LLm2Node/FindinDB.py

import gradio as gr
from faiss import write_index, read_index

from langchain import PromptTemplate
from langchain.chains import LLMChain
from langchain.document_loaders import TextLoader
from langchain.text_splitter import CharacterTextSplitter
from langchain.vectorstores import FAISS
from langchain.text_splitter import RecursiveCharacterTextSplitter
from langchain.document_loaders import UnstructuredFileLoader
from langchain.document_loaders.recursive_url_loader import RecursiveUrlLoader
from langchain.document_loaders import UnstructuredURLLoader
from langchain.document_loaders.csv_loader import CSVLoader
from langchain import  LLMChain
from langchain.llms import GPT4All
from langchain.embeddings import GPT4AllEmbeddings
from langchain.callbacks.streaming_stdout import StreamingStdOutCallbackHandler
from langchain.callbacks.base import BaseCallbackManager
from langchain.document_loaders import DataFrameLoader
from langchain.embeddings import HuggingFaceEmbeddings
import pandas as pd
import sqlite3
from sentence_transformers import SentenceTransformer
from fastapi import FastAPI
#from cleantext import clean
import re
model_name = 'hiiamsid/sentence_similarity_spanish_es'
model_kwargs = {'device': 'cpu'}
encode_kwargs = {'normalize_embeddings': True}
hf = HuggingFaceEmbeddings(
    model_name=model_name,
    model_kwargs=model_kwargs,
    encode_kwargs=encode_kwargs
)

CUSTOM_PATH = "/angela"
app = FastAPI()

@app.get("/")
def read_main():
    return {"message": "This is your main app"}


def loadModels():
    #model = GPT4All("orca-mini-3b.ggmlv3.q4_0.bin")
    callback_manager = BaseCallbackManager([StreamingStdOutCallbackHandler()])
    llm = GPT4All(model="orca-mini-3b.ggmlv3.q4_0.bin",temp=0.1,streaming=True)#callback_manager=callback_manager, verbose=True,repeat_last_n=0
    embeddings = GPT4AllEmbeddings()
    return llm, embeddings


def loadCopysAndData(pathsqlite="motor.sqlite"):
    con = sqlite3.connect(pathsqlite)
    copies_df = pd.read_sql_query("SELECT * from copies", con)
    copiesT = copies_df[copies_df.copy_start =="T"]
    copiesT=copiesT[["copy_message","id","name"]]
    data = copiesT 
    B=DataFrameLoader(data,page_content_column="copy_message")
    B2=DataFrameLoader(data,page_content_column="name")
    documents=B.load()
    documents2=B2.load()
    return documents,documents2

def makeFaissdb(documents,folder_path,embedding):
    try:
        db=FAISS.load_local(folder_path=folder_path,embeddings=embedding)
            
    except:
        db = FAISS.from_documents(documents, embedding)
        FAISS.save_local(db,folder_path=folder_path)
    return db

llm,emb=loadModels()
documents,documents2=loadCopysAndData()

db=makeFaissdb(documents,"Copies",emb)
db2=makeFaissdb(documents2,"names",emb)
db3=makeFaissdb(documents2,"nameshf",hf)

def FinderDbs(query,dbs,filtred=False,th=1.2):
    AllData={}
    for dbt in dbs:
        Sal = dbt.similarity_search_with_score(query,4)
        for output in Sal:
            if output[0].metadata["id"] in AllData.keys():
                AllData[output[0].metadata["id"]]["d"]=min([AllData[output[0].metadata["id"]]["d"]-0.1,output[1]-0.1])
            else:
                AllData[output[0].metadata["id"]]={"d":output[1],"page_content":output[0].page_content}
    #for item in AllData.items():
    #    print(item)
    
    if filtred:
        filtredData={}
        for row in AllData.keys():
            if AllData[row]["d"]<1.2:
                filtredData[row]=AllData[row]
        filtredData=dict(sorted(filtredData.items(), key=lambda item: item[1]["d"]))
        return  filtredData,filtredData.keys()


    else:
        AllData=dict(sorted(AllData.items(), key=lambda item: item[1]["d"]))
        return  AllData,AllData.keys()

def QARequest(Pregunta,filtred=False):
    query = Pregunta
    AllData=FinderDbs(query,[db,db2],filtred)

    if AllData:
        import markdown
        AllData = list(AllData)
        #lista = "<div style='border-style = solid;border-width:1px;border-radius:10px'>"
        lista = ""
        for k,i in enumerate(AllData[0].items()):
            titulo = f"<div style='border-style = solid;border-width:1px;border-radius:10px;margin:14px;padding:14px'><h2>Respuesta {k+1}</h2>"
            to_append = markdown.markdown(i[1]['page_content'])
            lista = lista + titulo + to_append + '</div>'
            #lista.append('<br>')
        #lista = lista + '</div>'
    
        AllData[0] = lista
    return AllData



with gr.Blocks() as demo:
    gr.Image("logo.jpg",height=100)
    gr.Markdown("Esta es la busqueda que hace el usuario")
    Pregunta = gr.Textbox(label="Pregunta")
    #Pregunta = re.sub(r"(@\[A-Za-z0-9]+)|([^0-9A-Za-z \t])|(\w+:\/\/\S+)|^rt|http.+?", "", Pregunta)
    #Pregunta=Pregunta.strip().lower()
    
    filtred=gr.Checkbox(label="filtrado")
    
    gr.Markdown("Respuestas para orca desde los copys")
    Respuesta = gr.Textbox(label="Respuesta")
    id = gr.Textbox(label="id")
    # metrica=gr.Textbox(label="metrica")
    # gr.Markdown("Respuestas para orca desde los names")
    # Respuesta2 = gr.Textbox(label="Respuesta2")
    # id2 = gr.Textbox(label="id2")
    # metrica2=gr.Textbox(label="metrica2")
    # gr.Markdown("Respuestas para hf desde los names")
    # Respuesta3 = gr.Textbox(label="Respuesta3")
    # id3 = gr.Textbox(label="id3")
    # metrica3=gr.Textbox(label="metrica3")
    Enviar_btn = gr.Button("Responder")

    Enviar_btn.click(fn=QARequest, inputs=[Pregunta,filtred], outputs=[gr.HTML(Respuesta),id], api_name="api_angela") # 

#demo.launch(root_path="angela") #

gradio_app = gr.routes.App.create_app(demo)

app.mount(CUSTOM_PATH, gradio_app)

#app = demo.mount_gradio_app(app, io, path=CUSTOM_PATH)