpected JSON structure: expected a list or dict.")

except Exception as e: raise FileNotFoundError(f"Error reading JSON file: {e}")

Check if document_text is empty

if not document_text.strip(): raise ValueError("The document text is empty. Please check the file content.")

Split the document into smaller sections for vectorization

sections = document_text.split("\n\n") if not sections: raise ValueError("No sections found in the document text. Please check the formatting.")

Load embedding model

embedding_model_name = "sentence-transformers/all-MiniLM-L6-v2" try: embeddings_model = HuggingFaceEmbeddings(model_name=embedding_model_name) except Exception as e: raise RuntimeError(f"Error loading embedding model: {e}")

Create FAISS vector store

try: vector_store = FAISS.from_texts( texts=sections, embedding=embeddings_model ) except Exception as e: raise RuntimeError(f"Error creating FAISS vector store: {e}")

Define chatbot prompt

prompt = """ You are a chatbot designed to answer questions about my following CV: {retrieved_data}

User Query: {user_query} """

Initialize Groq API client

Ensure Groq is correctly installed and the API key is valid.

try: from groq.api import Groq client = Groq(api_key="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") except Exception as e: raise RuntimeError(f"Error initializing Groq client: {e}")

Function to process user queries

def process_query(user_query): try: retrieved_docs = vector_store.similarity_search(user_query, k=3) retrieved_data = "\n".join([doc.page_content for doc in retrieved_docs]) formatted_prompt = prompt.format(retrieved_data=retrieved_data, user_query=user_query)

    completion = client.chat.completions.create(
        model="llama3-70b-8192",
        messages=[{"role": "user", "content": formatted_prompt}],
        temperature=0.5,
        max_tokens=500,
        top_p=0.85,
        stream=False,
        stop=None,
    )
    response = completion.choices[0].message.content
    return response
except Exception as e:
    return f"Error processing query: {e}"

Gradio app

with gr.Blocks() as app: gr.Markdown("""

CV Chatbot

Use this chatbot to ask questions about my CV. """)

# CV Chatbot
query_input = gr.Textbox(
    label="Ask a Question",
    placeholder="Enter your question about the CV...",
    lines=3
)
query_output = gr.Textbox(
    label="Response",
    placeholder="The chatbot's response will appear here...",
    lines=10,
    interactive=False
)
ask_button = gr.Button("Ask")
ask_button.click(
    fn=process_query,
    inputs=query_input,
    outputs=query_output
)

gr.Markdown("""<h3>Disclaimer</h3>
The chatbot provides responses based on my CV content. Verify critical details independently.
""")

app.launch()