app.py

import os
import gradio as gr
from pinecone import Pinecone
from langchain_chroma import Chroma
from langchain_core.prompts import PromptTemplate
from langchain_pinecone import PineconeVectorStore
from langchain_community.vectorstores import FAISS
from langchain_community.vectorstores import LanceDB
from langchain_text_splitters import CharacterTextSplitter
from langchain_community.document_loaders import PyPDFLoader
from langchain_google_genai import GoogleGenerativeAIEmbeddings, GoogleGenerativeAI

embeddings = GoogleGenerativeAIEmbeddings(model="models/text-embedding-004")
gemini = GoogleGenerativeAI(model="models/gemini-2.0-flash")

prompt_template = """
    
    Context:\n {context}?\n
    Question: \n{question}\n

    Answer:
    """

prompt = PromptTemplate(template = prompt_template, input_variables = ["context", "question"])

chain = prompt | gemini

def inference(pdf_path, chunk_size, chunk_overlap):
    raw_documents = PyPDFLoader(pdf_path).load()
    text_splitter = CharacterTextSplitter(chunk_size=chunk_size, chunk_overlap=chunk_overlap)
    documents = text_splitter.split_documents(raw_documents)

    pc = Pinecone(api_key=os.environ["PINECONE_API_KEY"])

    index_name = "langchain-test-index"

    index = pc.Index(host="https://langchain-test-index-la2n80y.svc.aped-4627-b74a.pinecone.io")

    index.delete(delete_all=True)

    chroma_db = Chroma.from_documents(documents, embeddings, persist_directory="./chroma_db")
    faiss_db = FAISS.from_documents(documents, embeddings)
    faiss_db.save_local("./faiss_db")
    lance_db = LanceDB.from_documents(documents, embeddings, uri="./lance_db")
    pinecone_db = PineconeVectorStore.from_documents(documents, index_name=index_name,
                                                     embedding=embeddings)
    
    return "All embeddings are stored in vector database"

title = "PDF Chat"
description = "A simple Gradio interface to query PDFs and compare vector database"
examples = [["data/amazon-10-k-2024.pdf", 1000, 100],
            ["data/goog-10-k-2023.pdf", 1000, 100]]

with gr.Blocks(theme=gr.themes.Monochrome()) as demo:
    gr.Markdown(f"# {title}\n{description}")
    with gr.Row():
        with gr.Column():
            pdf = gr.UploadButton(file_types=[".pdf"])
            chunk_size = gr.Slider(0, 2000, 1000, 100, label="Size of Chunk")
            chunk_overlap = gr.Slider(0, 1000, 100, 100, label="Size of Chunk Overlap")
            with gr.Row():
                clear_btn = gr.ClearButton(components=[pdf, chunk_size, chunk_overlap])
                submit_btn = gr.Button("Store Embeddings", variant='primary')
        with gr.Column():
            message = gr.Textbox(label="Status", type="text")

    submit_btn.click(inference, inputs=[pdf, chunk_size, chunk_overlap], outputs=message)

    examples_obj = gr.Examples(examples=examples, inputs=[pdf, chunk_size, chunk_overlap])

demo.launch()