import chromadb
import requests
import chromadb.utils.embedding_functions as embedding_functions
import gradio as gr
import os
embeddingfunc = embedding_functions.HuggingFaceEmbeddingFunction(api_key=os.environ["hf_token"],model_name="sentence-transformers/all-MiniLM-L6-v2")
elibbookAI = chromadb.HttpClient("https://shethjenil-chromadb-server.hf.space/",port=443).get_or_create_collection("jainebooks")
def qna(query:str,limit:int=1)->list:
    return [i["contentimg"] for i in elibbookAI.query(embeddingfunc(requests.get(f"https://translate.googleapis.com/translate_a/single?client=gtx&sl=gu&tl=en&dt=t&q={query}").json()[0][0][0]),n_results=limit)["metadatas"][0]]
gr.Interface(qna,[gr.Textbox(),gr.Slider(1, 4, value=1, label="Count",step=1)],gr.Gallery()).launch()