app.py

import gradio as gr
from huggingface_hub import InferenceClient

import json
import pandas as pd
import numpy as np

import torch
from sentence_transformers import SentenceTransformer
import nltk
from nltk.tokenize import sent_tokenize
import faiss
from langchain_text_splitters import RecursiveCharacterTextSplitter

optimus = SentenceTransformer('sentence-transformers/all-MiniLM-L6-v2')
textsplitter = RecursiveCharacterTextSplitter(chunk_size=500, chunk_overlap=100)

dbpath = r''##push datasets to the hub to use here##
gridpath = r''

with open(dbpath) as f:
    papers = [json.loads(line) for line in f]
df = pd.DataFrame(papers)
reqdf = df[['id', 'title', 'categories', 'abstract']]

d = 384
index = faiss.IndexFlatL2(d)
thegird = []#load the grid and index from json file here

def gen_embeddings(text):
    sentences = sent_tokenize(text)
    embeddings = optimus.encode(sentences)
    return embeddings

query_list = gen_embeddings(query)
if len(query_list) > 1:
    query_list = torch.mean(query_list, dim=0)
query_matrix = np.array(query_list).astype('float32').reshape(-1,1)
k = 25
distances, indices = index.search(query_matrix, k)
result_texts = [thegrid[idx]['text'] for idx in indices[0]]
for i, text in enumerate(result_texts):
    printres = f"Match {i+1}: {text}"
    

searched_topics = []
idcache = []
for text in result_texts:
    rowid = text.split("|||")[0]
    if rowid in idcache:
        break;
    else:
        topic = reqdf.loc[reqdf['id'] == rowid, 'title'].values[0]
        searched_topics.append(rowid)
        idcache.append(rowid)

def respond(
    message,
    history: list[tuple[str, str]],
    system_message,
    max_tokens,
    temperature,
    top_p,
):
    messages = [{"role": "system", "content": system_message}]

    for val in history:
        if val[0]:
            messages.append({"role": "user", "content": val[0]})
        if val[1]:
            messages.append({"role": "assistant", "content": val[1]})

    messages.append({"role": "user", "content": message})

    response = ""

    for message in client.chat_completion(
        messages,
        max_tokens=max_tokens,
        stream=True,
        temperature=temperature,
        top_p=top_p,
    ):
        token = message.choices[0].delta.content

        response += token
        yield response


"""
For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
"""
demo = gr.ChatInterface(
    respond,
    additional_inputs=[
        gr.Textbox(value="You are a friendly Chatbot.", label="System message"),
        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
        gr.Slider(
            minimum=0.1,
            maximum=1.0,
            value=0.95,
            step=0.05,
            label="Top-p (nucleus sampling)",
        ),
    ],
)


if __name__ == "__main__":
    demo.launch()