app.py

from huggingface_hub import hf_hub_download

n_gpu_layers = 40 # Change this value based on your model and your GPU VRAM pool.
n_batch = 256 

import paperscraper
from paperqa import Docs
from langchain.llms import LlamaCpp
from langchain import PromptTemplate, LLMChain
from langchain.callbacks.manager import CallbackManager
from langchain.embeddings import LlamaCppEmbeddings
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from g4f import Provider, models
from langchain.llms.base import LLM

from langchain_g4f import G4FLLM

# Make sure the model path is correct for your system!
llm = LLM = G4FLLM(
        model=models.gpt_35_turbo,
        provider=Provider.FreeGpt,
    )
    
from langchain.embeddings import HuggingFaceEmbeddings

model_name = "sentence-transformers/all-mpnet-base-v2"
model_kwargs = {'device': 'cpu'}
encode_kwargs = {'normalize_embeddings': True}
embeddings = HuggingFaceEmbeddings(
    model_name=model_name,
    model_kwargs=model_kwargs,
    encode_kwargs=encode_kwargs
)
docs = Docs(llm=llm, embeddings=embeddings)

docs.add_url("https://33bbf3d5-c3fe-409d-a723-d22ea129e9a0.usrfiles.com/ugd/33bbf3_a21b940230be4adbb8be48927b9dc92b.pdf") 
answer = docs.query("Que dis l'article 114 ?")
print(answer)

def re(r):

    print(answer)
    return r 

gr.Interface(fn=re,inputs=gr.Textbox(),outputs=gr.Textbox).launch()